Load Forecasting Research Articles

Short term load forecasting analysis using machine learning method: An SVM based study

Short-Term Load Forecasting (STLF) is crucial for effective energy management, enabling utilities to optimize electricity generation, distribution, and pricing strategies. This study explores the application of three machine learning models—Linear Regression (LR), Artificial Neural Networks (ANN), and Support Vector Machines (SVM)—to predict short-term electrical load demand. Each model was trained using historical load data enriched with temporal features to capture daily, seasonal, and other variations in electricity consumption. The SVM model demonstrated strong predictive capability, achieving a Mean Absolute Error (MAE) of 1887.41 MW, Mean Squared Error (MSE) of 6942.36 GW, Root Mean Squared Error (RMSE) of 2634.83 MW, and an R2 score of 91.95%. In comparison, the ANN model showed slightly higher errors, while the LR model had the highest error rates, indicating its limitations in capturing non-linear relationships. The results suggest that SVM and ANN models are more effective than LR for STLF due to their ability to handle non-linear dependencies and high-dimensional data. This study highlights the potential of machine learning techniques in enhancing the accuracy and reliability of load forecasting, ultimately supporting better decision-making in energy management.

Short-term load forecasting by GRU neural network and DDPG algorithm for adaptive optimization of hyperparameters

Short-term load forecasting (STLF) is critical to optimizing power system operation. Deep learning (DL) methods can provide extremely high accuracy for STLF. However, most models in existing research lack adaptive optimization capabilities in the prediction process and suffer from performance degradation. To resolve the above difficulties, we propose a hybrid model (DDPG-GRU) based on gated recurrent units and deep deterministic policy gradients for STLF. First, the GRU network has the advantage of processing multiple time series inputs and can simultaneously consider multi-dimensional load characteristics, thereby making the model more efficient. Since the GRU model structure is relatively complex, choosing a good set of hyperparameters is very difficult. Therefore, the purpose of using DDPG is to optimize the hyperparameters of the GRU model adaptively. The proposed model is a combination of DL methods and reinforcement learning. In order to prove the superiority of the proposed model, it is applied to the load data of Area 1 in China to perform single-step and multi-step load forecasting, respectively. The results show that DDPG-GRU has a better fitting effect than the baseline method. Taking the multi-step prediction results as an example, compared with the classic GRU network, the MAPE, MAE, and RMSE of the proposed model are reduced by 22.75 %, 14.44 %, and 14.02 %, respectively, while the R2 coefficient is increased by 13.23 %. At the same time, we use the China Area 2 data set to verify the universality of the proposed model. Furthermore, we compared the proposed method with state-of-the-art methods and achieved better accuracy.

Short-term power load forecasting in China: A Bi-SATCN neural network model based on VMD-SE.

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%.

Power data analysis and mining technology in smart grid

This study proposes a smart grid model named “GridOptiPredict”, which aims to achieve efficient analysis and processing of power system data through deep fusion of deep learning and graph neural network, so as to improve the intelligent level and overall efficiency of power grid operation. The model integrates three core functions of load forecasting, power grid state sensing and resource optimization into one, forming a closely connected and complementary framework. Through carefully designed experimental scheme, the practical value and effectiveness of “Grid OptiPredict” model are fully verified from three aspects: accuracy of load forecasting, sensitivity of power grid state sensing and efficiency of resource allocation strategy. Experimental results show that the model has significant advantages in prediction accuracy, model stability and robustness, resource optimization, security, information security, social and economic benefits and user experience.

Hybrid Long Short-Term Memory Wavelet Transform Models for Short-Term Electricity Load Forecasting

To ensure the constant availability of electrical energy, power companies must consistently maintain a balance between supply and demand. However, electrical load is influenced by a variety of factors, necessitating the development of robust forecasting models. This study seeks to enhance electricity load forecasting by proposing a hybrid model that combines Sorted Coefficient Wavelet Decomposition with Long Short-Term Memory (LSTM) networks. This approach offers significant advantages in reducing algorithmic complexity and effectively processing patterns within the same class of data. Various models, including Stacked LSTM, Bidirectional Long Short-Term Memory (BiLSTM), Convolutional Neural Network—Long Short-Term Memory (CNN-LSTM), and Convolutional Long Short-Term Memory (ConvLSTM), were compared and optimized using grid search with cross-validation on consumption data from Lome, a city in Togo. The results indicate that the ConvLSTM model outperforms its counterparts based on Mean Absolute Percentage Error (MAPE), Root Mean Squared Error (RMSE), and correlation coefficient (R2) metrics. The ConvLSTM model was further refined using wavelet decomposition with coefficient sorting, resulting in the WT+ConvLSTM model. This proposed approach significantly narrows the gap between actual and predicted loads, reducing discrepancies from 10–50 MW to 0.5–3 MW. In comparison, the WT+ConvLSTM model surpasses Autoregressive Integrated Moving Average (ARIMA) models and Multilayer Perceptron (MLP) type artificial neural networks, achieving a MAPE of 0.485%, an RMSE of 0.61 MW, and an R2 of 0.99. This approach demonstrates substantial robustness in electricity load forecasting, aiding stakeholders in the energy sector to make more informed decisions.

