Book chapter · Advances in computational intelligence and robotics book series · October 23, 2026
Forecasting Electrical Load and Renewable Energy Generation Using Machine Learning Methods
Vitalii Lapin, Dmitriy Saltykov, Mekhriddin Nurmamatov, Alice Kushchenko, Vladimir Lapin
Abstract
This chapter per the authors examines machine learning for forecasting electrical load and renewable generation under energy transition and grid digitalization. The purpose is to show why power systems need models handling nonlinear, non-stationary, and heterogeneous data. The chapter reviews LSTM, BiLSTM, GRU, CNN, TCN, hybrid architectures, ensembles, SVR, and GPR. Solar and wind forecasting depend on weather uncertainty, spatial relationships, and telemetry quality. The chapter compares facility types with forecasting methods and discusses digital twins, adaptive forecasting, and closed-loop control. Key problems: data drift, limited transferability, interpretability, computational complexity, and SCADA cybersecurity. Development requires integrating forecasting with digital twins, XAI, reinforcement learning, anomaly detection, and cybersecurity. Machine learning becomes a foundation for proactive and resilient power system management.
More by Mekhriddin Nurmamatov
- Lean Quantum Intelligence: A Compact Variational-Circuit Hybrid for Turbofan RUL Prediction with SHAP AttributionComputers · 2026
- Investigation of Vulnerabilities of Machine Learning Models to Adversarial Attacks in Smart Grid Forecasting SystemsAdvances in computational intelligence and robotics book series · 2026
- Capacity-Constrained Multi-robot Task Allocation via Quantum Approximate Optimisation: A Reproducible Benchmark on a Solomon VRPTW C101-Derived InstanceCommunications in computer and information science · 2026
- Explainable Variational Quantum Policy Gradient: SHAP-Based Interpretability of Quantum Reinforcement Learning Agents on CartPoleCommunications in computer and information science · 2026