Review and Prospect of Explainable Artificial Intelligence and Its Application in Power Systems

被引：0
作者：
Wang X. [1 ]
Dou J. [1 ]
Liu Z. [1 ]
Liu C. [1 ]
Pu T. [2 ]
He J. [1 ]
机构：
[1] School of Electrical Engineering, Beijing Jiaotong University, Beijing
[2] China Electric Power Research Institute, Beijing
来源：
Dianli Xitong Zidonghua/Automation of Electric Power Systems | 2024年 / 48卷 / 04期
基金：
中国国家自然科学基金;
关键词：
artificial intelligence; explainability; machine learning; power system;
D O I：
10.7500/AEPS20230509007
中图分类号：
学科分类号：
摘要：
Explainable artificial intelligence (XAI), as a new type of artificial intelligence (AI) technologies, can present the logic of the AI process, reveal the AI black-box knowledge, and improve the credibility of the AI results. The deep coupling between XAI and power systems may accelerate the AI technology application in the power system and assist with the safety and stability of human-machine interaction. Therefore, this paper reviews the historical context, development needs, and hot technologies of XAI in the power system, summarizes its applications in source-load forecasting, operation control, fault diagnosis, and electricity market, and explores the application prospects of XAI in the power system around aspects such as interpretability, iterative framework, and number-matrix fusion. This paper aims to provide theoretical references and practical ideas for promoting the intelligent transformation and iterative human-machine interaction of the power system. © 2024 Automation of Electric Power Systems Press. All rights reserved.
引用
收藏
页码：169 / 191
页数：22
相关论文
共 147 条
[1]  
HAN Xiao, GUO Jianbo, PU Tianjiao, Et al., Theoretical foundation and directions of electric power artificial intelligence （ Ⅰ ） ： hypothesis analysis and application paradigm ［J］, Proceedings of the CSEE, 43, 8, pp. 2877-2891, (2023)
[2]  
GUO Jianbo, Insights into the evolutionary trends and relationships of new power systems, 2022 Annual Meeting of the Chinese Society for Electrical Engineering
[3]  
XAI—explainable artificial intelligence［J］, Science Robotics, 4, 37, (2019)
[4]  
Notice on the publication of the 2023 project guidelines of the major research program on interpretable and generalizable next-generation artificial intelligence methods［EB/OL］
[5]  
MILLER T., Explanation in artificial intelligence：insights from the social sciences［J］, Artificial Intelligence, 267, pp. 1-38, (2019)
[6]  
MULLER K R., Methods for interpreting and understanding deep neural networks［J］, Digital Signal Processing, 73, pp. 1-15, (2018)
[7]  
CARDOSO J S., Machine learning interpretability：a survey on methods and metrics［J］, Electronics, 8, 8, (2019)
[8]  
GUAN C T., A survey on explainable artificial intelligence（XAI）：toward medical XAI［J］, IEEE Transactions on Neural Networks and Learning Systems, 32, 11, pp. 4793-4813, (2021)
[9]  
GUO W S., Explainable artificial intelligence for 6G：improving trust between human and machine［J］, IEEE Communications Magazine, 58, 6, pp. 39-45, (2020)
[10]  
PU Tianjiao, QIAO Ji, ZHAO Zixuan, Et al., Research on interpretable methods of machine learning applied in intelligent analysis of power system （part Ⅰ ） ： basic concept and framework［J］, Proceedings of the CSEE, 43, 18, pp. 7010-7030
12345678910