Special Session 1
AI-Driven Panoramic Perception, Temporal Forecasting, and Intelligent Dispatch for High-Renewable Power Systems
“面向高比例新能源电力系统的人工智能驱动全景感知、时序预测与智能调度”
The rapid growth of renewable energy resources is transforming modern power systems into highly uncertain, dynamic, and data-intensive cyber-physical systems. High penetration of wind power, photovoltaic generation, distributed energy resources, energy storage, and flexible loads introduces strong intermittency, complex spatiotemporal correlations, and frequent operational deviations. These challenges require advanced artificial intelligence methods to support real-time system awareness, accurate temporal forecasting, fast dispatch decision-making, and secure control optimization. Artificial intelligence technologies, including machine learning, deep learning, graph neural networks, reinforcement learning, foundation models, and large language models, provide powerful tools for modeling complex source-load-storage-grid interactions. By integrating multi-source data fusion, spatiotemporal prediction, learning-augmented optimization, and intelligent control, AI-driven methods can enhance the observability, predictability, flexibility, and resilience of high-renewable power systems. In particular, AI can play a critical role in addressing incomplete measurements, forecast errors, abrupt renewable power variations, extreme-weather disturbances, and large-scale dispatch optimization.
This special session focuses on AI methodologies, system architectures, and practical applications for high-renewable power systems. It aims to bring together researchers and practitioners working on intelligent perception, temporal forecasting, dispatch optimization, control decision-making, and AI-enabled engineering deployment in modern power systems.
随着风电、光伏、分布式能源、储能和柔性负荷的大规模接入，现代电力系统正逐步演化为具有高度不确定性、强动态性和数据密集特征的复杂信息物理系统。高比例新能源带来的间歇性、波动性、源荷储网多主体耦合关系以及频繁运行偏差，对系统实时感知、时序预测、快速调度和安全控制提出了更高要求。人工智能技术，包括机器学习、深度学习、图神经网络、强化学习、基础模型和大语言模型，为刻画复杂源荷储网交互关系提供了新的方法。通过融合多源数据感知、时空预测、学习增强优化和智能控制，人工智能方法能够提升高比例新能源电力系统的可观测性、可预测性、灵活性和韧性。特别是在量测不完备、预测偏差、功率陡变、极端天气扰动和大规模调度优化等问题中，人工智能具有重要应用潜力。本专题聚焦高比例新能源电力系统中的人工智能方法、系统架构和工程应用，重点关注智能感知、时序预测、调度优化、控制决策以及AI赋能的新型电力系统工程实践。
Topics (Including but not limited to)
- ● AI-enabled multi-source data fusion and real-time panoramic perception for power grid resources, including renewable generation, load, storage, electric vehicles, and flexible demand-side resources. | 人工智能驱动的多源数据融合与电网资源实时全景感知，包括新能源、负荷、储能、电动汽车和需求侧柔性资源的状态识别与能力感知。
- ● Deep learning, graph neural networks, and foundation-model-based temporal forecasting of source-load-storage power curves under incomplete, asynchronous, noisy, or heterogeneous information. | 基于深度学习、图神经网络和基础模型的源荷储功率曲线时序预测，面向非完备、异步、含噪和异构信息条件下的预测问题。
- ● AI-assisted dispatch technologies for high-renewable scenarios, including renewable power forecast errors, abrupt power variations, ramping events, and extreme-weather disturbances. | 面向新能源功率预测偏差、功率陡变、爬坡事件和极端天气扰动等典型场景的人工智能辅助调度技术。
- ● Learning-augmented optimization, reinforcement learning, and graph-based fast decision-making for large-scale power system operation and dispatch. | 面向大规模电力系统运行与调度的学习增强优化、强化学习和图学习快速决策方法。
- ● AI-based flexibility assessment, aggregation modeling, and coordinated operation of distributed energy resources, energy storage systems, controllable loads, and virtual power plants. | 基于人工智能的分布式能源、储能系统、可控负荷和虚拟电厂灵活性评估、聚合建模与协同运行。
- ● Intelligent control and security enhancement for high-renewable power systems, including voltage regulation, frequency support, emergency control, resilience improvement, and stability assessment. | 高可再生能源电力系统的智能控制与安全增强，包括电压调节、频率支撑、紧急控制、韧性提升及稳定性评估。
- ● Digital twins, cloud-edge intelligence, and large-language-model-based decision-support platforms for renewable-rich power system monitoring, dispatch, and control.
