基于LSTM算法的配电网线损计算  

Line Loss Calculation of Distribution Network Based on LSTM Algorithm

作　　者：王娅双 WANG Ya-shuang(State Grid Hubei Jingmen Power Supply Company,Jingmen 448000,China)

机构地区：[1]国网湖北省电力有限公司荆门供电公司,湖北荆门448000

出　　处：《电气开关》2022年第1期35-37,共3页Electric Switchgear

摘　　要：配电网的线损是电力企业的重要考核标准之一,对配电网的规划和设计具有重要作用,因此运用合适的算法对配电网的线损进行精确预测受到了广泛关注。为此,本文首先概述了配电网线损的概念及组成,并分析了长短期记忆网络算法计算线损的原理,最后分别采用长短期记忆网络法和随机森林法对线损进行了计算,验证了长短期记忆网络算法的优越性,为后续配电网线损研究提供了理论依据。The line loss of distribution network is one of the important assessment standards of power enterprises,which plays an important role in the planning and design of distribution network.Therefore,the accurate calculation of line loss of distribution network by using appropriate algorithms has attracted extensive attention.Therefore,this paper first summarizes the concept and composition of distribution network line loss,and analyzes the principle of long-term and short-term memory network method to calculate line loss.Finally,the long-term and short-term memory network method and random forest method are used to calculate line loss respectively,which verifies the superiority of long-term and short-term memory network algorithm,and provides a theoretical basis for the follow-up research of distribution network line loss.

关 键 词：神经网络 配电网 线损 

分 类 号：TM72[电气工程—电力系统及自动化]