Privacy-Preserving Generation Fraud Detection for Distributed Photovoltaic Systems: A Solar Irradiance-Fused Federated Learning Framework

2026-05-16

AI Summary

This work addresses the challenges of intermittency, data privacy, and scalability in detecting power generation fraud within distributed photovoltaic systems by proposing a privacy-preserving detection framework based on federated learning. The approach introduces a co-attention architecture incorporating solar irradiance and integrates a prototype alignment mechanism to mitigate class imbalance. Cross-community knowledge sharing and local model optimization are achieved through collaborative aggregation of both model parameters and prototypes. Experimental evaluation on real-world residential photovoltaic datasets demonstrates that the proposed method significantly outperforms existing federated learning approaches, exhibiting superior scalability, robustness, and detection performance across varying community sizes and class imbalance scenarios.

Abstract

The wide adoption of residential photovoltaic (PV) systems introduces new challenges for generation fraud detection (FD). Unlike traditional electricity theft detection, which focuses on electricity consumption-side behavior, PV generation fraud detection (PVG-FD) is complicated by the inherent intermittency and uncertainty of PV generation. The distributed nature of PV systems poses further challenges for centralized PVG-FD approaches due to scalability and privacy concerns. This paper develops a privacy-preserving distributed PVG-FD framework based on federated learning (FL). In this framework, a utility company manages multiple household communities, where each of which is equipped with a local detector. The framework integrates a novel detection model architecture with privacy-preserving global collaboration. Each community's local model fuses PV generation and weather data via a co-attention mechanism to detect discrepancies critical for PVG-FD. The FL framework enables cross-community collaboration by aggregating model parameters and prototypes, leveraging global knowledge sharing with local refinement while preserving privacy. It also uses prototype alignment to address class imbalance by enhancing fraud sample representation. Extensive experiments on a real-world residential PV dataset validate the effectiveness of the developed method and demonstrate that it outperforms state-of-the-art FL methods across various scenarios. The results also show its scalability across varying community sizes and strong robustness to class imbalance.

Problem

• generation fraud detection
• distributed photovoltaic systems
• privacy preservation
• federated learning
• class imbalance

Innovation

• federated learning
• photovoltaic generation fraud detection
• co-attention mechanism
• prototype alignment
• privacy-preserving