Load Forecasting Research Articles

Short-Term Electrical Load Forecasting Based on Fuzzy Rough Set Feature Selection and Multi-kernel Extreme Learning Machine

As the complexity of power systems increases, accurate load forecasting becomes crucial. This paper proposes a method for short-term electrical load forecasting that integrates fuzzy rough set (FRS) theory and multi-kernel extreme learning machine (MKELM) to improve both the accuracy and reliability of load predictions. First, we introduce the FRS theory for pre-selecting features. Next, we use correlation analysis (CA) to get rid of redundant features and choose the most important ones as prediction targets. Second, we introduce a novel prediction model based on the multi-kernel extreme learning machine (MKELM), utilizing an enhanced differential evolution algorithm (DEA) to optimize the kernel function’s parameters and the model’s weights. This approach allows for effective adaptation to various feature subsets. Experimental results on actual power load data demonstrate that our approach achieves high accuracy and reliability in short-term load forecasting. Moreover, comparative evaluations reveal that the proposed method outperforms alternative prediction models on key metrics. ANOVA and multiple comparisons further validate the statistical significance and superiority of the proposed method.

Sparse dynamic graph learning for district heat load forecasting

Accurate heat load forecasting is crucial for the efficient operation and management of district heating systems. This study introduces a novel Sparse Dynamic Graph Neural Network (SDGNN) framework designed to address the complexities of forecasting heat load in district heating networks. The proposed model represents the district heating network as a dynamic graph, with nodes corresponding to consumers or heat sources and edges denoting temporal dependencies. The SDGNN framework comprises three key components: (1) a sparse graph learning module that identifies the most relevant nodes and edges, (2) a spatio-temporal memory enhancement module that captures both short-term and long-term dependencies, and (3) a temporal fusion module that integrates node representations into a comprehensive global forecast. Evaluated on a real-world district heating dataset from Denmark, the SDGNN model demonstrates superior accuracy and efficiency compared to existing methods. The results indicate that the SDGNN framework effectively captures intricate spatio-temporal patterns in historical heat load data, achieving up to 5.7% improvement in RMSE, 7.4% in MAE, and 5.7% in CVRMSE over baseline models. Additionally, incorporating meteorological factors into the model further enhances its predictive performance. These findings suggest that the SDGNN framework is a robust and scalable solution for district heat load forecasting, with potential applications in other domains involving spatio-temporal graph data.

Efektivitas Mutasi Transformator Dalam Mengatasi Fluktuasi Beban Pada Trafo Distribusi ULP Bululawang

Transformer is a very important component in the distribution of electricity from the distribution substation to consumers. Overloading and underloading of transformers can lead to significant inefficiencies and increased losses in the electrical distribution system. Based on data measurement of the ULP Bululawang transformer in 2022, it was found that the C0177 transformer (100 KVA) was overloaded (88.4%) and the C0254 transformer (160 KVA) was underloaded (21.4%). Load forecasting for 2027 predicts that the C0177 transformer load will reach 107%, causing overheating, while the C0254 transformer will remain underloaded at 23.68%. To address these issues, a transformer mutation was proposed. This study aims to evaluate the effectiveness of transformer mutation in redistributing loads and improving efficiency. The method involved measuring transformer loads before and after mutation and using the Least Square method for load forecasting. Post-mutation measurements showed the C0177 transformer load reduced to 62.6% and the C0254 transformer load increased to 37%. These results indicate that the transformer mutation significantly balanced the load distribution. The study also adjusted the protection settings, including FCO, output cable, main switch, PHB-TR, and NH Fuse output cable. The findings suggest that transformer mutation can effectively address load imbalances, improve operational efficiency, and reduce power losses in the distribution system.

