Engineering › Electrical and Electronic Engineering

Energy Load and Power Forecasting

Works Count: 53352

Wikipedia

Description

This cluster of papers focuses on the methods and techniques for forecasting electricity prices and load demand, with an emphasis on short-term forecasting using neural networks, ARIMA models, and probabilistic approaches. The cluster also covers topics related to wind power generation, deep learning applications, and renewable energy forecasting.

Keywords

Electricity Price Forecasting; Load Forecasting; Short-Term Forecasting; Neural Networks; Wind Power Generation; ARIMA Models; Probabilistic Forecasting; Deep Learning; Renewable Energy; Time Series Analysis

A review on artificial intelligence based load demand forecasting techniques for smart grid and buildings

2015-06-16

Muhammad Qamar Raza , Abbas Khosravi

The structure of atmospheric turbulence

1964-12-01

E.V. Appleton

Day-ahead wind speed forecasting using f-ARIMA models

2008-10-26

Rajesh Kavasseri , Karthika Murugandi Reddiar Seetharaman

Current methods and advances in forecasting of wind power generation

2011-07-05

Aoife Foley , Paul Leahy , Antonino Marvuglia +1 more

View PDF Chat

Applying support vector machines to predict building energy consumption in tropical region

2004-12-15

Bing Dong , Cheng Cao , Siew Eang Lee

Forecast of hourly average wind speed with ARMA models in Navarre (Spain)

2004-11-05

J.L. Torres , A. Garcı́a , M. De Blas +1 more

A review on the forecasting of wind speed and generated power

2008-03-07

Lei Ma , Luan Shiyan , Chuanwen Jiang +2 more

POWER SPECTRUM OF HORIZONTAL WIND SPEED IN THE FREQUENCY RANGE FROM 0.0007 TO 900 CYCLES PER HOUR

1957-04-01

I. Van der Hoven

A power-spectrum analysis of horizontal wind speed is made over a wide range of frequencies by piecing together various portions of the spectrum. There appear to be two major eddy-energy … A power-spectrum analysis of horizontal wind speed is made over a wide range of frequencies by piecing together various portions of the spectrum. There appear to be two major eddy-energy peaks in the spectrum ; one peak occurs at a period of about 4 days, and a second peak occurs at a period of about 1 minute. Between the two peaks, a broad spectral gap is centered at a frequency ranging from 1 to 10 cycles per hour. The spectral gap seems to exist under varying terrain and synoptic conditions.

View PDF Chat

On comparing three artificial neural networks for wind speed forecasting

2010-01-22

Gong Li , Jing Shi

A review of combined approaches for prediction of short-term wind speed and power

2014-03-28

Akın Taşçıkaraoğlu , M. Uzunoglu

Electric load forecasting: Literature survey and classification of methods

2002-01-01

Hesham K. Alfares , Mohammad Khaja Nazeeruddin

A review and categorization of electric load forecasting techniques is presented. A wide range of methodologies and models for forecasting are given in the literature. These techniques are classified here … A review and categorization of electric load forecasting techniques is presented. A wide range of methodologies and models for forecasting are given in the literature. These techniques are classified here into nine categories: (1) multiple regression, (2) exponential smoothing, (3) iterative reweighted least-squares, (4) adaptive load forecasting, (5) stochastic time series, (6) ARMAX models based on genetic algorithms, (7) fuzzy logic, (8) neural networks and (9) expert systems. The methodology for each category is briefly described, the advantages and disadvantages discussed, and the pertinent literature reviewed. Conclusions and comments are made on future research directions.

Applications of artificial neural-networks for energy systems

2000-09-01

Soteris A. Kalogirou

Current status and future advances for wind speed and power forecasting

2014-01-22

Jaesung Jung , Robert Broadwater

A review of wind power and wind speed forecasting methods with different time horizons

2010-09-01

Saurabh S. Soman , Hamidreza Zareipour , O.P. Malik +1 more

In recent years, environmental considerations have prompted the use of wind power as a renewable energy resource. However, the biggest challenge in integrating wind power into the electric grid is … In recent years, environmental considerations have prompted the use of wind power as a renewable energy resource. However, the biggest challenge in integrating wind power into the electric grid is its intermittency. One approach to deal with wind intermittency is forecasting future values of wind power production. Thus, several wind power or wind speed forecasting methods have been reported in the literature over the past few years. This paper provides insight on the foremost forecasting techniques, associated with wind power and speed, based on numeric weather prediction (NWP), statistical approaches, artificial neural network (ANN) and hybrid techniques over different time-scales. An overview of comparative analysis of various available forecasting techniques is discussed as well. In addition, this paper further gives emphasis on the major challenges and problems associated with wind power prediction.

Short-term load forecasting

1987-01-01

George Gross , F.D. Galiana

This paper discusses the state of the art in short-term load forecasting (STLF), that is, the prediction of the system load over an interval ranging from one hour to one … This paper discusses the state of the art in short-term load forecasting (STLF), that is, the prediction of the system load over an interval ranging from one hour to one week. The paper reviews the important role of STLF in the on-line scheduling and security functions of an energy management system (EMS). It then discusses the nature of the load and the different factors influencing its behavior. A detailed classification of the types of load modeling and forecasting techniques is presented. Whenever appropriate, the classification is accompanied by recommendations and by references to the literature which support or expand the discussion. The paper also presents a lengthy discussion of practical aspects for the development and usage of STLF models and packages. The annotated bibliography offers a representative selection of the principal publications in the STLF area.

View PDF Chat

Energy models for demand forecasting—A review

2011-10-07

L. Suganthi , Anand A. Samuel

A review on the young history of the wind power short-term prediction

2007-04-17

Alexandre Carlos Araújo da Costa , António Crespo , Jorge Navarro‐Ortiz +3 more

View PDF Chat

ARMA based approaches for forecasting the tuple of wind speed and direction

2010-11-15

Ergin Erdem , Jing Shi

Artificial neural networks in renewable energy systems applications: a review

2001-12-01

Soteris A. Kalogirou

Electricity price forecasting: A review of the state-of-the-art with a look into the future

2014-09-18

Rafał Weron

A variety of methods and ideas have been tried for electricity price forecasting (EPF) over the last 15 years, with varying degrees of success. This review article aims to explain … A variety of methods and ideas have been tried for electricity price forecasting (EPF) over the last 15 years, with varying degrees of success. This review article aims to explain the complexity of available solutions, their strengths and weaknesses, and the opportunities and threats that the forecasting tools offer or that may be encountered. The paper also looks ahead and speculates on the directions EPF will or should take in the next decade or so. In particular, it postulates the need for objective comparative EPF studies involving (i) the same datasets, (ii) the same robust error evaluation procedures, and (iii) statistical testing of the significance of one model's outperformance of another.

View PDF Chat

A review on applications of ANN and SVM for building electrical energy consumption forecasting

2014-02-22

Ahmad Sukri Ahmad , Mohammad Yusri Hassan , Md Pauzi Abdullah +4 more

A review of energy models

2004-11-12

S. Jebaraj , S. Iniyan

Statistical Analysis of Wind Power Forecast Error

2008-08-01

Hans Bludszuweit , José A. Domínguez‐Navarro , A. Llombart

Wind power forecast error usually has been assumed to have a near Gaussian distribution. With a simple statistical analysis, it can be shown that this is not valid. To obtain … Wind power forecast error usually has been assumed to have a near Gaussian distribution. With a simple statistical analysis, it can be shown that this is not valid. To obtain a more appropriate probability density function (pdf) of the wind power forecast error, an indirect algorithm based on the Beta pdf is proposed. Measured one-year time series from two different wind farms are used to generate the forecast data. Three different forecast scenarios are simulated based on the persistence approach. This makes the results comparable to other forecast methods. It is found that the forecast error pdf has a variable kurtosis ranging from 3 (like the Gaussian) to over 10, and therefore it can be categorized as fat-tailed. A new approximation function for the parameters of the Beta pdf is proposed because results from former publications could not be confirmed. Besides, a linear approximation is developed to describe the relationship between the persistence forecast and the related mean measured power. An energy storage system (ESS), which reduces the forecast error and smooths the wind power output, is considered. Results for this case show the usefulness of the proposed forecast error pdf for finding the optimum rated ESS power.

