XGBoost-Based Algorithm Interpretation and Application on Post-Fault Transient Stability Status Prediction of Power System

被引：149

作者：

Chen, Minghua ^{[1
]}

Liu, Qunying ^{[1
]}

Chen, Shuheng ^{[2
]}

Liu, Yicen ^{[1
]}

Zhang, Chang-Hua ^{[2
]}

Liu, Ruihua ^{[3
]}

机构：

[1] Univ Elect Sci & Technol China, Sch Automat Engn, Chengdu 611731, Sichuan, Peoples R China

[2] Univ Elect Sci & Technol China, Sch Mech & Elect Engn, Chengdu 611731, Sichuan, Peoples R China

[3] State Grid Sichuan Elect Power Co, Skills Training Ctr, Chengdu 611133, Sichuan, Peoples R China

来源：

IEEE ACCESS | 2019年 / 7卷

基金：

中国博士后科学基金;

关键词：

Feature importance scores; model interpretation; XGBoost model; transient stability prediction;

D O I：

10.1109/ACCESS.2019.2893448

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

The artificial intelligence (AI) techniques have been widely used in the transient stability analysis of a power system. They are recognized as the most promising approaches for predicting the post-fault transient stability status with the use of phasor measurement units data. However, the popular AI methods used for power systems are often "black boxes," which result in the poor interpretation of the model. In this paper, a transient stability prediction method based on extreme gradient boosting is proposed. In this model, a decision graph and feature importance scores are provided to discover the relationship between the features of the power system and transient stability. Meanwhile, the key features are selected according to the feature importance scores to remove redundant variables. The simulation results on the New England 39-bus system have demonstrated the superiority of the proposed model over the prior methods in the computation speed and prediction accuracy. Finally, an algorithm is proposed to interpret the prediction results for a specific fault of the power system, which further improves the interpretability of the model and makes it attractive for real-time transient stability prediction.

引用

页码：13149 / 13158

页数：10

共 24 条

[11]

Gomez F., 2011, 2011 IEEE Power & Energy Society General Meeting, DOI 10.1109/PES.2011.6038936

[12] Power system transient stability margin estimation using neural networks [J].

Karami, A. .

INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS, 2011, 33 (04) :983-991

[13]

Kundur P., 1994, POWER SYSTEM STABILI, V7

[14] Application of XGBoost Algorithm in Fingerprinting Localisation Task [J].

Luckner, Marcin ;

Topolski, Bartosz ;

Mazurek, Magdalena .

COMPUTER INFORMATION SYSTEMS AND INDUSTRIAL MANAGEMENT (CISIM 2017), 2017, 10244 :661-671

[15] Bioactive Molecule Prediction Using Extreme Gradient Boosting [J].

Mustapha, Ismail Babajide ;

Saeed, Faisal .

MOLECULES, 2016, 21 (08)

[16]

Pannell Z, 2018, 2018 IEEE TEXAS POWER AND ENERGY CONFERENCE (TPEC)

[17] "Why Should I Trust You?" Explaining the Predictions of Any Classifier [J].

Ribeiro, Marco Tulio ;

Singh, Sameer ;

Guestrin, Carlos .

KDD'16: PROCEEDINGS OF THE 22ND ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, 2016, :1135-1144

[18] A parallel transient stability simulation for power systems [J].

Shu, JW ;

Xue, W ;

Zheng, WM .

IEEE TRANSACTIONS ON POWER SYSTEMS, 2005, 20 (04) :1709-1717

[19] AdaBoost classifiers for phasor measurements-based security assessment of power systems [J].

Thirugnanasambandam, Venkatesh ;

Jain, Trapti .

IET GENERATION TRANSMISSION & DISTRIBUTION, 2018, 12 (08) :1747-1755

[20] A boosted decision tree approach using Bayesian hyper-parameter optimization for credit scoring [J].

Xia, Yufei ;

Liu, Chuanzhe ;

Li, YuYing ;

Liu, Nana .

EXPERT SYSTEMS WITH APPLICATIONS, 2017, 78 :225-241

← 1 2 3 →