Towards Secure and Scalable Energy Theft Detection: A Federated Learning Approach for Resource-Constrained Smart Meters

2026-02-17

AI Summary

This work proposes a lightweight federated learning framework tailored for edge-based smart meters to enable privacy-preserving electricity theft detection in smart grids. Addressing the dual challenges of privacy leakage from centralized user data processing and the difficulty of deploying complex models on resource-constrained meters, the approach integrates a lightweight multilayer perceptron with a differential privacy mechanism via Gaussian noise injection. This design ensures formal privacy guarantees while remaining compatible with low-power hardware. Experimental evaluation on real-world smart meter datasets demonstrates that the proposed method achieves competitive performance in terms of accuracy, precision, recall, and AUC under both IID and non-IID data distributions, offering a balanced trade-off among security, efficiency, and scalability.

Technology Category

• Machine Learning: Privacy
• Intelligent Robots: State Estimation
• Humans and AI: Human-in-the-loop Machine Learning

Application Category

• Security and Privacy: Large-scale security measurements
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems

Abstract

Energy theft poses a significant threat to the stability and efficiency of smart grids, leading to substantial economic losses and operational challenges. Traditional centralized machine learning approaches for theft detection require aggregating user data, raising serious concerns about privacy and data security. These issues are further exacerbated in smart meter environments, where devices are often resource-constrained and lack the capacity to run heavy models. In this work, we propose a privacy-preserving federated learning framework for energy theft detection that addresses both privacy and computational constraints. Our approach leverages a lightweight multilayer perceptron (MLP) model, suitable for deployment on low-power smart meters, and integrates basic differential privacy (DP) by injecting Gaussian noise into local model updates before aggregation. This ensures formal privacy guarantees without compromising learning performance. We evaluate our framework on a real-world smart meter dataset under both IID and non-IID data distributions. Experimental results demonstrate that our method achieves competitive accuracy, precision, recall, and AUC scores while maintaining privacy and efficiency. This makes the proposed solution practical and scalable for secure energy theft detection in next-generation smart grid infrastructures.

Problem

• energy theft detection
• smart meters
• privacy
• resource-constrained
• smart grids

Innovation

• Federated Learning
• Differential Privacy
• Lightweight MLP
• Energy Theft Detection
• Smart Meters