A regression-based approach to short-term system load forecasting

1990-01-01

A. Papalexopoulos , Tim Hesterberg

A linear regression-based model for the calculation of short-term system load forecasts is described. The model's most significant aspects fall into the following areas: innovative model building, including accurate holiday … A linear regression-based model for the calculation of short-term system load forecasts is described. The model's most significant aspects fall into the following areas: innovative model building, including accurate holiday modeling by using binary variables and temperature modeling by using heating and cooling degree functions; robust parameter estimation and parameter estimation under heteroskedasticity by using weighted least-squares linear regression techniques; use of 'reverse errors-in-variables' techniques to mitigate the effects on load forecasts of potential errors in the explanatory variables; and distinction between time-independent daily peak load forecasts and the maximum of the hourly load forecasts in order to prevent peak forecasts from being negatively biased. The model was tested under a wide variety of conditioning and is shown to produce excellent results.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">></ETX>

Support vector machines for wind speed prediction

2004-01-20

M. Mohandes , T.O. Halawani , Shafiqur Rehman +1 more

Probabilistic Forecasting of Wind Power Generation Using Extreme Learning Machine

2013-11-19

Can Wan , Zhao Xu , Pierre Pinson +2 more

Accurate and reliable forecast of wind power is essential to power system operation and control. However, due to the nonstationarity of wind power series, traditional point forecasting can hardly be … Accurate and reliable forecast of wind power is essential to power system operation and control. However, due to the nonstationarity of wind power series, traditional point forecasting can hardly be accurate, leading to increased uncertainties and risks for system operation. This paper proposes an extreme learning machine (ELM)-based probabilistic forecasting method for wind power generation. To account for the uncertainties in the forecasting results, several bootstrap methods have been compared for modeling the regression uncertainty, based on which the pairs bootstrap method is identified with the best performance. Consequently, a new method for prediction intervals formulation based on the ELM and the pairs bootstrap is developed. Wind power forecasting has been conducted in different seasons using the proposed approach with the historical wind power time series as the inputs alone. The results demonstrate that the proposed method is effective for probabilistic forecasting of wind power generation with a high potential for practical applications in power systems.

View PDF Chat

Short-term load forecasting using an artificial neural network

1992-01-01

K.Y. Lee , Y.T. Cha , Jong-Seong Park

An artificial neural network (ANN) method is applied to forecast the short-term load for a large power system. The load has two distinct patterns: weekday and weekend-day patterns. The weekend-day … An artificial neural network (ANN) method is applied to forecast the short-term load for a large power system. The load has two distinct patterns: weekday and weekend-day patterns. The weekend-day pattern includes Saturday, Sunday, and Monday loads. A nonlinear load model is proposed and several structures of an ANN for short-term load forecasting were tested. Inputs to the ANN are past loads and the output of the ANN is the load forecast for a given day. The network with one or two hidden layers was tested with various combinations of neurons, and results are compared in terms of forecasting error. The neural network, when grouped into different load patterns, gives a good load forecast.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">></ETX>

View PDF Chat

Day-Ahead Electricity Price Forecasting Using the Wavelet Transform and ARIMA Models

2005-05-01

Antonio J. Conejo , M.A. Plazas , Rosa Espínola +1 more

This paper proposes a novel technique to forecast day-ahead electricity prices based on the wavelet transform and ARIMA models. The historical and usually ill-behaved price series is decomposed using the … This paper proposes a novel technique to forecast day-ahead electricity prices based on the wavelet transform and ARIMA models. The historical and usually ill-behaved price series is decomposed using the wavelet transform in a set of better-behaved constitutive series. Then, the future values of these constitutive series are forecast using properly fitted ARIMA models. In turn, the ARIMA forecasts allow, through the inverse wavelet transform, reconstructing the future behavior of the price series and therefore to forecast prices. Results from the electricity market of mainland Spain in year 2002 are reported.

ARIMA models to predict next-day electricity prices

2003-07-29

Javier Contreras , Rosa Espínola , Francisco J. Nogales +1 more

Price forecasting is becoming increasingly relevant to producers and consumers in the new competitive electric power markets. Both for spot markets and long-term contracts, price forecasts are necessary to develop … Price forecasting is becoming increasingly relevant to producers and consumers in the new competitive electric power markets. Both for spot markets and long-term contracts, price forecasts are necessary to develop bidding strategies or negotiation skills in order to maximize benefit. This paper provides a method to predict next-day electricity prices based on the ARIMA methodology. ARIMA techniques are used to analyze time series and, in the past, have been mainly used for load forecasting, due to their accuracy and mathematical soundness. A detailed explanation of the aforementioned ARIMA models and results from mainland Spain and Californian markets are presented.

Short-term load forecasting via ARMA model identification including non-gaussian process considerations

2003-05-01

Shyh‐Jier Huang , Kuang‐Rong Shih

In this paper, the short-term load forecast by use of autoregressive moving average (ARMA) model including non-Gaussian process considerations is proposed. In the proposed method, the concept of cumulant and … In this paper, the short-term load forecast by use of autoregressive moving average (ARMA) model including non-Gaussian process considerations is proposed. In the proposed method, the concept of cumulant and bispectrum are embedded into the ARMA model in order to facilitate Gaussian and non-Gaussian process. With embodiment of a Gaussianity verification procedure, the forecasted model is identified more appropriately. Therefore, the performance of ARMA model is better ensured, improving the load forecast accuracy significantly. The proposed method has been applied on a practical system and the results are compared with other published techniques.

Review on Methods to Fix Number of Hidden Neurons in Neural Networks

2013-01-01

K. Gnana Sheela , S. N. Deepa

This paper reviews methods to fix a number of hidden neurons in neural networks for the past 20 years. And it also proposes a new method to fix the hidden … This paper reviews methods to fix a number of hidden neurons in neural networks for the past 20 years. And it also proposes a new method to fix the hidden neurons in Elman networks for wind speed prediction in renewable energy systems. The random selection of a number of hidden neurons might cause either overfitting or underfitting problems. This paper proposes the solution of these problems. To fix hidden neurons, 101 various criteria are tested based on the statistical errors. The results show that proposed model improves the accuracy and minimal error. The perfect design of the neural network based on the selection criteria is substantiated using convergence theorem. To verify the effectiveness of the model, simulations were conducted on real-time wind data. The experimental results show that with minimum errors the proposed approach can be used for wind speed prediction. The survey has been made for the fixation of hidden neurons in neural networks. The proposed model is simple, with minimal error, and efficient for fixation of hidden neurons in Elman networks.

View PDF Chat

Forecasting next-day electricity prices by time series models

2002-05-01

Francisco J. Nogales , Javier Contreras , Antonio J. Conejo +1 more

In the framework of competitive electricity markets, power producers and consumers need accurate price forecasting tools. Price forecasts embody crucial information for producers and consumers when planning bidding strategies in … In the framework of competitive electricity markets, power producers and consumers need accurate price forecasting tools. Price forecasts embody crucial information for producers and consumers when planning bidding strategies in order to maximize their benefits and utilities, respectively. This paper provides two highly accurate yet efficient price forecasting tools based on time series analysis: dynamic regression and transfer function models. These techniques are explained and checked against each other. Results and discussions from real-world case studies based on the electricity markets of mainland Spain and California are presented.

Neural networks for short-term load forecasting: a review and evaluation

2001-01-01

Henrique S. Hippert , Carlos E. Pedreira , Reinaldo Castro Souza

Load forecasting has become one of the major areas of research in electrical engineering, and most traditional forecasting models and artificial intelligence techniques have been tried out in this task. … Load forecasting has become one of the major areas of research in electrical engineering, and most traditional forecasting models and artificial intelligence techniques have been tried out in this task. Artificial neural networks (NNs) have lately received much attention, and a great number of papers have reported successful experiments and practical tests with them. Nevertheless, some authors remain skeptical, and believe that the advantages of using NNs in forecasting have not been systematically proved yet. In order to investigate the reasons for such skepticism, this review examines a collection of papers (published between 1991 and 1999) that report the application of NNs to short-term load forecasting. Our aim is to help to clarify the issue, by critically evaluating the ways in which the NNs proposed in these papers were designed and tested.

A GARCH Forecasting Model to Predict Day-Ahead Electricity Prices

2005-05-01

Reinaldo C. Garcia , Javier Contreras , M. vanAkkeren +1 more

Price forecasting is becoming increasingly relevant to producers and consumers in the new competitive electric power markets. Both for spot markets and long-term contracts, price forecasts are necessary to develop … Price forecasting is becoming increasingly relevant to producers and consumers in the new competitive electric power markets. Both for spot markets and long-term contracts, price forecasts are necessary to develop bidding strategies or negotiation skills in order to maximize profits. This paper provides an approach to predict next-day electricity prices based on the Generalized Autoregressive Conditional Heteroskedastic (GARCH) methodology that is already being used to analyze time series data in general. A detailed explanation of GARCH models is presented and empirical results from the mainland Spain and California deregulated electricity-markets are discussed.

