Search

To tackle the challenges of high variability and low accuracy in short-term electricity load forecasting, this study introduces an enhanced prediction model that addresses overfitting issues by integrating an error-optimal weighting approach with an improved ensemble forecasting framework. The model employs a hybrid algorithm combining grey relational analysis and radial kernel principal component analysis to preprocess the multi-dimensional input data. It then leverages an ensemble of an optimized deep bidirectional gated recurrent unit (BiGRU), an enhanced long short-term memory (LSTM) network, and an advanced temporal convolutional neural network (TCN) to generate predictions. These predictions are refined using an error-optimal weighting scheme to yield the final forecasts. Furthermore, a Bayesian-optimized Bagging and Extreme Gradient Boosting (XGBoost) ensemble model is applied to minimize prediction errors. Comparative analysis with existing forecasting models demonstrates superior performance, with an average absolute percentage error (MAPE) of 1.05% and a coefficient of determination (R2) of 0.9878. These results not only validate the efficacy of our proposed strategy, but also highlight its potential to enhance the precision of short-term load forecasting, thereby contributing to the stability of power systems and supporting societal production needs. [ABSTRACT FROM AUTHOR]

Electric load forecasting plays a vital role in all aspects of the electrical system, including generation, transmission, distribution, and electricity retail. The LightGBM ensemble learning method has been widely applied in load forecasting and has yielded many positive results. This study presents an algorithm combining the grid space of hyperparameters with cross-validation to evaluate the accuracy of LightGBM models across different hyperparameter values. Peak load data from Ho Chi Minh City were used to enhance the reliability of the results. Analysis of the results based on boxplot statistical charts indicated that the accuracy of the LightGBM model significantly depends on the hyperparameter values. Moreover, using default hyperparameter values may result in large errors in load forecasting. [ABSTRACT FROM AUTHOR]

This study focuses on improving short-term power load forecasting, a critical aspect of power system planning, control, and operation, especially within the context of China's "dual-carbon" policy. The integration of renewable energy under this policy has introduced complexities such as nonlinearity and instability. To enhance forecasting accuracy, the VMD-SE-BiSATCN prediction model is proposed. This model improves computational efficiency and reduces prediction errors by analyzing and reconstructing sequence component complexity using sample entropy (SE) following variational mode decomposition (VMD). Additionally, a self-attention mechanism is integrated into the temporal convolutional network (TCN) to overcome the traditional TCN's limitations in capturing long-term dependencies. The model was evaluated using data from the China Ninth Electrical Attribute Modeling Competition and validated with real-world data from a specific county in Shijiazhuang City, Hebei Province, China. Results indicate that the VMD-SE-BiSATCN model outperforms other models, achieving a mean absolute error (MAE) of 92.87, a root mean square error (RMSE) of 126.906, and a mean absolute percentage error (MAPE) of 0.81%. [ABSTRACT FROM AUTHOR]

Accurate load forecasting is essential for reliable and efficient operation of power systems. Traditional forecasting methods often struggle with capturing complex nonlinear patterns in load data. Artificial neural networks (ANNs) have emerged as a promising alternative due to their ability to learn complex relationships from historical data (Syed et al. in IEEEA 9:54992–55008, 2021. https://doi.org/10.1109/ACCESS.2021.3071654). This study investigates the potential of ANNs for short-term peak load forecasting in a 150 kV power system in Semarang, Indonesia. The study examines the impact of different input variables, including historical peak load, minimum load, population, and energy production, on forecasting accuracy. Several ANN architectures are trained and evaluated using mean absolute percentage error (MAPE) and mean squared error (MSE) metrics as reported by Demuth and De Jesús (neural network design). The results indicate that ANNs can achieve high accuracy in predicting peak load, with MAPE values below 10%. The study also demonstrates the importance of carefully selecting input variables and training parameters for optimal model performance. The findings highlight the potential of ANNs for improving load forecasting accuracy in power systems, contributing to enhanced grid reliability and operational efficiency. The findings of this study contribute to a deeper understanding of the application of ANNs in power system load forecasting. They demonstrate the potential of ANNs to achieve high accuracy and provide valuable insights into the factors influencing model performance. The findings are relevant for power system operators, researchers, and policymakers working to improve grid reliability and efficiency as reported by Prabha Kundur and Malik (Power System Stability and Control, McGraw-Hill Education, New York, 2022. https://www.accessengineeringlibrary.com/content/book/9781260473544). [ABSTRACT FROM AUTHOR]

The integration of stochastic and intermittent distributed PVs brings great challenges for power system operation. Precise net load forecasting performs a critical factor in dependable operation and dispensing. An approach to probabilistic net load prediction is introduced for sparse variant Gaussian process based algorithms. The forecasting of the net load is transferred to a regression problem and solved by the sparse variational Gaussian process (SVPG) method to provide uncertainty quantification results. The proposed method can capture the uncertainties caused by the customer and PVs and provide effective inductive reasoning. The results obtained using real-world data show that the proposed method outperforms other best-of-breed algorithms. [ABSTRACT FROM AUTHOR]

Due to changes in urban residents' consumption habits and lifestyles, accurately predicting natural gas consumption has become increasingly important. To address this issue, this paper proposes a forecasting model that combines Ensemble Learning (EL), Variational Mode Decomposition (VMD), Transformer, and LSTM. First, XGBoost, CatBoost, and LightGBM are used as base learners in the ensemble learning framework, with the predictions generated by the ensemble model integrated into the original dataset. Next, the VMD method is employed to decompose the natural gas load sequence into several intrinsic mode functions (IMFs), effectively extracting the inherent features of the natural gas load sequence. Finally, the data is input into the Transformer-ResLSTM network for prediction. This network replaces the original Transformer decoder structure with an LSTM network and fully connected layers, creating a new decoder structure. Additionally, a residual connection mechanism is introduced in both the encoder of the Transformer network and the new decoder structure. Experimental results show that, compared to traditional models such as ARIMA, Transformer, GRU, and LSTM, the proposed hybrid model significantly improves prediction accuracy, reducing MSE by 92–98% and MAE by 74–83%. In summary, this method demonstrates significant potential and practical value in enhancing the accuracy of natural gas load forecasting. [ABSTRACT FROM AUTHOR]

