Research Article
Correlation Analysis of Production and Operation Indicators of Power Grid Enterprises Based on XGBoost Model
@INPROCEEDINGS{10.4108/eai.19-5-2023.2334366, author={Liyu Xia and Yuheng Sha and Zhuo Song and Hong Liu and Wan He}, title={Correlation Analysis of Production and Operation Indicators of Power Grid Enterprises Based on XGBoost Model}, proceedings={Proceedings of the 2nd International Conference on Bigdata Blockchain and Economy Management, ICBBEM 2023, May 19--21, 2023, Hangzhou, China}, publisher={EAI}, proceedings_a={ICBBEM}, year={2023}, month={7}, keywords={correlation analysis production and operation indicator management}, doi={10.4108/eai.19-5-2023.2334366} }- Liyu Xia
Yuheng Sha
Zhuo Song
Hong Liu
Wan He
Year: 2023
Correlation Analysis of Production and Operation Indicators of Power Grid Enterprises Based on XGBoost Model
ICBBEM
EAI
DOI: 10.4108/eai.19-5-2023.2334366
Abstract
It is of great significance to establish a set of key indicators for production and operation of power grid enterprises, clarify the relationship between production indicators and operation indicators, and provide technical methods for analyzing the overall changes in production and operation caused by abnormal changes in a certain indicator of power grid enterprises. This paper combs the key indicators of production and operation of power grid enterprises and forms a set of key indicators of production and operation. Based on the variable importance judgment method of XGBoost model, judge the strength of the correlation relationship between indicators, and form a network diagram of the correlation relationship between indicators. The research shows that there is a linkage relationship between production indicators and operation indicators of power grid enterprises. Basic indicators mainly affect the power supply or sales of power grid enterprises, and less affect production or operation indicators. Power grid enterprises can better predict and manage production and operation activities according to the relationship between key indicators.
