基于双向LSTM的用户用电行为识别

谢禄江; 段立; 谭刚; 蒋荣; 钟淘淘; 刘美川; 雷洋; 廖军

Chinese

您当前的位置：

首页 >

文章列表页 >

基于双向LSTM的用户用电行为识别

更新时间：2026-09-04

- 基于双向LSTM的用户用电行为识别
- Electrical behavior recognition based on bidirectional LSTM
- 微电子学与计算机 2021年38卷第5期页码：36-41
- 作者机构：
  
  1. 国网重庆市电力公司信息通信分公司,重庆,400010
  2. 重庆智网科技有限公司信息通信分公司,重庆,400000
  3. 重庆大学大数据与软件学院,重庆,401331
- 作者简介：
- 基金信息：
  
  国家重点研发计划 2017YFB1401702重庆市人工智能技术创新重大主题专项课题 cstc2017rgzn-zdyf0051国家自然科学基金面上项目 61977012
- DOI：
  中图分类号：
- 纸质出版：2021
- 稿件说明：
移动端阅览
谢禄江, 段立, 谭刚, 蒋荣, 钟淘淘, 刘美川, 雷洋, 廖军. 基于双向LSTM的用户用电行为识别[J]. 微电子学与计算机, 2021, 38(5): 36-41.

XIE Lu-jiang, DUAN Li, TAN Gang, et al. Electrical behavior recognition based on bidirectional LSTM[J]. 2021, 38(5): 36-41.
谢禄江, 段立, 谭刚, 蒋荣, 钟淘淘, 刘美川, 雷洋, 廖军. 基于双向LSTM的用户用电行为识别[J]. 微电子学与计算机, 2021, 38(5): 36-41. DOI：

XIE Lu-jiang, DUAN Li, TAN Gang, et al. Electrical behavior recognition based on bidirectional LSTM[J]. 2021, 38(5): 36-41. DOI：

摘要

为了解决由非技术性损失所造成的用户用电异常问题，本文提出了一种基于双向长短时记忆神经网络(Bi-LSTM)的用户异常用电行为检测方法.该方法首先采用插值法处理用电缺失数据，并通过分位数归一化平滑用电异常行为值的不对称分布性.然后，结合LSTM神经网络单元和双向网络构建Bi-LSTM模型，用于获取用户异常用电行为中的隐含关系.最后，采用交叉熵确定最优参数，从而识别出异常用电用户行为.实验表明，该方法的识别性能显著优于其他模型，并且结合国家电网的实际数据验证了该方法的准确性和稳定性.

Abstract

To solve the problem of abnormal user power consumption caused by non-technical losses

a method for detecting abnormal power consumption behavior based on a bidirectional long-term short-term memory neural network (Bi-LSTM) is proposed. In this method

firstly

the missing data is processed by interpolation method

and the asymmetric distribution of abnormal electricity consumption behavior value is smoothed by quantile normalization. Then

the Bi-LSTM model is constructed by combining the LSTM neural network unit and bidirectional network

which is used to obtain the implicit relationship of abnormal electricity consumption behavior of users. Finally

the cross entropy is used to determine the optimal parameters

thereby detecting the abnormal power consumer. The experiments are conducted based on real energy consumption data

and the results show that the detection performance of this proposed method outperforms other methods in terms of accuracy and stability.

关键词

Keywords

references

NABIL M, ISMAIL M, MAHMOUD M, et al. Deep learning-based detection of electricity theft cyber-attacks in smart grid AMI networks[M]//ALAZAB M, TANG M. Deep Learning Applications for Cyber Security. Cham: Springer, 2019.

MICHELI G, SODA E, VESPUCCI M T, et al. Big data analytics: an aid to detection of non-technical losses in power utilities[J]. Computational Management Science, 2019, 16(1-2): 329-343. DOI: 10.1007/s10287-018-0325-x.

AHMAD T, CHEN H X, WANG J Y, et al. Review of various modeling techniques for the detection of electricity theft in smart grid environment[J]. Renewable and Sustainable Energy Reviews, 2018, 82: 2916-2933. DOI: 10.1016/j.rser.2017.10.040.

ZHANG S, ZHENG D Q, HU X C, et al. Bidirectional long short-term memory networks for relation classification[C]//29th Pacific Asia Conference on Language, Information and Computation. Shanghai, 2015: 73-78.

李婉华, 陈宏, 郭昆, 等. 基于随机森林算法的用电负荷预测研究[J]. 计算机工程与应用, 2016, 52(23): 236-243. DOI: 10.3778/j.issn.1002-8331.1606-0203. LI W H, CHEN H, GUO K, et al. Research on electrical load prediction based on random forest algorithm[J]. Computer Engineering and Applications, 2016, 52(23): 236-243. DOI: 10.3778/j.issn.1002-8331.1606-0203.

孙向阳. 基于XGBoost算法的窃电用户行为研究[D]. 兰州: 兰州交通大学, 2018. SUN X Y, Research on stealing user behavior based on XGBoost algorithm[D]. Lanzhou: Lanzhou Jiaotong University, 2018.

赵文清, 沈哲吉, 李刚. 基于深度学习的用户异常用电模式检测[J]. 电力自动化设备, 2018, 38(9): 34-38. DOI: 10.16081/j.issn.1006-6047.2018.09.006. ZHAO W Q, SHEN Z J, LI G. Anomaly detection for power consumption pattern based on deep learning[J]. Electric Power Automation Equipment, 2018, 38(9): 34-38. DOI: 10.16081/j.issn.1006-6047.2018.09.006.

BOLSTAD B M, IRIZARRY R A, ÁSTRAND M, et al. A comparison of normalization methods for high density oligonucleotide array data based on variance and bias[J]. Bioinformatics, 2003, 19(2): 185-193. DOI: 10.1093/bioinformatics/19.2. 185.

田野, 张程, 毛昕儒, 等. 运用PCA改进BP神经网络的用电异常行为检测[J]. 重庆理工大学学报(自然科学), 2017, 31(8): 125-133. DOI: 10.3969/j.issn.1674-8425(z).2017.08.021. TIAN Y, ZHANG C, MAO X R, et al. Research on abnormal behavior of power consumption based on BP neural network with PCA[J]. Journal of Chongqing University of Technology (Natural Science), 2017, 31(8): 125-133. DOI: 10.3969/j.issn.1674-8425(z).2017.08.021.

GAO Y Q, FOGGO B, YU N P. A physically inspired data-driven model for electricity theft detection with smart meter data[J]. IEEE Transactions on Industrial Informatics, 2019, 15(9): 5076-5088. DOI: 10.1109/TⅡ.2019.2898171.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

一种基于特征上下文理解与切片分析的肺结核检测算法

基于多尺度融合与小目标增强的航拍车辆检测算法

基于监控指标关联性的微服务异常检测

面向处理器分支预测单元的Spectre攻击轻量化防御方法

基于改进RT-DETR的航拍小目标检测算法