Early fault detection and diagnosis of grid-connected photovoltaic systems (GCPS) is imperative to improve their performance and reliability. Low-cost edge devices have emerged as innovative solutions for real-time monitoring, reducing latency, and improving response times. In this work, a lightweight Convolutional Neural Network (CNN) is designed and fine-tuned using Energy Valley Optimizer (EVO) for fault diagnosis. The CNN input consists of two-dimensional scalograms generated using Continuous Wavelet Transform (CWT). The proposed diagnosis technique demonstrated superior performance compared to benchmark architectures, namely MobileNet, NASNetMobile, and InceptionV3, achieving higher test accuracies and lower losses on binary and multi-fault classification tasks on balanced, unbalanced, and noisy datasets. Further, a quantitative comparison is conducted with similar recent studies. The obtained results indicate good performance and high reliability of the proposed fault diagnosis method.

Applied Automation and Industrial Diagnostics Laboratory LAADI University of Djelfa Djelfa Algeria

Center for Information Analytical and Technical Support of Nuclear Power Facilities Monitoring of the National Academy of Sciences of Ukraine Akademika Palladina Avenue 34 A Kyiv Ukraine

Department of Electrical Engineering College of Engineering Taif University 21944 Taif Saudi Arabia

Department of Electrical Engineering Faculty of Science and Technology University of Djelfa Djelfa Algeria

Department of Electrical Engineering Graphic Era Dehradun 248002 India

Department of Theoretical Electrical Engineering and Diagnostics of Electrical Equipment Institute of Electrodynamics National Academy of Sciences of Ukraine Peremogy 56 Kyiv 57 03680 Ukraine

Graphic Era Hill University Dehradun 248002 India

Hourani Center for Applied Scientific Research Al Ahliyya Amman University Amman Jordan

Telecommunications and Smart Systems Laboratory University of Djelfa PO Box 3117 17000 Djelfa Algeria

See more in PubMed

Paramati, S. R., Shahzad, U. & Doğan, B. The role of environmental technology for energy demand and energy efficiency: Evidence from OECD countries. Renew. Sustain. Energy Rev.153, 111735. 10.1016/j.rser.2021.111735 (2022).10.1016/j.rser.2021.111735 DOI

Kober, T. et al. Global energy perspectives to 2060–WEC’s World Energy Scenarios 2019. Energ. Strat. Rev.31, 100523. 10.1016/j.esr.2020.100523 (2020).10.1016/j.esr.2020.100523 DOI

Bhattarai, U., Maraseni, T. & Apan, A. Assay of renewable energy transition: A systematic literature review. Sci. Total Environ.833, 155159. 10.1016/j.scitotenv.2022.155159 (2022). 10.1016/j.scitotenv.2022.155159 PubMed DOI

Kijo-Kleczkowska, A., Bruś, P. & Więciorkowski, G. Profitability analysis of a photovoltaic installation: A case study. Energy261, 125310. 10.1016/j.energy.2022.125310 (2022).10.1016/j.energy.2022.125310 DOI

Ahmad, M., Dai, J., Mehmood, U. & Abou, Houran M. Renewable energy transition, resource richness, economic growth, and environmental quality: Assessing the role of financial globalization. Renew. Energy216, 119000. 10.1016/j.renene.2023.119000 (2023).10.1016/j.renene.2023.119000 DOI

Greim, P., Solomon, A. A. & Breyer, C. Assessment of lithium criticality in the global energy transition and addressing policy gaps in transportation. Nat. Commun.11(1), 4570. 10.1038/s41467-020-18402-y (2020). 10.1038/s41467-020-18402-y PubMed DOI PMC

Xie, P. & Jamaani, F. Does green innovation, energy productivity and environmental taxes limit carbon emissions in developed economies: Implications for sustainable development. Struct. Change Econ. Dyn.63, 66–78. 10.1016/j.strueco.2022.09.002 (2022).10.1016/j.strueco.2022.09.002 DOI

Nagarajan, K. et al. Optimizing dynamic economic dispatch through an enhanced Cheetah-inspired algorithm for integrated renewable energy and demand-side management. Sci. Rep.14(1), 3091. 10.1038/s41598-024-53688-8 (2024). 10.1038/s41598-024-53688-8 PubMed DOI PMC

Korkmaz, D. & Acikgoz, H. An efficient fault classification method in solar photovoltaic modules using transfer learning and multi-scale convolutional neural network. Eng. Appl. Artif. Intell.113, 104959. 10.1016/j.engappai.2022.104959 (2022).10.1016/j.engappai.2022.104959 DOI

Mustafa, Z., Awad, A. S., Azzouz, M. & Azab, A. Fault identification for photovoltaic systems using a multi-output deep learning approach. Exp. Syst. Appl.211, 118551. 10.1016/j.eswa.2022.118551 (2023).10.1016/j.eswa.2022.118551 DOI