Short-term electricity demand forecasting using double seasonal exponential smoothing

2003-07-24

James W. Taylor

View PDF Chat

Load Forecasting Using Support Vector Machines: A Study on EUNITE Competition 2001

2004-11-01

Bing Chen , Ming‐Wei Chang , Chih‐Jen Lin

Load forecasting is usually made by constructing models on relative information, such as climate and previous load demand data. In 2001, EUNITE network organized a competition aiming at mid-term load … Load forecasting is usually made by constructing models on relative information, such as climate and previous load demand data. In 2001, EUNITE network organized a competition aiming at mid-term load forecasting (predicting daily maximum load of the next 31 days). During the competition we proposed a support vector machine (SVM) model, which was the winning entry, to solve the problem. In this paper, we discuss in detail how SVM, a new learning technique, is successfully applied to load forecasting. In addition, motivated by the competition results and the approaches by other participants, more experiments and deeper analyses are conducted and presented here. Some important conclusions from the results are that temperature (or other types of climate information) might not be useful in such a mid-term load forecasting problem and that the introduction of time-series concept may improve the forecasting.

View PDF Chat

Time Series Prediction Using Support Vector Machines: A Survey

2009-04-24

Nicholas I. Sapankevych , Ravi Sankar

Time series prediction techniques have been used in many real-world applications such as financial market prediction, electric utility load forecasting , weather and environmental state prediction, and reliability forecasting. The … Time series prediction techniques have been used in many real-world applications such as financial market prediction, electric utility load forecasting , weather and environmental state prediction, and reliability forecasting. The underlying system models and time series data generating processes are generally complex for these applications and the models for these systems are usually not known a priori. Accurate and unbiased estimation of the time series data produced by these systems cannot always be achieved using well known linear techniques, and thus the estimation process requires more advanced time series prediction algorithms. This paper provides a survey of time series prediction applications using a novel machine learning approach: support vector machines (SVM). The underlying motivation for using SVMs is the ability of this methodology to accurately forecast time series data when the underlying system processes are typically nonlinear, non-stationary and not defined a-priori. SVMs have also been proven to outperform other non-linear techniques including neural-network based non-linear prediction techniques such as multi-layer perceptrons.The ultimate goal is to provide the reader with insight into the applications using SVM for time series prediction, to give a brief tutorial on SVMs for time series prediction, to outline some of the advantages and challenges in using SVMs for time series prediction, and to provide a source for the reader to locate books, technical journals, and other online SVM research resources.

Probabilistic electric load forecasting: A tutorial review

2016-02-19

Tao Hong , Fan Shu

Probabilistic energy forecasting: Global Energy Forecasting Competition 2014 and beyond

2016-03-12

Tao Hong , Pierre Pinson , Fan Shu +3 more

Wind speed forecasting based on the hybrid ensemble empirical mode decomposition and GA-BP neural network method

2016-04-06

Shouxiang Wang , Na Zhang , Lei Wu +1 more

Deep learning based ensemble approach for probabilistic wind power forecasting

2016-12-08

Huaizhi Wang , Gangqiang Li , Guibin Wang +3 more

A review on time series forecasting techniques for building energy consumption

2017-03-11

Chirag Deb , Fan Zhang , Junjing Yang +2 more

Deep Learning for Household Load Forecasting—A Novel Pooling Deep RNN

2017-03-23

Heng Shi , Minghao Xu , Ran Li

The key challenge for household load forecasting lies in the high volatility and uncertainty of load profiles.Traditional methods tend to avoid such uncertainty by load aggregation (to offset uncertainties), customer … The key challenge for household load forecasting lies in the high volatility and uncertainty of load profiles.Traditional methods tend to avoid such uncertainty by load aggregation (to offset uncertainties), customer classification (to cluster uncertainties) and spectral analysis (to filter out uncertainties).This paper, for the first time, aims to directly learn the uncertainty by applying a new breed of machine learning algorithms -deep learning.However simply adding layers in neural networks will cap the forecasting performance due to the occurrence of overfitting.A novel pooling-based deep recurrent neural network (PDRNN) is proposed in this paper which batches a group of customers' load profiles into a pool of inputs.Essentially the model could address the over-fitting issue by increasing data diversity and volume.This work reports the first attempts to develop a bespoke deep learning application for household load forecasting and achieved preliminary success.The developed method is implemented on Tensorflow deep learning platform and tested on 920 smart metered customers from Ireland.Compared with the state-of-art techniques in household load forecasting, the proposed method outperforms ARIMA by 19.5%, SVR by 13.1% and classical deep RNN by 6.5% in terms of RMSE.

View PDF Chat

Short-Term Residential Load Forecasting Based on LSTM Recurrent Neural Network

2017-09-18

Weicong Kong , Zhao Yang Dong , Youwei Jia +3 more

As the power system is facing a transition toward a more intelligent, flexible, and interactive system with higher penetration of renewable energy generation, load forecasting, especially short-term load forecasting for … As the power system is facing a transition toward a more intelligent, flexible, and interactive system with higher penetration of renewable energy generation, load forecasting, especially short-term load forecasting for individual electric customers plays an increasingly essential role in the future grid planning and operation. Other than aggregated residential load in a large scale, forecasting an electric load of a single energy user is fairly challenging due to the high volatility and uncertainty involved. In this paper, we propose a long short-term memory (LSTM) recurrent neural network-based framework, which is the latest and one of the most popular techniques of deep learning, to tackle this tricky issue. The proposed framework is tested on a publicly available set of real residential smart meter data, of which the performance is comprehensively compared to various benchmarks including the state-of-the-arts in the field of load forecasting. As a result, the proposed LSTM approach outperforms the other listed rival algorithms in the task of short-term load forecasting for individual residential households.

Optimal Deep Learning LSTM Model for Electric Load Forecasting using Feature Selection and Genetic Algorithm: Comparison with Machine Learning Approaches †

2018-06-22

Salah Bouktif , Ali Fiaz , Ali Ouni +1 more

Background: With the development of smart grids, accurate electric load forecasting has become increasingly important as it can help power companies in better load scheduling and reduce excessive electricity production. … Background: With the development of smart grids, accurate electric load forecasting has become increasingly important as it can help power companies in better load scheduling and reduce excessive electricity production. However, developing and selecting accurate time series models is a challenging task as this requires training several different models for selecting the best amongst them along with substantial feature engineering to derive informative features and finding optimal time lags, a commonly used input features for time series models. Methods: Our approach uses machine learning and a long short-term memory (LSTM)-based neural network with various configurations to construct forecasting models for short to medium term aggregate load forecasting. The research solves above mentioned problems by training several linear and non-linear machine learning algorithms and picking the best as baseline, choosing best features using wrapper and embedded feature selection methods and finally using genetic algorithm (GA) to find optimal time lags and number of layers for LSTM model predictive performance optimization. Results: Using France metropolitan’s electricity consumption data as a case study, obtained results show that LSTM based model has shown high accuracy then machine learning model that is optimized with hyperparameter tuning. Using the best features, optimal lags, layers and training various LSTM configurations further improved forecasting accuracy. Conclusions: A LSTM model using only optimally selected time lagged features captured all the characteristics of complex time series and showed decreased Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) for medium to long range forecasting for a wider metropolitan area.

View PDF Chat

Predicting residential energy consumption using CNN-LSTM neural networks

2019-06-03

Tae Young Kim , Sung-Bae Cho

A review of deep learning for renewable energy forecasting

2019-07-17

Huaizhi Wang , Zhenxing Lei , Xian Zhang +2 more

Artificial intelligence in sustainable energy industry: Status Quo, challenges and opportunities

2021-01-09

Tanveer Ahmad , Dongdong Zhang , Chao Huang +4 more

View PDF Chat

ARIMA Models to Predict Next-Day Electricity Prices

2002-09-01

Javier Contreras , Rosario Espinola , Francisco J. Nogales +1 more

Price forecasting is becoming increasingly relevant to producers and consumers in the new competitive electric power markets. Both for spot markets and long-term contracts, price forecasts are necessary to develop … Price forecasting is becoming increasingly relevant to producers and consumers in the new competitive electric power markets. Both for spot markets and long-term contracts, price forecasts are necessary to develop bidding strategies or negotiation skills in order to maximize benefit. This paper provides a method to predict next-day electricity prices based on the ARIMA methodology. ARIMA techniques are used to analyze time series and, in the past, have been mainly used for load forecasting due to their accuracy and mathematical soundness. A detailed explanation of the aforementioned ARIMA models and results from mainland Spain and Californian markets are presented.

