《计算机应用》唯一官方网站 ›› 2022, Vol. 42 ›› Issue (3): 904-910.DOI: 10.11772/j.issn.1001-9081.2021030447

• 数据科学与技术 • 上一篇    

基于金融技术指标的用电数据分析

杨安1, 蒋群2, 孙钢2, 殷杰3, 刘英1()   

  1. 1.浙江大学 信息与电子工程学院,杭州 310027
    2.国网浙江省电力有限公司 营销服务中心,杭州 311121
    3.浙江华云信息科技有限公司,杭州 310012
  • 收稿日期:2021-03-23 修回日期:2021-07-06 接受日期:2021-07-07 发布日期:2022-04-09 出版日期:2022-03-10
  • 通讯作者: 刘英
  • 作者简介:杨安(1998—),男,山东聊城人,博士研究生,主要研究方向:数据挖掘、迁移学习
    蒋群(1989—),女,浙江杭州人,工程师,硕士,主要研究方向:电能计量、用电信息采集、电力营销服务
    孙钢(1987—),男,浙江余杭人,高级工程师,硕士,主要研究方向:营销计量
    殷杰(1982—),男,浙江海宁人,高级工程师, 主要研究方向:用电信息采集、数据分析;

Power data analysis based on financial technical indicators

An YANG1, Qun JIANG2, Gang SUN2, Jie YIN3, Ying LIU1()   

  1. 1.College of Information Science & Electronic Engineering,Zhejiang University,Hangzhou Zhejiang 310027,China
    2.Marketing Service Center,State Grid Zhejiang Electric Power Company Limited,Hangzhou Zhejiang 311121,China
    3.Zhejiang Huayun Information Technology Company Limited,Hangzhou Zhejiang 310012,China
  • Received:2021-03-23 Revised:2021-07-06 Accepted:2021-07-07 Online:2022-04-09 Published:2022-03-10
  • Contact: Ying LIU
  • About author:YANG An, born in 1998, Ph. D. candidate. His research interests include data mining, transfer learning.
    JIANG Qun, born in 1989, M. S., engineer. Her research interests include electric energy measurement, power information acquisition, power marketing service.
    SUN Gang, born in 1987, M. S., senior engineer. His research interests include marketing measurement.
    YIN Jie, born in 1982, senior engineer. His research interests include power information acquisition, data analysis.

摘要:

针对已有用电数据分析缺乏有效描述趋势性特征的不足,适应性地将金融领域中十字过滤线(VHF)、异同移动平均线(MACD)等技术指标迁移至用电数据分析中,提出了基于金融技术指标的异动检测算法和负荷预测算法。所提异动检测算法通过统计各指标的统计情况划定阈值,并采用阈值检测捕捉用户异常用电行为。所提负荷预测算法通过提取14项与金融技术指标相关的日负荷特征,构建了长短期记忆网络(LSTM)负荷预测模型。在杭州市工业用电数据上的实验结果表明,所提负荷预测算法将平均绝对百分比误差(MAPE)降低至9.272%,相较于差分整合移动平均自回归(ARIMA)算法、Prophet算法和支持向量机(SVM)算法,分别将MAPE降低了2.322、24.175和1.310个百分点,能够较好地应用于用电数据分析中。

关键词: 用电数据分析, 智能电网, 金融技术指标, 异动检测, 负荷预测, 长短期记忆网络

Abstract:

Considering the lack of effective trend feature descriptors in existing methods, financial technical indicators such as Vertical Horizontal Filter (VHF) and Moving Average Convergence/Divergence (MACD) were introduced into power data analysis. An anomaly detection algorithm and a load forecasting algorithm using financial technical indicators were proposed. In the proposed anomaly detection algorithm, the thresholds of various financial technical indicators were determined based on statistics, and then the abnormal behaviors of user power consumption were detected using threshold detection. In the proposed load forecasting algorithm, 14 dimensional daily load characteristics related to financial technical indicators were extracted, and a Long Shot-Term Memory (LSTM) load forecasting model was built. Experimental results on industrial power data of Hangzhou City show that the proposed load forecasting algorithm reduces the Mean Absolute Percentage Error (MAPE) to 9.272%, which is lower than that of Autoregressive Integrated Moving Average (ARIMA), Prophet and Support Vector Machine (SVM) algorithms by 2.322, 24.175 and 1.310 percentage points, respectively. The results show that financial technical indicators can be effectively applied to power data analysis.

Key words: power data analysis, smart grid, financial technical indicator, anomaly detection, load forecasting, Long Short-Term Memory (LSTM) network

中图分类号: