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.
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
Fig. 9 : Spectrograms of representative operating conditions for nuisance trip evaluation.
Fig. 10 : Screenshots of some test cases of the proposed AFCI method.
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 Δ 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.
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.
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 identifies abnormal behavior in machines, sensors, infrastructure, software, and autonomous systems before it causes harm or disruption.
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.
Xiaolu Chen, Chenghao Huang, Yanru Zhang +1
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
Reliable photovoltaic (PV) power generation requires timely detection of module defects that may reduce energy yield, accelerate degradation, and increase lifecycle operation and maintenance costs during field operation. Electroluminescence (EL) imaging has therefore been widely adopted for PV module inspection. However, automated defect detection in real operational environments remains challenging due to heterogeneous module geometries, low-resolution imaging conditions, subtle defect morphology, long-tailed defect distributions, and continual data shifts introduced by evolving inspection and labeling processes. These factors significantly limit the robustness and long-term maintainability of conventional deep-learning inspection pipelines. To address these challenges, this paper proposes SEPDD, a Self-Evolving Photovoltaic Defect Detection framework designed for evolving industrial PV inspection scenarios. SEPDD integrates automated model optimization with a continual self-evolving learning mechanism, enabling the inspection system to progressively adapt to distribution shifts and newly emerging defect patterns during long-term deployment. Experiments conducted on both a public PV defect benchmark and a private industrial EL dataset demonstrate the effectiveness of the proposed framework. Both datasets exhibit severe class imbalance and significant domain shift. SEPDD achieves a leading mAP50 of 91.4% on the public dataset and 49.5% on the private dataset. It surpasses the autonomous baseline by 14.8% and human experts by 4.7% on the public dataset, and by 4.9% and 2.5%, respectively, on the private dataset.
Haoyu He, Yu Duan, Wenzhen Liu +5
EcoFlow Inc, Shenzhen, China · School of Electrical Engineering, Xi’an Jiaotong University, Xi’an, China
Detecting cyberattacks in photovoltaic (PV) monitoring and MPPT control signals requires models that are robust to bias, drift, and transient spikes, yet lightweight enough for resource-constrained edge controllers. While deep learning outperforms traditional physics-based diagnostics and handcrafted features, standard fine-tuning is computationally prohibitive for edge devices. Furthermore, existing Parameter-Efficient Fine-Tuning (PEFT) methods typically apply uniform adaptation or rely on expensive architectural searches, lacking the flexibility to adhere to strict hardware budgets. To bridge this gap, we propose Constraint-Driven Warm-Freeze (CDWF), a budget-aware adaptation framework. CDWF leverages a brief warm-start phase to quantify gradient-based block importance, then solves a constrained optimization problem to dynamically allocate full trainability to high-impact blocks while efficiently adapting the remaining blocks via Low-Rank Adaptation (LoRA). We evaluate CDWF on standard vision benchmarks (CIFAR-10/100) and a novel PV cyberattack dataset, transferring from bias pretraining to drift and spike detection. The experiments demonstrate that CDWF retains 90 to 99% of full fine-tuning performance while reducing trainable parameters by up to 120x. These results establish CDWF as an effective, importance-guided solution for reliable transfer learning under tight edge constraints.
Yasmeen Saeed, Ahmed Sharshar, Mohsen Guizani
Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates