Anomaly Detection with Machine Learning Algorithms and Big Data in Electricity Consumption

被引:38
|
作者
Oprea, Simona-Vasilica [1 ]
Bara, Adela [1 ]
Puican, Florina Camelia [1 ]
Radu, Ioan Cosmin [2 ]
机构
[1] Bucharest Univ Econ Studies, Dept Econ Informat & Cybernet, Romana Sq 6, Bucharest 010374, Romania
[2] Univ Politehn Bucuresti, Dept Engn Foreign Languages, Splaiul Independent 313, Bucharest 060042, Romania
关键词
anomaly detection; unsupervised and supervised machine learning; big data; smart grid; fraud detection; DETECTION FRAMEWORK; THEFT DETECTION; FRAUD DETECTION; ENERGY THEFT;
D O I
10.3390/su131910963
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
When analyzing smart metering data, both reading errors and frauds can be identified. The purpose of this analysis is to alert the utility companies to suspicious consumption behavior that could be further investigated with on-site inspections or other methods. The use of Machine Learning (ML) algorithms to analyze consumption readings can lead to the identification of malfunctions, cyberattacks interrupting measurements, or physical tampering with smart meters. Fraud detection is one of the classical anomaly detection examples, as it is not easy to label consumption or transactional data. Furthermore, frauds differ in nature, and learning is not always possible. In this paper, we analyze large datasets of readings provided by smart meters installed in a trial study in Ireland by applying a hybrid approach. More precisely, we propose an unsupervised ML technique to detect anomalous values in the time series, establish a threshold for the percentage of anomalous readings from the total readings, and then label that time series as suspicious or not. Initially, we propose two types of algorithms for anomaly detection for unlabeled data: Spectral Residual-Convolutional Neural Network (SR-CNN) and an anomaly trained model based on martingales for determining variations in time-series data streams. Then, the Two-Class Boosted Decision Tree and Fisher Linear Discriminant analysis are applied on the previously processed dataset. By training the model, we obtain the required capabilities of detecting suspicious consumers proved by an accuracy of 90%, precision score of 0.875, and F1 score of 0.894.
引用
收藏
页数:20
相关论文
共 50 条
  • [1] A machine learning-based Anomaly Detection Framework for building electricity consumption data
    Mascali, Lorenzo
    Schiera, Daniele Salvatore
    Eiraudo, Simone
    Barbierato, Luca
    Giannantonio, Roberta
    Patti, Edoardo
    Bottaccioli, Lorenzo
    Lanzini, Andrea
    SUSTAINABLE ENERGY GRIDS & NETWORKS, 2023, 36
  • [2] Machine learning classification algorithms and anomaly detection in conventional meters and Tunisian electricity consumption large datasets
    Oprea, Simona-Vasilica
    Bara, Adela
    COMPUTERS & ELECTRICAL ENGINEERING, 2021, 94
  • [3] Anomaly Detection in Electricity Consumption Data using Deep Learning
    Kardi, Mohammad
    AlSkaif, Tarek
    Tekinerdogan, Bedir
    Catalao, Joao P. S.
    2021 21ST IEEE INTERNATIONAL CONFERENCE ON ENVIRONMENT AND ELECTRICAL ENGINEERING AND 2021 5TH IEEE INDUSTRIAL AND COMMERCIAL POWER SYSTEMS EUROPE (EEEIC/I&CPS EUROPE), 2021,
  • [4] Anomaly Detection and Visualization for Electricity Consumption Data
    Lee, Nyoungwoo
    Nam, Jehyun
    Choi, Ho-Jin
    20TH IEEE INTERNATIONAL CONFERENCE ON DATA MINING WORKSHOPS (ICDMW 2020), 2020, : 743 - 749
  • [5] Machine Learning Algorithms for Predicting Electricity Consumption of Buildings
    Hosseini, Soodeh
    Fard, Reyhane Hafezi
    WIRELESS PERSONAL COMMUNICATIONS, 2021, 121 (04) : 3329 - 3341
  • [6] Machine Learning Algorithms for Predicting Electricity Consumption of Buildings
    Soodeh Hosseini
    Reyhane Hafezi Fard
    Wireless Personal Communications, 2021, 121 : 3329 - 3341
  • [7] Anomaly Detection and Visualization of School Electricity Consumption Data
    Cui, Wenqiang
    Wang, Hao
    2017 IEEE 2ND INTERNATIONAL CONFERENCE ON BIG DATA ANALYSIS (ICBDA), 2017, : 606 - 611
  • [8] Comparative Analysis of Unsupervised Machine Learning Algorithms for Anomaly Detection in Network Data
    Oliveira, Junia Maisa
    Almeida, Jonatan
    Macedo, Daniel
    Nogueira, Jose Marcos
    2023 IEEE LATIN-AMERICAN CONFERENCE ON COMMUNICATIONS, LATINCOM, 2023,
  • [9] Big data algorithms beyond machine learning
    Mnich M.
    KI - Kunstliche Intelligenz, 2018, 32 (01): : 9 - 17
  • [10] Anomaly Prediction in Electricity Consumption Using a Combination of Machine Learning Techniques
    El-Hadad, Rawan
    Tan, Yi-Fei
    Tan, Wooi-Nee
    INTERNATIONAL JOURNAL OF TECHNOLOGY, 2022, 13 (06) : 1317 - 1325