面向高比例新能源电力系统监测、调度与控制的数字孪生、云边智能和大语言模型辅助决策平台。 - ● Trustworthy, explainable, and robust AI methods for power engineering applications, including uncertainty quantification, safety constraints, physical consistency, and engineering validation. | 面向电力工程应用的可信、可解释和鲁棒人工智能方法，包括不确定性量化、安全约束、物理一致性和工程验证
Chair: Prof. Min Xia, Nanjing University of Information Science and Technology, China
Prof. Min Xia is a Professor and PhD supervisor at the School of Automation, Nanjing University of Information Science and Technology, China. He received the B.S. degree in Applied Mathematics from Shandong University in 2005 and the Ph.D. degree in Control Theory and Control Engineering from Donghua University in 2009. His research interests include artificial intelligence for energy and power systems, power grid dispatch optimization, distributed photovoltaic monitoring, multi-energy load forecasting, remote sensing image analysis, and graph/deep learning methods for power systems. In the past Five years, he has published more than 100 SCI-indexed papers, including 17 highly cited papers, and has been listed among the World’s Top 2% Scientists for three consecutive years. His team has undertaken 12 projects funded by the National Natural Science Foundation of China and has received one first prize and four second prizes at provincial/ministerial level or above.
Co-chair: Prof. Yaping Li, China Electric Power Research Institute, China
Prof. Yaping Li is currently the deputy director of the Optimal Dispatch and Intelligent Decision-making Research Section of China Electric Power Research Institute, and is in charge of the intelligent decision-making direction. She received the B.S. degree from Sichuan University, Chengdu, China, the Ph. D. degree from Hohai University, Nanjing, China, in 2003 and 2017 respectively, all in Power System and its Automation. Her research interests include artificial intelligence technology applied in power dispatching, power system optimal dispatch, "source-grid-load-storage" interactive operation, and demand response. She has been engaged in the field of dispatch automation for nearly 20 years. She has led projects funded by the National Natural Science Foundation of China and the National Science and Technology Major Project on Smart Grid, and participated in nearly 10 major projects such as the National Key Research and Development Program. She has published over 30 high-level SCI/EI indexed papers and won one first prize and four second prizes for scientific and technological progress at the provincial and ministerial levels.
Co-chair: Dr. Shi Liang, Nanjing University of Information Science and Technology, China
Dr. Liang Shi is a Lecturer at the School of Automation, Nanjing University of Information Science and Technology, China. He received the Ph.D. degree from Zhejiang University in 2020. From 2021 to 2022, he worked as a Research Associate in the Department of Mechanical Engineering at The University of Hong Kong. Since 2024, he has been serving as an Honorary Assistant Professor at The University of Hong Kong, with the appointment period from 2024 to 2026. He was selected as a Jiangsu Province “Double-Innovation Doctor” and received the Excellent Scientific and Technological Achievement Innovation Award at the China Hi-Tech Fair in 2024. He has served as a sub-project leader or key contributor in several AI-related State Grid of China Science and Technology Programs. He has published around 20 SCI/EI-indexed journal papers, including articles in IEEE Transactions on Cybernetics and IEEE Transactions on Industrial Electronics. His research interests include state estimation, meteorological automation, and intelligent analysis for high-renewable power grids.
Submission 投稿信息
Template(文章模板): Word Formatting.doc or LATEX Tempalte
Paper submission link for AIPE is at: Electronic Submission System (投稿链接)