English: This track focuses on the cutting-edge developments in data-driven modeling, dynamic analysis, and intelligent control techniques for inverter-dominated power systems. With the large-scale integration of PV, wind power, energy storage, VSC-HVDC, and EV charging facilities, power systems are transitioning from traditional synchronous generator dominance to high-penetration power electronic equipment dominance. The system features of low inertia, weak support, strong coupling, and multi-time-scale dynamics are becoming increasingly prominent. Data-driven and intelligent methods have become critical for enhancing system stability, operational resilience, and renewable energy hosting capacity. The track covers electromagnetic transient modeling, dynamic equivalence, parameter identification, impedance modeling, and stability analysis. It explores the deep fusion of mechanism models with data-driven methods such as Koopman operators, Physics-Informed Neural Networks (PINNs), Graph Neural Networks (GNNs), Neural Operators, and time-series foundation models. Special focus is placed on wide-band oscillation, grid-forming and grid-following inverter coordination, oscillation source localization, and risk warning. Intelligent control techniques—including MPC, Reinforcement Learning, adaptive control, and distributed coordination—as well as digital twin and hardware-in-the-loop simulations are highlighted to reshape the modeling, monitoring, and operation of inverter-dominated power systems.

中文: 本专题聚焦于逆变器主导电力系统的数据驱动建模、动态分析与智能控制技术的前沿发展。随着光伏、风电、储能、柔性直流及电动汽车充换电设施的大规模接入，电力系统正由传统同步机主导逐步转向高比例电力电子装备主导。系统低惯量、弱支撑、强耦合和多时间尺度动态特征日益突出，数据驱动建模与智能分析控制方法已成为提升系统稳定性、运行韧性和新能源消纳能力的重要技术途径。 专题重点涵盖逆变器主导电力系统的电磁暂态建模、动态等值、参数辨识、阻抗建模以及稳定性分析等方向。近年来，Koopman 算子、物理信息神经网络、图神经网络、神经算子、时序基础模型等数据驱动方法正不断与电力系统机理模型深度融合。专题特别关注高比例新能源和多逆变器并联系统中的宽频振荡、弱电网并网稳定性、构网型与跟网型逆变器协同、振荡源定位以及运行风险预警等关键问题。智能控制方面，涵盖构网型控制、模型预测控制、强化学习控制、自适应控制、分布式协同控制、数字孪生、硬件在环仿真及智能优化方法，旨在提升其在复杂电网环境下的安全性、稳定性和韧性。