AI‑Enabled Intelligent Forecasting and Optimal Operation for Hydrogen‑Integrated Energy Systems in the Power Market

Hydrogen‑Integrated Energy Systems (HIES) are emerging as critical enablers of sustainable, resilient, and low‑carbon energy infrastructures. By integrating hydrogen production, storage, and utilization with electricity, heating, and cooling services — along with high-penetration renewable energy resources and electric vehicles (EVs) — HIES provide a multi-dimensional solution for energy system decarbonization.However, the inherent variability of renewable generation, stochastic multi-energy demand, and uncertain EV charging/discharging behaviors pose significant challenges to system stability, energy efficiency, and economic performance within competitive power markets. Traditional prediction and optimization approaches are often insufficient for managing these highly coupled, multi-scale dynamics under uncertainty.In this context, AI‑enabled and physics-informed methodologies — including large language models (LLMs), physics-informed neural networks (PINNs), deep reinforcement learning, and hybrid physics-data frameworks — have become increasingly important. Integrating data-driven intelligence with physical principles offers a promising pathway toward intelligent, low-carbon, and economically optimized energy system operation.This Research Topic aims to showcase innovative interdisciplinary research on intelligent forecasting and optimal operation of hydrogen-integrated energy systems in the context of power markets, with an emphasis on sustainability, system-level integration, and low-carbon performance. We invite contributions that explore hybrid AI-physical frameworks, advanced optimization methods, and validated case studies demonstrating improvements in efficiency, reliability, and environmental impact. Potential topics include, but are not limited to:• LLM-based data analysis, feature extraction, and forecasting for HIES.• PINN and physics-informed methods for multi-energy demand prediction and operational decision-making.• Advanced forecasting and optimization of renewable energy output (wind, PV) and multi-energy demands (hydrogen, electricity, heat/cooling).• Hybrid AI-physics frameworks and reinforcement learning for optimal operation in power markets.• Uncertainty quantification, risk management, and resilience assessment under high renewable penetration and EV integration.• Digital twin integration with AI models for real-time simulation, forecasting, and operational control.• Scalable, energy-efficient algorithms for large-scale HIES optimization.• Empirical case studies and high-fidelity simulations demonstrating real-world impact on system sustainability, low-carbon performance, and economic efficiency.We welcome original research articles, comprehensive reviews, perspectives, methods papers, and data-rich case studies that contribute rigorously to advancing sustainable, intelligent, and low-carbon multi-energy systems. Topic editors: Jing Qiu, Siqi Bu Source: https://www.frontiersin.org/research-topics/77506/ai-enabled-intelligent-forecasting-and-optimal-operation-for-hydrogen-integrated-energy-systems-in-the-power-market