A Lightweight, Transferable, and Self-Adaptive Framework for Intelligent DC Arc-Fault Detection in Photovoltaic Systems

Xiaoke Yang; Long Gao; Haoyu He; Hanyuan Hang; Qi Liu; Shuai Zhao; Qiantu Tuo; Rui Li

eess.SPMar 16, 2026

A Lightweight, Transferable, and Self-Adaptive Framework for Intelligent DC Arc-Fault Detection in Photovoltaic Systems

Authors: Xiaoke Yang, Long Gao, Haoyu He, Hanyuan Hang, Qi Liu, Shuai Zhao, Qiantu Tuo, Rui Li

Organizations: EcoFlow Inc, Shenzhen, China. · AAU Energy, Aalborg University, Denmark

Abstract

Arc-fault circuit interrupters (AFCIs) are essential for mitigating fire hazards in residential photovoltaic (PV) systems, yet achieving reliable DC arc-fault detection under real-world conditions remains challenging. Spectral interference from inverter switching, hardware heterogeneity, operating-condition drift, and environmental noise collectively compromise conventional AFCI solutions. This paper proposes a lightweight, transferable, and self-adaptive learning-driven framework (LD-framework) for intelligent DC arc-fault detection. At the device level, LD-Spec learns compact spectral representations enabling efficient on-device inference and near-perfect arc discrimination. Across heterogeneous inverter platforms, LD-Align performs cross-hardware representation alignment to ensure robust detection despite hardware-induced distribution shifts. To address long-term evolution, LD-Adapt introduces a cloud-edge collaborative self-adaptive updating mechanism that detects unseen operating regimes and performs controlled model evolution. Extensive experiments involving over 53,000 labeled samples demonstrate near-perfect detection, achieving 0.9999 accuracy and 0.9996 F1-score. Across diverse nuisance-trip-prone conditions, including inverter start-up, grid transitions, load switching, and harmonic disturbances, the method achieves a 0% false-trip rate. Cross-hardware transfer shows reliable adaptation using only 0.5%-1% labeled target data while preserving source performance. Field adaptation experiments demonstrate recovery of detection precision from 21% to 95% under previously unseen conditions. These results indicate that the LD-framework enables a scalable, deployment-oriented AFCI solution maintaining highly reliable detection across heterogeneous devices and long-term operation.

Figures & tables

Fig. 1 : Overview of the PV-BESS system architecture.

Fig. 2 : Spectrum of PV currents during normal and arc-fault operation. Arc faults exhibit elevated broadband spectral magnitude.

Panel of Figure 3 — Fig. 3 : Time-domain waveforms and spectrograms of PV current under steady operation and arc-fault conditions.

Fig. 4 : Spectrum of PV currents from two inverter platforms exhibiting distinct switching-frequency characteristics.

Fig. 5 : Spectrum of PV currents from a laboratory PV source and a real solar panel under identical current conditions.

Fig. 6 : System-level architecture of the proposed LD-framework, illustrating the interaction between on-device lightweight AFCI detection, offline data acquisition and training, cross-converter transfer learning (LD-Align), and online self-adaptive evolution (LD-Adapt) with OTA deployment.

Fig. 7 : Architecture of the spectral CNN (LD-Spec) for lightweight on-device arc-fault detection.

Fig. 8 : Experimental data acquisition and testing environment consisting of an impedance network cabinet (left), an arc generator (upper right), and the power conversion system (PCS, lower right).

Category	Operating Conditions
System Start-up Processes	7
Parallel Operation of PV Strings	3
PV Direct-Connection Modes	6
DC Circuit Breaker Operation	4
Variable PV Input Modes	3
Limited Grid-Feeding & Repeated Start–Stop	2

TABLE I : Operating Conditions for Nuisance Trip Evaluation

Panel of Figure 10 — Fig. 9 : Spectrograms of representative operating conditions for nuisance trip evaluation.

Panel of Figure 11 — Fig. 10 : Screenshots of some test cases of the proposed AFCI method.

Panel of Figure 12 — Fig. 11 : Oscilloscope waveforms during series arc fault tests on a PV string: current (Ch1), voltage (Ch2), and calculated power (MATH). The fault clearance time $\Delta$ x is measured from arc initiation to AFCI trip. For the START location (a), the time is 1.356 s; for the MIDDLE location (b), the time is 1.36 s.

Fig. 12 : Scaling behavior of LD-Spec under increasing dataset sizes.

Panel of Figure 14 — Fig. 13 : Cross-hardware transfer behavior of LD-Align.

Fig. 14 : Typical installation of the photovoltaic and battery energy storage system.

Fig. 15 : AFCI alert statistics from field-deployed over a one-month period. Device Index denotes an individual device, with notable variation in false alarm rates across devices. The line on top shows detection precision when LD-Adapt is applied.

Panel of Figure 17 — Fig. 16 : Spectra of false alarms compared with lab testing normal and arc conditions. Distinct spectral deviations highlight domain shift between field and lab testing environments.

Fault Detection

Fault detection identifies abnormal behavior in machines, sensors, infrastructure, software, and autonomous systems before it causes harm or disruption.

See all 104 papers

Privacy-Preserving Generation Fraud Detection for Distributed Photovoltaic Systems: A Solar Irradiance-Fused Federated Learning Framework
May 16, 2026Xiaolu Chen, Chenghao Huang, Yanru Zhang +1Privacy-Preserving ML Federated Learning
School of Computer Science and Technology, University of Electronic Science and Technology of China, Chengdu, China · Department of Data Science and AI, Faculty of IT, Monash University, Melbourne, VIC 3800, Australia · Department of Data Science and AI, Faculty of IT and Monash Energy Institute, Monash University, Melbourne, VIC 3800, Australia +1
A Self-Evolving Defect Detection Framework for Industrial Photovoltaic Systems
Mar 16, 2026Haoyu He, Yu Duan, Wenzhen Liu +5Fault Detection Industrial Inspection
EcoFlow Inc, Shenzhen, China · School of Electrical Engineering, Xi’an Jiaotong University, Xi’an, China
Constraint-Driven Warm-Freeze for Efficient Transfer Learning in Photovoltaic Systems
Apr 7, 2026Yasmeen Saeed, Ahmed Sharshar, Mohsen GuizaniFine-Tuning Transfer Learning
Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates

May 16, 2026J/K move · Enter open · S save

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

Xiaolu Chen, Chenghao Huang, Yanru Zhang, Hao Wang

School of Computer Science and Technology, University of Electronic Science and Technology of China, Chengdu, China · Department of Data Science and AI, Faculty of IT, Monash University, Melbourne, VIC 3800, Australia · Department of Data Science and AI, Faculty of IT and Monash Energy Institute, Monash University, Melbourne, VIC 3800, Australia+1

Privacy-Preserving ML Federated Learning Anomaly Detection

Open paper AskPDF arXiv

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.

Abstract

Fault Detection

Explore similar work

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

A Self-Evolving Defect Detection Framework for Industrial Photovoltaic Systems

Constraint-Driven Warm-Freeze for Efficient Transfer Learning in Photovoltaic Systems