Search

Short-term load forecasting (STLF) is essential for developing reliable and sustainable economic and operational strategies for power systems. This study presents a forecasting model combining cascade forward neural network (CFNN) and intuitionistic fuzzy time series (IFTS) models for STLF. The proposed cascading intuitionistic fuzzy time series forecasting model (C-IFTS-FM) offers the advantage of CFNN using the links of both linear and nonlinear to model fuzzy relations between inputs and outputs. Moreover, it offers a more reliable and realistic approach to uncertainty, taking notice of also the degree of hesitation. C-IFTS-FM works in univariate structure when it uses only hourly load data, and in bivariate structure when it uses hourly load data and hourly temperature time series together. The conversion of time series into IFTS is realized with intuitionistic fuzzy c-means (IFCM). Thus, the membership and non-membership values for each data point are produced. In modelling process, membership and non-membership values, in addition to actual lagged observations, are used as input of the CFNNs. The effectiveness of C-IFTS-FM on test sets for both structures was discussed comparatively via different error criteria, in addition, the convergence time was examined, and also the fit of forecasts and observations was presented with different illustrations. Among different combinations of hyperparameters, in the best case, approximately 86% better accuracy is achieved than the best of the others, while even in the case of the worst of hyperparameters combination, the accuracy was improved by over 20% for the PSJM data sets. For HEXING, CHENGNAN, and EUNITE data sets, these progress rates reached approximately 90% in the best case. [ABSTRACT FROM AUTHOR]

Accurate electricity demand forecasting is crucial for ensuring the sustainability and reliability of power systems. Least square support vector machines (LSSVM) are well suited to handle complex non-linear power load series. However, the less optimal regularization parameter and the Gaussian kernel function in the LSSVM model have contributed to flawed forecasting accuracy and random generalization ability. Thus, these parameters of LSSVM need to be chosen appropriately using intelligent optimization algorithms. This study proposes a new hybrid model based on the LSSVM optimized by the improved bacterial foraging optimization algorithm (IBFOA) for forecasting the short-term daily electricity load in Peninsular Malaysia. The IBFOA based on the sine cosine equation addresses the limitations of fixed chemotaxis constants in the original bacterial foraging optimization algorithm (BFOA), enhancing its exploration and exploitation capabilities. Finally, the load forecasting model based on LSSVM-IBFOA is constructed using mean absolute percentage error (MAPE) as the objective function. The comparative analysis demonstrates the model, achieving the highest determination coefficient (R2) of 0.9880 and significantly reducing the average MAPE value by 28.36%, 27.72%, and 5.47% compared to the deep neural network (DNN), LSSVM, and LSSVM-BFOA, respectively. Additionally, IBFOA exhibits faster convergence times compared to BFOA, highlighting the practicality of LSSVM-IBFOA for short-term load forecasting. [ABSTRACT FROM AUTHOR]

Load forecasting is an integral part of the power industries. Load-forecasting techniques should minimize the percentage error while prediction future demand. This will inherently help utilities have an uninterrupted power supply. In addition to that, accurate load forecasting can result in saving large amounts of money. This article provides a systematic review based on the Preferred Reporting Items for Systematic Review and Meta-Analyses (PRISMA) framework. This article presents a complete framework for short-term load forecasting using metaheuristic algorithms. This framework consists of three sub-layers: the data-decomposition layer, the forecasting layer, and the optimization layer. The data-decomposition layer decomposes the input data series to extract important features. The forecasting layer is used to predict the result, which involves different statistical and machine-learning models. The optimization layer optimizes the parameters of forecasting methods to improve the accuracy and stability of the forecasting model using different metaheuristic algorithms. Single models from the forecasting layer can predict the results. However, they come with their limitations, such as low accuracy, high computational burden, stuck to local minima, etc. To improve the prediction accuracy, the hyperparameters of these models need to be tuned properly. Metaheuristic algorithms cab be used to tune these hyperparameters considering their interdependencies. Hybrid models combining the three-layer methods can perform better by overcoming the issues of premature convergence and trapping into a local minimum solution. A quantitative analysis of different metaheuristic algorithms and deep-learning forecasting methods is presented. Some of the most common evaluation indices that are used to evaluate the performance of the forecasting models are discussed. Furthermore, a taxonomy of different state-of-the-art articles is provided, discussing their advantages, limitations, contributions, and evaluation indices. A future direction is provided for researchers to deal with hyperparameter tuning. [ABSTRACT FROM AUTHOR]

Accurate and efficient short-term load forecasting (STLF) is essential for optimizing power system operations. This study proposes a novel hybrid forecasting model that integrates XGBoost-RF feature selection with a CNN-GRU neural network to enhance prediction performance while reducing model complexity. The XGBoost-RF approach is first applied to select the most predictive features from historical load data, weather conditions, and time-based variables. A convolutional neural network (CNN) is then employed to extract spatial features, while a gated recurrent unit (GRU) captures temporal dependencies for load forecasting. By leveraging a dual-channel structure that combines long- and short-term historical load trends, the proposed model significantly mitigates cumulative errors from recursive predictions. Experimental results demonstrate that the model achieves superior performance with an average root mean square error (RMSE) of 53.29 and mean absolute percentage error (MAPE) of 3.56% on the test set. Compared to traditional models, the prediction accuracy improves by 28.140% to 110.146%. Additionally, the model exhibits strong robustness across different climatic conditions. This research validates the efficacy of integrating XGBoost-RF feature selection with CNN-GRU for STLF, offering reliable decision support for power system management. [ABSTRACT FROM AUTHOR]

