A hierarchical framework for smart grid anomaly detection using large-scale smart meter data

Ramin Moghaddass, Jianhui Wang

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

Real-time monitoring and control of smart grids (SGs) is critical to the enhancement of reliability and operational efficiency of power utilities. We develop a real-time anomaly detection framework, which can be built based upon smart meter (SM) data collected at the consumers' premises. The model is designed to detect the occurrence of anomalous events and abnormal conditions at both lateral and customer levels. We propose a generative model for anomaly detection that takes into account the hierarchical structure of the network and the data collected from SMs. We also address three challenges existing in SG analytics: 1) large-scale multivariate count measurements; 2) missing points; and 3) variable selection. We present the effectiveness of our approach with numerical experiments.

Original languageEnglish (US)
Article number7908945
Pages (from-to)5820-5830
Number of pages11
JournalIEEE Transactions on Smart Grid
Volume9
Issue number6
DOIs
StatePublished - Nov 1 2018

Fingerprint

Smart meters
Monitoring
Experiments

Keywords

  • anomaly detection
  • big data
  • response count data
  • Smart grid analytics

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

A hierarchical framework for smart grid anomaly detection using large-scale smart meter data. / Moghaddass, Ramin; Wang, Jianhui.

In: IEEE Transactions on Smart Grid, Vol. 9, No. 6, 7908945, 01.11.2018, p. 5820-5830.

Research output: Contribution to journalArticle

@article{4aca3618530c4deb943920c3d16d3bec,
title = "A hierarchical framework for smart grid anomaly detection using large-scale smart meter data",
abstract = "Real-time monitoring and control of smart grids (SGs) is critical to the enhancement of reliability and operational efficiency of power utilities. We develop a real-time anomaly detection framework, which can be built based upon smart meter (SM) data collected at the consumers' premises. The model is designed to detect the occurrence of anomalous events and abnormal conditions at both lateral and customer levels. We propose a generative model for anomaly detection that takes into account the hierarchical structure of the network and the data collected from SMs. We also address three challenges existing in SG analytics: 1) large-scale multivariate count measurements; 2) missing points; and 3) variable selection. We present the effectiveness of our approach with numerical experiments.",
keywords = "anomaly detection, big data, response count data, Smart grid analytics",
author = "Ramin Moghaddass and Jianhui Wang",
year = "2018",
month = "11",
day = "1",
doi = "10.1109/TSG.2017.2697440",
language = "English (US)",
volume = "9",
pages = "5820--5830",
journal = "IEEE Transactions on Smart Grid",
issn = "1949-3053",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "6",

}

TY - JOUR

T1 - A hierarchical framework for smart grid anomaly detection using large-scale smart meter data

AU - Moghaddass, Ramin

AU - Wang, Jianhui

PY - 2018/11/1

Y1 - 2018/11/1

N2 - Real-time monitoring and control of smart grids (SGs) is critical to the enhancement of reliability and operational efficiency of power utilities. We develop a real-time anomaly detection framework, which can be built based upon smart meter (SM) data collected at the consumers' premises. The model is designed to detect the occurrence of anomalous events and abnormal conditions at both lateral and customer levels. We propose a generative model for anomaly detection that takes into account the hierarchical structure of the network and the data collected from SMs. We also address three challenges existing in SG analytics: 1) large-scale multivariate count measurements; 2) missing points; and 3) variable selection. We present the effectiveness of our approach with numerical experiments.

AB - Real-time monitoring and control of smart grids (SGs) is critical to the enhancement of reliability and operational efficiency of power utilities. We develop a real-time anomaly detection framework, which can be built based upon smart meter (SM) data collected at the consumers' premises. The model is designed to detect the occurrence of anomalous events and abnormal conditions at both lateral and customer levels. We propose a generative model for anomaly detection that takes into account the hierarchical structure of the network and the data collected from SMs. We also address three challenges existing in SG analytics: 1) large-scale multivariate count measurements; 2) missing points; and 3) variable selection. We present the effectiveness of our approach with numerical experiments.

KW - anomaly detection

KW - big data

KW - response count data

KW - Smart grid analytics

UR - http://www.scopus.com/inward/record.url?scp=85055433390&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85055433390&partnerID=8YFLogxK

U2 - 10.1109/TSG.2017.2697440

DO - 10.1109/TSG.2017.2697440

M3 - Article

AN - SCOPUS:85055433390

VL - 9

SP - 5820

EP - 5830

JO - IEEE Transactions on Smart Grid

JF - IEEE Transactions on Smart Grid

SN - 1949-3053

IS - 6

M1 - 7908945

ER -