Medium–long-term photovoltaic (PV) output forecasting is of great significance to power grid planning, power market transactions, power dispatching operations, equipment maintenance and overhaul. However, PV output fluctuates greatly due to weather changes. Furthermore, it is frequently challenging to ensure the accuracy of forecasts for medium–long-term forecasting involving a long time span. In response to the above problems, this paper proposes a medium–long-term forecasting method for PV output based on amplitude-aware permutation entropy component reconstruction and the graph attention network. Firstly, the PV output sequence data are decomposed by ensemble empirical mode decomposition (EEMD), and the decomposed intrinsic mode function (IMF) subsequences are combined and reconstructed according to the amplitude-aware permutation entropy. Secondly, the graph node feature sequence is constructed from the reconstructed subsequences, and the mutual information of the node feature sequence is calculated to obtain the graph node adjacency matrix which is applied to generate a graph sequence. Thirdly, the graph attention network is utilized to forecast the graph sequence and separate the PV output forecasting results. Finally, an actual measurement system is used to experimentally verify the proposed method, and the outcomes indicate that the proposed method, which has certain promotion value, can improve the accuracy of medium–long-term forecasting of PV output. [ABSTRACT FROM AUTHOR]

Accurate and reliable medium- and long-term load forecasting is crucial for the rational planning and operation of power systems. However, existing methods often struggle to accurately extract and capture long-term dependencies in load data, leading to poor predictive accuracy. Therefore, this paper proposes a medium- and long-term residential load forecasting method based on FEDformer, aiming to capture long-term temporal dependencies of load data in the frequency domain while considering factors such as electricity prices and temperature, ultimately improving the accuracy of medium- and long-term load forecasting. The proposed model employs Discrete Cosine Transform (DCT) for frequency domain transformation of time-series data to address the Gibbs phenomenon caused by the use of Discrete Fourier Transform (DFT) in FEDformer. Additionally, causal convolution and attention mechanisms are applied in the frequency domain to enhance the model's capability to capture long-term dependencies. The model is evaluated using real-world load data from power systems, and experimental results demonstrate that the proposed model effectively learns the temporal and nonlinear characteristics of load data. Compared to other baseline models, DCTformer improves prediction accuracy by 37.5% in terms of MSE, 26.9% in terms of MAE, and 26.24% in terms of RMSE. [ABSTRACT FROM AUTHOR]

A CNN-BIGRU-AT model for power load forecasting is constructed by introducing Attention Mechanism (AT) into a model combining Convolutional Neural Network (CNN) and Bidirectional Gated Recurrent Unit (BIGRU), which has high prediction accuracy. In this model, CNN is first used to extract relevant features from power load data, and then BIGRU is applied to capture the inherent complex nonlinear dynamic patterns of power load. Additionally, Attention Mechanism (AT) is incorporated to further refine the feature extraction of power load data. The North Grey Wolf Optimizer Algorithm (NGO) is used to optimize parameters such as the number of hidden layer nodes, initial learning rate, and regularization coefficient in BIGRU, thus obtaining the modeling method of NGO-CNN-BIGRU-AT. Finally, the validity and feasibility of the model are substantiated using actual power load data from a certain region in China. The results demonstrate that the model has better performance than conventional models, including BP, BIGRU, CNN-BIGRU, and CNN-BIGRU-AT. [ABSTRACT FROM AUTHOR]

Load forecasting is a key aspect of power system design, operation, and maintenance. To obtain an accurate forecast model which is very vital for the development of any power sector capacity expansion plan be it on generation, transmission and distribution, regression (0.0139) and mean square error (0.99791) were used as criteria for selecting the optimal model for load forecasting. The higher the value of regression, the better the value of the accuracy of the load forecast. In the same vein, the lower the value of the mean square error, the better the accuracy of the load forecast. The load forecast using Backpropagation artificial neural network (BPANN) obtained load forecast in the year 2035 to be 85998MW. This forecast is necessary to provide an increase in generation capacity to meet 85836.99MW of load by 2035. Taking 2021 as base year, the total load demand, which comprises the industrial, commercial, and residential customers were estimated and used to forecast the total load requirements of the customers in year 2035. The ten experimental results obtained by creating ten different topologies of BPANN validated the choice of 30 hidden layer neurons for use in the load forecasting. [ABSTRACT FROM AUTHOR]

An improved fuzzy time series algorithm based on clustering is designed in this paper. The algorithm is successfully applied to short-term load forecasting in the distribution stations. Firstly, the K-means clustering method is used to cluster the data, and the midpoint of two adjacent clustering centers is taken as the dividing point of domain division. On this basis, the data is fuzzed to form a fuzzy time series. Secondly, a high-order fuzzy relation with multiple antecedents is established according to the main measurement indexes of power load, which is used to predict the short-term trend change of load in the distribution stations. Matlab/Simulink simulation results show that the load forecasting errors of the typical fuzzy time series on the time scale of one day and one week are [−50, 20] and [−50, 30], while the load forecasting errors of the improved fuzzy time series on the time scale of one day and one week are [−20, 15] and [−20, 25]. It shows that the fuzzy time series algorithm improved by clustering improves the prediction accuracy and can effectively predict the short-term load trend of distribution stations. [ABSTRACT FROM AUTHOR]

The change in the electricity demand pattern globally due to sudden extreme weather conditions or situations like COVID 19 pandemic has brought unanticipated challenges for the electric utilities and operators around the world. This work primarily deals with the issue of load forecasting during such type of high impact low frequency (HILF) events. In this paper, we propose a novel resilient short-term load forecasting model capable of producing good forecasting performance for normal as well as critical situations during the COVID 19 pandemic and will also be useful for load forecasting for other HILF situations like natural calamity effect on load demand of the power system. The proposed method uses a feed-forward neural network (FFNN) with an added training feature named resiliency factor to forecast load in both regular and special scenarios. The resiliency factor for any type of node in the distribution system is decided by the power utility using the historical data and declared in advance. The proposed model is tested using the smart metered data available from a real-life distribution grid of an academic cum residential campus. The model is giving satisfactory results for both normal as well as COVID scenario for the said network. [ABSTRACT FROM AUTHOR]