Studies on probabilistic demand forecasting remain relatively limited compared with point forecasting, despite it being especially valuable for operational and planning purposes. This paper demonstrates different applications of probabilistic forecasting in demand response, together with Physical-Based Load Models. The first application shows how to determine the percentage of uncertainty potentially covered by demand response throughout a day, whereas the second application deals with obtaining the number of consumers that would be needed in demand response actions for a desired percentage of coverage. Finally, in the third application, a specific hourly strategy is proposed for demand response policies. These applications facilitate the aggregator's energy purchasing in the market and the planning of subsequent consumption adjustments through demand response to minimize deviations from the purchased energy. The approach is illustrated using hourly demand data from a small Spanish city, and two machine learning methods were used to produce a set of probabilistic forecasts and compare results: Linear Quantile Regression and a Quantile Regression Forest. Main results show a significant reduction in deviations from the purchased energy after applying the proposed strategy, especially in the case of the forecasting method being less accurate (40.95% and 33.62% of reduction, respectively). [ABSTRACT FROM AUTHOR]

To enhance the refinement of load decomposition in power systems and fully leverage seasonal change information to further improve prediction performance, this paper proposes a seasonal short-term load combination prediction model based on modal decomposition and a feature-fusion multi-algorithm hybrid neural network model. Specifically, the characteristics of load components are analyzed for different seasons, and the corresponding models are established. First, the improved complete ensemble empirical modal decomposition with adaptive noise (ICEEMDAN) method is employed to decompose the system load for all four seasons, and the new sequence is obtained through reconstruction based on the refined composite multiscale fuzzy entropy of each decomposition component. Second, the correlation between different decomposition components and different features is measured through the max-relevance and min-redundancy method to filter out the subset of features with strong correlation and low redundancy. Finally, different components of the load in different seasons are predicted separately using a bidirectional long-short-term memory network model based on a Bayesian optimization algorithm, with a prediction resolution of 15 min, and the predicted values are accumulated to obtain the final results. According to the experimental findings, the proposed method can successfully balance prediction accuracy and prediction time while offering a higher level of prediction accuracy than the current prediction methods. The results demonstrate that the proposed method can effectively address the load power variation induced by seasonal differences in different regions. [ABSTRACT FROM AUTHOR]

Short-term load forecasting plays an important role in power system scheduling, optimization, and maintenance, but no existing typical method can consistently maintain high prediction accuracy. Hence, fusing different complementary methods is increasingly focused on. To improve forecasting accuracy and stability, these features that affect the short-term power system are firstly extracted as prior knowledge, and the advantages and disadvantages of existing methods are analyzed. Then, three typically methods are used for short-term power load forecasting, and their interaction and complementarity are studied. Finally, the Choquet integral (CI) is used to fuse the three existing complementarity methods. Different from other fusion methods, the CI can fully utilize the interactions and complementarity among different methods to achieve consistent forecasting results, and reduce the disadvantages of a single forecasting method. Essentially, a CI with n inputs is equivalent to n! constrained feedforward neural networks, leading to a strong generalization ability in the load prediction process. Consequently, the CI-based method provides an effective way for the fusion forecasting of short-term load in power systems. [ABSTRACT FROM AUTHOR]

The accurate, rapid, and stable prediction of electrical energy consumption is essential for decision-making, energy management, efficient planning, and reliable power system operation. Errors in forecasting can lead to electricity shortages, wasted resources, power supply interruptions, and even grid failures. Accurate forecasting enables timely decisions for secure energy management. However, predicting future consumption is challenging due to the variable behavior of customers, requiring flexible models that capture random and complex patterns. Forecasting methods, both traditional and modern, often face challenges in achieving the desired level of accuracy. To address these shortcomings, this research presents a novel hybrid approach that combines a robust forecaster with an advanced optimization technique. Specifically, the FS-FCRBM-GWDO model has been developed to enhance the performance of short-term load forecasting (STLF), aiming to improve prediction accuracy and reliability. While some models excel in accuracy and others in convergence rate, both aspects are crucial. The main objective was to create a forecasting model that provides reliable, consistent, and precise predictions for effective energy management. This led to the development of a novel two-stage hybrid model. The first stage predicts electrical energy usage through four modules using deep learning, support vector machines, and optimization algorithms. The second stage optimizes energy management based on predicted consumption, focusing on reducing costs, managing demand surges, and balancing electricity expenses with customer inconvenience. This approach benefits both consumers and utility companies by lowering bills and enhancing power system stability. The simulation results validate the proposed model's efficacy and efficiency compared to existing benchmark models. [ABSTRACT FROM AUTHOR]

The development of accurate models to forecast load demand across different time horizons is challenging due to demand patterns and endogenous variables that affect short-term and long-term demand. This paper presents two contributions. First, it addresses the problem of the accuracy of the probabilistic forecasting model for short-term time series where endogenous variables interfere by emphasizing a low computational cost and efficient approach such as Granular Weighted Multivariate Fuzzy Time Series (GranularWMFTS) based on the fuzzy information granules method and a univariate form named Probabilistic Fuzzy Time Series. Secondly, it compares time series forecasting models based on algorithms such as Holt-Winters, Auto-Regressive Integrated Moving Average, High Order Fuzzy Time Series, Weighted High Order Fuzzy Time Series, and Multivariate Fuzzy Time Series (MVFTS) where this paper is based on Root Mean Squared Error, Symmetric Mean Absolute Percentage Error, and Theil's U Statistic criteria relying on 5% error criteria. Finally, it presents the concept and nuances of the forecasting approaches evaluated, highlighting the differences between fuzzy algorithms in terms of fuzzy logical relationship, fuzzy logical relationship group, and fuzzification in the training phase. Overall, the GranularWMVFTS and weighted MVFTS outperformed other evaluated forecasting approaches regarding the performance criteria adopted with a low computational cost. [ABSTRACT FROM AUTHOR]

