A comprehensive review of hydrogen integrated hybrid renewable energy systems: Configurations, models, simulation and optimization with artificial intelligence

This work presents a comprehensive review of hydrogen-based hybrid renewable energy systems (HRESs), covering mathematical models, simulation and artificial intelligence (AI)-driven optimization approaches. Emphasizing the potential of hydrogen as an energy carrier to deepen renewable energy integration, especially in solar and wind HRESs, this review systematically details mathematical models for various renewable generation and storage systems, serving as a structured reference for researchers. Given the complexity of HRES modeling, this work provides insights into different modeling software and optimization algorithms, with a particular focus on artificial intelligence methods. The integration of software and artificial intelligence promises to solve complex modeling and optimization challenges with potential applications in different environments. Future directions suggest that the physical model-assisted AI framework, which embeds physical principles within AI models, holds promise for enhancing prediction accuracy and reliability in HRES applications. This framework, especially when combined with stochastic optimization, offers a potential pathway to address challenges in data availability and computational complexity, supporting the effective design and optimization of hydrogen-based HRESs for real-world applications. The overall findings will help improve the design and optimization of hydrogen-based hybrid renewable energy systems for practical implementation. • A state-of-the-art review is carried out on hybrid renewable energy systems (HRESs). • Models of HRESs and energy storage systems based on hydrogen and battery are provided. • Different software tools for HRES modeling and optimization are compared and analyzed. • Various optimization techniques for HRESs based hydrogen storage are summarized. • Artificial intelligence enhances performance prediction and optimization for HRES.