Aiming at the nonlinear and non‐stationary characteristics of the power load, in order to improve the accuracy of load forecasting, a short‐term load forecasting method based on variational modal decomposition and the combination of convolutional neural network and bi‐directional long short‐term memory (Bi‐LSTM) network is proposed. The load sequence is decomposed into components with different frequencies by variational modal decomposition, and each component is predicted by Bi‐LSTM. Then the convolution neural network is introduced to process multi‐source data. The load, temperature, day and other data are constructed according to the time sliding window as the input, and the convolution neural network is used to extract the effective feature vector, the eigenvector is constructed in a time series and used as the input data of Bi‐LSTM network. Taking the public data set provided by a US public utility department as an example, the proposed model is compared with other methods. The results show that the proposed method can better track the change of load and effectively improve the accuracy of short‐term load forecasting. © 2023 Institute of Electrical Engineer of Japan and Wiley Periodicals LLC. [ABSTRACT FROM AUTHOR]

Based on the analysis of the test data and Miner's rule, a combined high and low cycle fatigue (CCF) life prediction model considering the loading interaction is established by introducing coupled damage. The coupled damage is determined by multiplying the high cycle fatigue damage and the low cycle fatigue damage by a coupled damage coefficient K. According to the analysis of the test data, the coupled damage coefficient K is positively correlated with the high cycle stress ratio R. In addition, an interaction factor, which reflects the loading interaction effect, is introduced to correct the coefficient K. The CCF experimental data of four materials are employed for model verification and comparison among the proposed model, Miner's rule, and Trufyakov–Kovalchuk model (T–K model). The proposed model exhibits a relatively higher prediction accuracy and is more suitable for predicting the fatigue life of CCF. Highlights: A combined fatigue life prediction model is proposed considering loading interaction.Coupled damage coefficient is determined through analysis of the test data.The proposed model exhibits a relatively higher prediction accuracy. [ABSTRACT FROM AUTHOR]

Since the existing prediction methods have encountered difficulties in processing themultiple influencing factors in short-term power load forecasting, we propose a bidirectional long short-term memory (BiLSTM) neural network model based on the temporal pattern attention (TPA) mechanism. Firstly, based on the grey relational analysis, datasets similar to forecast day are obtained. Secondly, thebidirectional LSTMlayermodels the data of thehistorical load, temperature, humidity, and date-type and extracts complex relationships between data from the hidden row vectors obtained by the BiLSTM network, so that the influencing factors (with different characteristics) can select relevant information from different time steps to reduce the prediction error of the model. Simultaneously, the complex and nonlinear dependencies between time steps and sequences are extracted by the TPA mechanism, so the attention weight vector is constructed for the hidden layer output of BiLSTM and the relevant variables at different time steps are weighted to influence the input. Finally, the chaotic sparrow search algorithm (CSSA) is used to optimize the hyperparameter selection of the model. The short-term power load forecasting on different data sets shows that the average absolute errors of short-termpower load forecasting based on our method are 0.876 and 4.238, respectively, which is lower than other forecastingmethods, demonstrating the accuracy and stability of our model. [ABSTRACT FROM AUTHOR]

The ever-growing modern smart grid with more distributed energy resources is providing efficient energy supply while facing several challenges that include harmonics induced among many. Previous and present literature shows that various machine and deep learning models are superior and accurate as compared to the traditional and conventional signal processing techniques. Obtaining accurate results becomes extremely important especially the fact that harmonics are essentially nonlinear, nonparametric, and adaptive in nature. This paper proposes a novel forecasting model that aggregates two deep learning models: convolutional neural network (CNN) and long short term memory (LSTM) recurrent neural network (RNN) detect and forecast harmonics in a power system. CNN-LSTM hybrid forecasting model for harmonics in the power grid system has achieved significantly superior performance in collaborative data mining on spatiotemporal measurement data. Sample features are extracted using CNN before they are passed through LSTM for prediction. To show the superiority of the hybrid CNN-LSTM deep neural prediction network model, it is compared with CNN, LSTM and NARX (Non-Linear Autoregressive with External (Exogenous) Input). CNN-LSTM forecasting performance is superior as compared to the other four models. MSE and RMSE for CNN-LSTM are 0.00038 (〖3.8 × 10〗^ (−4)) and 0.0000014917 (1.4917 × 10^(−6)) respectively. [ABSTRACT FROM AUTHOR]

With photovoltaic power being increasingly integrated into power grid, accurately forecasting solar irradiance is of critical for ensuring stable and economical operation of power systems. The forecast accuracy in ultra-short-term horizons can be greatly improved by employing ground-based sky images. Although wide range of computer vision methods have been used for modelling, effectively extracting spatiotemporal features from sky image sequence is still a tough task. In this study, a sparse spatiotemporal feature descriptor is introduced to enhance the process of dynamic spatiotemporal information extraction from continuous grayscale sky images, while spatial pyramid pooling is used for feature refinement. Parallelly, dense convolutional network is used to extract static features from the nearest single-frame RGB sky images. Both dynamic and static spatiotemporal features were adequately extracted and subsequently fused for the multi-step prediction of global horizontal irradiance. In addition, various competitive models in object detection are adopted as benchmarks for comparison. The experimental results revealed that the proposed method outperformed baseline models, with up to 5.51% reduction on normalized root mean square error (NRMSE) and 9.38% improvement on ramp event forecast. The proposed method can be widely applied to photovoltaic stations equipped with all-sky-imagers. [ABSTRACT FROM AUTHOR]

Wind power prediction is an important research topic in the wind power industry and many prediction algorithms have recently been studied for the sake of achieving the goal of improving the accuracy of short-term forecasting in an effective way. To tackle the issue of generating a huge transition matrix in the traditional Markov model, this paper introduces a real-time forecasting method that reduces the required calculation time and memory space without compromising the prediction accuracy of the original model. This method is capable of obtaining the state probability interval distribution for the next moment through real-time calculation while preserving the accuracy of the original model. Furthermore, the proposed Markov-based Back Propagation (BP) neural network was optimized using the Particle Swarm Optimization (PSO) algorithm in order to effectively improve the prediction approach with an improved PSO-BP neural network. Compared with traditional methods, the computing time of our improved algorithm increases linearly, instead of growing exponentially. Additionally, the optimized Markov-based PSO-BP neural network produced a better predictive effect. We observed that the Mean Absolute Percentage Error (MAPE) and Mean Absolute Error (MAE) of the prediction model were 12.7% and 179.26, respectively; compared with the existing methods, this model generates more accurate prediction results. [ABSTRACT FROM AUTHOR]