Short-term residential load forecasting plays a crucial role in smart grids, ensuring an optimal match between energy demands and generation. With the inherent volatility of residential load patterns, deep learning has gained attention due to its ability to capture complex nonlinear relationships within hidden layers. However, most existing studies have relied on default loss functions such as mean squared error (MSE) or mean absolute error (MAE) for neural networks. These loss functions, while effective in overall prediction accuracy, lack specialized focus on accurately predicting load peaks. This article presents a comparative analysis of soft-DTW loss function, a smoothed formulation of Dynamic Time Wrapping (DTW), compared to other commonly used loss functions, in order to assess its effectiveness in improving peak prediction accuracy. To evaluate peak performance, we introduce a novel evaluation methodology using confusion matrix and propose new errors for peak position and peak load, tailored specifically for assessing peak performance in short-term load forecasting. Our results demonstrate the superiority of soft-DTW in capturing and predicting load peaks, surpassing other commonly used loss functions. Furthermore, the combination of soft-DTW with other loss functions, such as soft-DTW + MSE, soft-DTW + MAE, and soft-DTW + TDI (Time Distortion Index), also enhances peak prediction. However, the differences between these combined soft-DTW loss functions are not substantial. These findings highlight the significance of utilizing specialized loss functions, like soft-DTW, to improve peak prediction accuracy in short-term load forecasting. [ABSTRACT FROM AUTHOR]

Short-term electricity load forecasting provides a basis for day-ahead energy scheduling. To improve the accuracy of short-term electricity load forecasts and deeply explore the temporal characteristics of load sequences, a method is proposed to extract predictable components of load sequences based on the secretary bird optimization algorithm (SBOA)-optimized successive variational mode decomposition (SVMD). This method decomposes the electricity load sequence into multiple subsequences under different time series. The combined forecasting architecture of the temporal convolutional network (TCN) and the bidirectional long short-term memory network (BiLSTM) is introduced to mine the temporal characteristics of each load component, resulting in short-term load forecasting outcomes. A case study is conducted using the annual electricity load data for the year 2018 from a specific region in Belgium. The experimental results show that the mean absolute error (MAE) of the TCN–BiLSTM model is reduced by 47.8%, 32.8%, and 11.5%, respectively, compared to other models. The root mean square error (RMSE) is reduced by 42.9%, 39.2%, and 11.3%, respectively, and the average goodness of fit R2 is reduced by 9.81%. [ABSTRACT FROM AUTHOR]

The current power load exhibits strong nonlinear and stochastic characteristics, increasing the difficulty of short-term prediction. To more accurately capture data features and enhance prediction accuracy and generalization ability, in this paper, we propose an efficient approach for short-term electric load forecasting that is grounded in a synergistic strategy of feature optimization and hyperparameter tuning. Firstly, a dynamic adjustment strategy based on the rate of the change of historical optimal values is introduced to enhance the PID-based Search Algorithm (PSA), enabling the real-time adjustment and optimization of the search process. Subsequently, the proposed Improved Population-based Search Algorithm (IPSA) is employed to achieve the optimal adaptive variational mode decomposition of the load sequence, thereby reducing data volatility. Next, for each load component, a Bi-directional Gated Recurrent Unit network with an attention mechanism (BiGRU-Attention) is established. By leveraging the interdependence between feature selection and hyperparameter optimization, we propose a synergistic optimization strategy based on the Improved Population-based Search Algorithm (IPSA). This approach ensures that the input features and hyperparameters for each component's predictive model achieve an optimal combination, thereby enhancing prediction performance. Finally, the optimal parameter prediction model is used for multi-step rolling forecasting, with the final prediction values obtained through superposition and reconstruction. The case study results indicate that this method can achieve an adaptive optimization of hybrid prediction model parameters, providing superior prediction accuracy compared to the commonly used methods. Additionally, the method demonstrates robust adaptability to load forecasting across various day types and seasons. Consequently, this approach enhances the accuracy of short-term load forecasting, thereby supporting more efficient power scheduling and resource allocation. [ABSTRACT FROM AUTHOR]

Short-term load forecasting (STLF) of heterogeneous multi-agents plays a significant role in smart grid. Faced with special difficulties of multi-agent STLF due to the high heterogeneity, uncertainty and volatility, traditional local methods usually make predictions based on load aggregation or clustering, the complexity of which will rise greatly with the increase of agent types. It has become more and more difficult for traditional methods to meet the STLF demand of smart grid. Meanwhile, global time series forecasting method emerges gradually in many fields, which can make predictions for many agents only by one model with much lower complexity. However, there is few researches on the multi-agent global STLF. This study proposes a global deep-Long Short-Term Memory (LSTM) STLF model based on a pretraining method. The model fully applies the information such as electricity consumption pattern, weather and calendar in a structural and orderly way. The empirical results show that our model can effectively predict the daily load of heterogeneous households, with prediction accuracies of 87.9–90.2% on the test set across various tasks. Compared with the base model, our model achieves an 8.7% higher accuracy with a much faster convergence speed. Furthermore, the fluctuations of accuracy on different tasks are within 2.3%, showing that our model is robust. The superiority of the global method is proved through the comparison with local method in the empirical results. This study is expected to make contribution to global STLF of heterogeneous households and providing experience for the global prediction of heterogeneous time series based on deep-LSTM and pretraining method. [ABSTRACT FROM AUTHOR]

