基于电量指纹的电网线损智能治理研究与应用  

RESEARCH AND APPLICATION ON INTELLIGENT MANAGEMENT OF LINE LOSS BASED ON ELECTRICITY FINGERPRINT

作　　者：吴仲超 孙航 朱明星 李莉莉 孙智慧 张敬周 仰继连 Wu Zhongchao;Sun Hang;Zhu Mingxing;Li Lili;Sun Zhihui;Zhang Jingzhou;Yang Jilian(State Grid Bengbu Power Supply Company,Bengbu 233090,Anhui,China;Shanghai Shangke ICT Engineering Research Institute,Shanghai 201206,China)

机构地区：[1]国网安徽省电力有限公司蚌埠供电公司,安徽蚌埠233090 [2]上海上科信息通信工程研究院,上海201206

出　　处：《计算机应用与软件》2024年第10期110-115,154,共7页Computer Applications and Software

摘　　要：线损治理是电力供给链的关键目标之一,也是促进提质增效,提升电网经济效益的基础。电网线路、台区和用户等所形成的用电特性、正常线损特性等具有各自的电量属性特征,像人类的指纹一样综合反映了各自不同的用电特征和线损特征。基于用电信息采集系统收集的用户数据和每日更新的气象温度数据,提出一种基于固定窗向量自回归温度模型的电量指纹滚动预测和诊断方法,智能分析线路和台区的线损异常,提升国家电网精准化管理水平。最后通过实验验证所提方法模型的可行性和有效性。Line loss management is one of the key goals of the power supply chain,and it is also the basis for promoting quality and efficiency improvements,enhancing the economic efficiency of the power grid.The power consumption characteristics and normal line loss characteristics formed by power grid lines,stations and users have their own power attribute characteristics,which comprehensively reflects their different power consumption characteristics and line loss characteristics like a human fingerprint.Based on the massive user data collected by the electricity consumption information collection system and the daily updated meteorological temperature data,a power fingerprint rolling prediction and diagnosis model based on a fixed window vector autoregressive temperature model is proposed,which intelligently analyzes the abnormal probability of lines and stations,and improves the precise management level of the State Grid.Experiments verify the feasibility and effectiveness of the proposed method.

关 键 词：电量指纹 向量自回归(VAR) 滚动预测 线损治理 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]