大数据 ›› 2018, Vol. 4 ›› Issue (1): 105-116.doi: 10.11959/j.issn.2096-0271.2018011

• 专栏:2017年度大数据应用实践Top10 • 上一篇    下一篇

基于关联分析与机器学习的配网台区重过载预测方法

张国宾,王晓蓉,邓春宇   

  1. 中国电力科学研究院,北京 100192
  • 出版日期:2018-01-15 发布日期:2018-02-05
  • 作者简介:张国宾(1988-),男,中国电力科学研究院工程师,主要从事智能电网大数据、配电网规划方面的研究工作。|王晓蓉(1973-),女,博士,中国电力科学研究院教授级高级工程师,主要从事新能源发电规划设计和功率预测、智能电网大数据等方面的研究工作。|邓春宇(1983-),男,博士,中国电力科学研究院高级工程师,主要从事电力信息化建设及电力大数据应用工作。

Prediction method in distribution transformer heavy and overload supply areas with relevance analyze and machine learning

Guobin ZHANG,Xiaorong WANG,Chunyu DENG   

  1. China Electric Power Research Institute,Beijing 100192,China
  • Online:2018-01-15 Published:2018-02-05

摘要:

针对配电网运行中长期存在的台区重过载问题,提出基于关联规则挖掘的重过载影响因素分析方法,从设备和用户属性、自然环境、短期负荷特性中挖掘针对各类重过载事件的关联规则。从关联项中提取重过载影响因素,并基于机器学习模型,建立重过载事件预测模型,实现对重过载事件的短期预测。最后利用业务系统实际数据,对所提方法进行了效果验证。算例结果表明,新方法能够更为系统、全面地刻画重过载事件,提出的重过载预测模型在命中率和准确率方面表现良好。

关键词: 台区重过载, 关联分析, 机器学习

Abstract:

Aiming at the heavy and over load issue in operation of distribution network,a heavy overload forecasting model to achieve short-term forecast of heavy and overload events was established.Using the actual data of the business system,the proposed method was validated.The results show that the proposed method can describe the heavy and overload events more systematically and comprehensively,and the heavy overload forecasting model based on association rules performs well in the hit rate and accuracy rate.This method provides a new technical means that has certain practical value to enhance the distribution network management which could be seen as important experience of attempts in grid big data as well.

Key words: distribution transformer heavy and overload, relevance analyze, machine learning

中图分类号: 

No Suggested Reading articles found!