Short-term multi-step wind power prediction model based on Pt-Transformer neural network integrating spatio-temporal feature and sparse attention

2025-06-25

Zhiyan Zhang , Zhenyang Sun , Xianghui Guo +3 more | Electric Power Systems Research

Multi-strategy improved black-winged kite algorithm and its application in short-term load forecasting using gated recurrent unit neural networks

2025-06-25

Hao Zhang , Liming Liu , Y. Yang +1 more | Evolutionary Intelligence

Carbon price volatility prediction using a hybrid CEEMDAN-attention-LSTM approach

2025-06-25

Jingjing Yao , Heping Wang , Suzhen Mao | Evolving Systems

Causal neural network for carbon prices probabilistic forecasting

2025-06-25

Te Han , Xiaoyang Gu , Dan Li +4 more | Applied Energy

A PatchTST-GRU based heterogeneous seq2seq model with numerical weather prediction refinement for multi-step wind power forecasting

2025-06-25

Shiwei Xu , Yongjun Wang , Xinglei Xu +3 more | Scientific Reports

A LightGBM-Based Power Grid Frequency Prediction Method with Dynamic Significance–Correlation Feature Weighting

2025-06-24

Jie Zhou , Xiangqian Tong , Shixian Bai +1 more | Energies

Accurate grid frequency prediction is essential for maintaining the stability and reliability of power systems. However, the complex dynamic characteristics of grid frequency and the nonlinear correlations among massive time … Accurate grid frequency prediction is essential for maintaining the stability and reliability of power systems. However, the complex dynamic characteristics of grid frequency and the nonlinear correlations among massive time series data make it challenging for traditional time series prediction methods to balance efficiency and accuracy. In this paper, we propose a Dynamic Significance–Correlation Weighting (D-SCW) method, which generates dynamic weight coefficients that evolve over time. This is achieved by constructing a joint screening mechanism of feature time series correlation analysis and statistical significance test, combined with the LightGBM gradient-boosting decision tree (GBDT) framework; accordingly, high-precision prediction of grid frequency time series data is realized. To verify the effectiveness of the D-SCW method, this study conducts comparative experiments on two actual grid operation datasets (including typical scenarios with wind/photovoltaic (PV) installations, accounting for 5–35% of the grid); additionally, the Spearman’s rank correlation coefficient method, mutual information (MI), Lasso regression, and the feature screening method of recursive feature elimination (RFE) are selected as the baseline control; root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE) are adopted as assessment indicators. The results show that the D-SCW-LightGBM framework reduces the root mean squared error (RMSE) by 5.2% to 10.4% and shortens the dynamic response delay by 52% compared with the benchmark method in high renewable penetration scenarios, confirming its effectiveness in both prediction accuracy and computational efficiency.

Leveraging Machine Learning in Next-Generation Climate Change Adaptation Efforts by Increasing Renewable Energy Integration and Efficiency

2025-06-24

Izabela Rojek , Dariusz Mikołajewski , Marek Andryszczyk +2 more | Energies

This article examines the growing role of machine learning (ML) in promoting next-generation climate change adaptation through the improved integration and performance of renewable energy systems. As climate change accelerates, … This article examines the growing role of machine learning (ML) in promoting next-generation climate change adaptation through the improved integration and performance of renewable energy systems. As climate change accelerates, innovative solutions are urgently needed to enhance the resilience and sustainability of energy infrastructure.ML offers powerful capabilities to handle complex data sets, forecast energy supply and demand, and optimize grid operations. This review highlights key applications of ML, such as predictive maintenance, intelligent grid management, and the real-time optimization of renewable energy resources. It also examines current challenges, including data availability, model transparency, and the need for interdisciplinary collaboration, both in technology development and policy and regulation. By synthesizing recent research and case studies, thisarticle shows how ML can significantly improve the performance, reliability, and scalability of renewable energy systems. This review emphasizes the importance of aligning technological advances with policy and infrastructure development. Successful implementation requires not only ensuring technological capabilities (robust infrastructure, structured data sets, and interdisciplinary collaboration) but also the careful consideration and alignment of ethical and regulatory factors from strategic to regional and local levels. Machine learning is becoming a key enabler for the transition to more adaptive, efficient, and low-carbon energy systems in response to climate change.

A Comparative Analysis of Price Forecasting Methods for Maximizing Battery Storage Profits

2025-06-24

Alessandro Fiori Maccioni , Simone Sbaraglia , Rahim Mahmoudvand +1 more | Energies

Battery energy storage systems (BESS) rely on accurate electricity price forecasts to maximize arbitrage profits in day-ahead markets. We examined whether specific forecasting models, ranging from statistical benchmarks to machine … Battery energy storage systems (BESS) rely on accurate electricity price forecasts to maximize arbitrage profits in day-ahead markets. We examined whether specific forecasting models, ranging from statistical benchmarks to machine learning methods, consistently deliver superior financial outcomes for storage operators. Using real market data from the Italian day-ahead electricity market over 2020–2024, we compared univariate singular spectrum analysis (SSA), ARIMA, SARIMA, random forests, and a 30-day simple moving average under a unified trading framework. All models were evaluated based on their ability to generate arbitrage profits. Univariate SSA clearly outperformed all alternatives, achieving on average 98% of the theoretical maximum profit while maintaining the lowest forecast error. Among the other models, simpler approaches performed surprisingly well: they achieved comparable, if not superior, profit performance to more complex, hour-specific, or computationally intensive configurations. These results were robust to plausible variations in battery parameters and retraining schedules, suggesting that univariate SSA offers a uniquely effective forecasting solution for battery arbitrage and that simplicity can often be more effective than complexity in operational revenue terms.

A Regression Model for Forecasting the Impact on Continuity Indicators and Its Influence on the Number of Critical Days

2025-06-24

Thiago Eliandro de Oliveira Gomes , Vinícius Jacques Garcia , André Ross Borniatti | Revista de Gestão Social e Ambiental

Objective: To evaluate the effectiveness of simple and multiple linear regression models in predicting the number of monthly critical days in an electric utility company in the state of Rio … Objective: To evaluate the effectiveness of simple and multiple linear regression models in predicting the number of monthly critical days in an electric utility company in the state of Rio Grande do Sul, considering climatic variables as predictive factors. Method: The research used data on critical days of electrical interruption and climatic variables (precipitation, atmospheric pressure, temperature, winds, and humidity) collected between 2015 and 2020. Following a descriptive and correlation analysis, multiple linear regression models were applied, and the least significant variables were iteratively removed. Statistical tests assessed the normality, homoscedasticity, and independence of the residuals to ensure the model's adequacy. Results and Discussion: The adjusted models explained a low variability in critical days (adjusted R² up to 32%), with high error rates in predictions. The model identified a significant relationship between critical days and climatic variables (especially precipitation and winds) but with insufficient results for reliable forecasting. This suggests the need for more robust models and new variables to improve accuracy. Research Implications: Practical implications indicate the limitation of linear regression models for accurate predictions of critical days due to high data variability. Practically, it highlights the importance of seeking additional variables and alternative methodologies to support proactive planning and management of electric networks, while theoretical implications add a new perspective on the use of climatic variables as predictors of power interruptions, suggesting that while linear regression is common, it may have limitations. This encourages future investigations with nonlinear or hybrid models to improve predictions in this field. Originality/Value: The originality of the research lies in the attempt to directly correlate specific climatic indicators (precipitation, atmospheric pressure, and wind speed) with critical days, a topic still underexplored in energy reliability forecasts. This approach is innovative by investigating the impact of climatic variables on monthly interruptions, even recognizing that these linear regression models have limitations in capturing all variability of critical days. The relevance and value of the research are in highlighting how climatic factors can directly influence the reliability of the power grid, especially for energy distributors facing frequent interruptions due to adverse climatic events.