Application of artificial neural network for peak load forecasting in 150 kV Semarang power system

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).

Multi-area short-term load forecasting based on spatiotemporal graph neural network

Short term power load forecasting can accurately evaluate the overall power load changes and provide accurate reference for power system operation decision-making. To address the limitations of traditional load forecasting methods, which are unable to capture spatial correlations and simultaneously predict load changes in multiple areas, this paper proposes a load forecasting model based on the spatiotemporal attention convolutional mechanism. The proposed model is composed of two key components: a spatiotemporal attention module and a spatiotemporal convolution module. First, the dynamic spatiotemporal correlations between different electricity load areas are captured and analyzed by using the spatiotemporal attention mechanism. Secondly, the spatial pattern and temporal features of the load data sequence are effectively obtained by spatiotemporal convolutional layers. Finally, this paper verifies the accuracy and effectiveness of the proposed method through a real electricity consumption load dataset. The experimental results demonstrate that, in comparison to various benchmark prediction methods, the proposed method can fully explore and utilize the spatiotemporal correlation between different electricity load areas, thereby improving the accuracy of load prediction.

The Cost-Optimal Control of Building Air Conditioner Loads Based on Machine Learning: A Case Study of an Office Building in Nanjing

Building envelopes and indoor environments exhibit thermal inertia, forming a virtual energy storage system in conjunction with the building air conditioner (AC) system. This system represents a current demand response resource for building electricity use. Thus, this study centers on the CatBoost algorithm within machine learning (ML) technology, utilizing the LASSO regression model for feature selection and applying the Optuna framework for hyperparameter optimization (HPO) to develop a cost-optimal control method for minimizing building AC loads. This method addresses the challenges associated with traditional load forecasting and control methods, which are often impacted by environmental temperature, building parameters, and user behavior uncertainties. These methods struggle to accurately capture the complex dynamics and nonlinear relationships of AC operations, making it difficult to devise AC operation and virtual energy storage scheduling strategies effectively. The proposed method was applied and validated using a case study of an office building in Nanjing, China. The prediction results showed coefficient of variation in root mean square error (CV-RMSE) values of 6.4% and 2.2%. Compared with the original operating conditions, the indoor temperature remained within a comfortable range, the AC load was reduced by 5.25%, and the operating energy costs were reduced by 24.94%. These results demonstrate that the proposed method offers improved computational efficiency, enhanced model performance, and economic benefits.

A novel energy management of public charging stations using attention-based deep learning model

Electricity grids are complex systems that must balance the supply and demand of electricity in real-time. However, with the increasing adoption of electric vehicles (EVs), managing the grid’s stability has become more challenging. EV charging can cause spikes in electricity demand, leading to peak demand periods that strain the power grid’s infrastructure. With the help of load forecasting, this effect on the grid can be mitigated by predicting the charging demand of electric vehicles in advance. This will help utilities adjust their energy supply in real-time, ensuring enough energy is available to meet demand, and preventing overloads or under utilization of the grid. Moreover, the EV charging demand is influenced by a wide range of factors, including charging station locations, weather, and time of day. Therefore, advanced deep learning models are required to learn these complex relationships and identify patterns in EV charging demand, enabling utilities to make more informed decisions. In this research, an attention-based deep learning approach is proposed for more accurate prediction of EV load demand. This novel approach integrates attention mechanisms with traditional deep learning models like LSTM and GRU, allowing the model to dynamically weight the importance of different features and focus on the most relevant information. The outcomes are compared to conventional deep learning and machine learning algorithms. To test the efficacy of the proposed framework, an actual ACN dataset for public EV charging stations is utilized.

MLFGCN: short-term residential load forecasting via graph attention temporal convolution network.

