Physics-Constrained Robustness Enhancement for Tree Ensembles Applied in Smart Grid  

作　　者：Zhibo Yang Xiaohan Huang Bingdong Wang Bin Hu Zhenyong Zhang 

机构地区：[1]State Key Laboratory of Public Big Data,College of Computer Science and Technology,Guizhou University,Guiyang,550025,China

出　　处：《Computers, Materials & Continua》2024年第8期3001-3019,共19页计算机、材料和连续体（英文）

基　　金：This work was supported by Natural Science Foundation of China(Nos.62303126,62362008,62066006,authors Zhenyong Zhang and Bin Hu,https://www.nsfc.gov.cn/,accessed on 25 July 2024);Guizhou Provincial Science and Technology Projects(No.ZK[2022]149,author Zhenyong Zhang,https://kjt.guizhou.gov.cn/,accessed on 25 July 2024);Guizhou Provincial Research Project(Youth)forUniversities(No.[2022]104,author Zhenyong Zhang,https://jyt.guizhou.gov.cn/,accessed on 25 July 2024);GZU Cultivation Project of NSFC(No.[2020]80,author Zhenyong Zhang,https://www.gzu.edu.cn/,accessed on 25 July 2024).

摘　　要：With the widespread use of machine learning(ML)technology,the operational efficiency and responsiveness of power grids have been significantly enhanced,allowing smart grids to achieve high levels of automation and intelligence.However,tree ensemble models commonly used in smart grids are vulnerable to adversarial attacks,making it urgent to enhance their robustness.To address this,we propose a robustness enhancement method that incorporates physical constraints into the node-splitting decisions of tree ensembles.Our algorithm improves robustness by developing a dataset of adversarial examples that comply with physical laws,ensuring training data accurately reflects possible attack scenarios while adhering to physical rules.In our experiments,the proposed method increased robustness against adversarial attacks by 100%when applied to real grid data under physical constraints.These results highlight the advantages of our method in maintaining efficient and secure operation of smart grids under adversarial conditions.

关 键 词：Tree ensemble robustness enhancement adversarial attack smart grid 

分 类 号：TM76[电气工程—电力系统及自动化]