Chair / 主席:
Yukun Bao, Professor / 教授, Huazhong University of Science and Technology / 华中科技大学

Co-Chairs / 共同主席:
Shichang Cui, Postdoctoral Researcher / 博士后, Huazhong University of Science and Technology / 华中科技大学
Tong Niu, Researcher / 研究员, Zhengzhou University / 郑州大学

The global energy transition toward decarbonization has intensified the integration of variable renewable resources into power systems, demanding unprecedented agility in managing renewable volatility, grid stability, and market efficiency. Traditional analytical models struggle to address the nonlinear dynamics of renewables, real-time market bidding, and multi-objective grid optimization. Machine learning (ML) offers transformative solutions, yet challenges like scalability, interpretability, and integration with physical constraints persist. This special track bridges cutting-edge ML research with practical energy applications, fostering cross-disciplinary innovation to enhance grid resilience, market efficiency, and renewable utilization.

全球能源向脱碳转型加剧了可变可再生能源在电力系统中的整合，要求在管理可再生能源波动性、电网稳定性和市场效率方面具备前所未有的灵活性。传统的分析模型难以应对可再生能源的非线性动态、实时市场竞价和多目标电网优化。机器学习(ML)提供了变革性的解决方案，但可扩展性、可解释性以及与物理约束的整合等挑战仍然存在。本专题将前沿的机器学习研究与实际能源应用联系起来，促进跨学科创新，以提高电网韧性、市场效率和可再生能源利用率。

1. Renewable Power Forecasting with Hybrid Physics-AI Models / 基于物理-AI混合模型的可再生能源发电预测
2. Decision-Focused Learning for Market and Grid Operations / 面向电力市场和电网运行的决策聚焦学习
3. Reinforcement Learning for Adaptive Control and Spot Market Biding / 自适应控制与现货市场竞价的强化学习应用
4. Hybrid Decomposition-Ensemble Frameworks for Complex Modeling / 复杂系统建模的混合分解-集成框架
5. Explainable AI (XAI) for Trustworthy Forecasting and Prediction in Power Generation and Market Biding / 面向发电与市场竞价的可解释人工智能(XAI)技术
6. Case Studies with Innovative Techniques / 创新技术应用案例研究