Guest Editor(s)
Dr. Mehdi Neshat
Email: mehdi.neshat@uts.edu.au
Affiliation: University of Technology Sydney, Sydney, Australia
Homepage:
Research Interests: artificial intelligence, machine learning, renewable energy systems, energy forecasting and optimisation
Summary
This Special Issue is dedicated to the rapidly evolving role of artificial intelligence (AI) in renewable energy systems, spanning classical machine learning methods through deep learning and emerging generative and foundation AI technologies. As renewable energy systems become increasingly complex, distributed, data-rich, and interconnected, advanced AI techniques are creating new opportunities to improve energy forecasting, system optimisation, control, reliability, efficiency, and decision-making.
Traditional machine learning approaches, including regression, decision trees, support vector machines, ensemble learning, and evolutionary computation, have played an important role in renewable energy modelling and prediction. More recently, deep neural networks, transformers, graph neural networks, reinforcement learning, physics-informed AI, explainable AI, multimodal learning, foundation models, and large language models (LLMs) have significantly expanded the capabilities of intelligent energy systems. These approaches can capture complex temporal, spatial, physical, and operational relationships that are difficult to represent using conventional modelling techniques.
The transition from classical machine learning to next-generation AI offers considerable potential across solar, wind, wave, tidal, hydropower, geothermal, hydrogen, energy storage, and hybrid renewable energy systems. AI-driven approaches can support more accurate renewable generation forecasting, predictive maintenance, optimal energy management, system design, fault diagnosis, intelligent control, grid integration, and decision support. At the same time, important challenges remain regarding model interpretability, robustness, uncertainty, computational requirements, data quality, generalisability, cybersecurity, and trustworthy deployment.
This Special Issue aims to bring together researchers and practitioners working across machine learning, artificial intelligence, optimisation, energy engineering, and renewable energy technologies to present methodological advances and practical applications of intelligent computational approaches for next-generation renewable energy systems.
This Special Issue focuses, among others, on the following topics:
· Classical and advanced machine learning techniques for renewable energy systems
· Deep learning and ensemble learning for renewable energy forecasting and modelling
· Transformers and attention-based architectures for energy time-series forecasting
· Generative AI, large language models, and foundation models for renewable energy applications
· Multimodal AI integrating sensor, image, weather, spatial, textual, and operational data
· Graph neural networks and spatiotemporal AI for renewable energy and smart-grid applications
· Physics-informed and physics-guided AI for energy modelling, forecasting, and control
· Explainable, interpretable, trustworthy, and uncertainty-aware AI for energy systems
· Reinforcement learning and intelligent control of renewable and hybrid energy systems
· Evolutionary computation, metaheuristic optimisation, and AI-assisted optimisation of energy systems
· AI-driven predictive maintenance, fault detection, condition monitoring, and remaining useful life prediction
· Renewable power forecasting for wind, solar, wave, tidal, hydro, and hybrid systems
· Intelligent energy storage, hydrogen systems, microgrids, and renewable-grid integration
· Digital twins, autonomous energy systems, and AI-enabled energy management
· Comparative benchmarking and real-world validation of classical ML, deep learning, and emerging AI approaches
We invite authors to submit original research articles, review papers, methodological studies, and practical case studies that advance the theory, development, validation, or real-world application of artificial intelligence in renewable energy engineering. Contributions that critically compare conventional machine learning with emerging AI paradigms, demonstrate trustworthy and interpretable AI, or explore the potential of generative AI and foundation models for next-generation renewable energy systems are particularly encouraged.
Keywords
machine learning, deep learning, generative AI, foundation models, large language models, renewable energy systems, intelligent energy optimisation
Login
Register
Submit a Paper
Propose a Special lssue