Understanding Discrepancy of Power System Dynamic Security Assessment with Unknown Faults: A Reliable Transfer Learning-based Method

作     者：Chao Ren Han Yu Yan Xu Zhao Yang Dong 

作者机构：School of Computer Science and EngineeringNanyang Technological UniversitySingapore School of Electrical and Electronic EngineeringNanyang Technological UniversitySingapore 

出 版 物：《CSEE Journal of Power and Energy Systems》 (中国电机工程学会电力与能源系统学报（英文）)

年 卷 期：2024年第10卷第1期

页      面：427-431页

核心收录：

学科分类：080802[工学-电力系统及其自动化] 0808[工学-电气工程] 08[工学] 

基　　金：supported by the Internal Talent Award(TRACS)with Wallenberg-NTU Presidential Postdoctoral Fellowship 2022 the National Research Foundation,Singapore and DSO National Laboratories under the AI Singapore Program(AISG Award No:AISG2-RP-2020-019) the RIE 2020 Advanced Manufacturing and Engineering(AME)Programmatic Fund(No.A20G8b0102),Singapore Future Communications Research&Development Program(FCP-NTU-RG-2021-014) 

主　　题：Adversarial training dynamic security assessment maximum classifier discrepancy missing data transfer learning 

摘      要：This letter proposes a reliable transfer learning(RTL)method for pre-fault dynamic security assessment(DSA)in power systems to improve DSA performance in the presence of potentially related unknown *** takes individual discrepancies into consideration and can handle unknown faults with incomplete *** experiment results demonstrate high DSA accuracy and computational efficiency of the proposed RTL *** analysis shows RTL can guarantee system performance.