Evaluating GAN-LSTM for Smart Meter Anomaly Detection in Power Systems

TL;DR

This paper evaluates a GAN-LSTM framework for detecting anomalies in smart meter data, demonstrating significant improvements over existing methods in power systems.

Contribution

It provides a systematic evaluation of GAN-LSTM for anomaly detection in power systems using a large-scale dataset, highlighting its superior performance.

Findings

GAN-LSTM achieves an F1-score of 0.89

Outperforms six baseline models in anomaly detection

Supports real-world power system monitoring

Abstract

Advanced metering infrastructure (AMI) provides high-resolution electricity consumption data that can enhance monitoring, diagnosis, and decision making in modern power distribution systems. Detecting anomalies in these time-series measurements is challenging due to nonlinear, nonstationary, and multi-scale temporal behavior across diverse building types and operating conditions. This work presents a systematic, power-system-oriented evaluation of a GAN-LSTM framework for smart meter anomaly detection using the Large-scale Energy Anomaly Detection (LEAD) dataset, which contains one year of hourly measurements from 406 buildings. The proposed pipeline applies consistent preprocessing, temporal windowing, and threshold selection across all methods, and compares the GAN-LSTM approach against six widely used baselines, including statistical, kernel-based, reconstruction-based, and GAN-based models. Experimental results demonstrate that the GAN-LSTM significantly improves detection performance, achieving an F1-score of 0.89. These findings highlight the potential of adversarial temporal modeling as a practical tool for supporting asset monitoring, non-technical loss detection, and situational awareness in real-world power distribution networks. The code for this work is publicly available