The high penetration of distributed energy resources poses significant challenges to the dispatch and operation of power systems. Improving the accuracy of short-term load forecasting (STLF) can optimize grid management, thus leading to increased economic and social benefits. Currently, some simple AI and hybrid models have issues to deal with and struggle with multivariate dependencies, long-term dependencies, and nonlinear relationships. This paper proposes a novel hybrid model for short-term load forecasting (STLF) that integrates multiple AI models with Lasso regression using the stacking technique. The base learners include ANN, XgBoost, LSTM, Stacked LSTM, and Bi-LSTM, while lasso regression serves as the metalearner. By considering factors such as temperature, rainfall, and daily electricity prices, the model aims to more accurately reflect real-world conditions and enhance predictive accuracy. Empirical analyses on real-world datasets from Australia and Spain show significant improvements in the forecasting accuracy, with a substantial reduction in the mean absolute percentage error (MAPE) compared to existing hybrid models and individual AI models. This research highlights the efficiency of the stacking technique in improving STLF accuracy, thus suggesting potential operational efficiency benefits for the power industry. [ABSTRACT FROM AUTHOR]

INTRODUCTION: As the penetration rate of renewable energy increases and patterns of energy demand evolve, fluctuations on both the supply and demand sides of electricity are becoming more pronounced. Consequently, accurate forecasting of community residential electrical loads has become crucial. OBJECTIVES: Although the widespread adoption of smart meters among residents provides abundant data for model training, strict challenges arise during the training process due to the need for privacy protection and data security. METHODS: This paper proposes a privacy-preserving community residential short-term electric load forecasting method based on federated learning. Initially, the method applies shared random masking encryption to the sensitive data of community residents, ensuring data privacy while maintaining consistency with the original data after preprocessing. Subsequently, a private data aggregation scheme is established to perform dynamic clustering of the community’s electrical load. RESULTS: The clustered model then serves as the basis for establishing individual load forecasting models for each category of community residents to predict short-term electrical loads. Finally, an empirical analysis is performed using the electrical load data from 120 households across 6 communities in a city in Southern China. CONCLUSION: The analysis demonstrates that the proposed method can achieve the prediction of community residential electrical loads without sharing residents’ data, thus verifying the effectiveness of this approach.

Short-term load forecasting is generally applied in power system real-time dispatching and day-ahead generation planning, which is of great significance for power system economic dispatching and safe operation of the system. Many researches on short-term load forecasting using smart models have been conducted at home and abroad. However, how to obtain the optimal structure and parameters accurately and quickly poses a challenge to short-term load forecasting, because the prediction performance of smart forecasting methods is more easily affected by the structure and parameters of the method, and the personality difference of the prediction object itself makes it difficult for the parameters to be reused. Aiming at this problem, a tree-structured Parzen estimator (TPE)-based boosting short-term load forecasting method is proposed. The results show that the proposed method can achieve rapid optimization of structure and parameters, which is verified in the application in short-term load forecasting of a southern province in China to improve the prediction accuracy.

To explore the hidden information in power load data and improve the accuracy of short-term load forecasting, a hybrid prediction model based on variational mode decomposition (VMD), long-term and short-term memory network (LSTM), improved particle swarm optimization (IPSO) algorithm and gated recurrent unit neural network (GRU) was proposed with consideration of strong non-linearity and non-stationarity in power load. First, correlation analysis was employed to determine input factors. The VMD algorithm combined with sample entropy was employed to decompose the load data into a series of intrinsic mode function ( IMF) and residual components, which then allowed for the rational determination of the decomposition levels and penalty factors. Then, these quantities were divided into low-frequency and high-frequency components based on the zero-crossing rate. The low-frequency components were forecasted using an LSTM network, while the high-frequency components were predicted with an IPSO-GRU network. Finally, the predicted results were reconstructed to obtain the final result of power load. Simulation results show that the proposed hybrid prediction model can effectively extract modal features and possesses higher predictive accuracy compared with alternative models. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Shanghai Jiao Tong University (1006-2467) is the property of Journal of Shanghai Jiao Tong University Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

An accurate short-term load forecasting plays an important role in modern power system's operation and economic development. However, short-term load forecasting is affected by multiple factors, and due to the complexity of the relationships between factors, the graph structure in this task is unknown. On the other hand, existing methods do not fully aggregating data information through the inherent relationships between various factors. In this paper, we propose a short-term load forecasting framework based on graph neural networks and dilated 1D-CNN, called GLFN-TC. GLFN-TC uses the graph learning module to automatically learn the relationships between variables to solve problem with unknown graph structure. GLFN-TC effectively handles temporal and spatial dependencies through two modules. In temporal convolution module, GLFN-TC uses dilated 1D-CNN to extract temporal dependencies from historical data of each node. In densely connected residual convolution module, in order to ensure that data information is not lost, GLFN-TC uses the graph convolution of densely connected residual to make full use of the data information of each graph convolution layer. Finally, the predicted values are obtained through the load forecasting module. We conducted five studies to verify the outperformance of GLFN-TC. In short-term load forecasting, using MSE as an example, the experimental results of GLFN-TC decreased by 0.0396, 0.0137, 0.0358, 0.0213 and 0.0337 compared to the optimal baseline method on ISO-NE, AT, AP, SH and NCENT datasets, respectively. Results show that GLFN-TC can achieve higher prediction accuracy than the existing common methods. [ABSTRACT FROM AUTHOR]

Accurate short-term load forecasting (STLF) plays an essential role in sustainable energy development. Specifically, energy companies can efficiently plan and manage their generation capacity, lessening resource wastage and promoting the overall efficiency of power resource utilization. However, existing models cannot accurately capture the nonlinear features of electricity data, leading to a decline in the forecasting performance. To relieve this issue, this paper designs an innovative load forecasting method, named Prophet–CEEMDAN–ARBiLSTM, which consists of Prophet, Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN), and the residual Bidirectional Long Short-Term Memory (BiLSTM) network. Specifically, this paper firstly employs the Prophet method to learn cyclic and trend features from input data, aiming to discern the influence of these features on the short-term electricity load. Then, the paper adopts CEEMDAN to decompose the residual series and yield components with distinct modalities. In the end, this paper designs the advanced residual BiLSTM (ARBiLSTM) block as the input of the above extracted features to obtain the forecasting results. By conducting multiple experiments on the New England public dataset, it demonstrates that the Prophet–CEEMDAN–ARBiLSTM method can achieve better performance compared with the existing Prophet-based ones. [ABSTRACT FROM AUTHOR]

