电力系统及其自动化学报2019，Vol.31Issue(3)：146-150,5.DOI:10.19635/j.cnki.csu-epsa.000022
基于多表融合数据的用户短期用电量预测
Short-term Electricity Consumption Forecasting Based on Multi-meter Data Fusion
郑国和 1贺民 1郑瑞云 2童建东 3刘英 4韩威5
作者信息
- 1. 国网浙江省电力有限公司宁波供电公司,宁波 315000
- 2. 国网浙江省电力有限公司宁波供电公司江北分公司,宁波 315000
- 3. 国网浙江省电力有限公司宁波市鄞州区供电有限公司,宁波 315100
- 4. 浙江大学信息与电子工程学院,杭州 310027
- 5. 浙江华云信息科技有限公司,杭州 310012
- 折叠
摘要
Abstract
Electricity consumption forecasting is one of the most important research topics in the user energy consump?tion analysis,and the improvement of forecasting accuracy is of great significance to both the user energy consumption analysis and abnormal detection. Based on the data collected by electricity,water and gas meters in an electricity con?sumption information acquisition system,a short-term electricity consumption forecasting method based on support vec?tor machine(SVM)is proposed. First,path analysis is used to calculate the weights of daily features that affect the user’ s electricity consumption quantity,as well as the corresponding fuzzy similar matrix. Then,similar days are selected by fuzzy clustering and transitive closure algorithm,and they are further used as samples to train the SVM model,thus real?izing the forecasting of electricity consumption. Finally,the multi-meter fusion data collected from Hangzhou City in 2016 are used to test the performance of the proposed method. Experimental results show that compared with the single-meter forecasting method,the forecasting method based on multi-meter fusion data can reduce the relative forecasting errors of single-and multi-user electricity consumption in one certain community by more than 6% and more than 1%,respectively.关键词
多表融合数据/用电量/短期预测/支持向量机/相似日Key words
multi-meter fusion data/electricity consumption/short-term forecasting/support vector machine(SVM)/similar days分类
信息技术与安全科学引用本文复制引用
郑国和,贺民,郑瑞云,童建东,刘英,韩威..基于多表融合数据的用户短期用电量预测[J].电力系统及其自动化学报,2019,31(3):146-150,5.
