A Comprehensive Review of Intelligent Electrical Load Forecasting Techniques for Modern Smart Power Systems
Keywords:
Electrical Load Forecasting, Smart Grid, Machine Learning, Deep Learning, Hybrid Forecasting Models, Artificial Intelligence.Abstract
Electrical load forecasting plays a crucial role in ensuring the reliable, secure, and economical operation of modern power systems. Accurate prediction of electricity demand enables effective generation scheduling, unit commitment, economic dispatch, demand-side management, renewable energy integration, and smart grid operation. This review presents a comprehensive analysis of recent advancements in electrical load forecasting techniques, covering conventional statistical methods, artificial intelligence, machine learning, deep learning, and hybrid forecasting frameworks. Traditional approaches, including regression analysis, time-series models, and autoregressive techniques, are discussed alongside their limitations in modeling complex nonlinear load patterns. The review further examines intelligent forecasting methods such as Artificial Neural Networks (ANN), Support Vector Machines (SVM), Random Forest, Long Short-Term Memory (LSTM), Gated Recurrent Units (GRU), Convolutional Neural Networks (CNN), Transformer architectures, reinforcement learning, and optimization-based hybrid models. Recent developments involving large language models, meta-learning, transfer learning, Bayesian optimization, and explainable artificial intelligence are also highlighted. A comparative evaluation of existing studies demonstrates that hybrid deep learning and optimization-based models generally provide superior forecasting accuracy, robustness, and adaptability under dynamic operating conditions. Despite these advances, several challenges remain, including computational complexity, dependence on large-scale high-quality datasets, model interpretability, parameter optimization, and the uncertainty introduced by renewable energy integration. The review identifies current research gaps and emphasizes the need for intelligent, scalable, and computationally efficient forecasting frameworks capable of handling diverse operating environments.
References
Eckhoff, Jannis, et al. "Electrical Load Forecasting in the Industrial Sector: A Literature Review of Machine Learning Models and Architectures for Grid Planning." Energies 19.2 (2026): 538.
Khan, Muhammad Farhan, et al. "A hybrid reinforcement learning framework for adaptive multi-horizon electricity load forecasting: The DWRNet approach." Computers and Electrical Engineering 131 (2026): 110926.
Rani, Sabiha, et al. "Dual Attention‐Empowered Bidirectional Long Short‐Term Memory Network for Short‐Term Electric Load Forecasting." Energy Technology 14.1 (2026): e202500914.
Song, Liye, et al. "Enhancing power load forecasting accuracy under high renewable energy penetration with a MSN-KAN framework: A novel approach to mitigate non-stationarity and enhance interpretability." Results in Engineering (2026): 109275.
Zhou, Pengfei, et al. "Multi-step electric load forecasting based on improved dual decomposition and error correction strategy." The Journal of Supercomputing 82.3 (2026): 119.
Gao, Shijie, et al. "DMC-LLMF: Dynamic multi-scale coordination and large language model cascade framework for power load forecasting." IEEE Access (2026).
Čeperić, Ervin, and Kristijan Lenac. "An Hour-Specific Hybrid DNN–SVR Framework for National-Scale Short-Term Load Forecasting." Sensors 26.3 (2026): 797.
Yuan, Fang, et al. "Adaptive load forecasting under regional distribution shifts: A meta-learning framework." Engineering Applications of Artificial Intelligence 164 (2026): 113104.
Guler, Zeynep Altiparmak, İnayet Özge Aksu, and Sina Ghaemi. "Hybrid VMD–LSTM–transformer model with Bayesian optimization for electricity load forecasting." Academia Green Energy 3.1 (2026).
da Paixão, Joelson Lopes. "ARTIFICIAL INTELLIGENCE IN ELECTRICAL SYSTEMS: A STRUCTURED NARRATIVE REVIEW OF FOUNDATIONS, APPLICATIONS, DIGITAL ARCHITECTURES AND CHALLENGES IN GRID MODERNIZATION." Journal International Review of Research Studies 1.03 (2026): 1-13.
Zakynthinos, Antonis, et al. "Transfer learning techniques on temporal fusion transformers for short-term building load forecasting under limited data conditions." Energy and Buildings (2026): 116935.
Kyryk, V. V., and Y. O. Shatalov. "Load Forecasting in Electrical Grids: Analysis of Methods and their Trends." Проблемы региональной энергетики 1 (65) (2025): 12-36.
El-Kenawy, El-Sayed M., et al. "Smart city electricity load forecasting using greylag goose optimization-enhanced time series analysis." Arabian Journal for Science and Engineering 51.6 (2026): 8359-8377.
Timur, Oğuzhan, and Halil Yaşar Üstünel. "Short-Term Electric Load Forecasting for an Industrial Plant Using Machine Learning-Based Algorithms." Energies 18.5 (2025): 1144.
Li, Peijin, et al. "Short-term electricity load forecasting based on large language models and weighted external factor optimization." Sustainable Energy Technologies and Assessments 82 (2025): 104449.
Majeed, Muhammad Asghar, et al. "Data-driven optimized load forecasting: An LSTM based RNN approach for smart grids." IEEE Access (2025).
Ullah, Kaleem, et al. "Short-term load forecasting: A comprehensive review and simulation study with CNN-LSTM hybrids approach." Ieee Access 12 (2024): 111858-111881.
Ali, Salman, et al. "From time-series to hybrid models: Advancements in short-term load forecasting embracing smart grid paradigm." Applied Sciences 14.11 (2024): 4442.
Sharifhosseini, Seyed Mohammad, et al. "Investigating intelligent forecasting and optimization in electrical power systems: A comprehensive review of techniques and applications." Energies 17.21 (2024): 5385.
Jain, Akanksha, and S. C. Gupta. "Evaluation of electrical load demand forecasting using various machine learning algorithms." Frontiers in Energy Research 12 (2024): 1408119.
Yousaf, Hamza, et al. "Time series and machine learning methods for short-term load forecasting in modern power systems." 2024 International Conference on Electrical, Communication and Computer Engineering (ICECCE). IEEE, 2024.
Zabin, Rifat, Khandaker Foysal Haque, and Ahmed Abdelgawad. "PredXGBR: A Machine Learning Framework for Short-Term Electrical Load Prediction." Electronics 13.22 (2024): 4521.
Zaboli, Aydin, et al. "A comprehensive review of behind-the-meter distributed energy resources load forecasting: Models, challenges, and emerging technologies." Energies 17.11 (2024): 2534.
Maleki, Neda, et al. "Future energy insights: Time-series and deep learning models for city load forecasting." Applied Energy 374 (2024): 124067.
Cordeiro-Costas, Moisés, et al. "Load forecasting with machine learning and deep learning methods." Applied Sciences 13.13 (2023): 7933.
Downloads
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