Duck shaped load curve supervision using demand response program with LSTM based load forecast

Duck shaped load curve supervision using demand response program with LSTM based load forecast

A short-term electricity load forecasting method integrating empirical modal decomposition with SAM-LSTM

Short-term power load forecasting is the basis for ensuring the safe and stable operation of the power system. However, because power load forecasting is affected by weather, economy, geography, and other factors, it has strong instability and nonlinearity, making it difficult to improve the accuracy of short-term power load forecasting. To solve the above problems, a load forecasting method combining empirical modal decomposition (EMD) and long short-term memory neural network (LSTM) has been proposed. The original signal is first decomposed into a series of eigenmode functions and a residual quantity using the EMD algorithm. Subsequently, all the components are fed into the LSTM network. To further improve the load prediction accuracy, a self-attention mechanism is introduced for large component signals to further explore the internal correlation of the data, and the Sparrow Optimisation Algorithm (SSA) is used to optimize the LSTM hyperparameters. Combining EMD, LSTM, self-attention mechanism (SAM), and SSA, the EMD-SSA- SAM -LSTM method for short-term power load forecasting is further proposed. The results show that the coefficient of determination (R2) of the method is 0.98, the mean absolute error (MAE) is 0.013, the root mean square error (RMSE) is 0.018, and the mean absolute percentage error (MAPE) is 2.57%, which verifies that the proposed model can improve the accuracy of load forecasting, and has a certain application prospect.

Electric vehicle load forecasting based on convolutional networks with attention mechanism and federated learning method

AbstractAccurate forecasting of electric vehicle (EV) load is essential for grid stability and energy management. EV load forecasting is influenced by multiple factors. At present, the load forecasting model for EVs mainly uses collected sample data to build a data‐driven model. But these algorithms need to collect all the data together to train the model, ignoring the privacy of each data collection source. In a competitive market environment, each device service provider is not willing to share the sample data they store. Aiming at this problem, this paper proposes an EV load diagnosis algorithm considering data privacy. Firstly, a convolutional neural network with dual attention mechanism is constructed as the basic time series forecasting model. The association rule algorithm is used to select weather data with strong associations as the inputs of the model. Each service provider uses local data to perform deep learning network. All models are then trained using a federated learning framework. During the entire training process, historical data is stored locally, and only model parameter information is shared and interacted; thus data privacy is protected. Finally, the validity of the algorithm in this paper is verified by using real collected EV load data.

A short-term power load forecasting system based on data decomposition, deep learning and weighted linear error correction with feedback mechanism

Accurate power load forecasting enables Independent System Operators (ISOs) to precisely quantify the demand patterns of users and achieve efficient management of the smart grid. However, with the increasing variety of power consumption patterns, the power load data displays increasingly irregular characteristics, which posing great challenges for accurate load forecasting. In order to solve above problem, a novel power load forecasting system is proposed based on data denoising, customized deep learning and weighted linear error correction. Specifically, we first proposed an improved optimization algorithm IGWO-JAYA which enhanced the Grey Wolf Optimizer (GWO) algorithm by using Halton low-discrepancy sequence and the mechanism of JAYA algorithm. In data denoising, the proposed optimizer was employed to optimize the Variational Mode Decomposition (VMD), enabling data-driven intelligent denoising. The customized deep learning framework contained multi-layer Convolution Neural Network (CNN), Bi-directional Long Short-Term Memory (Bi-LSTM) and Multi-Head Attention mechanism. The effective integration of these layers can significantly improve the capacity for nonlinear fitting of deep learning. In weighted linear error correction, the IGWO-JAYA algorithm was employed to determine the appropriate weight for point forecasting values and residual forecasting values. By weighting them, the forecasting precision has been further enhanced. To verify the forecasting ability of the system, we conducted experiments on power load datasets from four states in Australia and found that it has the best performance compared with all rivals. In the discussion, we demonstrated the convergence efficiency of the IGWO-JAYA algorithm by CEC test function.

