基于粒子群优化神经网络算法的用户防窃电研究  

Research on User's Anti Stealing Power Based on Particle Swarm Optimization Neural Network Algorithm

作　　者：任关友 王昕 李英娜[1] 李川[1] REN Guan-you;WANG Xin;LI Ying-na;LI Chuan(Automation in Kunming University of Science and Technology, Kunming 650000, Yunnan, China;Electric Power Research Institute Yunnan Power Grid Limited Liability Corporation, Kunming 650000, Yunnan, China;Key Laboratory of Energy Metering of Southern Power Grid, Kunming 650217, Yunnan Province, China)

机构地区：[1]昆明理工大学信息工程与自动化学院,云南昆明650000 [2]云南电网有限责任公司电力科学研究院,云南昆明650000 [3]中国南方电网公司电能计量重点实验室,云南昆明650217

出　　处：《软件》2017年第8期215-219,共5页Software

摘　　要：电能的准确计量是电力企业生产经营管理及电网经济稳定运行的重要环节,计量准确性及质量可靠性直接影响用户的经济利益和社会能源利用率。如何准确分辨因用户行为导致的计量异常是一个有待解决的技术难题。近年来,因智能电能表的推广及用电信息采集系统建设的全面完善,电网公司积累了海量用户用电数据,基于此,本文提出一种基于粒子群优化的神经网络算法对用户用电行为进行检测,实验表明该方法具有较高的可行性和可靠性,可以进行推广。Accurate measurement of electric energy is an important part of the production and management of power enterprises and the stable operation of the power grid.The accuracy and quality of the measurement directly affect the economic benefits and social energy utilization of the users.How to accurately distinguish abnormal measurements caused by user behavior is a difficult technical problem to be solved.In recent years,because of the intelligent electrical energy table promotion and construction of electric information acquisition system of the comprehensive improvement of Power Grid Corp accumulated a massive user consumption data,based on this,this paper proposes a neural network algorithm based on Particle Swarm Optimization of electricity users behavior detection,Experimental results show the feasibility and reliability of this method is high and can be popularized.

关 键 词：防窃电 数据挖掘 粒子群算法 神经网络 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]