电力系统自动化2025，Vol.49Issue(10)：20-28,9.DOI:10.7500/AEPS20240723007
基于网络能量轨迹特征学习的新能源电力系统暂态稳定评估
Transient Stability Assessment of Power System with Renewable Energy Based on Network Energy Trajectory Feature Learning
摘要
Abstract
Rapid and accurate transient stability assessment is the key to ensure the safe and stable operation of power system.The high proportion of power electronic equipment connected to the power grid leads to the non-smooth system characteristics of multi-control switching after the power system is disturbed,which brings challenges to the accuracy and generalization of the existing transient stability discrimination methods.A transient stability assessment method based on network energy trajectory feature learning is proposed for the grid-connected power systems with renewable energy and DC transmission.First,the transient energy function of power system with renewable energy based on augmented network data is constructed,the mapping relationship between the spatio-temporal distribution characteristics of network energy and transient stability is studied,and the branch vulnerability index and stability discrimination index are proposed.Then,attention weights are guided by branch vulnerability index to enhance key branch features.Using stability assessment function based on network energy and branch phase angle difference as input features,a transient stability assessment model of power system with renewable energy is proposed.Finally,through simulation analysis of New England 10-machine 39-bus system and CEPRI-TAS practical system with 197 buses,the impact of power electronic equipment switching control on stability discrimination methods is analyzed,and the accuracy and effectiveness of the proposed model are verified.关键词
网络能量/特征学习/暂态稳定/新能源电力系统Key words
network energy/feature learning/transient stability/power system with renewable energy引用本文复制引用
张宇驰,蔡国伟,刘铖,张泽栋,王盈月,杨晶莹..基于网络能量轨迹特征学习的新能源电力系统暂态稳定评估[J].电力系统自动化,2025,49(10):20-28,9.基金项目
国家自然科学基金面上项目(52377082) （52377082）
国家重点研发计划资助项目(2021YFB2400800). This work is supported by National Natural Science Foundation of China(No.52377082)and National Key R&D Program of China(No.2021YFB2400800). （2021YFB2400800）