Wavelet-Enhanced Sequence-to-Sequence Modeling with Attention Mechanism for Short-Term Wind Power Forecasting

2025-06-24

Baysal Karaca , Kamil Demirberk Ünlü , Semra Türkan | Cybernetics & Systems

Acceptable cost-driven multivariate load forecasting for integrated coal mine energy systems

2025-06-24

Xiaoxuan Xing , Dunwei Gong , Yan Wang +2 more | Applied Energy

Statistical and Machine Learning Approaches for Energy Consumption Forecasting Using Time Series Analysis

2025-06-24

Ismail Mohamed Youssouf , Taha Etem | Muş Alparslan Üniversitesi Fen Bilimleri Dergisi

Energy production is a rapidly growing activity, especially with the impacts of climate change. It has even become a competitive activity among countries. However, this production is not constant or … Energy production is a rapidly growing activity, especially with the impacts of climate change. It has even become a competitive activity among countries. However, this production is not constant or continuous most of the time, as it depends on external factors such as weather conditions or, in some cases, fossil fuel production. Therefore, predicting energy production has become essential to optimize and manage its efficiency. In this study, a time series of renewable energy production is predicted using statistical models such as ARIMA and SARIMAX, as well as machine learning models such as LSTM and Gaussian Process Regression (GPR). These models are compared, based on evaluation metrics, on predictions made by each model, and on the forecasting over a period of 72 steps. After applying the various comparison techniques, the best-performing model is SARIMAX, with an MSE of 0.000031, an RMSE of 0.0026, an MAE of 0.0015 , and an R² of 99.98%. Furthermore, this model predicts the data as effectively as other models and provides near-perfect forecasting.

A decomposition–integration interval prediction strategy for iron ore shipping freight rates with reinforcement learning

2025-06-24

Hongyue Guo , Yijia Zhang , Yating Yu +3 more | Engineering Applications of Artificial Intelligence

A Comparative Evaluation of Time-Series Forecasting Models for Energy Datasets

2025-06-24

Nikitas Maragkos , Ioannis Refanidis | Computers

Time series forecasting plays a critical role across numerous domains such as finance, energy, and healthcare. While traditional statistical models have long been employed for this task, recent advancements in … Time series forecasting plays a critical role across numerous domains such as finance, energy, and healthcare. While traditional statistical models have long been employed for this task, recent advancements in deep learning have led to a new generation of state-of-the-art (SotA) models that offer improved accuracy and flexibility. However, there remains a gap in understanding how these forecasting models perform under different forecasting scenarios, especially when incorporating external variables. This paper presents a comprehensive review and empirical evaluation of seven leading deep learning models for time series forecasting. We introduce a novel dataset that combines energy consumption and weather data from 24 European countries, allowing us to benchmark model performance across various forecasting horizons, granularities, and variable types. Our findings offer practical insights into model strengths and limitations, guiding future applications and research in time series forecasting.

Improving Streamflow Forecasting Efficiency Using Signal Decomposition Approaches

2025-06-24

Dinesh Kumar Vishwakarma , Salim Heddam , Arpit Gaur +7 more | Water Resources Management

Wind Energy Prediction Using Hybrid LSTM and CNN Approaches

2025-06-24

R. Biswas , Sunit Jana , Koushik Pal +3 more | International Journal of Advanced Research in Science Communication and Technology

Maintaining grid stability and optimizing energy dispatch depend heavily on accurate wind energy forecasting. The complex temporal and spatial fluctuations present in wind patterns are frequently difficult to model using … Maintaining grid stability and optimizing energy dispatch depend heavily on accurate wind energy forecasting. The complex temporal and spatial fluctuations present in wind patterns are frequently difficult to model using conventional statistical and stand-alone machine learning models. This work presents a new hybrid deep learning framework that combines Long Short-Term Memory (LSTM) networks for temporal dependency capture and Convolutional Neural Networks (CNN) for spatial feature extraction in a synergistic manner. By utilizing real-world wind power datasets, the suggested model outperforms traditional methods, such as CNN, standalone LSTM, and classical regressors, resulting in a significant decrease in both Mean Absolute Error (MAE) and Root Mean Square Error (RMSE). The outcomes highlight the framework's efficacy and scalability, providing a solid way to support the integration of renewable energy sources into contemporary power systems

Analysis of a steam turbine’s availability and reliability for the sugar industry using the Kolmogorov–Smirnov Test

2025-06-24

Bahubali Balaso Farande , Hanumant P. Jagtap , Suyog S. Patil | International Journal of Systems Assurance Engineering and Management

Energy Demand Forecasting and Policy Development in Turkey

2025-06-24

Ercan Köse , Sevil Kutlu Kaynar | Energies

As Turkey’s energy demand surges due to industrialization, population growth, and economic development, precise forecasting of electricity demand has become crucial for ensuring energy security and facilitating sustainable planning. This … As Turkey’s energy demand surges due to industrialization, population growth, and economic development, precise forecasting of electricity demand has become crucial for ensuring energy security and facilitating sustainable planning. This study undertakes an analysis of Turkey’s current energy landscape and develops long-term electricity demand forecasts utilizing a diverse array of statistical and machine learning models, including linear regression, polynomial regression, and artificial neural networks (ANNs). By incorporating economic indicators, demographic trends, and historical consumption data, this research projects Turkey’s electricity demand up to 2045. Among the various influencing factors, industrial production stands out as the most significant driver. The findings offer strategic insights into infrastructure investments, the integration of renewable energy, and policies aimed at enhancing efficiency. This research presents a data-driven, policy-oriented framework to assist decision-makers in reducing import dependence while steering Turkey towards a sustainable energy transition.

Leveraging a deep learning model to improve mid- and long-term operations of hydro-wind-photovoltaic complementary systems

2025-06-23

Qian Cheng , Pan Liu , Maoyuan Feng +7 more | Renewable and Sustainable Energy Reviews

Forecasting electricity prices in the Polish Day-Ahead Market using machine learning models

2025-06-23

Rafał Sowiński , Aleksandra Komorowska | Polityka Energetyczna – Energy Policy Journal

Multi-Step Natural Gas Load Forecasting Incorporating Data Complexity Analysis with Finite Features

2025-06-23

Ning Tian , Bilin Shao , Huibin Zeng +4 more | Entropy

Data complexity directly affects the dynamics of complex systems, which in turn influences the accuracy and robustness of forecasting models. However, the load data exhibit complex features such as self-similarity, … Data complexity directly affects the dynamics of complex systems, which in turn influences the accuracy and robustness of forecasting models. However, the load data exhibit complex features such as self-similarity, long-term memory, randomness, and chaos. This study aims to quantify and evaluate the complexity features of natural gas loads and to develop a multi-step-ahead forecasting model that integrates data decomposition and ensemble deep learning while considering these complexity features. Firstly, the complexity features of the series are quantified by rolling the fractal dimension, Hurst exponent, sample entropy, and maximum Lyapunov exponent. The analysis contributes to understanding data characteristics and provides information on complex features. Secondly, the ensemble learning eXtreme Gradient Boosting (XGBoost) can effectively screen complexity features and meteorological factors. Concurrently, variational mode decomposition (VMD) provides frequency-domain decomposition capability, while the gated recurrent unit (GRU) captures long-term dependencies. This synergy enables effective learning of local features and long-term temporal patterns, resulting in precise predictions. The results indicate that compared to other models, the proposed method (XGBoost-VMD-GRU considering complex features) demonstrates superior performance in forecasting, with R2 of 0.9922, 0.9860, and 0.9679 for one-step, three-step, and six-step prediction, respectively. This study aims to bring innovative ideas to load forecasting by integrating complex features into the decomposition forecasting framework.

Forecasting of Sea-Surface Wind Speed Using Deep-Learning Method Based on Multidimensional Frequency-Domain Feature Fusion

2025-06-23

Jiaru He , Zengan Deng | Journal of Ocean University of China

A multi-objective optimization-based ensemble neural network wind speed prediction model

2025-06-23

Haoyuan Ma , Chang Liu , Zhiwei Qiao +2 more | International Journal of Electrical Power & Energy Systems

Forecasting Seasonal Trends in ENT Diseases: A Comparative Analysis of Statistical and Machine Learning Models

2025-06-23

Phuc T. Le | Journal on Information Technologies & Communications

This study examines patterns of seasonal illnesses at an ENT hospital using statistical methods andadvanced machine learning techniques to improve disease prediction and support healthcare planning. Thedata underwent careful cleaning … This study examines patterns of seasonal illnesses at an ENT hospital using statistical methods andadvanced machine learning techniques to improve disease prediction and support healthcare planning. Thedata underwent careful cleaning to ensure accuracy, which involved identifying outliers, managing missingvalues, and normalizing information. The study looked at how seasonal illnesses develop, using a mix oftechniques. This research used advanced tools like Long Short-Term Memory (LSTM) networks andProphet, as well as simpler models such as Holt-Winters and SARIMA. To make the models easier tounderstand, there is an application of SHAP (SHapley Additive Explanations) values. Finally, thesestatistical measures like Mean Absolute Error (MAE) and confidence periods had been used to check theaccuracy of the forecasts at some stage in the overall performance assessment. Moreover, to discover howweather influences sickness seasonality, connections between patterns of contamination and environmentalvariables like temperature, humidity, and rainfall have been additionally looked at with the aid of the usageof correlation prediction. In well-known, this blended method shows how conventional and system gainingknowledge of models can monitor seasonal illness traits. The effects not simplest display disorder styles,but in addition they assist with allocating resources and making guidelines for better healthcaremanagement.

