Open AccessComplaint electricity customer clustering method based on electricity big data
Author(s) -
Biqiang Zhao,
Lü Li,
Jiajia Zhang,
Jingyu Feng,
Lipeng Xia,
Jingye Liu,
Yongxing Yu
Publication year - 2022
Publication title -
iop conference series. earth and environmental science
Language(s) - English
Resource type - Journals
eISSN - 1755-1307
pISSN - 1755-1315
DOI - 10.1088/1755-1315/983/1/012115
Subject(s) - cluster analysis , computer science , convergence (economics) , complaint , data stream clustering , electricity , data mining , canopy clustering algorithm , competition (biology) , dimension (graph theory) , cure data clustering algorithm , correlation clustering , artificial intelligence , engineering , mathematics , ecology , biology , political science , pure mathematics , law , economics , economic growth , electrical engineering
In the fierce domestic market competition, the improvement of service quality is an important goal of electricity companies. This paper proposes the k-means algorithm based on the improved wolf pack algorithm, which is suitable for the power company complains, there are many factors that affect user complaints. Firstly, the PCA method is used to reduce the dimension of the complaint user’s behavior influencing factors, so as to improve the accuracy of clustering. Secondly, due to the shortcomings of falling into local optimal solution and low clustering accuracy, this paper proposes an improved wolf pack algorithm, which proposes the interactive strategy of walking behavior, calling behavior and an adaptive siege strategy for behavior, the clustering accuracy and convergence speed are improved.This algorithm overcomes the shortcomings of the original algorithm. Moreover, it improves the efficiency and clustering quality of the algorithm and it can realize the accurate classification of users.