Residential load forecasting is a challenging task due to the random fluctuations caused by complex correlations and individual differences. The existing short-term load forecasting models usually introduce external influencing factors such as climate and date. However, these additional information not only bring computational burden to the model, but also have uncertainty. To address these issues, we propose a novel multi-level feature fusion model based on graph attention temporal convolutional network (MLFGCN) for short-term residential load forecasting. The proposed MLFGCN model fully considers the potential long-term dependencies in a single load series and the correlations between multiple load series, and does not require any additional information to be added. Temporal convolutional network (TCN) with gating mechanism is introduced to learn potential long-term dependencies in the original load series. In addition, we design two graph attentive convolutional modules to capture potential multi-level dependencies in load data. Finally, the outputs of each module are fused through an information fusion layer to obtain the highly accurate forecasting results. We conduct validation experiments on two real-world datasets. The results show that the proposed MLFGCN model achieves 0.25, 7.58% and 0.50 for MAE, MAPE and RMSE, respectively. These values are significantly better than those of baseline models. The MLFGCN algorithm proposed in this paper can significantly improve the accuracy of short-term residential load forecasting. This is achieved through high-quality feature reconstruction, comprehensive information graph construction and spatiotemporal features capture.

Stochastic configuration networks for short-term power load forecasting

The accuracy of power load forecasting can enhance the operational efficacy and economic efficiency of the power system. This paper utilizes the stochastic configuration network (SCN) and improved marine predator algorithm (IMPA) for power systems short-term load forecasting. First, the daily load data is clustered using the kernel fuzzy C-means (KFCM), and the clustering results are utilized as training input data for the load forecasting model. Then, load forecasting is performed using SCN. Next, IMPA is developed by integrating the opposite-based differential evolution (ODE) and normal mutation perturbation strategy for the purpose of preventing the algorithm from converging to local minima. Finally, IMPA is employed to optimize the critical parameters of the load forecasting model. The experimental results clearly demonstrate that the proposed algorithm performs favorably in terms of the prediction accuracy compared to other modeling algorithms.

Attention-Based Load Forecasting with Bidirectional Finetuning

Accurate load forecasting is essential for the efficient and reliable operation of power systems. Traditional models primarily utilize unidirectional data reading, capturing dependencies from past to future. This paper proposes a novel approach that enhances load forecasting accuracy by fine tuning an attention-based model with a bidirectional reading of time-series data. By incorporating both forward and backward temporal dependencies, the model gains a more comprehensive understanding of consumption patterns, leading to improved performance. We present a mathematical framework supporting this approach, demonstrating its potential to reduce forecasting errors and improve robustness. Experimental results on real-world load datasets indicate that our bidirectional model outperforms state-of-the-art conventional unidirectional models, providing a more reliable tool for short and medium-term load forecasting. This research highlights the importance of bidirectional context in time-series forecasting and its practical implications for grid stability, economic efficiency, and resource planning.

Regional Load Forecasting Scheme for Security Outsourcing Computation

Smart grids generate an immense volume of load data. When analyzed using intelligent technologies, these data can significantly improve power load management, optimize energy distribution, and support green energy conservation and emissions reduction goals. However, in the process of data utilization, a pertinent issue arises regarding potential privacy leakage concerning both regional and individual user power load data. This paper addresses the scenario of outsourcing computational tasks for regional power load forecasting in smart grids, proposing a regional-level load forecasting solution based on secure outsourcing computation. Initially, the scheme designs a secure outsourcing training protocol to carry out model training tasks while ensuring data security. This protocol guarantees that sensitive information, including but not limited to individual power consumption data, remains comprehensively safeguarded throughout the entirety of the training process, effectively mitigating any potential risks of privacy infringements. Subsequently, a secure outsourcing online prediction protocol is devised, enabling efficient execution of prediction tasks while safeguarding data privacy. This protocol ensures that predictions can be made without compromising the privacy of individual or regional power load data. Ultimately, experimental analysis demonstrates that the proposed scheme meets the requirements of privacy, accuracy, and timeliness for outsourcing computational tasks of load forecasting in smart grids.