Sustainable energy transition optimization through decentralized hybrid energy systems with various energy storage technologies under multi-criterion indices: A mid-career repowering scenarios

Sustainable energy transition (SET) refers to the formulation of effective policies for quantifying the paradigm shift from fossil fuels to carbon-neutral technologies. Despite the anticipation of sustainable solutions, many developing nations continue to experience unsustainable energy regimes. Understanding the potential of this transition demands a multifaceted approach, emphasizing techno-economic optimization and performance enhancement to address future decentralized energy constraints. Although one of several ways to enable SET, the consideration of renewable energy sources (RESs) coupled with energy storage technologies (ESTs), which can offer multi-dimensional decision flexibility in present energy policies, is quite restricted. Based on a comparative analysis of various ESTs, this paper provides insight exploration of the SET framework by leveraging a diverse range of renewable potentials. Utilizing a proprietary derivative-free algorithm (PDFA) and an original grid-search algorithm (OGSA), the study focuses on load forecasting across different time horizons using a real-time dataset from multiple load centers in Pakistan. Load forecasting is carried out based on a combination of seasonal naïve forecasting (SNF), seasonal and trend decomposition using loess forecasting (STLF), and artificial neural networks (ANN). Results reveal a minimum Levelized cost of energy (LCOE) ranging from $0.105/kWh to $0.109/kWh in the presence of solar and dispatchable renewable-based hybrid configurations. For battery ESTs, based on NPC and LCOE, the feasibility is observed in the order of lead-acid (La), lithium-ion (Li-ion), and vanadium redox flow (VRF) technology. From a technical and capacity shortage fraction (CSF) perspective, Li-ion performed better than both La and VRF in terms of storage depletion as well as annual losses. Finally, a mid-career repowering analysis examines the behavior of energy storage technologies (ESTs), while sensitivity analyses and results validation highlight the significance of the proposed study's findings.

Deep learning-driven hybrid model for short-term load forecasting and smart grid information management

Accurate power load forecasting is crucial for the sustainable operation of smart grids. However, the complexity and uncertainty of load, along with the large-scale and high-dimensional energy information, present challenges in handling intricate dynamic features and long-term dependencies. This paper proposes a computational approach to address these challenges in short-term power load forecasting and energy information management, with the goal of accurately predicting future load demand. The study introduces a hybrid method that combines multiple deep learning models, the Gated Recurrent Unit (GRU) is employed to capture long-term dependencies in time series data, while the Temporal Convolutional Network (TCN) efficiently learns patterns and features in load data. Additionally, the attention mechanism is incorporated to automatically focus on the input components most relevant to the load prediction task, further enhancing model performance. According to the experimental evaluation conducted on four public datasets, including GEFCom2014, the proposed algorithm outperforms the baseline models on various metrics such as prediction accuracy, efficiency, and stability. Notably, on the GEFCom2014 dataset, FLOP is reduced by over 48.8%, inference time is shortened by more than 46.7%, and MAPE is improved by 39%. The proposed method significantly enhances the reliability, stability, and cost-effectiveness of smart grids, which facilitates risk assessment optimization and operational planning under the context of information management for smart grid systems.

Experimental validation of a predictive energy management strategy for agricultural fuel cell electric tractors

Efficiency and durability are critical challenges for the large-scale adoption of fuel cell powertrains in agricultural tractors due to the demanding nature of farm-related tasks. This study presents a novel predictive energy management strategy that uses forecasts of the average load of the farming cycle to achieve stationary fuel cell operation, thus limiting degradation caused by load cycling, high-power, and low-power operation. The recurrent characteristics exhibited by agricultural duty cycles allow the calculation of highly accurate average load prediction, which can be sufficient for a predictive energy management strategy to reduce degradation without hindering fuel consumption. As a result, this forecast is utilized in conjunction with a straightforward and real-time-capable energy management strategy, which foresees the operation of the fuel cell system at the level of the average load. The work is structured into two main contributions: model-based design of the energy management strategy, and experimental validation on a fuel cell powertrain testbed. Three typical agricultural duty cycles were studied to evaluate the benefits of the proposed strategy, demonstrating that energy management strategies can mitigate fuel cell degradation without compromising system efficiency. In particular, the predictive energy management strategy offers the potential to mitigate the negative impact of tractor operational idling time at the headland turns through the reduction of fuel consumption, thereby enhancing overall tractor performance. The experimental powertrain setup stands as an innovative contribution within the research landscape concerning fuel cell powertrains for tractors and validates the benefits of the proposed strategy. Furthermore, the conducted testbed analyses assume significance in highlighting the effects of the energy management strategy on the physical fuel cell operating factors and emphasizing the comprehensive benefits across the powertrain system, particularly with regard to the thermal management of the fuel cell system, where the prevention of derating is achievable through the implementation of the proposed energy management approach. Overall, the findings of this study have important implications for the development of sustainable and efficient farming procedures through the adoption of fuel cell technology in agricultural machinery.