To enhance the control effect of intelligent transportation system (ITS) of expressway, avoid blind travel causing traffic congestion, improve road capacity, and achieve the purpose of smooth and efficient operation of the network, 3σ criterion and 2σ cycle removal criterion were used to eliminate the abnormal data of travel time. Thereafter, a combined prediction model of Long Short‐Term Memory (LSTM) based on the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) algorithm and attention mechanism is proposed. Travel time data, collected from the real world, is decomposed into several Intrinsic Mode Functions (IMFs) and a residue with the CEEMDAN. Then, the decomposed sub‐sequence is predicted and the final prediction result is obtained by comprehensive superposition. The results indicate that: the CEEMDAN algorithm has significantly improved the prediction performance. Compared with the AT‐LSTM model, mean absolute percentage error (MAPE) is reduced by 10.75%, 24.84%, 31.80%, 24.98%, 14.29%, and 31.42% when the time window was 3, 6, 9, 12, 15, and 18, respectively, in the dataset of Yaxi expressway. In the dataset of Chengnan expressway, the number of error points with MAPE greater than 40% is significantly reduced after the adoption of the LSTM model. After the introduction of CEEMDAN algorithm, the error at each time point is controlled within 30%. The proposed model controls the error at each time point within 25%. In different datasets, the proposed model has better prediction ability for highly non‐linear travel time, and can better capture the trend abrupt characteristics of rush hour traffic flow. [ABSTRACT FROM AUTHOR]

Short-term power load forecasting is of great significance for the reliable and safe operation of power systems. In order to improve the accuracy of short-term load forecasting, for the problems of random fluctuation in load and the complexity of load-influencing factors, this paper proposes a two-stage short-term load forecasting method, SSA–VMD-LSTM-MLR-FE (SVLM–FE) based on sparrow search algorithm (SSA), to optimize variational mode decomposition (VMD) and feature engineering (FE). Firstly, an evaluation criterion on the loss of VMD decomposition is proposed, and SSA is used to find the optimal combination of parameters for VMD under this criterion. Secondly, the first stage of forecasting is carried out, and the different components obtained from SSA–VMD are predicted separately, with the high-frequency components input to a long short-term memory network (LSTM) for forecasting and the low-frequency components input to a multiple linear regression model (MLR) for forecasting. Finally, the forecasting values of the components obtained in the first stage are input to the second stage for error correction; factors with a high degree of influence on the load are selected using the Pearson correlation coefficient (PCC) and maximal information coefficient (MIC), and the load value at the moment that has a great influence on the load value at the time to be predicted is selected using autocorrelation function (ACF). The forecasting values of the components are fused with the selected feature values to construct a vector, which is fed into the fully connected layer for forecasting. In this paper, the performance of SVLM–FE is evaluated experimentally on two datasets from two places in China. In Place 1, the RMSE, MAE, and MAPE are 128.169 MW, 102.525 MW, and 1.562%, respectively; in Place 2, the RMSE, MAE, and MAPE are 111.636 MW, 92.291 MW, and 1.426%, respectively. The experimental results show that SVLM–FE has high accuracy and stability. [ABSTRACT FROM AUTHOR]

Wind and solar energy are two popular forms of renewable energy used in microgrids and facilitating the transition towards net-zero carbon emissions by 2050. However, they are exceedingly unpredictable since they rely highly on weather and atmospheric conditions. In microgrids, smart energy management systems, such as integrated demand response programs, are permanently established on a step-ahead basis, which means that accurate forecasting of wind speed and solar irradiance intervals is becoming increasingly crucial to the optimal operation and planning of microgrids. With this in mind, a novel “bidirectional long short-term memory network” (Bi-LSTM)-based, deep stacked, sequence-to-sequence autoencoder (S2SAE) forecasting model for predicting short-term solar irradiation and wind speed was developed and evaluated in MATLAB. To create a deep stacked S2SAE prediction model, a deep Bi-LSTM-based encoder and decoder are stacked on top of one another to reduce the dimension of the input sequence, extract its features, and then reconstruct it to produce the forecasts. Hyperparameters of the proposed deep stacked S2SAE forecasting model were optimized using the Bayesian optimization algorithm. Moreover, the forecasting performance of the proposed Bi-LSTM-based deep stacked S2SAE model was compared to three other deep, and shallow stacked S2SAEs, i.e., the LSTM-based deep stacked S2SAE model, gated recurrent unit-based deep stacked S2SAE model, and Bi-LSTM-based shallow stacked S2SAE model. All these models were also optimized and modeled in MATLAB. The results simulated based on actual data confirmed that the proposed model outperformed the alternatives by achieving an accuracy of up to 99.7%, which evidenced the high reliability of the proposed forecasting. [ABSTRACT FROM AUTHOR]

The short-term forecast of photovoltaic (PV) power is crucial for the security and economics of power system operations. However, the fluctuation characteristics of the PV power, which are closely related to the meteorological factors, introduce inaccuracies in its forecast. Towards this end, the paper studies the effects of clustering analysis at long time scale and data reconstruction technique at short time scale on capturing PV power fluctuation characteristics. A short-term PV power forecasts method based on multi-scale fluctuation characteristics extraction (MFCE), which employs a path analysis to identify the relevance of meteorological factors with PV power at long time scale and a phase space reconstruction to analyze PV power fluctuation characteristics at short time scale, is proposed in this paper. The proposed MFCE methodology deploys a widely-used extreme gradient boosting (XGBoost) model to output the forecasting results. Both the effectiveness and accuracy of the proposed methodology are verified by using the real data under the conditions of sunny and cloudy days of four seasons compared to traditional methodologies. • The multi-scale fluctuation characteristics are analyzed for PV power forecast. • Identify dominant meteorological factors affecting PV power by path analysis. • The hour-level fluctuation is reduced by using path analysis-based clustering. • The phase space reconstruction is used to reduce the minute-level fluctuation. [ABSTRACT FROM AUTHOR]

