中国电力 ›› 2021, Vol. 54 ›› Issue (8): 98-102.DOI: 10.11930/j.issn.1004-9649.202101015

• 电网 • 上一篇    下一篇

基于配网新形态下电费风险模型构建与应用

戴璐平1, 瞿青1, 黄露1, 潘晔2   

  1. 1. 国网上海市电力公司,上海 200120;
    2. 上海欣能信息科技发展有限公司,上海 200025
  • 收稿日期:2021-01-05 修回日期:2021-05-17 发布日期:2021-08-05
  • 作者简介:戴璐平(1977-),男,高级经济师,从事电力营销业务客户服务及电费管理研究,E-mail:dailp@sh.sgcc.com.cn;瞿青(1979-),女,经济师,从事电力营销业务客户服务及电费管理研究,E-mail:quqing@sh.sgcc.com.cn;黄露(1981-),女,高级营销师,从事电力营销业务电费及电价管理研究,E-mail:huanglu@sh.sgcc.com.cn;潘晔(1981-),男,通信作者,工程师,从事电力信息化建设及大数据应用研究,E-mail:8145962@qq.com
  • 基金资助:
    上海张江国家自主创新示范区专项发展资金重大项目(市北区块链生态谷创新能力建设及重大行业应用示范,ZJ2020-ZD-003)

Modelling and Application of Electricity Marketing Tariff Risk Prediction Driven by New Forms of Distribution Networks

DAI Luping1, QU Qing1, HUANG Lu1, PAN Ye2   

  1. 1. State Grid Shanghai Municipal Electric Power Company, Shanghai 200120, China;
    2. Shanghai Shineenergy Information Technology Development Co.,Ltd., Shanghai 200025, China
  • Received:2021-01-05 Revised:2021-05-17 Published:2021-08-05
  • Supported by:
    This work is supported by Shanghai Zhangjiang National Independent Innovation Demonstration Zone Special Development Fund Major Projects (Innovation Capability Construction and Major Industry Application Demonstration of Shibei Block Chain Ecological Valley, No.ZJ2020-ZD-003)

摘要: 随着大数据时代来临,在电力企业数字化转型的过程中,配电网工作从简单满足基本负荷需求,向为客户提供个性化方案的市场化转变,给配电网及电力营销业务融合提出了更高要求。电费管理成为营销优质服务的主要考核指标。通过大数据手段,结合各网省的业务特性,构建具有一定通用性的电费风险预测模型,助力营销市场的标准化、精益化建设,实现电费风险防控、降本增效。

关键词: 配电网, 数字化转型, 电费回收风险, 机器学习

Abstract: In the era of big data, digital transformation is being carried out for electric power companies. The role of distribution network would shift from satisfying basic load requirements to providing customers with personalized solutions, proposing high requirements for electricity marketing services. Electricity fee management has long become the main evaluation indicator for marketing quality services. The goal of this work is to build a universal model of tariff risk prediction based on big data techs and provincial features. In this regard, the risk of tariff and the operation costs would be controlled.

Key words: distribution network, digital transformation, risk of electricity charge recovery, machine learning