Advanced time series modelling to address seasonal variability and extreme rainfall in Ghana

2025-06-22

Senyefia Bosson-Amedenu , Emmanuel Mensah Baah , Francis Ayiah-Mensah +1 more | Deleted Journal

Prediction of Power Grid Energy Storage Capacity Demand Based on LSTM

2025-06-22

Jianxu Zhong , Lingzhi Xi , Shaofeng Yu +2 more | Strategic Planning for Energy and the Environment

With the continuous development of the power system, accurately predicting the power grid energy storage capacity demand is crucial for enhancing the stability and economy of the power system. This … With the continuous development of the power system, accurately predicting the power grid energy storage capacity demand is crucial for enhancing the stability and economy of the power system. This paper proposes a prediction method for power grid energy storage capacity demand based on the Long Short-Term Memory (LSTM) network. The LSTM network can effectively handle the long-term dependency problem in time series data and is suitable for the time series prediction of power grid energy storage capacity demand, which is affected by various complex factors. This paper utilizes its unique gating mechanism to process the time series affected by complex factors such as the intermittency of new energy generation and dynamic load changes. By collecting multi-dimensional data of a certain regional power grid over many years, including historical load, new energy generation, meteorology, and holidays, the model is optimized using the Adaptive Moment Estimation (Adam) optimizer and Dropout technology. Experiments show that the LSTM model can effectively improve the prediction accuracy and provide strong support for the planning and construction of power grid energy storage.

Elastic Momentum-Enhanced Adaptive Hybrid Method for Short-Term Load Forecasting

2025-06-22

Wenting Zhao , Haoran Xu , Peng Chen +3 more | Energies

Load forecasting plays a crucial role in power system planning and operational dispatch management. Accurate load prediction is essential for enhancing power system reliability and facilitating the local integration of … Load forecasting plays a crucial role in power system planning and operational dispatch management. Accurate load prediction is essential for enhancing power system reliability and facilitating the local integration of renewable energy. This paper proposes a hybrid approach combining traditional time series models (ARIMA) with machine learning models (SVR). The particle swarm optimization (PSO) algorithm is improved by adjusting its elastic momentum, and the enhanced APSO algorithm is employed to optimize the adaptive weights of the hybrid model. Consequently, an elastic momentum-enhanced adaptive weighted load forecasting model (APSO-ARIMA-SVR) is developed. Numerical simulations using real-world datasets validate the model’s effectiveness. Results demonstrate that the proposed APSO-ARIMA-SVR model achieves optimal fitting performance, with prediction errors of 274.23 (MAE) and 321.50 (RMSE), representing the lowest errors among all comparative models.

A Dual Decomposition and Dynamic Weighting-Based Integrated Forecasting Method for Ultra-Short-Term Wind Power

2025-06-21

Jian Tang , Junfu Lv , Guangxi Yue +1 more | International Journal of High Speed Electronics and Systems

Accurate wind power forecasting is crucial for the safe scheduling, stable operation, and economic benefits of the power grid. However, the volatility and randomness of wind power present significant challenges … Accurate wind power forecasting is crucial for the safe scheduling, stable operation, and economic benefits of the power grid. However, the volatility and randomness of wind power present significant challenges in developing high-precision forecasting models. This study proposes an ultra-short-term wind power integrated forecasting model based on dual decomposition and intelligent optimization algorithms. The model first employs seasonal-trend (STL) decomposition to decompose the wind power time series into long-term trends, seasonal components, and residuals, revealing the multi-scale characteristics of the data. Then, various forecasting models are applied to model each decomposed component in order to capture their distinct characteristics. Subsequently, the Stacking method is used to integrate the predictions of these models, with linear regression (LR) serving as the meta-learner to combine the results. An intelligent optimization algorithm is introduced to tune the model parameters, thereby enhancing the forecasting performance. Additionally, to address the error between the predicted and actual values, variational mode decomposition (VMD) is applied to further decompose the errors, and a long short-term memory (LSTM)network is employed for dynamic correction, thus improving the final prediction accuracy. Experimental results on data from a wind farm in Xinjiang, China, show that compared to traditional methods and other advanced techniques, the proposed model demonstrates significant advantages in forecasting accuracy, stability, and handling the nonlinear and non-stationary characteristics of wind power.

A dynamic graph-based multiscale spatio-temporal feature enhancement network applied to ENSO prediction

2025-06-21

Wei Shao , Guoxiang Tong | Applied Intelligence

Key Technologies of Agent Power Purchasing Service Evaluation Based on Multidimensional Correlation and Fine-Grainedness

2025-06-21

Jinfeng Gao , Yulu Ren , Daqing Gao +2 more | International Journal of High Speed Electronics and Systems

This study constructs a framework for evaluating proxy power purchasing services based on multidimensional associations, aiming to improve the performance and value of proxy power purchasing services by comprehensively analyzing … This study constructs a framework for evaluating proxy power purchasing services based on multidimensional associations, aiming to improve the performance and value of proxy power purchasing services by comprehensively analyzing the complex relationships among multidimensional attributes such as electricity price, electricity consumption, and supply and demand balance. The study first proposes a multifaceted feature space model, using covariance matrix and radial basis kernel function (RBF) to capture linear and nonlinear correlations, providing a theoretical basis for data-driven service optimization. Subsequently, the study designs a dataset with a hierarchical time series structure. It combines the entropy method to select key attributes to ensure the scientificity and comprehensiveness of the evaluation indicators. Fine-grained evaluation indicators include response time, cost optimization rate, and fluctuation coefficient, which accurately measure service quality. Principal component analysis (PCA) dimensionality reduction and fuzzy clustering techniques are used for dimensional optimization to improve the evaluation efficiency. Experimental results show that the new model is significantly superior to traditional models and competitors regarding response time, cost savings, price fluctuation control, personalized demand satisfaction, seasonal adaptability, and emergency response capabilities. The study verifies the effectiveness of multidimensional association analysis and provides practical guidance for the scientific management of the power market.

Wind Speed Forecasting in the Greek Seas Using Hybrid Artificial Neural Networks

2025-06-21

Lateef Adesola Afolabi , Takvor Soukissian , Diego Vicinanza +1 more | Atmosphere

The exploitation of renewable energy is essential for mitigating climate change and reducing fossil fuel emissions. Wind energy, the most mature technology, is highly dependent on wind speed, and the … The exploitation of renewable energy is essential for mitigating climate change and reducing fossil fuel emissions. Wind energy, the most mature technology, is highly dependent on wind speed, and the accurate prediction of the latter substantially supports wind power generation. In this work, various artificial neural networks (ANNs) were developed and evaluated for their wind speed prediction ability using the ERA5 historical reanalysis data for four potential Offshore Wind Farm Organized Development Areas in Greece, selected as suitable for floating wind installations. The training period for all the ANNs was 80% of the time series length and the remaining 20% of the dataset was the testing period. Of all the ANNs examined, the hybrid model combining Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) networks demonstrated superior forecasting performance compared to the individual models, as evaluated by standard statistical metrics, while it also exhibited a very good performance at high wind speeds, i.e., greater than 15 m/s. The hybrid model achieved the lowest root mean square errors across all the sites—0.52 m/s (Crete), 0.59 m/s (Gyaros), 0.49 m/s (Patras), 0.58 m/s (Pilot 1A), and 0.55 m/s (Pilot 1B)—and an average coefficient of determination (R2) of 97%. Its enhanced accuracy is attributed to the integration of the LSTM and GRU components strengths, enabling it to better capture the temporal patterns in the wind speed data. These findings underscore the potential of hybrid neural networks for improving wind speed forecasting accuracy and reliability, contributing to the more effective integration of wind energy into the power grid and the better planning of offshore wind farm energy generation.