There are many influencing factors present in different situations of power load. There is also a strong imbalance in the number of load samples. In addition to examining the problem of low training efficiency of existing algorithms, this paper proposes a short-term power load prediction method based on feature selection and error compensation under imbalanced samples. After clustering the load data, we expand some sample data to balance the sample categories and input the load data and filtered feature sequences into the improved GRU for prediction. At the same time, the errors generated during the training process are used as training data. An error correction model is constructed and trained, and the results are used for error compensation to further improve prediction accuracy. The experimental results show that the overall prediction accuracy of the model has increased by 80.24%. After expanding a few samples, the prediction accuracy of the region where the samples are located increased by 59.41%. Meanwhile, due to the improvement of the algorithms, the running time was reduced by approximately 14.92%. [ABSTRACT FROM AUTHOR]

In recent years, electrical systems have evolved, creating uncertainties in short-term economic dispatch programming due to demand fluctuations from self-generating companies. This paper proposes a flexible Machine Learning (ML) approach to address electrical load forecasting at various levels of disaggregation in the Peruvian Interconnected Electrical System (SEIN). The novelty of this approach includes utilizing meteorological data for training, employing an adaptable methodology with easily modifiable internal parameters, achieving low computational cost, and demonstrating high performance in terms of MAPE. The methodology combines modified Fuzzy ARTMAP Neural Network (FAMM) and hybrid Support Vector Machine FAMM (SVMFAMM) methods in a parallel process, using data decomposition through the Wavelet filter db20. Experimental results show that the proposed approach outperforms state-of-the-art models in predicting accuracy across different time intervals. [ABSTRACT FROM AUTHOR]

Short-term load forecasting (STLF) is critical for the energy industry. Accurate predictions of future electricity demand are necessary to ensure power systems' reliable and efficient operation. Various STLF models have been proposed in recent years, each with strengths and weaknesses. This paper comprehensively reviews some STLF models, including time series, artificial neural networks (ANNs), regression-based, and hybrid models. It first introduces the fundamental concepts and challenges of STLF, then discusses each model class's main features and assumptions. The paper compares the models in terms of their accuracy, robustness, computational efficiency, scalability, and adaptability and identifies each approach's advantages and limitations. Although this study suggests that ANNs and hybrid models may be the most promising ways to achieve accurate and reliable STLF, additional research is required to handle multiple input features, manage massive data sets, and adjust to shifting energy conditions. [ABSTRACT FROM AUTHOR]

Accurate short-term load forecasting is crucial for the steady operation of the power system and power market schedule planning. The extraction of features and training of prediction models are challenging as the load series is extremely volatile and nonlinear. To address the above issues, we propose a deep bidirectional long short-term memory (DBiLSTM) network based on variational mode decomposition (VMD) and an attention mechanism, in which the model hyperparameters are optimized using the improved particle swarm optimization (IPSO) technique. In this study, the mode number k of the VMD is determined by the ratio of residual energy following decomposition. Subsequently, the DBiLSTM is stacked using multiple layers of BiLSTM for a more precise representation of time-series data and the capturing of information at different scales, thereby enabling nonlinear load sequence forecasting and enhancing the accuracy. Finally, the IPSO uses nonlinear decreasing inertia weights to overcome the drawbacks of premature convergence and local optima. The effectiveness and progress of the proposed method are evaluated using the power load dataset from the ninth electrical attribute modeling competition test questions. [ABSTRACT FROM AUTHOR]

Accurate power load forecasting can facilitate effective distribution of power and avoid wasting power so as to reduce costs. Power load is affected by many factors, so accurate forecasting is more difficult, and the current methods are mostly aimed at short-term power load forecasting problems. There is no good method for long-term power load forecasting problems. Aiming at this problem, this paper proposes an LSTM-Informer model based on ensemble learning to solve the long-term load forecasting problem. The bottom layer of the model uses the long short-term memory network (LSTM) model as a learner to capture the short-term time correlation of power load, and the top layer uses the Informer model to solve the long-term dependence problem of power load forecasting. In this way, the LSTM-Informer model can not only capture short-term time correlation but can also accurately predict long-term power load. In this paper, a one-year dataset of the distribution network in the city of Tetouan in northern Morocco was used for experiments, and the mean square error (MSE) and mean absolute error (MAE) were used as evaluation criteria. The long-term prediction of this model is 0.58 and 0.38 higher than that of the lstm model based on MSE and MAE. The experimental results show that the LSTM-Informer model based on ensemble learning has more advantages in long-term power load forecasting than the advanced baseline method. [ABSTRACT FROM AUTHOR]

Accurate and efficient short-term forecasting of multiple loads is of great significance to the operation control and scheduling of integrated energy distribution systems. In order to improve the effect of load forecasting, a mogrifier-quantum weighted memory enhancement long short-term memory (Mogrifier-QWMELSTM) neural network forecasting model is proposed. Compared with the conventional LSTM neural network model, the model proposed in this paper has three improvements in model structure and model composition. First, the mogrifier is added to make the data fully interact with each other. This addition can help enhance the correlation between the front and rear data and improve generalization, which is the main disadvantage of LSTM neural network. Second, the memory enhancement mechanism is added on the forget gate to realize the extraction and recovery of forgotten information. The addition can help improve the gradient transmission ability in the learning process of the neural network, make the neural network remain sensitive to distant data information, and enhance the memory ability. Third, the model is composed of quantum weighted neurons. Compared with conventional neurons, quantum weighted neurons have significant advantages in nonlinear data processing and parallel computing, which help to improve the accuracy of load forecasting. The simulation results show that the weighted mean accuracy of the proposed model can reach more than 97.5% in summer and winter. Moreover, the proposed model has good forecasting effect on seven typical days in winter, which shows that the model has good stability. [ABSTRACT FROM AUTHOR]

