A Minute-Level High-Frequency Data Acquisition and Lightweight Edge Diagnosis Algorithm for Low-Voltage Distributed Photovoltaic Systems Based on a Temporal Graph Convolutional Network
DOI:
https://doi.org/10.4108/ew.14123Keywords:
Temporal Graph Convolutional Network, Low-Voltage Distributed Photovoltaics, High-Frequency Data Acquisition, Lightweight Processing, Edge DiagnosisAbstract
The performance disparities and operational characteristics among diverse devices within low-voltage distributed photovoltaic (PV) systems lead to variations in fault manifestations. The limited sampling frequency inherent in conventional approaches fails to capture critical fault features and temporal information in a timely manner. Moreover, the presence of periodic fluctuations in PV fault data contributes to persistently high false alarm rates. This paper proposes a high-frequency, minute-level data acquisition framework and a lightweight edge diagnosis algorithm for low-voltage distributed PV systems based on a temporal graph convolutional network. The proposed approach employs intelligent PV edge terminals to enable high-frequency data acquisition from distributed PV generation units. A graphical representation of the low-voltage distributed PV plant is constructed, from which dynamic temporal features of PV generation data are extracted using temporal convolutional layers, while topological correlations among PV devices are captured through graph convolutional layers. This enables the spatiotemporal joint modeling of fault characteristics. To accommodate the computational constraints of edge devices, a customized adaptation of the MobileNet-V3 architecture is introduced. By integrating attention mechanisms and implementing layer pruning, the model is tailored for enhanced performance in photovoltaic fault classification, thereby achieving lightweight edge diagnosis. Experimental results demonstrate that the proposed algorithm accurately diagnoses output voltage fluctuation faults in PV inverters and effectively identifies abnormal phase voltage fluctuation faults. It achieves high precision, recall, and F1 scores across various fault types. The model exhibits rapid training convergence with a low loss function value, satisfying the requirements for lightweight edge diagnosis in low-voltage distributed PV systems.
Downloads
References
[1] Han Jie, Jiang Tong, Liang Hao, et al. Stability Control Strategy for Photovoltaic Grid Connected Systems Considering Weak Grid Impedance[J].Computer Simulation,2025,42(3):117-122.
[2] Wu L , Zhang W , Chen W ,et al.A Multi-Time scale optimal scheduling strategy for integrated energy systems considering the power randomness of wind and photovoltaic[J].Electrical Engineering, 2025, 107(7):9109-9123.
[3] Xu H , Yu C , Chen C ,et al.Impedance Model-based Stability Analysis of Single-stage Grid-connected Inverters Considering PV Panel Characteristics and DC-side Voltage[J].Protection and Control of Modern Power Systems, 2025, 10(4):130-145.
[4] Hanrieder N , Kujawa A , Seychelles A B ,et al.Estimation of maximum photovoltaic cover ratios in greenhouses based on global irradiance data[J].Applied Energy, 2024, 365(7):1-9.
[5] Gupta A K , Singh R K .A review of the state of the art in solar photovoltaic output power forecasting using data-driven models[J].Electrical Engineering, 2025, 107(4):4727-4770.
[6] Chakar J , J.-P. C , Bonnassieux Y ,et al.A Bayesian inference approach to extract circuit model parameters and analyze photovoltaic degradation from power production data[J].Solar Energy, 2024, 274(5):1-9.
[7] Ashfaq I , Uddin Z , Islam N U ,et al.Fault diagnosis and localization in photovoltaic-fed cascaded half-bridge five-level inverter using residual network architecture[J].Electrical Engineering, 2025, 107(10):12861-12884.
[8] Hamza A , Ali Z , Dudley S ,et al.A multi-stage review framework for AI-driven predictive maintenance and fault diagnosis in photovoltaic systems[J].Applied Energy, 2025, 393(9):1-38.
[9] Guo F , Fu W , Wang Y ,et al.Research on fault diagnosis method for photovoltaic array based on model fusion[J].Electrical Engineering, 2025, 107(6):8189-8199.
[10] Chen X , Jiang M , Ding K ,et al.Fault Prediagnosis, Type Identification, and Degree Diagnosis Method of the Photovoltaic Array Based on the Current–Voltage Conversion[J].IEEE Transactions on Power Electronics, 2024, 39(12):16708-16719.
[11] Souhe F G Y , Mbey C F , Kakeu V J F ,et al.Optimized forecasting of photovoltaic power generation using hybrid deep learning model based on GRU and SVM[J].Electrical Engineering, 2024, 106(6):7879-7898.
[12] Yue H , Ali M M , Lin Y ,et al.Ultra-Short-Term Forecasting of Large Distributed Solar PV Fleets Using Sparse Smart Inverter Data[J].IEEE transactions on sustainable energy, 2024,15(3):1968-1980.
[13] Fan Y , Wu H , Lin J ,et al.A distributed photovoltaic short-term power forecasting model based on lightweight AI for edge computing in low-voltage distribution network[J].Renewable Power Generation, IET, 2024, 18(16)3955-3966.
[14] Ye J , Liu Y , Yang L ,et al.A Lightweight Edge Computing Neural Network for Online Photovoltaic Defect Inspection[J].IEEE Transactions on Instrumentation and Measurement, 2025, 74(1):1-14.
[15] Bhowmick S , Mukherjee D , Basu T S ,et al.A Three-Phase Four-Leg Neutral Point Clamped Photovoltaic Inverter With Decoupled Active & Reactive Power Control and DC Link Voltage Ripple Minimization Under Unbalanced Grid Operation[J].IEEE Transactions on Power Electronics, 2025, 40(6):1-14.
[16] Debanjan M , Sourav M .Efficient operation of photovoltaic-interfaced reduced switch 11-level inverter using adaptive swarm-based metaheuristic[J].Electrical engineering, 2024, 106(1):521-551.
[17] Khazaeefar S , Valizadeh M , Sarvenoee A K .An improved Z-source multi-level inverter scheme for grid-connected photovoltaic systems[J].Electrical Engineering, 2025, 107(6):8045-8058.
[18] Du X , Huang Q , Yan Z ,et al.Underwater SLAM front-end matching method based on graph convolutional neural network[J].Ocean Engineering, 2025, 331(1):1-13
[19] Li J , Ren X , Zhang F ,et al.Multi-timescale photovoltaic station power prediction based on Reformer model[J].Energy, 2025, 327(7):1-15.
[20] Zhang Y , Hao Q , Zheng W ,et al.User similarity-based graph convolutional neural network for shilling attack detection[J].Applied Intelligence, 2025, 55(5):1-14.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Xuekai Hu, Shiwei Xue, Xingzhi Chang, Kun Jiang, Da Zhang
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open-access article distributed under the terms of the Creative Commons Attribution CC BY 4.0 license, which permits unlimited use, distribution, and reproduction in any medium so long as the original work is properly cited.
