Electricity Behavior Modeling and Anomaly Detection Services Based on a Deep Variational Autoencoder Network

被引:1
作者
Lin, Rongheng [1 ]
Chen, Shuo [1 ]
He, Zheyu [1 ]
Wu, Budan [1 ]
Zou, Hua [1 ]
Zhao, Xin [2 ]
Li, Qiushuang [2 ]
机构
[1] Beijing Univ Posts & Telecommun, Sch Comp Sci, Natl Pilot Software Engn Sch, State Key Lab Networking & Switching Technol, Beijing 100876, Peoples R China
[2] State Grid Shandong Elect Power Co, Econ & Res Inst, Jinan 250021, Peoples R China
关键词
load pattern; anomaly detection; autoencoder network;
D O I
10.3390/en17163904
中图分类号
TE [石油、天然气工业]; TK [能源与动力工程];
学科分类号
0807 ; 0820 ;
摘要
Understanding electrical load profiles and detecting anomaly behaviors are important to the smart grid system. However, current load identification and anomaly analysis are based on static analysis, and less consideration is given to anomaly findings under load change conditions. This paper proposes a deep variational autoencoder network (DVAE) for load profiles, along with anomaly analysis services, and introduces auto-time series data updating strategies based on sliding window adjustment. DVAE can help reconstruct the load curve and measure the difference between the original and the newer curve, whose measurement indicators include reconstruction probability and Pearson similarity. Meanwhile, the design of the sliding window strategy updates the data and DVAE model in a time-series manner. Experiments were carried out based on datasets from the U.S. Department of Energy and from Southeast China. The results showed that the proposed services could result in a 5% improvement in the AUC value, which helps to identify the anomaly behavior.
引用
收藏
页数:20
相关论文
共 28 条
  • [11] A data mining-based framework for the identification of daily electricity usage patterns and anomaly detection in building electricity consumption data
    Liu, Xue
    Ding, Yong
    Tang, Hao
    Xiao, Feng
    [J]. ENERGY AND BUILDINGS, 2021, 231
  • [12] Nakayama K, 2017, 2017 RESILIENCE WEEK (RWS), P24, DOI 10.1109/RWEEK.2017.8088643
  • [13] O'Shea K, 2015, Arxiv, DOI arXiv:1511.08458
  • [14] Recognition and classification of typical load profiles in buildings with non-intrusive learning approach
    Piscitelli, Marco Savino
    Brandi, Silvio
    Capozzoli, Alfonso
    [J]. APPLIED ENERGY, 2019, 255
  • [15] A comparative study of clustering techniques for electrical load pattern segmentation
    Rajabi, Amin
    Eskandari, Mohsen
    Ghadi, Mojtaba Jabbari
    Li, Li
    Zhang, Jiangfeng
    Siano, Pierluigi
    [J]. RENEWABLE & SUSTAINABLE ENERGY REVIEWS, 2020, 120
  • [16] Convolutional Autoencoder Based Feature Extraction and Clustering for Customer Load Analysis
    Ryu, Seunghyoung
    Choi, Hyungeun
    Lee, Hyoseop
    Kim, Hongseok
    [J]. IEEE TRANSACTIONS ON POWER SYSTEMS, 2020, 35 (02) : 1048 - 1060
  • [17] Saraswat Deepti, 2021, Proceedings of 2021 2nd International Conference on Intelligent Engineering and Management (ICIEM), P417, DOI 10.1109/ICIEM51511.2021.9445353
  • [18] Anomaly Detection in IIoT: A Case Study using Machine Learning
    Shah, Gauri
    Tiwari, Aashis
    [J]. PROCEEDINGS OF THE ACM INDIA JOINT INTERNATIONAL CONFERENCE ON DATA SCIENCE AND MANAGEMENT OF DATA (CODS-COMAD'18), 2018, : 295 - 300
  • [19] Temperature anomaly detection for electric load forecasting
    Sobhani, Masoud
    Hong, Tao
    Martin, Claude
    [J]. INTERNATIONAL JOURNAL OF FORECASTING, 2020, 36 (02) : 324 - 333
  • [20] Sun M., 2020, Security of Cyber-Physical Systems, P131