The need for and interest in very-short-term load forecasting (VSTLF) is increasing and important for goals such as energy pricing markets. There is greater challenge in predicting load consumption for residential-load-type data, which is highly variable in nature and does not form visible patterns present in aggregated nodal-type load data. Previous works have used methods such as LSTM and CNN for VSTLF; however, the use of DNN has yet to be investigated. Furthermore, DNNs have been effectively used in STLF but have not been applied to very-short-term time frames. In this work, a deep network architecture is proposed and applied to very-short-term forecasting of residential load patterns that exhibit high variability and abrupt changes. The method extends previous work by including delayed load demand as an input, as well as working for 1 min data resolution. The deep model is trained on the load demand data of selected days—one, two, and a week—prior to the targeted day. Test results on real-world residential load patterns encompassing a set of 32 days (a sample from different seasons and special days) exhibit the efficiency of the deep network in providing high-accuracy residential forecasts, as measured with three different error metrics, namely MSE, RMSE, and MAPE. On average, MSE and RMSE are lower than 0.51 kW and 0.69 kW, and MAPE lower than 0.51%. [ABSTRACT FROM AUTHOR]

Runoff prediction with high accuracy is vital to protect people's properties and lives. In this study, a Short-Term Streamflow Forecasting Framework combining Long Short-Term Memory (LSTM) with Self-Organizing Map (SOM) is proposed, which clusters hydro-meteorological factors through SOM network to cluster the streamflow into several flow modes with different physical characteristics, converting complex global modeling into local modeling. The framework also considers the temporal characteristics of the streamflow, so the data of different flow modes are fitted with multiple LSTM separately. Besides, Random Forest is used in the framework for feature selection. The model is used for streamflow forecasting 1 to 3 day(s) ahead in the Qingxi River Basin in China, and the performance is compared with those of SVR, ANN, LSTM, SOM-SVR, SOM-ANN, FCM-LSTM, and K-means-LSTM. In addition, SOM-LSTM with three and four clusters were compared. The results show that (1) the sub-processes obtained by SOM clustering show some physical characteristics consistent with the actual process. (2) SOM-LSTM significantly improves the prediction accuracy of short-term streamflow forecasting. (3) All the integrated models using different clustering methods can improve the prediction accuracy of a single LSTM, and SOM-LSTM has the most reliable prediction when the lead time is 1–2 day(s). (4) The number of clusters being set to 4 is more suitable for the proposed prediction framework. The overall results show that the SOM-LSTM provides an efficient method for short-term streamflow forecasting. [ABSTRACT FROM AUTHOR]

Large-scale integration of photovoltaics (PV) into electricity grids is challenged by the intermittent nature of solar power. Sky-image-based solar forecasting using deep learning has been recognized as a promising approach to predicting the short-term fluctuations. However, there are few publicly available standardized benchmark datasets for image-based solar forecasting, which limits the comparison of different forecasting models and the exploration of forecasting methods. To fill these gaps, we introduce SKIPP'D—a SKy Images and Photovoltaic Power Generation Dataset. The dataset contains three years (2017–2019) of quality-controlled down-sampled sky images and PV power generation data that is ready-to-use for short-term solar forecasting using deep learning. In addition, to support the flexibility in research, we provide the high resolution, high frequency sky images and PV power generation data as well as the concurrent sky video footage. We also include a code base containing data processing scripts and baseline model implementations for researchers to reproduce our previous work and accelerate their research in solar forecasting. • A curated sky image and PV generation dataset is released for short-term solar forecasting. • Processed benchmark data and raw data are both provided for flexibility of research. • Reference codes for data processing and baseline model implementations are provided. • Baseline deep learning models are developed to demonstrate the uses of the dataset. [ABSTRACT FROM AUTHOR]

Accurate multi-energy load prediction plays a very crucial role in integrated energy system management. To address the load characteristics of strong relational coupling, volatility and uncertainty in user-side integrated energy systems, this paper proposes a multi-task learning based short-term multi-energy load prediction method. Load participation factor is proposed to portray the proportion of different loads in the total load demand, and multi-task learning method is introduced to deeply explore the coupling relationships among them. Then, the proposed method is validated on a real-world dataset. The results show that the method has higher prediction accuracy than the existing methods, and the prediction accuracy is improved by at least 1.3%. [ABSTRACT FROM AUTHOR]

Recent economic growth and development have considerably raised energy consumption over the globe. Electric load prediction approaches become essential for effective planning, decision-making, and contract evaluation of the power systems. In order to achieve effective forecasting outcomes with minimum computation time, this study develops an improved whale optimization with deep learning enabled load prediction (IWO-DLELP) scheme for energy storage systems (ESS) in smart grid platform. The major intention of the IWO-DLELP technique is to effectually forecast the electric load in SG environment for designing proficient ESS. The proposed IWO-DLELP model initially undergoes pre-processing in two stages namely min-max normalization and feature selection. Besides, partition clustering approach is applied for the decomposition of data into distinct clusters with respect to distance and objective functions. Moreover, IWO with bidirectional gated recurrent unit (BiGRU) model is applied for the prediction of load and the hyperparameters are tuned by the use of IWO algorithm. The experiment analysis reported the enhanced results of the IWO-DLELP model over the recent methods interms of distinct evaluation measures. [ABSTRACT FROM AUTHOR]

Accurate multivariate load forecasting plays an important role in the planning management and safe operation of integrated energy systems. In order to simultaneously reduce the prediction bias and variance, a hybrid ensemble learning method for load forecasting of an integrated energy system combining sequential ensemble learning and parallel ensemble learning is proposed. Firstly, the load correlation and the maximum information coefficient (MIC) are used for feature selection. Then the base learner uses the Boost algorithm of sequential ensemble learning and uses the Bagging algorithm of parallel ensemble learning for hybrid ensemble learning prediction. The grid search algorithm (GS) performs hyper-parameter optimization of hybrid ensemble learning. The comparative analysis of the example verification shows that compared with different types of single ensemble learning, hybrid ensemble learning can better balance the bias and variance and accurately predict multiple loads such as electricity, cold, and heat in the integrated energy system. [ABSTRACT FROM AUTHOR]

