湖南电力 ›› 2025, Vol. 45 ›› Issue (1): 68-72.doi: 10.3969/j.issn.1008-0198.2025.01.010

• 源网协调与能源转换利用 • 上一篇    下一篇

基于K-means聚类算法和BP神经网络的代理购电量预测模型研究

于志诚1, 穆士才2, 梁晔2, 李镓辰2, 林华3, 陈己宸1, 金鑫1   

  1. 1.国网北京朝阳供电公司,北京 100020;
    2.国网北京客服中心,北京 100010;
    3.国网北京市电力公司,北京 100032
  • 收稿日期:2024-10-11 修回日期:2024-11-17 出版日期:2025-02-25 发布日期:2025-03-05
  • 通信作者: 于志诚(1991),男,硕士,工程师,主要从事电力营销工作。

Research on Electricity Prediction Model of Power Purchasing Agent Based on K-means Clustering Algorithm and BP Neural Network

YU Zhicheng1, MU Shicai2, LIANG Ye2, LI Jiachen2, LIN Hua3, CHEN Jichen1, JIN Xin1   

  1. 1. State Grid Beijing Chaoyang Power Supply Company, Beijing 100020, China;
    2. State Grid Beijing Customer Service Center, Beijing 100010, China;
    3. State Grid Beijing Electric Power Company, Beijing 100032, China
  • Received:2024-10-11 Revised:2024-11-17 Online:2025-02-25 Published:2025-03-05

摘要: 通过对某地区代理购电用户的深入画像分析,研究不同因素对代理购电用户电量的影响;通过聚类算法实现用户群体的分类;通过神经网络算法将纵向时序电量和横向影响因素纳入预测公式,针对不同聚类簇构建符合其特征的预测模型;最后将模型整合,实现对整体电量的高准确率预测。

关键词: 代理购电, 电量预测, 聚类算法, 神经网络, 画像分析

Abstract: Through the in-depth portrait analysis of power purchasing agents in a certain region, the influence of different factors on the power consumption of power purchasing agents is studied, and the classification of user groups is realized through the clustering algorithm. Through the neural network algorithm, the longitudinal time series electricity and horizontal influencing factors are incorporated into the prediction formula, and the prediction models conforming to the characteristics of different clusters are constructed. Finally, the models are integrated to achieve high accuracy prediction of the overall electricity.

Key words: power purchasing agent, electricity prediction, clustering algorithm, neural network, portrait analysis

中图分类号: