Advanced AI-Assisted Identification, Optimization, and Control of Integrated Heating, Cooling, Renewable, and Storage Systems

Energy systems combining heating, cooling, renewable energy integration, and energy storage involve simultaneous heat and mass transfer, where transport delays occur naturally and physical variables act non-simultaneously. Subsystems arranged in feedback loops produce internal state delays alongside direct input-output lag. When combined with nonlinear dynamics, stochastic operational disturbances from intermittent renewables, and modeling inaccuracies, these processes form complex, infinite-dimensional systems that are exceedingly difficult to model, identify, and control using classical approaches. This necessitates the development and application of highly original, advanced artificial intelligence frameworks. Goal: This Research Topic explores how modern optimization methods and original advances in artificial intelligence can overcome the limitations of classical identification and control in complex, integrated thermal and renewable energy systems. We welcome contributions leveraging novel surrogate AI architectures (e.g., physics-informed networks) for model predictive control, advanced metaheuristics for complex parameter estimation and controller tuning, and deep reinforcement learning strategies for robust control. All advanced AI applications should be supported by rigorous experimental and simulation-based validation. Scope and information for authors: With this Research Topic, we aim to collect articles advancing identification, optimization, and control methodologies across heating, cooling, coupled thermal systems, renewable energy integration, and energy storage. Topics of interest include, but are not limited to: • Advanced AI-driven identification and modeling of time-delay and infinite-dimensional thermal and renewable systems. • Original surrogate and deep data-driven modeling architectures for model predictive control (MPC). • Advanced metaheuristic and AI-enhanced numerical optimization for controller tuning. • Deep reinforcement learning and novel adaptive control strategies for complex thermal, renewable, and storage processes. • Experimental validation and real-world deployment in district heating/cooling, HVAC, heat pumps, renewable generation, and battery/thermal storage systems. Topic editors: Libor Pekař, Mengjie SONG Source: https://www.frontiersin.org/research-topics/85836/advanced-ai-assisted-identification-optimization-and-control-of-integrated-heating-cooling-renewable-and-storage-systems