As the demand for electricity, electrification, and renewable energy rises, accurate forecasting and flexible energy management become imperative. Distribution network operators face capacity limits set by regional grids, risking economic penalties if exceeded. This study examined data-driven approaches of load forecasting to address these challenges on a city scale through a use case study of Eskilstuna, Sweden. Multiple Linear Regression was used to model electric load data, identifying key calendar and meteorological variables through a rolling origin validation process, using three years of historical data. Despite its low cost, Multiple Linear Regression outperforms the more expensive non-linear Light Gradient Boosting Machine, and both outperform the "weekly Naïve" benchmark with a relative Root Mean Square Errors of 32–34% and 39–40%, respectively. Best-practice hyperparameter settings were derived, and they emphasize frequent re-training, maximizing the training data size, and setting a lag size larger than or equal to the forecast horizon for improved accuracy. Combining both models into an ensemble could the enhance accuracy. This paper demonstrates that robust load forecasts can be achieved by leveraging domain knowledge and statistical analysis, utilizing readily available machine learning libraries. The methodology for achieving this is presented within the paper. These models have the potential for economic optimization and load-shifting strategies, offering valuable insights into sustainable energy management. [ABSTRACT FROM AUTHOR]

Short-term load forecasting (STLF) plays a vital role in ensuring the safe, efficient, and economical operation of power systems. Accurate load forecasting provides numerous benefits for power suppliers, such as cost reduction, increased reliability, and informed decision-making. However, STLF is a complex task due to various factors, including non-linear trends, multiple seasonality, variable variance, and significant random interruptions in electricity demand time series. To address these challenges, advanced techniques and models are required. This study focuses on the development of an efficient short-term power load forecasting model using the random forest (RF) algorithm. RF combines regression trees through bagging and random subspace techniques to improve prediction accuracy and reduce model variability. The algorithm constructs a forest of trees using bootstrap samples and selects random feature subsets at each node to enhance diversity. Hyperparameters such as the number of trees, minimum sample leaf size, and maximum features for each split are tuned to optimize forecasting results. The proposed model was tested using historical hourly load data from four transformer substations supplying different campus areas of the University of Beira Interior, Portugal. The training data were from January 2018 to December 2021, while the data from 2022 were used for testing. The results demonstrate the effectiveness of the RF model in forecasting short-term hourly and one day ahead load and its potential to enhance decision-making processes in smart grid operations. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Chongqing University of Technology (Natural Science) is the property of Chongqing University of Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Abstract With the continuous transformation of the global power system, ensuring the flexibility and stability of the power system has become a direction that the global energy industry has been striving for. This puts forward higher requirements for load forecasting, especially high‐precision short‐term residential load forecasting. However, the high volatility and uncertainty of electric consumption make this problem challenging. Existing methods usually focus on capturing temporal correlations and ignore the underlying spatial correlations in historical loads, which is crucial for accurate forecasting. In this paper, we propose a novel spatial–temporal gated fusion network (STGNet) for short‐term residential load forecasting including not only individual residential load but also aggregated load. By seeking both adaptive neighbors and temporal similarity neighbors, we construct a dynamic graph based on a data‐driven method. On this basis, we provide an adaptive graph gated fusion mechanism to capture fine‐grained node‐specific spatial dependence more accurately and comprehensively. Finally, a bidirectional gated recurrent unit (BiGRU) is utilized to learn the temporal dependence of load data. Extensive experiments on real‐world datasets are conducted and demonstrate the superiority of STGNet over the existing approaches.

Abstract Accurate power load prediction is an important guide for power system planning and operation. High‐ or low‐load prediction results will affect the operation of the power system. In recent years, deep learning technology represented by convolution neural network (CNN) and transformer has been proved to be suitable for power load prediction. This paper proposes a new short‐term power load hybrid forecasting model, called channel enhanced attention (CEA) and temporal convolutional network (TCN)‐based transformer comprehensive forecasting model. This method combines the short‐term feature extraction ability of TCN with the long‐term dependent capture ability of transformer for short‐term load forecasting. And the CEA designed in this study is added to improve the prediction accuracy. On the same dataset, the designed model predicts power load mean square errors of 0.056 and 0.146 for the next 24 h and the next week, respectively, which is 0.002 to 0.073 and 0.012 to 0.024 lower than the baseline model. The experimental results show that the hybrid short‐term power load prediction model proposed in this paper is significantly better than the existing methods. The predicted curve is in agreement with the actual charge change, which provides a good guidance for short‐term power load prediction.

This paper introduces a novel approach for improving load forecasting accuracy in smart grids when integrating peak shaving strategies. Our research proposes a practical framework that demonstrates the negative impact of peak shaving on load forecasting accuracy and identifies the necessary algorithmic transformations to accommodate load demand fluctuations arising from such actions. We integrate a binary descriptor carrying information about the timing of the peak shaving events into the input vector used to train the forecasting model. We conducted two investigations based on two different billing strategies: “daily peak shaving” to address variable power rates and “peak shaving on a subset of days within a monthly billing cycle” to address power rates based on energy/peak demand. Our approach was validated using two public datasets from different climates collected in Australia and Greece. It evaluated two different forecasting techniques, the Feedforward Neural Network and the Long Short-Term Memory Network, with different levels and frequencies of peak shaving. The results demonstrate that our solution effectively mitigates the negative impact of peak shaving, leading to significant forecasting accuracy enhancements across both forecasting techniques, billing strategies, and peak shaving frequency and levels. The solution remarkably reduced the forecasting error metrics in all cases studied when comparing forecasts generated with and without the peak shaving descriptor. This study also provides practical insights into how our approach can be applied in real-world power systems to not only improve load forecasting accuracy but also assess the impact of demand response actions and improve grid reliability and efficiency.