Worldwide, the demand for power load forecasting is increasing. A multi-step power-load forecasting model is established based on Informer, which takes the historical load data as the input to realize the prediction of the power load in the future. The constructed model abandons the common recurrent neural network to deal with time-series problems, and uses the seq2seq structure with sparse self-attention mechanism as the main body, supplemented by specific input and output modules to deal with the long-range relationship in the time series, and makes effective use of the parallel advantages of the self-attention mechanism, so as to improve the prediction accuracy and prediction efficiency. The model is trained, verified and tested by using the power-load dataset of the Taoyuan substation in Nanchang. Compared with RNN, LSTM and LSTM with the attention mechanism and other common models based on a cyclic neural network, the results show that the prediction accuracy and efficiency of the Informer-based power-load forecasting model in 1440 time steps have certain advantages over cyclic neural network models. [ABSTRACT FROM AUTHOR]

Accurate medium- and long-term power load forecasting is of great significance for the scientific planning and safe operation of power systems. Monthly power load has multiscale time series correlation and seasonality. The existing models face the problems of insufficient feature extraction and a large volume of prediction models constructed according to seasons. Therefore, a hybrid feature pyramid CNN-LSTM model with seasonal inflection month correction for medium- and long-term power load forecasting is proposed. The model is constructed based on linear and nonlinear combination forecasting. With the aim to address the insufficient extraction of multiscale temporal correlation in load, a time series feature pyramid structure based on causal dilated convolution is proposed, and the accuracy of the model is improved by feature extraction and fusion of different scales. For the problem that the model volume of seasonal prediction is too large, a seasonal inflection monthly load correction strategy is proposed to construct a unified model to predict and correct the monthly load of the seasonal change inflection point, so as to improve the model's ability to deal with seasonality. The model proposed in this paper is verified on the actual power data in Shaoxing City. [ABSTRACT FROM AUTHOR]

Main Forecasting Problems There are different types of forecasting problems that can arise in electricity demand forecasting, including: Very short-term forecasting, which refers to the prediction of electricity demand or production for a time horizon from seconds to a few hours ahead. The applications of long-term forecasts of wind farm power generation are, e.g., maintenance scheduling, wind farm design, electricity market restructuring, and optimization of operating costs. A modern power system is a complex network of interconnected components, such as generators, transmission lines, and distribution subsystems, that are designed to provide electricity to consumers in an efficient and reliable manner. A power system requires forecasts that predict the future electricity demand, the power generation from RESs, and meteorological data that are important regarding consumer demand and the level of generation from RESs. [Extracted from the article]

Increased demand for fast edge computation and privacy concerns have shifted researchers' focus towards a type of distributed learning known as federated learning (FL). Recently, much research has been carried out on FL; however, a major challenge is the need to tackle the high diversity in different clients. Our research shows that using highly diverse data sets in FL can lead to low accuracy of some local models, which can be categorised as anomalous behaviour. In this paper, we present FedBranched, a clustering-based framework that uses probabilistic methods to create branches of clients and assigns their respective global models. Branching is performed using hidden Markov model clustering (HMM), and a round of branching depends on the diversity of the data. Clustering is performed on Euclidean distances of mean absolute percentage errors (MAPE) obtained from each client at the end of pre-defined communication rounds. The proposed framework was implemented on substation-level energy data with nine clients for short-term load forecasting using an artificial neural network (ANN). FedBranched took two clustering rounds and resulted in two different branches having individual global models. The results show a substantial increase in the average MAPE of all clients; the biggest improvement of 11.36% was observed in one client. [ABSTRACT FROM AUTHOR]

Numerous studies on short‐term load forecasting (STLF) have used feature extraction methods to increase the model's accuracy by incorporating multidimensional features containing time, weather and distance information. However, less attention has been paid to the input data size and output dimensions in STLF. To address these two issues, an STLF model is proposed based on output dimensions using only load data. First, the load data's long‐term behavior (trend and seasonality) is extracted through the long short‐term memory network (LSTM), followed by convolution to obtain the load data's non‐stationarity. Then, using the self‐attention mechanism (SAM), the crucial input load information is emphasized in the forecasting process. The calculation example shows that the proposed algorithm outperforms LSTM, LSTM‐based SAM, and CNN‐GRU‐based SAM by more than 10% in eight different buildings, demonstrating its suitability for forecasting with only load data. Additionally, compared to earlier research utilizing two well‐known public data sets, the MAPE is optimized by 2.2% and 5%, respectively. Also, the method has good prediction accuracy for a wide variety of time granularities and load aggregation levels, so it can be applied to various load forecasting scenarios and has good reference significance for load forecasting instrumentation. [ABSTRACT FROM AUTHOR]

Wind speed forecasting is advantageous in reducing wind-induced accidents or disasters and increasing the capture of wind power. Accordingly, this forecasting process has been a focus of research in the field of engineering. However, because wind speed is chaotic and random in nature, its forecasting inevitably includes errors. Consequently, specifying the appropriate method to obtain accurate forecasting results is difficult. The probabilistic forecasting method has considerable relevance to short-term wind speed forecasting because it provides both the predicted value and the error distribution. This study proposes a probabilistic forecasting method for short-term wind speeds based on the Gaussian mixture model and long short-term memory. The precision of the proposed method is evaluated by prediction intervals (i.e., prediction interval coverage probability, prediction interval normalized average width, and coverage width-based criterion) using 29 monitored wind speed datasets. The effects of wind speed characteristics on the forecasting precision of the proposed method were further studied. Results show that the proposed method is effective in obtaining the probability distribution of predicted wind speeds, and the forecast results are highly accurate. The forecasting precision of the proposed method is mainly influenced by the wind speed difference and standard deviation. [ABSTRACT FROM AUTHOR]

In a real-world scenario of load forecasting, it is crucial to determine the energy consumption in electrical networks. The energy consumption data exhibit high variability between historical data and newly arriving data streams. To keep the forecasting models updated with the current trends, it is important to fine-tune the models in a timely manner. This article proposes a reliable inductive transfer learning (ITL) method, to use the knowledge from existing deep learning (DL) load forecasting models, to innovatively develop highly accurate ITL models at a large number of other distribution nodes reducing model training time. The outlier-insensitive clustering-based technique is adopted to group similar distribution nodes into clusters. ITL is considered in the setting of homogeneous inductive transfer. To solve overfitting that exists with ITL, a novel weight regularized optimization approach is implemented. The proposed novel cross-model methodology is evaluated on a real-world case study of 1000 distribution nodes of an electrical grid for one-day ahead hourly forecasting. Experimental results demonstrate that overfitting and negative learning in ITL can be avoided by the dissociated weight regularization (DWR) optimizer and that the proposed methodology delivers a reduction in training time by almost 85.6% and has no noticeable accuracy losses. [ABSTRACT FROM AUTHOR]