Short-Term Electrical Load Forecasting Based on IDBO-PTCN-GRU Model

Accurate electrical load forecasting is crucial for the stable operation of power systems. However, existing forecasting models face limitations when handling multidimensional features and feature interactions. Additionally, traditional metaheuristic algorithms tend to become trapped in local optima during the optimization process, negatively impacting model performance and prediction accuracy. To address these challenges, this paper proposes a short-term electrical load forecasting method based on a parallel Temporal Convolutional Network–Gated Recurrent Unit (PTCN-GRU) model, optimized by an improved Dung Beetle Optimization algorithm (IDBO). This method employs a parallel TCN structure, using TCNs with different kernel sizes to extract and integrate multi-scale temporal features, thereby overcoming the limitations of traditional TCNs in processing multidimensional input data. Furthermore, this paper enhances the optimization performance and global search capability of the traditional Dung Beetle Optimization algorithm through several key improvements. Firstly, Latin hypercube sampling is introduced to increase the diversity of the initial population. Next, the Golden Sine Algorithm is integrated to refine the search behavior. Finally, a Cauchy–Gaussian mutation strategy is incorporated in the later stages of iteration to further strengthen the global search capability. Extensive experimental results demonstrate that the proposed IDBO-PTCN-GRU model significantly outperforms comparison models across all evaluation metrics. Specifically, the mean absolute error (MAE), mean absolute percentage error (MAPE), and root mean square error (RMSE) were reduced by 15.01%, 14.44%, and 14.42%, respectively, while the coefficient of determination (R2) increased by 2.13%. This research provides a novel approach to enhancing the accuracy of electrical load forecasting.

AI learning-driven optimization of microgrid systems for rural electrification and economic empowerment

Artificial Intelligence (AI) and machine learning (ML) are transforming the landscape of rural electrification through their application in microgrid systems. Microgrids, localized networks that can operate independently or in conjunction with the main grid, offer a viable solution for delivering reliable electricity to rural areas. AI-driven optimization enhances the performance and efficiency of these microgrids, addressing the unique challenges faced in remote regions and contributing to economic empowerment. AI technologies, including machine learning algorithms and data analytics, play a critical role in optimizing microgrid systems. By employing predictive maintenance, AI can forecast equipment failures and schedule timely repairs, thereby minimizing downtime and reducing maintenance costs. Additionally, AI enhances energy management through precise load forecasting, optimizing energy distribution, and integrating renewable energy sources like solar and wind. This not only balances energy supply and demand but also mitigates the variability associated with renewable sources. The impact of AI-driven microgrid optimization on rural electrification is profound. Improved system reliability and efficiency result in more stable energy supplies, which is crucial for supporting local businesses, educational facilities, and healthcare services in remote areas. Economically, the reduction in energy costs and the creation of new job opportunities further empower rural communities. Socially, reliable electricity enhances the quality of life, enabling better educational outcomes and promoting economic development. Successful implementations of AI in microgrid systems have demonstrated significant benefits. For instance, AI-optimized microgrids in rural communities have shown improved performance and stability, leading to greater energy access and economic benefits. However, challenges remain, including technical complexities, financial constraints, and regulatory hurdles. Addressing these challenges through continued research, investment, and policy support is essential for scaling AI-driven solutions and achieving broader impacts. AI-driven optimization of microgrid systems offers a powerful tool for advancing rural electrification and economic empowerment. By leveraging AI technologies, we can enhance energy reliability, reduce costs, and foster economic growth in underserved regions, paving the way for a more equitable and sustainable future. Keywords: AI Learning-Driven, Microgrid Systems, Rural Electrification, Economic Empowerment.

Short-term power load forecasting based on Seq2Seq model integrating Bayesian optimization, temporal convolutional network and attention

Power load forecasting is of great significance to the electricity management. However, extant research is insufficient in comprehensively combining data processing and further optimization of existing prediction models. Therefore, this paper propose an improved power load prediction methods from two aspects: data processing and optimization of Sequence to Sequence (Seq2Seq) model. Firstly, in the data processing, Extreme Gradient Boosting (XGBoost) is adopted to eliminate the redundant features for feature extraction. Meanwhile, Successive Variational Mode Decomposition (SVMD) is employed to solve the unsteadiness and nonlinearities present in electricity data during the decomposition process. Secondly, the Seq2Seq model is selected and improved with a variety of machine learning methods. Specifically, input data features are extracted using Convolutional Neural Networks (CNN), enhancing the decoder's focus on vital information with the Attention mechanism (AM). Temporal Convolutional Network (TCN) serves as both the encoder and decoder of Seq2Seq, with further optimization of the model parameters through the Bayesian Optimization (BO) algorithm. Finally, the cases of two real power market datasets in Switzerland and Singapore illustrate the efficiency and superiority of proposed hybrid forecasting method. Through a comprehensive comparison and analysis with the other six models and four commonly used evaluation metrics, it is evident that the proposed method excels in performance, attaining the highest level of prediction accuracy, with the highest accuracy rate of 95.83 %. Consequently, it exhibits significant practical utility in the realm of power load forecasting.

