Loading...

Unsupervised learning for distribution grid line outage and electricity theft identification

Soleymani, M ; Sharif University of Technology | 2019

662 Viewed
  1. Type of Document: Article
  2. DOI: 10.1109/SGC49328.2019.9056579
  3. Publisher: Institute of Electrical and Electronics Engineers Inc , 2019
  4. Abstract:
  5. The development of smart meters enables situational awareness in electric power distribution systems. The situational awareness provides significant advantages such as line outage and electricity theft detection. This paper aims at using smart meter data to detect these anomalies. To do so, an appropriate cluster-based method as an unsupervised machine learning approach is applied. A stochastic method based on conditional correlation is also proposed to localize the anomalies. It is shown that this can be done by detecting changes in bus connections using present and historical smart meter data. Therefore, network topology inspection can be avoided if the proposed method is applied. A complex mesh grid is used to demonstrate performance of the data-driven anomaly detection approach. The results show that determining the right value of hyper-parameter and adequate features extraction leads to acceptable accuracy. © 2019 IEEE
  6. Keywords:
  7. Electricity theft identification ; Line outage identification ; Smart grid ; Smart meter ; Unsupervised learning ; Anomaly detection ; Crime ; Machine learning ; Smart meters ; Stochastic systems ; Cluster-based methods ; Conditional correlation ; Data-driven anomalies ; Electric power distribution systems ; Electricity theft detection ; Features extraction ; Situational awareness ; Unsupervised machine learning ; Outages
  8. Source: 2019 Smart Gird Conference, SGC 2019, 18 December 2019 through 19 December 2019 ; 2019 ; 9781728158945 (ISBN)
  9. URL: https://ieeexplore.ieee.org/abstract/document/9056579