Improved dendritic learning: Activation function analysis

This study conducted a thorough evaluation of an improved dendritic learning (DL) framework, focusing specifically on its application in power load forecasting. The objective was to optimise the activation functions within the synapses and somas of DL to enhance their adaptability across diverse real-world scenarios. Through a rigorous analysis involving 25 experiments across five activation functions (sigmoid, hyperbolic tangent (tanh), rectified linear unit (ReLU), leaky ReLU, and exponential linear unit (ELU)), we elucidated their impacts on both regression and classification performance. Notably, the leaky ReLU–tanh combination demonstrated exceptional mean performance and effectiveness across 14 benchmark datasets from the University of California Irvine Machine Learning Repository, surpassing alternative combinations. When applied to power load forecasting, this combination outperformed other models, particularly transformer and LSTM. These findings underscore the significant advantages of the leaky ReLU–tanh-based DL framework in accurately predicting electricity load in smart grids, as evidenced by the lowest mean absolute error (39.27), root mean squared error (29.13), and mean absolute percentage error (2.84).

A lightweight method of integrated local load forecasting and control of edge computing in active distribution networks

The strong resource constraints of edge-computing devices and the dynamic evolution of load characteristics put forward higher requirements for forecasting methods of active distribution networks. This paper proposes a lightweight adaptive ensemble learning method for local load forecasting and predictive control of active distribution networks based on edge computing in resource constrained scenarios. First, the adaptive sparse integration method is proposed to reduce the model scale. Then, the auto-encoder is introduced to downscale the model variables to further reduce computation time and storage overhead. An adaptive correction method is proposed to maintain the adaptability. Finally, a multi-timescale predictive control method for the edge side is established, which realizes the collaboration of local load forecasting and control. All cases can be deployed on an actual edge-computing device. Compared to other benchmark methods and the existing researches, the proposed method can minimize the model complexity without reducing the forecasting accuracy.

Short-term aggregate electric vehicle charging load forecasting in diverse conditions with minimal data using transfer and meta-learning

Short-term aggregate electric vehicle charging load forecasting in diverse conditions with minimal data using transfer and meta-learning

Enhancing multivariate, multi-step residential load forecasting with spatiotemporal graph attention-enabled transformer

Short-term residential load forecasting (STRLF) holds great significance for the stable and economic operation of distributed power systems. Different households in the same region may exhibit similar consumption patterns owing to the analogous environmental parameters. Incorporating the spatiotemporal correlations can enhance the load forecasting performance of individual households. To this end, a spatiotemporal graph attention (STGA)-enabled Transformer is proposed for multivariate, multi-step residential load forecasting in this paper. Specifically, the multiple residential loads are cast to a graph and a Transformer with a graph sequence-to-sequence (Seq2Seq) structure is employed to model the multi-step load forecasting problem. Gated fusion-based STGA blocks are embedded in the encoder and decoder of the Transformer to extract dynamic spatial correlations and non-linear temporal patterns among multiple residential loads. A transform attention block is further designed to transfer historical graph observations into future graph predictions and alleviate the error propagation between the encoder and decoder. The embedding of multiple attention modules in the Seq2Seq framework allows us to capture the spatiotemporal correlations between residents and achieve confident inference of load values several steps ahead. Numerical simulations on residential data from three different regions demonstrate that the developed Transformer method improves multi-step load forecasting by 14.7% at least, compared to the state-of-the-art benchmarks.