Transforming Mexico’s Electric Load Infrastructure: A Quantile Transformer Network Deep Learning Approach, 2019-2020

To transform Mexico's electric load infrastructure, accurate electric load forecasts are required that are crucial to efficiently allocate resources, maintain system stability, and manage energy. The purpose of this study is to use the Quantile Transformer Network (QTN) as a novel approach for a deep learning framework for load forecasting, emphasizing its potential and practical consequences in enhancing the accuracy of load forecasting in real-world energy systems. Moreover, it is shown that QTN efficiently captures complex patterns, temporal relationships and interconnections among factors that influence electric load. The dataset utilized consists of past records of energy consumption in the Baja California System in Mexico. It includes several factors such as electricity demand, marginal prices, temporal characteristics, temperature-related variables, seasonal patterns, and holidays. Additionally, QTN is combined with the Rainbow Technique (RT) to manage categorical variables, resulting in the creation of a unified feature called category. In this case, RT examines the connections between descriptive phrases that reflect distinct combinations of categorical factors depending on the load values. Moreover, this research shows that the common Quantile Regression (QR) outperforms QTN in capturing dependencies in sequential data. Finally, several recommendations for promoting Mexico's Electric Load Infrastructure are provided.

Affinity-Driven Transfer Learning for Load Forecasting.

In this study, we introduce an innovative method for load forecasting that capitalizes on the concept of task affinity score to measure the similarity between various tasks. The task affinity score emerges as a superior technique for assessing task similarity within the realm of transfer learning. Through empirical evaluation on a synthetic dataset, we establish the superiority of the task affinity score over traditional metrics in task selection scenarios. To operationalize this method, we unveil the Affinity-Driven Transfer Learning (ADTL) algorithm to enhance load forecasting precision. The ADTL algorithm enriches the transfer learning framework by incorporating insights from both pre-trained models and datasets, thereby augmenting the accuracy of load forecasting for new and unseen datasets. The robustness of the ADTL algorithm is further evidenced through its application to two empirical datasets, namely the dataset provided by the Australian Energy Market Operator (AEMO) and the Smart Australian dataset. In conclusion, our research underscores the important role of the task affinity score in refining transfer learning methodologies for load forecasting applications.

Short-term power load forecasting based on hybrid feature extraction and parallel BiLSTM network

Electricity is a vital resource for societal and economic activities. Accurate electricity load forecasting can effectively reduce costs and enhance energy efficiency. Nevertheless, current research has limitations in effectively extracting and utilizing load forecasting information. This encompasses both undiscovered latent features and models that have not effectively captured long-term dependencies. To address these issues, this paper proposes a novel network architecture, which utilizes a hybrid feature extraction strategy and integrates machine learning methods with deep learning techniques. This method employs a hybrid feature extraction strategy composed of gradient-boosted regression trees, Fisher Score, and mutual information to achieve comprehensive feature representation. The network architecture utilizes a multi-head convolutional neural network and a bi-directional long short-term memory (BiLSTM) with lag parameters. This architecture can simultaneously learn multiple levels and aspects of features, further enhancing the BiLSTM model’s ability to capture long-term dependencies. Through multiple experiments conducted on datasets from Maine, Singapore, New South Wales, Australia, and European countries, our method outperformed the comparison models in three out of the five datasets.

Ultra-short-term Load Forecasting Based on XGBoost-BiGRU

High-precision load forecasting serves as the foundation for power grid scheduling planning and safe economic operation. In scenarios where only historical power load data is available without other external information, fully exploiting meaningful features from the temporal load sequence is crucial for improving the accuracy of load forecasting. Therefore, an ultra-short-term load forecasting method that combines eXtreme gradient boosting (XGBoost) and bidirectional gated recurrent unit (BiGRU) is proposed in this paper. Considering various factors that affect loads, a candidate feature set is established, which includes temporal information and historical loads. XGBoost is used to select the features that contribute significantly to load forecasting, forming an optimal feature set. These optimal features are then used as inputs to the BiGRU, and the bayesian optimization algorithm is applied to optimize the network hyperparameters. Then the load forecasting model for the next 15 minutes based on BiGRU is generated by training iteratively. The proposed XGBoost-BiGRU method is validated on real load data from a province in China. Experimental results demonstrate that the method can effectively avoid the impact of redundant features, improving both prediction accuracy and efficiency. The research has significant importance for guiding real-time supply-demand balance calculations and scheduling in power grids.