Accurate short-term power load forecasting is the key to determining the grid company’s dispatch plan and system operation mode. Aiming at the problem of low prediction accuracy due to the difficulty in selecting hyperparameters of BiLSTM, a hybrid parallel Harris hawk optimization algorithm (DE-IHHO) is proposed to choose the optimal hyperparameters of BiLSTM to improve the prediction accuracy of the model. In this paper, several load forecasting models are tested and BiLSTM with better performance is chosen as the baseline model. Aiming to solve the problem of the complex selection of hyperparameters for BiLSTM, the Harris Hawk Optimization (HHO) algorithm is used to obtain better hyperparameter combinations and improve prediction accuracy. To further explore the optimal hyperparameter combinations of BiLSTM, running in parallel with differential evolutionary algorithm (DE) to enhance the search diversity, adopting chaotic dyadic learning strategy and mutation operation strategy to improve the global search capability of HHO, and finally smoothing the optimal solution to reduce the influence of abnormal solutions. The results show that the convergence speed and optimization ability of DE-IHHO are significantly improved, and the BiLSTM optimized in this way improves considerably in all three metrics of MAE, MAPE, and RMSE, proving this prediction model’s effectiveness.

Short-term load forecasting (STLF) is vital in effectively managing the reserve requirement in modern power grids. Subsequently, it supports the grid operator in making effective and economical decisions during the power balancing operation. Therefore, this study comprehensively reviews STLF methods, including time series analysis, regression-based frameworks, artificial neural networks (ANNs), and hybrid models that employ different forecasting approaches. Detailed mathematical and graphical analyses and a comparative evaluation of these methods are provided, highlighting their advantages and disadvantages. Further, the study proposes a hybrid CNN-LSTM model comprised of Convolutional neural networks (CNN) for feature extraction of high dimensional data and Long short-term memory (LSTM) networks to boost the model’s efficiency for temporal sequence prediction. This study assessed the model using a comprehensive dataset from Pakistan’s NTDC national grid. The analysis revealed superior performance in short-term load prediction, achieving enhanced accuracy. For single-step forecasting, the model yielded an RMSE of 538.71, MAE of 371.97, and MAPE of 2.72. In 24-hour forecasting, it achieved an RMSE of 951.94, MAE of 656.35, and MAPE of 4.72 on the NTDC dataset. Moreover, the model has outperformed previous models in comparison using the AEP dataset, demonstrating its superiority in enhancing reserve management and balancing supply and demand in modern electricity networks.

One of the key components of achieving sustainability and energy efficiency in power utility networks is accurate short-term load forecasting (STLF). STLF is essential for effective operational planning. Overestimation leads to unnecessary energy consumption and costs, while underestimation leads to energy shortages and potential blackouts, severely impacting the community and the economy. This study highlights the potential of regularized greedy forest (RGF) algorithm for STLF, which integrates the underlying tree structure with regularization to learn a decision forest. In particular, we propose the RGF model combined with two gradient-boosting frameworks, namely eXtreme gradient boosting and light gradient boosting machine models, to create a more robust ensemble model using Bayesian optimization techniques. The proposed ensemble model is evaluated in the real-world case study. It performs better than the existing models in terms of mean absolute percentage error (MAPE) and mean absolute error (MAE) in various scenarios. The experimental results show that the MAPE of the proposed model on average is 1.60% in the daily operation scenario, which provides accurate day-ahead (24 h) load forecasting with a half-day gap. The study demonstrates that the proposed model is suitable and practical for the STLF problem, and thus it contributes to the overall sustainability and resilience of power utility networks.

Power loads usually have multiple cycles, and the traditional forecasting methods only use the historical loads under various types of cycles together as input features to construct the forecasting model, ignoring the deep features under multiple cycles. The simultaneous inputs will lead to the cycles overlapping and influencing each other, which will be difficult to deal with when building the model. Therefore, this paper proposes a GRO-Bagging day-ahead power curve forecasting model based on multi-cycle feature extraction. First, the multi-periodicity of the power load is analyzed. The one-dimensional time series is converted to two-dimensional according to the multiple cycles of power load. Then, the multi-periodic feature extraction is performed by a multi-size convolutional feature extraction layer with parallel selected based on the data characteristics and modeling mechanism, and Bootstrap Aggregating (Bagging) method is used to construct different prediction models for the datasets containing different periodic features; finally, Gold Rush Optimization (GRO) algorithm is introduced and improved by using the Tent chaotic mapping and elite strategy, and the improved optimization algorithm is used for the weight optimization of the model, the error feedback mechanism is introduced to achieve the weight dynamic Updating. To prove the superiority of the proposed model, a series of comparison experiments and ablation experiments are carried out on real datasets, and the results show that the proposed method has higher prediction accuracy, and prove that the multi-period feature extraction and dynamic weighting methods have a positive and active effect on load prediction.

