计算机与数字工程2019，Vol.47Issue(3)：689-695,7.DOI:10.3969/j.issn.1672-9722.2019.03.041
基于混合神经网络的电力客户细分研究
Research on Power Customer Segmentation Based on Hybrid Neural Network
摘要
Abstract
With the gradual deepening of China's power market reform,the characteristics of diversified demand in the power market have gradually emerged. Formulating targeted marketing strategies to meet different customers'electricity demand,achieving personalized and differentiated services,improving the core competitiveness of power grid companies,and increasing the share of electric energy in social consumer terminals have become a power company urgent task. In order to formulate electricity customers' power services,power customer segmentation is particularly important. In this paper,the neural network method of H-LSTM(Hy?brid-Long Short-Term Memory)is proposed to subdivide the power customers,and the power customers are classified by the char?acteristics of customers and time. Through experiments on power supply marketing data of major power customers,comparisons are made with decision trees and the original LSTM neural network. The experimental results show that the power customer segmentation method of H-LSTM is more accurate and has practical application value.关键词
LSTM/电力客户细分/循环神经网络/混合神经网络/用电行为Key words
LSTM/power customer segmentation/recurrent neural network/hybrid neural network/power consumption be⁃havior分类
管理科学引用本文复制引用
欧家祥,曹湘,张俊玮,丁超..基于混合神经网络的电力客户细分研究[J].计算机与数字工程,2019,47(3):689-695,7.基金项目
国家自然科学基金"随焊式自适应控制船用厚板焊接变形和抗裂性能的方法和机理研究"(编号:2010BA181B02)资助. （编号:2010BA181B02）
