Drift-Aware Methodology for Anomaly Detection in Smart Grid

Energy efficiency and sustainability are important factors to address in the context of smart cities. In this sense, smart metering and nonintrusive load monitoring play a crucial role in fighting energy thefts and for optimizing the energy consumption of the home, building, city, and so forth. The...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access 2019, Vol.7, p.9645-9657
Main Authors: Fenza, Giuseppe, Gallo, Mariacristina, Loia, Vincenzo
Format: Article
Language:English
Subjects:
Anomalies
Anomaly detection
Clustering algorithms
concept drift
Consumption
Context
Drift
Electricity consumption
Electricity meters
Energy consumption
machine learning
Monitoring
Power consumption
Real time
Smart grid
Smart grids
Smart meters
time series analysis
Training
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Energy efficiency and sustainability are important factors to address in the context of smart cities. In this sense, smart metering and nonintrusive load monitoring play a crucial role in fighting energy thefts and for optimizing the energy consumption of the home, building, city, and so forth. The estimated number of smart meters will exceed 800 million by 2020. By providing near real-time data about power consumption, smart meters can be used to analyze electricity usage trends and to point out anomalies guaranteeing companies' safety and avoiding energy wastes. In literature, there are many proposals approaching the problem of anomaly detection. Most of them are limited because they lack context and time awareness and the false positive rate is affected by the change in consumer habits. This research work focuses on the need to define anomaly detection method capable of facing the concept drift, for instance, family structure changes; a house becomes a second residence, and so forth. The proposed methodology adopts long short term memory network in order to profile and forecast the consumers' behavior based on their recent past consumptions. The continuous monitoring of the consumption prediction errors allows us to distinguish between possible anomalies and changes (drifts) in normal behavior that correspond to different error motifs. The experimental results demonstrate the suitability of the proposed framework by pointing out an anomaly in a near real-time after a training period of one week.
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2019.2891315