A Real-time Anomaly Detection Using Convolutional Autoencoder with Dynamic Threshold

TL;DR

This paper presents a real-time anomaly detection system for smart meter energy data, combining statistical methods and convolutional autoencoders with dynamic thresholds to identify unusual patterns early.

Contribution

It introduces a hybrid approach integrating statistics and deep learning for real-time anomaly detection in energy consumption data, with a dynamic threshold mechanism.

Findings

Effective detection of anomalies in real-world energy data

Early warning system improves reliability of energy monitoring

Potential for cost savings and disaster prevention

Abstract

The majority of modern consumer-level energy is generated by real-time smart metering systems. These frequently contain anomalies, which prevent reliable estimates of the series' evolution. This work introduces a hybrid modeling approach combining statistics and a Convolutional Autoencoder with a dynamic threshold. The threshold is determined based on Mahalanobis distance and moving averages. It has been tested using real-life energy consumption data collected from smart metering systems. The solution includes a real-time, meter-level anomaly detection system that connects to an advanced monitoring system. This makes a substantial contribution by detecting unusual data movements and delivering an early warning. Early detection and subsequent troubleshooting can financially benefit organizations and consumers and prevent disasters from occurring.