Development of an integrated energy management system for off-grid solar applications with advanced solar forecasting, time-of-use tariffs, and direct load control

Effectively managing and maximizing the integration of renewable energy sources is essential for a sustainable power grid due to the stochastic and intermittent nature of renewable energy generation. This study develops a comprehensive Integrated Energy Management System incorporating supply-demand side management in the form of time-of-use credit, direct load control, and generator control to enhance photovoltaic utilization in off-grid applications. A novel three-step solar energy forecasting approach is proposed in this paper, utilizing low-level data fusion and regression models to predict next-day photovoltaic generation with improved accuracy, and a rule-based decision algorithm is developed to correct forecast errors and manage loads dynamically. A techno-economic analysis covering a 20-year duration is carried out for scenarios with and without the integrated energy management system; three configurations are investigated for supplying an off-grid residential home, including diesel generator, diesel generator/photovoltaic system, and diesel generator/photovoltaic system/integrated energy management system. Results reveal that the hybrid configuration with integrated energy management system achieved 44 % and 46 % reductions in costs and carbon dioxide emissions compared to the diesel generator alone, and 8 % and 9 % compared to the diesel generator/photovoltaic setup respectively. The Integrated Energy Management System further enhanced photovoltaic utilisation rate by over 113 % when compared to the diesel generator/photovoltaic system. Further evaluations include customer behaviour impacts, demonstrating that a fully automated system with 100 % compliance significantly outperforms systems with manual customer control, highlighting the detrimental effect of overrides on the efficiency of direct load control. The flexibility of the Integrated Energy Management System framework allows potential adaptation for on-grid applications, showcasing its utility in diverse operational contexts.

Evaluation of electrical load demand forecasting using various machine learning algorithms

The energy sector heavily relies on a diverse array of machine learning algorithms for power load prediction, which plays a pivotal role in shaping policies for power generation and distribution. The precision of power load prediction depends on numerous factors that reflect nonlinear traits within the data. Notably, machine learning algorithms and artificial neural networks have emerged as indispensable components in contemporary power load forecasting. This study focuses specifically on machine learning algorithms, encompassing support vector machines (SVMs), long short-term memory (LSTM), ensemble classifiers, recurrent neural networks, and deep learning methods. The research meticulously examines short-term power load prediction by leveraging Chandigarh UT electricity utility data spanning the last 5 years. The assessment of prediction accuracy utilizes metrics such as normalized mean square error (NMSE), root mean squared error (RMSE), mean absolute error (MAE), and mutual information (MI). The prediction results demonstrate superior performance in LSTM compared to other algorithms, with the prediction error being the lowest in LSTM and 13.51% higher in SVMs. These findings provide valuable insights into the strengths and limitations of different machine learning algorithms. Validation experiments for the proposed method are conducted using MATLAB R2018 software.

Electrical Load Forecasting using Improved Feature Selection and Hybrid Deep Learning Algorithms for Power System Situational Awareness

Accurate electrical load prediction is imperative for effective energy management, grid stability, and resource planning. This research endeavours to enhance forecasting precision by developing an advanced electrical load forecasting model that integrates improved feature selection and hybrid deep learning algorithms. In this study, a novel Electrical Load Forecasting model is meticulously crafted, encompassing phases of pre-processing, feature extraction, feature selection, and the prediction phase. The process initiates with the pre-processing of raw data, employing data cleaning and normalization techniques for ensuring data quality and consistency. Relevant features for load forecasting, including Improved Principal Component Analysis, Skewness, Kurtosis, and Variance-based features, are subsequently extracted. The research introduces a novel Improved Information Gain approach for feature selection, aiming to discern the most informative and discriminative features crucial for precise load forecasting. Additionally, a hybrid classifier model is implemented in the load forecasting phase, synergizing the strengths of deep learning classifiers - the Artificial Neural Network and Long Short-Term Memory. The ANN and LSTM models are adeptly trained using the selected features acquired from the Improved Information Gain approach. The predictions from both LSTM and ANN models are intelligently fused to yield the final load forecasting outcome. This comprehensive approach contributes to the advancement of electrical load forecasting models, providing a robust framework for accurate predictions and informed decision-making in the realm of energy management and planning.