Electricity load forecasting is an essential part of power system planning and operation, and it is crucial to make accurate predictions. The smart grid paradigm and the new energy market necessitate better demand-side management (DSM) and more reliable end-user forecasts to system scale. This paper proposes a time-series clustering-based probabilistic electricity future prediction for short-term load forecasting (STLF), which makes forecasts more accurate and intelligent. The weather and data noise uncertainties are considered, with the load probabilistic interval as the model’s output for individual and aggregated household energy consumption. This paper adapts the logarithm of the hyperbolic cosine (log-cosh) of the error value as quantile loss and time feature with long short-term memory (LSTM) to bridge the gap. This paper presents a framework for probabilistic electric load forecasting that incorporates clustering-based quantile-LSTM learning to improve the accuracy and robustness of short-term electricity prediction. The proposed model is primarily applied to energy demand information on 15-minute and 1-hour time horizons for day-ahead prediction tasks, which are the key concerns for electricity utilities. Various state-of-the-art regression learning techniques, i.e., quantile regression forest (QRF), quantile regression neural network (QRNN), quantile gradient boosting regression tree (QGBRT), and quantile LSTM (Q-LSTM), were utilized and evaluated. The findings indicate that the proposed cluster-based probabilistic forecasting approach outperforms the existing benchmark models in terms of prediction interval coverage probability (PICP) evaluation metric.

For distribution networks, accurate short-term load forecasting is a prerequisite for the safe and stable operation as well as economically optimized dispatching of the grid. In order to enhance the accuracy of short-term power load forecasting, this paper proposes a forecasting method that combines convolutional neural network (CNN), long short-term memory (LSTM) network, and the Neuralprophet model. This method utilizes the Neuralprophet model to capture trends, seasonal cycles, holiday activities, and other components within load data, while leveraging the data feature extraction capability of the CNN model and the long-term sequence prediction ability of the LSTM model. The optimal hyperparameters of the models are determined using the Bayesian optimization algorithm, and the predictions of the two models are fused through the least squares method. Application of this method to forecasting on various load datasets demonstrates its superior prediction accuracy compared to other classical models.

In short-term load forecasting, deep learning models with recurrent units are widely used. For Long Short-term Memory (LSTM) models, in terms of the input features at one particular time-step, there is a weight series for each input feature. Hence, an input feature with a larger value of weight can be regarded as more important to the final forecasting result. Since the weights of the features are time-invariant, the model considers the input features as equally important at each time step, thus lack of the capability of reflecting the importance fluctuation through the time span. To tackle this issue, this paper proposes a forecasting scheme, which integrates mutual information (MI) into bi-directional long short-term memory (BILSTM) network. The MI method is used to extract the importance value of input features at different time-steps, and constitute the fluctuation matrix of the importance values for input features, which is used as coefficients to correct the original input feature. The corrected features are substituted into the BILSTM network, which further improves the forecasting accuracy. Numerical experiments have been carried out based on real-world load data. The results demonstrate the superior performance of the proposed scheme compared with a series of state-of-the-art methods and thus indicate the importance and effectiveness of capturing the fluctuation of the importance value.

With the growing number of user-side resources connected to the distribution system, an occasional imbalance between the distribution side and the user side arises, making short-term power load forecasting technology crucial for addressing this issue. To strengthen the capability of load multi-feature extraction and improve the accuracy of electric load forecasting, we have constructed a novel BILSTM-SimAM network model. First, the entirely non-recursive Variational Mode Decomposition (VMD) signal processing technique is applied to decompose the raw data into Intrinsic Mode Functions (IMF) with significant regularity. This effectively reduces noise in the load sequence and preserves high-frequency data features, making the data more suitable for subsequent feature extraction. Second, a convolutional neural network (CNN) mode incorporates Dropout function to prevent model overfitting, this improves recognition accuracy and accelerates convergence. Finally, the model combines a Bidirectional Long Short-Term Memory (BILSTM) network with a simple parameter-free attention mechanism (SimAM). This combination allows for the extraction of multi-feature from the load data while emphasizing the feature information of key historical time points, further enhancing the model's prediction accuracy. The results indicate that the R2 of the BILSTM-SimAM algorithm model reaches 97.8%, surpassing mainstream models such as Transformer, MLP, and Prophet by 2.0%, 2.7%, and 3.6%, respectively. Additionally, the remaining error metrics also show a reduction, confirming the validity and feasibility of the method proposed.

Accurate electricity demand forecasting is crucial for ensuring the sustainability and reliability of power systems. Least square support vector machines (LSSVM) are well suited to handle complex non-linear power load series. However, the less optimal regularization parameter and the Gaussian kernel function in the LSSVM model have contributed to flawed forecasting accuracy and random generalization ability. Thus, these parameters of LSSVM need to be chosen appropriately using intelligent optimization algorithms. This study proposes a new hybrid model based on the LSSVM optimized by the improved bacterial foraging optimization algorithm (IBFOA) for forecasting the short-term daily electricity load in Peninsular Malaysia. The IBFOA based on the sine cosine equation addresses the limitations of fixed chemotaxis constants in the original bacterial foraging optimization algorithm (BFOA), enhancing its exploration and exploitation capabilities. Finally, the load forecasting model based on LSSVM-IBFOA is constructed using mean absolute percentage error (MAPE) as the objective function. The comparative analysis demonstrates the model, achieving the highest determination coefficient (R2) of 0.9880 and significantly reducing the average MAPE value by 28.36%, 27.72%, and 5.47% compared to the deep neural network (DNN), LSSVM, and LSSVM-BFOA, respectively. Additionally, IBFOA exhibits faster convergence times compared to BFOA, highlighting the practicality of LSSVM-IBFOA for short-term load forecasting.

