Vice Chair 1 : Zongsheng Zheng, Sichuan University, China

Vice Chair 2 : Shilin Gao, Sichuan University, China

Description of the Session:
In the context of the “Dual Carbon” goals and the development of new-type power systems, the widespread integration of large-scale power electronic equipment, a high proportion of renewable energy, and diverse types of loads has endowed the power system with new characteristics, such as strong coupling, weak damping, low inertia, and significant uncertainty. Traditional stability analysis and control methods, which rely on analytical models and hierarchical control frameworks, face challenges including high modeling complexity, time-varying parameters, and significant multi-timescale coupling. This special issue focuses on “AI-Enabled Stability Mechanism Analysis and Adaptive Control Technologies for New-Type Power Systems”, concentrating on the mechanistic reconstruction and control paradigm shift for power system stability under conditions of high power electronics penetration. It explores new theories and methods that integrate data-driven approaches with physical models. The aim is to establish an interdisciplinary platform connecting power system stability analysis, artificial intelligence algorithms, and engineering applications, thereby promoting the development of an intelligent stability control system with real-time sensing, autonomous decision-making, and adaptive control capabilities. This effort seeks to provide technical support for the secure, resilient, and efficient operation of future power grids.

Related Topics:
· Analysis of multi-timescale stability mechanisms and dynamic coupling characteristics in power systems with high power electronic devices penetration
· Unified modeling and criterion construction methods for frequency, voltage, and rotor angle coupling stability issues
· Application of physics-constrained machine learning and mechanism-integrated modeling in stability analysis
· Data-driven methods for small-signal stability assessment and fast transient stability discrimination techniques
· Online inertia estimation and damping characteristic identification methods under high uncertainty scenarios
· Reinforcement learning and adaptive control strategies for coordinated regulation of source-grid-load-storage systems
· Intelligent identification and mitigation techniques for wide-frequency oscillations and sub-synchronous oscillations
· Stability situation awareness, risk prediction, and decision support systems for large-scale power grids
· Multi-agent collaborative control and distributed stability assurance mechanisms
· Application of digital twin and real-time simulation technologies in the validation of stability control strategies

Description of the Session:
With the rapid development of new-type power systems, large-scale renewable energy integration, power-electronic-interfaced equipment, energy storage, flexible loads, and integrated energy systems are significantly reshaping power system operation. While these changes improve flexibility and sustainability, they also make power quality issues more complex and dynamic. Voltage deviations, voltage sags, flicker, harmonics, three-phase imbalance, and frequency stability problems are increasingly coupled across multiple time scales, operating conditions, and physical domains. Conventional power quality analysis and mitigation methods are facing growing challenges in this evolving environment, including insufficient real-time responsiveness, limited adaptability to highly uncertain operating conditions, inadequate utilization of multi-source heterogeneous data, and restricted capability for coordinated analysis and decision support. In recent years, artificial intelligence technologies have developed rapidly and are becoming an important enabler for power quality monitoring, analysis, diagnosis, assessment, and mitigation in new-type power systems. In particular, machine learning, knowledge-guided intelligence, large models, and intelligent agents provide new opportunities for disturbance identification, source tracing, state perception, risk assessment, and coordinated control. This special session aims to bring together researchers and engineers from academia and industry to discuss recent advances in AI-enabled power quality analysis and mitigation for new-type power systems. Topics of interest include intelligent sensing, data-driven and physics-informed modeling, harmonic and voltage disturbance analysis, three-phase imbalance mitigation, integrated energy system power quality, large-model applications, and AI-assisted coordinated optimization and decision-making. The session seeks to promote the development of accurate, adaptive, explainable, and practical solutions for future power systems.

Related Topics:
1.Voltage sag perception, early warning, location, and mitigation technologies;
2.Transient characteristic analysis of AC/DC power grids under voltage sag conditions;
3.Harmonic responsibility allocation and tracing;
4.Harmonic power flow algorithms considering distributed generation;
5.Generation, propagation characteristics, and impacts of ultra-high harmonics;
6.Harmonic monitoring and analysis in new power systems;
7.Harmonic characteristics of AC/DC hybrid power systems;
8.Frequency stability assessment of high-penetration renewable energy power systems;
9.Harmonic source and load identification;
10.Three-phase imbalance analysis and mitigation;
11.Power quality data analytics and applications;
12.Power quality issues in integrated energy systems;
13.Modeling of power quality disturbance sources;
14.Optimization and management of power quality problems in new power systems;
15.Three-phase unbalanced power flow analysis;
16.Power quality analysis and economic assessment;
17.Multi-energy flow coordinated optimization for power quality management;
18.Power quality characteristics of hydrogen energy storage grid integration;
19.Electricity-carbon-market-driven optimization for power quality management;
20.Large-model and AI-enabled power quality perception, diagnosis, and decision support;
21.Domain-specific foundation models and intelligent agents for power systems;
22.Multi-modal data fusion and knowledge-enhanced power quality analysis;
23.Data-driven and physics-informed hybrid methods for power quality assessment;
24.Explainable AI and trustworthy intelligent applications for power quality governance.