<style type="text/css">.wpb_animate_when_almost_visible{opacity:1}</style>

Session 16: Advances in AI, Graph Technologies, GNNs, and LLMs for Power System Applications

“面向电力系统应用的人工智能、图技术、图神经网络与大语言模型前沿进展”

Session 16

Advances in AI, Graph Technologies, GNNs, and LLMs for Power System Applications
“面向电力系统应用的人工智能、图技术、图神经网络与大语言模型前沿进展”

The rapid evolution of modern power systems—characterized by increasing operational complexity, high penetration of renewable energy, and the growing need for resilient and intelligent grid management—calls for advanced computational paradigms beyond traditional analytical methods. Artificial Intelligence (AI) offers strong capabilities in adaptive learning, fast optimization, and robust decision-making; however, many existing AI approaches struggle to effectively model the structural dependencies and relational patterns inherent in power system data. Graph-based technologies, including Graph Computing, Graph Neural Networks (GNNs), and Knowledge Graphs (KGs), provide a natural way to represent the topology, constraints, and interactions of power systems by encoding entities as nodes and relationships as edges. These technologies enable efficient traversal, reasoning, and contextual analysis across heterogeneous datasets. When combined with AI, they unlock new potential for enhanced situational awareness, improved prediction, and intelligent optimization. The integration of Large Language Models (LLMs) further enriches this framework by enhancing interpretability, enabling natural language interaction, and supporting knowledge-driven decision processes. Together, AI, graph technologies, GNNs, and LLMs form a powerful foundation for the next generation of intelligent power system applications.
This special issue focuses on innovative methodologies, system designs, and practical deployments that harness these technologies to advance planning, operation, control, and asset management in modern power systems.

Topics (Including but not limited to)  

  • Development of AI, graph computing, GNNs, and LLM methodologies and tools for improving performance, scalability, usability, and confidence in power system applications.
    面向电力系统性能、可扩展性、可信度等关键问题的AI、图计算、GNNs、LLMs方法与工具研究;
  • Applications in power system planning, including spatiotemporal load forecasting, capacity expansion, site selection, and simulation enhancement.
    图技术与AI/GNN/LLM支撑的规划应用,包括时空负荷预测、容量优化、站址选择、仿真增强;
  • Applications in system operation, such as real-time dynamic security assessment, OPF/SCUC/SCED approximation, and accelerated optimization.
    支撑电力系统运行的应用,包括实时动态安全稳定评估、OPF/SCUC/SCED 近似与求解加速;
  • Applications in control and protection involving preventive/corrective control, special protection schemes, fault detection, and alarm processing.
    面向控制与保护的应用,包括预防/校正控制、特防系统、故障检测、告警处理;
  • Applications in asset management including outage management, equipment health assessment, and cybersecurity.
    面向资产管理的应用,包括停电管理、设备健康评估、网络安全;
  • Demonstration projects and practical experience involving integrated graph-AI-GNN-LLM solutions.
    图数据库、知识图谱、AI/GNN/LLM的工程示范与实践经验

Chair: Dr. Yachen Tang, Univers, USA

Dr. Tang received the B.S. degree in telecommunications engineering from Jilin University, Changchun, China, in 2011, and the M.S.E.E. and Ph.D. degrees in electrical and computer engineering from Michigan Technological University, Houghton, MI, USA, in 2014 and 2018, respectively. He was working as Post-Doc Researcher and Research Engineer with GEIRI North America, CA, US and he is currently a Staff Research Engineer with Univers, CA, US. He has published more than 60 SCI/EI journal/conference papers, 1 textbook “Electric Power: Distribution Emergency Operation”, 1 bookchapter “Construction and Application of Spatiotemporal Graph Model for Modern Power Systems”, and more than 20 invention patents. He is IEEE Senior and a member of the Youth Experts Group with Chinese Society for Electrical Engineering. His primary research interests are graph database and graph computing applications in power systems, electricity carbon accounting and analysis, data modeling for heterogeneous and homogeneous data sources, knowledge graph, machine learning, smart grid, and digital image processing.

Co-chair: Dr. Yawei Wei, China Electric Power Research Institute, China

He received the B.S. degree in electrical engineering and automation from the College of Electric Power and Automation Engineering, Shanghai University of Electric Power, Shanghai, China, in 2010; the M.S. degree in electrical and computer engineering from Michigan Technological University, US, in 2014, and the Ph.D. degree in electrical and computer engineering from Clemson University, US, in 2018. From 2019 to 2022, he conducted Post-Doc research at China Electric Power Research Institute (CEPRI). Since 2022, he has been working at the same institute, focusing on online security and stability assessment and intelligent analysis technologies for power systems. He was promoted to Senior Engineer in December 2023. Previously, he worked as a Visiting Scholar at the Pacific Northwest National Laboratory (PNNL), USA, from June to August 2013. He has published more than 35 SCI/EI journal/conference papers, and 20 patents. He has won the 2025 CEEPE Best Presentation Award, and the 2025 ACPEE Conference Best Session Paper. His primary research interests are wavelet analysis, machine learning, smart grid applications in power system stability assessment.

Co-chair: Dr. Shi Liang, Nanjing University of Information Science and Technology, China

Dr. Shi Liang is a Lecturer at the School of Automation, Nanjing University of Information Science and Technology, China. He received his Ph.D. degree from Zhejiang University in 2020. From 2021 to 2022, he worked in the Department of Mechanical Engineering at the University of Hong Kong (HKU) as a Research Associate. Since 2024, he has been serving as an Honorary Assistant Professor at HKU. He is also a Recognised Teacher at the University of Reading, UK. He received the Outstanding Reviewer Award from IET Control Theory & Applications in 2023 and 2024, and was selected as a Jiangsu Province “Double-Innovation Doctor” in 2025. He has served as sub-project lead or key contributor in multiple State Grid of China Science and Technology Programs, including the project “Research on Key Technologies for Grid Dispatch Optimization Solving Based on Graph Deep Learning.” He has published more than 10 SCI journal papers, including articles in IEEE Transactions on Cybernetics and IEEE Transactions on Industrial Electronics. His research focuses on state estimation, secure sensing, and intelligent analysis for high-renewable power grids, with recent interests in graph-based optimization and AI-driven dispatch for modern power systems.

Call for Papers Timeline / 征稿时间

  • Submission of Full Paper: December 30th, 2025
    投稿截止日: 2025年12月30日 

  • Notification Deadline: January 30th, 2026
    通知书发送: 2026年1月30日 

  • Registration Deadline: February 20th, 2026
    注册截止日期: 2026年2月20日