Optimization of Double Exponential Smoothing Using Particle Swarm Optimization Algorithm in Electricity Load

Electricity load forecasting plays a critical role in ensuring the efficient allocation of resources, maintenance optimization, and uninterrupted power supply. The double exponential smoothing (DES) method is widely used in forecasting time series data due to its adaptability and robustness, particularly in handling linear trends without seasonal patterns. However, determining the optimal value of the alpha parameter in DES is crucial for accurate forecasting results. This study proposes the use of the Particle Swarm Optimization (PSO) algorithm to optimize the alpha parameter in DES for electricity load forecasting. PSO is a computational method that iteratively improves candidate solutions by moving particles in the search space based on simple mathematical formulas. By optimizing the alpha parameter using PSO, we aim to enhance the accuracy of short-term electricity load forecasts. Our results demonstrate that the PSO-optimized DES approach achieves a Mean Absolute Percentage Error (MAPE) of 2.89% and an accuracy of 97.11%, indicating significant improvements in forecasting performance. While the PSO algorithm provides promising results, future research may explore the application of other metaheuristic algorithms, such as the whale or orca algorithms, to further enhance the optimization of DES parameters for electricity load forecasting. This study contributes to the advancement of forecasting techniques in the power industry, facilitating more efficient power generation and distribution planning.

Design of short-term load forecasting method considering user behavior

In order to ensure optimize the short-term power load forecasting effect, load forecasting method design taking into account the user behavior is studied. Mining user power consumption behavior data from power user power consumption information acquisition system, and suppressing power consumption behavior data noise through empirical mode decomposition algorithm; Input the denoised user behavior data into the improved Relief algorithm, extract the user power consumption behavior characteristics, eliminate redundant features through correlation analysis, and cluster the user behavior characteristics using K-means clustering algorithm to reduce the dimension of the feature data and the complexity of the features, then input the clustered features into the online extreme learning machine (OS-ELM), load forecasting is realized through online learning. Experiments show that this method can accurately predict the power consumption of each type of users in different time periods, and its prediction results have a high interval coverage.

Short-Term Load Forecasting of Electric Vehicle Charging Stations Accounting for Multifactor IDBO Hybrid Models

The charging behavior of electric vehicle users is highly stochastic, which makes the short-term prediction of charging load at electric vehicle charging stations difficult. In this paper, a data-driven hybrid model optimized by the improved dung beetle optimization algorithm (IDBO) is proposed to address the problem of the low accuracy of short-term prediction. Firstly, the charging station data are preprocessed to obtain clear and organized load data, and the input feature matrix is constructed using factors such as temperature, date type, and holidays. Secondly, the optimal CNN-BiLSTM model is constructed using convolutional neural network (CNN) and Bi-directional Long Short-Term Memory (BiLSTM), which realizes the feature extraction of the input matrix and better captures the hidden patterns and regularities in it. Then, methods such as Bernoulli mapping are used to improve the DBO algorithm and its hyperparameters; for example, hidden neurons of the hybrid model are tuned to further improve the model prediction accuracy. Finally, a simulation experiment platform is established based on MATLAB R2023a to validate the example calculations on the historical data of EV charging stations in the public dataset of ANN-DATA, and comparative analyses are carried out. The results show that compared with the traditional models such as CNN, BiLSTM and PSO-CNN-BiLSTM, the coefficient of determination of the model exceeds 0.8921 and the root mean square error is maintained at about 4.413 on both the training and test sets, which proves its effectiveness and stability.