基于行业用电模式的企业电费逾期风险预测  

Research on risk screening model for tariff recovery of high voltage power customers by integrating social data

作　　者：江明 邹云峰 徐超 倪巍伟[3] JIANG Ming;ZOU Yunfeng;XU Chao;NI Weiwei(State Grid Jiangsu Electric Power Co.,Ltd.,Nanjing 210024,China;Electric Power Research Institute,State Grid Jiangsu Electric Power Co.,Ltd.,Nanjing 210019,China;Southeast University,Nanjing 210096,China)

机构地区：[1]国网江苏省电力有限公司,南京210024 [2]国网江苏省电力有限公司电力科学研究院,南京210019 [3]东南大学,南京210096

出　　处：《电力需求侧管理》2019年第5期79-83,共5页Power Demand Side Management

基　　金：国家自然科学基金项目(61772131)~~

摘　　要：我国经济进入新常态,传统产业面临诸多挑战,企业客户电费回收风险不断加大,对企业用电逾期风险进行预测,最大限度地减小影响公司经营的被动风险变得日益迫切。目前电费回收逾期风险管控手段主要依靠企业历史欠费情况进行风险判断,缺乏对用户用电量趋势及缴费历史的深入挖掘,导致企业逾期风险判断准确性与及时性存在不足。针对上述问题,基于企业历史用电与逾期数据记录,聚焦行业用电典型模式挖掘,提出基于聚类的行业典型用电模式库构建方法。在此基础上,采用k近邻的思想,定义模式距离度量函数,引入风险等级概念,提出一种基于行业用电模式的企业电费逾期风险预测模型PEORPM,实现具有自演化能力的企业偏离度4级逾期风险等级标注以及风险预测。理论分析和实验结果验证了所提方法的有效性。China’s economy has entered a new normal,sup?ply?side reform and the battle for environmental protection have continued to advance,international trade unilateralism has risen,traditional industries are facing many challenges,and the risk of electricity tariff recovery for enterprise customers is increasing.Therefore,predicting the overdue risk of power consumption of en?terprises and minimizing the impact on the company's operations are becoming more and more urgent.At present,overdue risk man?agement and control methods can only rely on the historical arrears of enterprises to conduct risk judgments,and lack of deep explora?tion of user power consumption trends and payment historyleads to the lack of accuracy and timeliness of enterprise overdue risk judg?ment.To solve the above problems,from the single perspective of enterprise electricity data,based on DBSCAN clustering algorithm,constructing the typical electricity consumption mode of the indus?try,and adopting the idea of k?nearest neighbor,defining the pat?tern distance measurement function,introducing the concept of risk level,and proposing a power?pattern based electricity overdue risk prediction model for enterprises to realize the self?evolving electrical deviation based on overdue risk level with degree 4 and risk prediction.Theoretical analysis and experimental results veri?fy the effectiveness of the proposed method.

关 键 词：DBSCAN 用电模式 风险预测 等级标注 

分 类 号：TM715[电气工程—电力系统及自动化] F407.61[经济管理—产业经济]