Submission Deadline: 31 January 2027 View: 34 Submit to Special Issue
Prof. Dr. Nikolay Hinov
Email: hinov@tu-sofia.bg
Affiliation: Department of Computer Systems, Faculty of Computer Systems and Technologies, Technical University of Sofia, Sofia, Bulgaria
Research Interests: industrial and power electronics, artificial intelligence systems, electronic converters, autonomous and electric vehicles, smart grids and cities, as well as modeling and optimization of mechatronic systems.
Prof. Dr. Darius Andriukaitis
Email: darius.andriukaitis@ktu.lt
Affiliation: Department of Electronics Engineering, Faculty of Electrical and Electronics Engineering, Kaunas University of Technology, Kaunas, Lithuania
Research Interests: interactive electronic systems, electric vehicles, smart biomedical electronic systems, intelligent transport systems, integrated information systems, EMC, WSN, electronic video surveillance system, image processing, indirect measurement methods
Accurate forecasting has become a core requirement for the reliable and efficient operation of modern power and energy systems. The growing penetration of renewable generation, electrification, demand-side flexibility, and market volatility has increased the need for advanced forecasting tools capable of capturing nonlinear, nonstationary, and uncertain behavior across multiple time horizons. In this context, artificial intelligence has emerged as a powerful enabler for improving prediction accuracy, adaptive modeling, and decision support in energy applications. This Special Issue aims to bring together recent advances in power forecasting, load forecasting models, and broader energy forecasting approaches driven by artificial intelligence, machine learning, deep learning, hybrid models, and data-centric methodologies.
The scope of the Special Issue covers both methodological developments and practical applications relevant to modern energy systems. Contributions are invited on short-, medium-, and long-term forecasting of electrical load, renewable power generation, energy consumption, and related variables. Particular interest is given to explainable and trustworthy AI, probabilistic forecasting, spatiotemporal models, hybrid physics-informed and data-driven approaches, transfer learning, federated and edge learning, forecasting under uncertainty, and model deployment in smart grids, buildings, microgrids, energy markets, and integrated energy systems. Suggested themes include AI methods for forecasting, uncertainty quantification, benchmark datasets, real-world validation, and digital tools for operational energy management.
Topics include, but are not limited to:
· Artificial intelligence methods for power and energy forecasting
· Short-, medium-, and long-term load forecasting models
· Renewable energy generation forecasting (solar, wind, hybrid systems)
· Probabilistic and uncertainty-aware forecasting methods
· Deep learning, neural networks, and hybrid forecasting models
· Spatiotemporal forecasting models for energy systems
· Explainable and trustworthy AI in energy forecasting
· Forecasting for smart grids, microgrids, and distributed energy resources
· Data-driven models for demand response and energy management
· Forecasting tools for buildings, industry, and integrated energy systems
· Benchmark datasets and validation frameworks for energy forecasting models
· The importance of electric vehicles in smart cities' grids
Login
Register
Submit a Paper
Propose a Special lssue