Short-Term Power Load Forecasting Using an Improved Model Integrating GCN and Transformer

2025-06-21

Man Wu , Wanyi Feng , Xinman Li +2 more | Applied Sciences

Improving the accuracy of power load forecasting is an important link in the optimization of power systems. Most of the existing studies in the short-term load forecasting task at present … Improving the accuracy of power load forecasting is an important link in the optimization of power systems. Most of the existing studies in the short-term load forecasting task at present have the problem of insufficient extraction of multi-scale features. Therefore, in order to improve prediction accuracy, this study designs a short-term power load forecasting model integrating multi-scale GCN and the improved Transformer, as well as the prediction method based on this model. First, multi-feature power load data were collected. Second, the random forest algorithm was used to preprocess the data. Next, multi-scale GCN was utilized to model the multi-scale spatio-temporal features in the power load data. The data processed by the multi-scale GCN were input into the improved Transformer module based on MLLA to extract long-term temporal dependencies. Subsequently, comparative experiments and ablation experiments were conducted on three public power datasets. The experimental results show that, compared to the comparative model, for the ETTh1 dataset, the RMSE index of this model decreased by up to 0.314, the MAE decreased by up to 0.304, and the R2 index result improved by up to 9.45%. For the ETTm1 dataset, the RMSE index of this model decreased by up to 0.266, the MAE decreased by up to 0.231, and the R2 index result improved by up to 3.3%. For the Australian dataset, the RMSE index of this model decreased by up to 494.366, the MAE decreased by up to 493.127, and the R2 index result improved by up to 54%, verifying the superiority and effectiveness of the proposed model.

Advanced Operator Theory for Energy Market Trading: A New Framework

2025-06-20

Michele Bufalo , Viviana Fanelli | Risks

This paper analyzes a parabolic operator L that generalizes several well-known operators commonly used in financial mathematics. We establish the existence and uniqueness of the Feller semigroup associated with L … This paper analyzes a parabolic operator L that generalizes several well-known operators commonly used in financial mathematics. We establish the existence and uniqueness of the Feller semigroup associated with L and derive its explicit analytical representation. The theoretical framework developed in this study provides a robust foundation for modeling stochastic processes relevant to financial markets. Furthermore, we apply these findings to energy market trading by developing specialized simulation algorithms and forecasting models. These methodologies were tested across all assets comprising the S&P 500 Energy Index, evaluating their predictive accuracy and effectiveness in capturing market dynamics. The empirical analysis demonstrated the practical advantages of employing generalized semigroups in modeling non-Gaussian market behaviors and extreme price fluctuations.

Spatio-Temporal Attention-Based Deep Learning for Smart Grid Demand Prediction

2025-06-20

Muhammed Cavus , Adib Allahham | Electronics

Accurate short-term load forecasting is vital for the reliable and efficient operation of smart grids, particularly under the uncertainty introduced by variable renewable energy sources (RESs) such as solar and … Accurate short-term load forecasting is vital for the reliable and efficient operation of smart grids, particularly under the uncertainty introduced by variable renewable energy sources (RESs) such as solar and wind. This study introduces ST-CALNet, a novel hybrid deep learning framework that integrates convolutional neural networks (CNNs) with an Attentive Long Short-Term Memory (LSTM) network to enhance forecasting performance in renewable-integrated smart grids. The CNN component captures spatial dependencies from multivariate inputs, comprising meteorological variables and generation data, while the LSTM module models temporal correlations in historical load patterns. An embedded attention mechanism dynamically weights input sequences, enabling the model to prioritise the most influential time steps, thereby improving its interpretability and robustness during demand fluctuations. ST-CALNet was trained and evaluated using real-world datasets that include electricity consumption, solar photovoltaic (PV) output, and wind generation. Experimental evaluation demonstrated that the model achieved a mean absolute error (MAE) of 0.0494, root mean squared error (RMSE) of 0.0832, and a coefficient of determination (R2) of 0.4376 for electricity demand forecasting. For PV and wind generation, the model attained MAE values of 0.0134 and 0.0141, respectively. Comparative analysis against baseline models confirmed ST-CALNet’s superior predictive accuracy, particularly in minimising absolute and percentage-based errors. Temporal and regime-based error analysis validated the model’s resilience under high-variability conditions such as peak load periods, while visualisation of attention scores offered insights into the model’s temporal focus. These findings underscore the potential of ST-CALNet for deployment in intelligent energy systems, supporting more adaptive, transparent, and dependable forecasting within smart grid infrastructures.

Short-Term Power Load Forecasting Model Based on BiLSTM-SDPAM

2025-06-20

Xiaojun Jin , Shoujun Zhang , Qinghe Zhao +3 more | International Journal of High Speed Electronics and Systems

In order to effectively mine historical data information and improve the accuracy of short-term electricity load forecasting, a short-term electricity load forecasting model is proposed that integrates a bidirectional long … In order to effectively mine historical data information and improve the accuracy of short-term electricity load forecasting, a short-term electricity load forecasting model is proposed that integrates a bidirectional long short-term memory (BiLSTM) network with a scaled dot-product attention mechanism (SDPAM). This model incorporates SDPAM into the BiLSTM framework, enabling the model to leverage the capacity of BiLSTM to process sequential data and capture bidirectional temporal dependencies within the sequence. Additionally, it dynamically weights the meteorological factors that are strongly correlated with the forecasting results through SDPAM, thereby achieving high-accuracy electricity load forecasting. Ablation experiments are conducted to analyze the contributions of different components of the model. The proposed model is applied to short-term electricity load forecasting in a certain prefecture-level city in the Heilongjiang Province. Case study analysis shows that, compared to other benchmark models, the proposed model demonstrates a significant improvement in the root mean square error (RMSE) by 9.36–53.49% and in the mean absolute error (MAE) by 9.43–55.77%. Ultimately, the results show that the proposed model has higher accuracy and certain engineering application value.

Empowering energy sustainability: A cutting-edge ensemble network for precise power forecasting

2025-06-20

Taimoor Khan , Chang Jae Choi | Energy Reports

Electricity Consumption Behavior and Load Forecasting Analysis Coupling Meteorological Factors Using BK-Means and NRBO-XGBoost Algorithms

2025-06-20

Nantian Huang , Jìngyuàn Zhāng , Shicheng Ren +3 more | Research Square (Research Square)

<title>Abstract</title> To address the challenges of extracting user electricity consumption behavior features and insufficient load prediction accuracy in multi-energy coupling scenarios, this study proposes an electricity behavior analysis and forecasting … <title>Abstract</title> To address the challenges of extracting user electricity consumption behavior features and insufficient load prediction accuracy in multi-energy coupling scenarios, this study proposes an electricity behavior analysis and forecasting methodology integrating data cleansing with meteorological correlations. Firstly, the Akima interpolation method is employed to rectify abnormal load data points, combined with a highly robust Z-M-ESD algorithm (Z-score Median-based Extreme Studentized Deviate) incorporating median identification and seasonal adjustment for iterative data cleansing, achieving an average 64.765% reduction in outlier correction errors. Secondly, BIRCH pre-clustering is utilized to adaptively determine optimal cluster numbers and initial centroids, thereby improving the traditional K-Means algorithm for joint meteorological clustering analysis of wind-photovoltaic power outputs and load coupling, as well as user clustering analysis. This enhancement elevates the user classification silhouette coefficient to 0.4679, representing a 24.04% improvement over conventional methods. Finally, an NRBO-XGBoost based load forecasting model incorporating meteorological parameters such as temperature and humidity is developed. Experimental results demonstrate that the proposed approach reduces the root mean square error to 49.2 kW and mean absolute error to 38.6 kW when considering meteorological factors. This methodology provides a theoretical foundation for demand-side management in power systems.

Calculation of the degree of variation of the electric power demand curve caused by the Covid-19 pandemic, using the Fractal Dimension

2025-06-20

Héctor A. Tabares-Ospina , Jaime Valencia | Fractals

Very Short-Term Load Forecasting Model for Large Power System Using GRU-Attention Algorithm

2025-06-20

Tae-Geun Kim , Sung‐Guk Yoon , Kyung‐Bin Song | Energies

This paper presents a very short-term load forecasting (VSTLF) model tailored for large-scale power systems, employing a gated recurrent unit (GRU) network enhanced with an attention mechanism. To improve forecasting … This paper presents a very short-term load forecasting (VSTLF) model tailored for large-scale power systems, employing a gated recurrent unit (GRU) network enhanced with an attention mechanism. To improve forecasting accuracy, a systematic input feature selection method based on Normalized Mutual Information (NMI) is introduced. Additionally, a novel input feature termed the load variationis proposed to explicitly capture real-time dynamic load patterns. Tailored data preprocessing techniques are applied, including load reconstitution to account for the impact of Behind-The-Meter (BTM) solar generation, and a weighted averaging method for constructing representative weather inputs. Extensive case studies using South Korea’s national power system data from 2021 to 2023 demonstrate that the proposed GRU-attention model significantly outperforms existing approaches and benchmark models. In particular, when expressing the accuracy of the proposed method in terms of the error rate, the Mean Absolute Percentage Error (MAPE) is 0.77%, which shows an improvement of 0.50 percentage points over the benchmark model using the Kalman filter algorithm and an improvement of 0.27 percentage points over the hybrid deep learning benchmark (CNN-BiLSTM). The simulation results clearly demonstrate the effectiveness of the NMI-based feature selection and the combination of load characteristics for very short-term load forecasting.

