skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Outage Detection in Partially Observable Distribution Systems Using Smart Meters and Generative Adversarial Networks

Journal Article · · IEEE Transactions on Smart Grid

In this paper, we present a novel data-driven approach to detect outage events in partially observable distribution systems by capturing the changes in smart meters' (SMs) data distribution. To achieve this, first, a breadth-first search (BFS)-based mechanism is proposed to decompose the network into a set of zones that maximize outage location information in partially observable systems. Then, using SM data in each zone, a generative adversarial network (GAN) is designed to implicitly extract the temporal-spatial behavior in normal conditions in an unsupervised fashion. After training, an anomaly scoring technique is leveraged to determine if real-time measurements indicate an outage event in the zone. Finally, to infer the location of the outage events in a multi-zone network, a zone coordination process is proposed to take into account the interdependencies of intersecting zones. We have provided analytical guarantees of performance for our algorithm using the concept of entropy, which is leveraged to quantify outage location information in multi-zone grids. Furthermore, the proposed method has been tested and verified on distribution feeder models with real SM data.

Research Organization:
Iowa State Univ., Ames, IA (United States)
Sponsoring Organization:
USDOE Office of Electricity (OE); National Science Foundation (NSF)
Grant/Contract Number:
OE0000875; ECCS 1929975
OSTI ID:
1961198
Journal Information:
IEEE Transactions on Smart Grid, Vol. 11, Issue 6; ISSN 1949-3053
Publisher:
IEEECopyright Statement
Country of Publication:
United States
Language:
English

References (23)

An introduction to ROC analysis journal June 2006
Low voltage system state estimation using smart meters conference September 2012
A General Polling Algorithm Using a Wireless AMR System for Restoration Confirmation journal April 2001
AdaBoost$^{+}$: An Ensemble Learning Approach for Estimating Weather-Related Outages in Distribution Systems journal January 2014
Anomaly detection: A survey journal July 2009
Generative Adversarial Networks: An Overview journal January 2018
Direction-Optimizing Breadth-First Search journal January 2013
A Time-Series Distribution Test System Based on Real Utility Data conference October 2019
Distributed Reactive Power Feedback Control for Voltage Regulation and Loss Minimization journal April 2015
Data-Driven Power Outage Detection by Social Sensors journal September 2016
Model-Free Renewable Scenario Generation Using Generative Adversarial Networks journal May 2018
AMI-Enabled Distribution Network Line Outage Identification via Multi-Label SVM journal September 2018
Entropy and diversity journal May 2006
Fault Location in Distribution Systems Based on Smart Feeder Meters journal February 2014
Nontechnical Loss and Outage Detection Using Fractional-Order Self-Synchronization Error-Based Fuzzy Petri Nets in Micro-Distribution Systems journal January 2015
A Hierarchical Framework for Smart Grid Anomaly Detection Using Large-Scale Smart Meter Data journal November 2018
Outage Detection Using Load and Line Flow Measurements in Power Distribution Systems journal March 2018
Outage management through AMR systems using an intelligent data filter journal January 2001
Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning? journal May 2016
Learning topology of distribution grids using only terminal node measurements conference November 2016
An empirical evaluation of deep architectures on problems with many factors of variation conference January 2007
A Game-Theoretic Data-Driven Approach for Pseudo-Measurement Generation in Distribution System State Estimation journal November 2019
f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization preprint January 2016