The level of air pollution is reflected by the air quality index (AQI). People can use the AQI to organize their activities in a way that reduces or prevents exposure to air pollution altogether. Based on the AQI, governments, organizations, and businesses can also make plans to reduce air pollution. The multi-model ensemble has recently become a popular method for forecasting time series; however, it encounters the research problems of multi-parameter optimization and interaction analysis. To this end, a reduced-form ensemble of short-term air quality forecasting with the Sparrow search algorithm and decomposition error correction model is proposed in this paper. First, the data are decomposed using the CEEMDAN decomposition algorithm. Second, the Sparrow search algorithm is used in the model training process to obtain the optimal hyperparameters of the deep learning model and construct the optimal deep learning model. Next, the constructed models are used to predict the decomposed data, and the Lagrange multiplier method is used to determine the weights of each deep learning model. At last, the prediction results of each deep learning model are combined according to the weights to obtain the combined prediction results. Experiments show that (1) GRU, Bi-GRU, LSTM, and Bi-LSTM are used to predict the undecomposed data and the data decomposed by CEEMADN. The outcomes demonstrate that the CEEMDAN decomposition technique can enhance the accuracy of the forecast, specifically an 11.248% reduction in average RMSE and a 0.865% increase in average R2. (2) A multi-model combination method based on the Lagrange multiplier method is designed, which can obtain the weights of each deep learning model, and the weights can combine multiple models. The results of the multi-model combination are better than those of the single model. (3) The Lagrange multiplier method was compared with the simple average combination model and the MAE inverse combination model. The experimental results show that the results obtained using the Lagrange multiplier method are better than the other two. [ABSTRACT FROM AUTHOR]

Accurate short-term load forecasting is the key to ensuring smooth and efficient power system operation and power market dispatch planning. However, the nonlinear, non-stationary, and time series nature of load sequences makes load forecasting difficult. To address these problems, this paper proposes a short-term load forecasting method (EPT-VMD-TCN-TPA) based on the hybrid decomposition of load sequences, which combines ensemble patch transform (EPT), variational modal decomposition (VMD), a temporal convolutional network (TCN), and a temporal pattern attention mechanism (TPA). In which, the trend component (Tr(t)) and the residual fluctuation component (Re(t)) of the load series are extracted using EPT, and then the Re(t) component is decomposed into intrinsic modal function components (IMFs) of different frequencies using VMD. The Tr(t) and IMFs components of the fused meteorological data are predicted separately by the TCN-TPA prediction model, and finally, the prediction results of each component are reconstructed and superimposed to obtain the final predicted value of the load. In addition, experiments after reconstructing each IMF component according to the fuzzy entropy (FE) values are discussed in this paper. To evaluate the performance of the proposed method in this paper, we used datasets from two Areas of the 9th Mathematical Modeling Contest in China. The experimental results show that the predictive precision of the EPT-VMD-TCN-TPA model outperforms other comparative models. More specifically, the experimental results of the EPT-VMD-TCN-TPA method had a MAPE of 1.25% and 1.58% on Area 1 and Area 2 test sets, respectively. [ABSTRACT FROM AUTHOR]

The operation and planning of power systems depend heavily on M-LTLF, which is complicated and nonlinear, making it challenging for conventional medium- and long-term forecasting models to produce reliable results. The SARIMA model is chosen for M-LTLF in this study, and the model's parameters are tuned. This study takes the electricity consumption data of the whole Yunnan as the research object. Among them, the electricity consumption data from 2008 to 2018 is used as a training sample for fitting and analysis, and the electricity consumption of the whole province is predicted from 2019 to 2020. The end results demonstrate the viability and efficacy of the SARIMA model for M-LTLF. [ABSTRACT FROM AUTHOR]

Accurate PV power forecasting is becoming a mandatory task to integrate the PV plant into the electrical grid, scheduling and guaranteeing the safety of the power grid. In this paper, a novel model to forecast the PV power using LSTM-TCN has been proposed. It consists of a combination between Long Short Term Memory and Temporal Convolutional Network models. LSTM is used to extract the temporal features from input data, then combined with TCN to build the connection between features and outputs. The proposed model has been tested using a dataset that includes historical time series of measured PV power. The accuracy of this model is then compared to LSTM and TCN models in different seasons, time periods forecast, cloudy, clear, and intermittent days. For one step forecasting, the results show that our proposed model outperforms the LSTM and TCN model. It has carried out a reduction of 8.47%, 14.26% for the autumn season, 6.91%,15.18 for the winter season, 10.22%,14.26% for spring season and 14.26%, 14.23% for the summer season on the Mean Absolute Error compared with LSTM, TCN. For multistep forecasting, LSTM-TCN surpassed all compared models in different time periods forecast from 2 steps to 7 steps PV power forecasting. [ABSTRACT FROM AUTHOR]

Accurate short-term load forecasting is of great significance to the safe and stable operation of power systems and the development of the power market. Most existing studies apply deep learning models to make predictions considering only one feature or temporal relationship in load time series. Therefore, to obtain an accurate and reliable prediction result, a hybrid prediction model combining a dual-stage attention mechanism (DA), crisscross grey wolf optimizer (CS-GWO) and bidirectional gated recurrent unit (BiGRU) is proposed in this paper. DA is introduced on the input side of the model to improve the sensitivity of the model to key features and information at key time points simultaneously. CS-GWO is formed by combining the horizontal and vertical crossover operators, to enhance the global search ability and the diversity of the population of GWO. Meanwhile, BiGRU is optimized by CS-GWO to accelerate the convergence of the model. Finally, a collected load dataset, four evaluation metrics and parametric and non-parametric testing manners are used to evaluate the proposed CS-GWO-DA-BiGRU short-term load prediction model. The experimental results show that the RMSE, MAE and SMAPE are reduced respectively by 3.86%, 1.37% and 0.30% of those of the second-best performing CSO-DA-BiGRU model, which demonstrates that the proposed model can better fit the load data and achieve better prediction results. [ABSTRACT FROM AUTHOR]