Studies on probabilistic demand forecasting remain relatively limited compared with point forecasting, despite it being especially valuable for operational and planning purposes. This paper demonstrates different applications of probabilistic forecasting in demand response, together with Physical-Based Load Models. The first application shows how to determine the percentage of uncertainty potentially covered by demand response throughout a day, whereas the second application deals with obtaining the number of consumers that would be needed in demand response actions for a desired percentage of coverage. Finally, in the third application, a specific hourly strategy is proposed for demand response policies. These applications facilitate the aggregator’s energy purchasing in the market and the planning of subsequent consumption adjustments through demand response to minimize deviations from the purchased energy. The approach is illustrated using hourly demand data from a small Spanish city, and two machine learning methods were used to produce a set of probabilistic forecasts and compare results: Linear Quantile Regression and a Quantile Regression Forest. Main results show a significant reduction in deviations from the purchased energy after applying the proposed strategy, especially in the case of the forecasting method being less accurate (40.95% and 33.62% of reduction, respectively).

Load forecasting is an integral part of the power industries. Load-forecasting techniques should minimize the percentage error while prediction future demand. This will inherently help utilities have an uninterrupted power supply. In addition to that, accurate load forecasting can result in saving large amounts of money. This article provides a systematic review based on the Preferred Reporting Items for Systematic Review and Meta-Analyses (PRISMA) framework. This article presents a complete framework for short-term load forecasting using metaheuristic algorithms. This framework consists of three sub-layers: the data-decomposition layer, the forecasting layer, and the optimization layer. The data-decomposition layer decomposes the input data series to extract important features. The forecasting layer is used to predict the result, which involves different statistical and machine-learning models. The optimization layer optimizes the parameters of forecasting methods to improve the accuracy and stability of the forecasting model using different metaheuristic algorithms. Single models from the forecasting layer can predict the results. However, they come with their limitations, such as low accuracy, high computational burden, stuck to local minima, etc. To improve the prediction accuracy, the hyperparameters of these models need to be tuned properly. Metaheuristic algorithms cab be used to tune these hyperparameters considering their interdependencies. Hybrid models combining the three-layer methods can perform better by overcoming the issues of premature convergence and trapping into a local minimum solution. A quantitative analysis of different metaheuristic algorithms and deep-learning forecasting methods is presented. Some of the most common evaluation indices that are used to evaluate the performance of the forecasting models are discussed. Furthermore, a taxonomy of different state-of-the-art articles is provided, discussing their advantages, limitations, contributions, and evaluation indices. A future direction is provided for researchers to deal with hyperparameter tuning.

The development of accurate models to forecast load demand across different time horizons is challenging due to demand patterns and endogenous variables that affect short-term and long-term demand. This paper presents two contributions. First, it addresses the problem of the accuracy of the probabilistic forecasting model for short-term time series where endogenous variables interfere by emphasizing a low computational cost and efficient approach such as Granular Weighted Multivariate Fuzzy Time Series (GranularWMFTS) based on the fuzzy information granules method and a univariate form named Probabilistic Fuzzy Time Series. Secondly, it compares time series forecasting models based on algorithms such as Holt-Winters, Auto-Regressive Integrated Moving Average, High Order Fuzzy Time Series, Weighted High Order Fuzzy Time Series, and Multivariate Fuzzy Time Series (MVFTS) where this paper is based on Root Mean Squared Error, Symmetric Mean Absolute Percentage Error, and Theil’s U Statistic criteria relying on 5% error criteria. Finally, it presents the concept and nuances of the forecasting approaches evaluated, highlighting the differences between fuzzy algorithms in terms of fuzzy logical relationship, fuzzy logical relationship group, and fuzzification in the training phase. Overall, the GranularWMVFTS and weighted MVFTS outperformed other evaluated forecasting approaches regarding the performance criteria adopted with a low computational cost.

The accurate, rapid, and stable prediction of electrical energy consumption is essential for decision-making, energy management, efficient planning, and reliable power system operation. Errors in forecasting can lead to electricity shortages, wasted resources, power supply interruptions, and even grid failures. Accurate forecasting enables timely decisions for secure energy management. However, predicting future consumption is challenging due to the variable behavior of customers, requiring flexible models that capture random and complex patterns. Forecasting methods, both traditional and modern, often face challenges in achieving the desired level of accuracy. To address these shortcomings, this research presents a novel hybrid approach that combines a robust forecaster with an advanced optimization technique. Specifically, the FS-FCRBM-GWDO model has been developed to enhance the performance of short-term load forecasting (STLF), aiming to improve prediction accuracy and reliability. While some models excel in accuracy and others in convergence rate, both aspects are crucial. The main objective was to create a forecasting model that provides reliable, consistent, and precise predictions for effective energy management. This led to the development of a novel two-stage hybrid model. The first stage predicts electrical energy usage through four modules using deep learning, support vector machines, and optimization algorithms. The second stage optimizes energy management based on predicted consumption, focusing on reducing costs, managing demand surges, and balancing electricity expenses with customer inconvenience. This approach benefits both consumers and utility companies by lowering bills and enhancing power system stability. The simulation results validate the proposed model’s efficacy and efficiency compared to existing benchmark models.

Short-term load forecasting plays an important role in power system scheduling, optimization, and maintenance, but no existing typical method can consistently maintain high prediction accuracy. Hence, fusing different complementary methods is increasingly focused on. To improve forecasting accuracy and stability, these features that affect the short-term power system are firstly extracted as prior knowledge, and the advantages and disadvantages of existing methods are analyzed. Then, three typically methods are used for short-term power load forecasting, and their interaction and complementarity are studied. Finally, the Choquet integral (CI) is used to fuse the three existing complementarity methods. Different from other fusion methods, the CI can fully utilize the interactions and complementarity among different methods to achieve consistent forecasting results, and reduce the disadvantages of a single forecasting method. Essentially, a CI with n inputs is equivalent to n! constrained feedforward neural networks, leading to a strong generalization ability in the load prediction process. Consequently, the CI-based method provides an effective way for the fusion forecasting of short-term load in power systems.