SCiTransformer: A Trend-Decomposition-Guided Spatio-Temporal Convolution Enhanced iTransformer for Wind Power Forecasting

2025-06-20

Yuchen Jiang , Yang Cheng | Applied and Computational Engineering

Wind power, as a vital component of renewable energy, plays a key role in achieving carbon neutrality targets and building a green energy system. However, the highly volatile and non-stationary … Wind power, as a vital component of renewable energy, plays a key role in achieving carbon neutrality targets and building a green energy system. However, the highly volatile and non-stationary nature of wind speed presents significant challenges for wind power forecasting. Traditional methods, such as Autoregressive Integrated Moving Average (ARIMA) models and Support Vector Regression (SVR), perform well when modeling linear or weakly nonlinear relationships but often struggle to capture long-term dependencies and non-stationary patterns when faced with multiple overlapping cycles and complex disturbance structures, leading to reduced prediction accuracy and limited adaptability. To address these challenges, this study proposes a wind power forecasting framework that integrates a decomposition mechanism with deep learning strategies, namely the SCiTransformer model. Specifically, the SCiTransformer model applies Seasonal and Trend decomposition using Loess (STL) to explicitly extract trend, seasonal, and residual components from wind power time series data. It further utilizes a Convolutional Neural Network (CNN) module to capture local disturbance features within the residual series, and employs the iTransformer framework to model the global dependencies of trend and seasonal components along the variable dimension, thereby establishing a multi-stage collaborative modeling system tailored to complex sequence characteristics. Empirical studies conducted on four real-world wind farm datasets demonstrate that SCiTransformer consistently outperforms mainstream benchmark modelsincluding Transformer, Informer, DLinear, and PatchTSTin terms of both Mean Absolute Error (MAE) and Mean Squared Error (MSE), achieving superior prediction accuracy and enhanced robustness across different scenarios. Additional ablation experiments further confirm the critical contributions of the STL decomposition and CNN modules to the overall model performance. These findings suggest that the proposed model holds broad potential for applications in multi-scale modeling, non-stationary sequence forecasting, and wind power dispatch prediction.

Physics-informed spatio-temporal network with trainable adaptive feature selection for short-term wind speed prediction

2025-06-19

Laeeq Aslam , Runmin Zou , Yaohui Huang +3 more | Computers & Electrical Engineering

Configuring the Transformer-Based Electricity Market Predictions Using Ant Colony Optimisation

2025-06-19

Jakub Sahs , Bogdan Ruszczak | Ambient intelligence and smart environments

Machine learning forecasting models are becoming more complex and are being trained using vast amounts of data, thereby substantially extending their deployment. The identification of optimal configurations necessitates the evaluation … Machine learning forecasting models are becoming more complex and are being trained using vast amounts of data, thereby substantially extending their deployment. The identification of optimal configurations necessitates the evaluation of thousands of potential variants, a process that is often time-consuming. In addressing this challenge, a more sophisticated approach involves the utilization of heuristic algorithms to enhance the search process. To this end, we propose the ant colony optimization metaheuristic application for the model hyperparameter tuning. The effectiveness of the proposed approach is verified using actual market quotes and the transformer model for time series forecasting. We found this method optimal for identifying suitable parameters, and we showcased that such an algorithm is almost as powerful as the exhaustive search while providing the configuration in 9 times fewer iterations.

Analysis of Solar Energy Production Using AI Predictions Based On Climatic Conditions

2025-06-19

Abdul Kareem , R. V. V. Krishna , Md Asaduzzaman Babu +2 more | Deleted Journal

Solar energy is recognized as one of the most reliable and environmentally friendly renewable resources. However, its production efficiency is highly sensitive to fluctuating climatic conditions such as solar irradiance, … Solar energy is recognized as one of the most reliable and environmentally friendly renewable resources. However, its production efficiency is highly sensitive to fluctuating climatic conditions such as solar irradiance, temperature, humidity, and cloud cover, which makes accurate energy prediction a significant challenge. To address this, we developed an AI-powered system based on a Raspberry Pi controller, integrated with solar panels, a Battery Management System (BMS), various sensors, and weather data APIs. The system collects real-time meteorological data along with historical solar generation information, which is then processed through machine learning models to predict energy output with enhanced accuracy. This improved prediction enables better energy utilization, optimized battery storage, and increased operational stability. In comparison to traditional forecasting methods, the AI-based solution provides superior adaptability, continuous learning capabilities, and scalability across diverse environments. The integration of AI with renewable energy infrastructure represents a significant advancement toward building intelligent, efficient, and sustainable energy systems for the future.

Applying the Extended Kalman Filter and Unscented Kalman Filter to Power System Forecasting-Aided State Estimation

2025-06-19

Yu-Jen Lin , Hongyi Lin | Turkish Journal of Electrical Power and Energy Systems

Abstract: This paper represents the power system forecasting-aided state estimation (FASE) using the extended Kalman filter (EKF) and unscented Kalman filter (UKF). First, the concepts and mathematical formulations of power … Abstract: This paper represents the power system forecasting-aided state estimation (FASE) using the extended Kalman filter (EKF) and unscented Kalman filter (UKF). First, the concepts and mathematical formulations of power system state estimation (SE) are studied. Two types of power system state estimation, dynamic state estimation (DSE), and FASE are examined. Second, the principles and the essentials of the EKF and the UKF are described. Finally, the EKF and UKF are applied to the FASE of a five-bus power system. The research results and computer simulations lead to two key findings. First, we conclude that some pioneering works on DSE should be more appropriately re-classified as FASE. Second, we observe that the performance of the UKF does not always outperform that of the EKF. These two findings differ slightly from previous pioneering works and represent the key contributions of this paper. Cite this article as: Y.-J.Lin and H.-Y. Lin, "Applying the extended Kalman filter and unscented Kalman filter to power system forecasting-aided state estimation," Turk J Electr Power Energy Syst., 2025; 5(2), 96-104.

A Socio-Technical Approach to Load Forecasting for Super Smart Grids. A Multi-domain Attention-Based Neural Network

2025-06-19

José García‐Rodríguez , Israel Macias , Ricardo Enrique Gutiérrez Carvajal | Research Square (Research Square)

<title>Abstract</title> Super Smart Grids aim to provide large-scale, multi-zonal electricity access while dynamically balancing supply and demand. However, their implementation faces multidisciplinary challenges that range from ensuring grid stability to … <title>Abstract</title> Super Smart Grids aim to provide large-scale, multi-zonal electricity access while dynamically balancing supply and demand. However, their implementation faces multidisciplinary challenges that range from ensuring grid stability to avoiding structural injustices in their design. Existing load forecasting approaches are unsuitable for Super Smart Grid planning or deployment due to an over-reliance on regional specificity, time-series data, and a lack of social understanding. This paper proposes to approach load forecasting as a hybrid problem composed of a mix between time-series power consumption and socioeconomic metrics, coupled with a novel deep learning algorithm that integrates Artificial Neural Networks and Luong's Attention Mechanism. First, two parallel Artificial Neural Networks are used to extract the main features of load demand behavior. Then, Luong's Attention Mechanism fuses both Artificial Neural Networks using an attention score function that dynamically selects the most relevant characteristics per sample to improve the generalization abilities of the model. The SHapley Additive exPlanations framework then interprets this algorithm to comprehend its load forecast decision-making thoroughly. Evaluated on 92 suburban zones in Australia, the proposed method achieves a Mean Absolute Percentage Error of 1.78%, outperforming Bidirectional Long-Short Term Memory, Long-Short Term Memory, and Recurrent Neural Network models. By merging high-resolution forecasting with socioeconomic awareness, this approach enhances demand and supply management, optimizes pricing strategies, and ensures equitable energy distribution—critical requirements for Super Smart Grids deployment. 2000 MSC: 68T10, 91D99, 37M10

A Novel Stacked Ensemble Framework with the Kolmogorov-Arnold Network for Short-Term Electric Load Forecasting

2025-06-19

Muhammad Abbas , Yanbo Che , Inam Ullah Khan | Energy

Short-term electrical load forecasting strategy based on EEMD-SSA-BiLSTM

2025-06-19

Xinhao Zhang | Signal Image and Video Processing