IRENA (2023), Renewable energy statistics 2023, International Renewable Energy Agency, Abu Dhabi. https://mc-cd8320d4-36a1-40ac-83cc-3389-cdn-endpoint.azureedge.net/ /media/Files/IRENA/Agency/Publication/2023/Jul/IRENA_Renewable_energy_statistics_2023.pdf?rev=7b2f44c294b84cad9a27fc24949d2134

Amiri, A., Samet, H. & Ghanbari, T. Recurrence plots based method for detecting series arc faults in photovoltaic systems. IEEE Transact. Indus. Electron.69(6), 6308–15. 10.1109/TIE.2021.3095819 (2021).10.1109/TIE.2021.3095819 DOI

Mellit, A., Tina, G. M. & Kalogirou, S. A. Fault detection and diagnosis methods for photovoltaic systems: A review. Renew. Sustain. Energy Rev.91, 1–7. 10.1016/j.rser.2018.03.062 (2018).10.1016/j.rser.2018.03.062 DOI

Hong, Y. Y. & Pula, R. A. Diagnosis of photovoltaic faults using digital twin and PSO-optimized shifted window transformer. Appl. Soft Comput.150, 111092. 10.1016/j.asoc.2023.111092 (2024).10.1016/j.asoc.2023.111092 DOI

Wang, J., Gao, D., Zhu, S., Wang, S. & Liu, H. Fault diagnosis method of photovoltaic array based on support vector machine. Energy Sour. Part a Recov. Util. Environ. Eff.45(2), 5380–95. 10.1080/15567036.2019.1671557 (2023).10.1080/15567036.2019.1671557 DOI

Ladel, A. A., Outbib, R., Benzaouia, A., Ouladsine, M. Simultaneous switched model-based fault detection and MPPT for photovoltaic systems. In: 2022 10th International Conference on Systems and Control (ICSC). IEEE, 2022. p. 410-415. 10.1109/ICSC57768.2022.9993833

Bouyeddou, B., Harrou, F., Taghezouit, B., Sun, Y. & Hadj, Arab A. Improved semi-supervised data-mining-based schemes for fault detection in a grid-connected photovoltaic system. Energies15(21), 7978. 10.3390/en15217978 (2022).10.3390/en15217978 DOI

El-Banby, G. M., Moawad, N. M., Abouzalm, B. A., Abouzaid, W. F. & Ramadan, E. A. Photovoltaic system fault detection techniques: A review. Neural Comput. Appl.35(35), 24829–42. 10.1007/s00521-023-09041-7 (2023).10.1007/s00521-023-09041-7 DOI

Bakdi, A., Bounoua, W., Guichi, A. & Mekhilef, S. Real-time fault detection in PV systems under MPPT using PMU and high-frequency multi-sensor data through online PCA-KDE-based multivariate KL divergence. Int. J. Electr. Power Energy Syst.125, 106457. 10.1016/j.ijepes.2020.106457 (2021).10.1016/j.ijepes.2020.106457 DOI

Tsanakas, J. A., Ha, L. & Buerhop, C. Faults and infrared thermographic diagnosis in operating c-Si photovoltaic modules: A review of research and future challenges. Renew. Sustain. Energy Rev.62, 695–709. 10.1016/j.rser.2016.04.079 (2016).10.1016/j.rser.2016.04.079 DOI

Herraiz, Á. H., Marugán, A. P. & Márquez, F. P. Photovoltaic plant condition monitoring using thermal images analysis by convolutional neural network-based structure. Renew. Energy153, 334–48. 10.1016/j.renene.2020.01.148 (2020).10.1016/j.renene.2020.01.148 DOI

Sizkouhi, A. M., Aghaei, M. & Esmailifar, S. M. A deep convolutional encoder-decoder architecture for autonomous fault detection of PV plants using multi-copters. Sol. Energy223, 217–28. 10.1016/j.solener.2021.05.029 (2021).10.1016/j.solener.2021.05.029 DOI

Gu, J. C., Lai, D. S., Wang, J. M., Huang, J. J. & Yang, M. T. Design of a DC series arc fault detector for photovoltaic system protection. IEEE Trans. Indus. Appl.55(3), 2464–71. 10.1109/TIA.2019.2894992 (2019).10.1109/TIA.2019.2894992 DOI

Li, B., Delpha, C., Migan-Dubois, A. & Diallo, D. Fault diagnosis of photovoltaic panels using full I-V characteristics and machine learning techniques. Energy Convers. Manag.248, 114785. 10.1016/j.enconman.2021.114785 (2021).10.1016/j.enconman.2021.114785 DOI

Mellit, A. & Kalogirou, S. Artificial intelligence and internet of things to improve efficacy of diagnosis and remote sensing of solar photovoltaic systems: Challenges, recommendations and future directions. Renew. Sustain. Energy Rev.143, 110889. 10.1016/j.rser.2021.110889 (2021).10.1016/j.rser.2021.110889 DOI

Amiri, A. F., Oudira, H., Chouder, A. & Kichou, S. Faults detection and diagnosis of PV systems based on machine learning approach using random forest classifier. Energy Convers. Manag.301, 118076. 10.1016/j.enconman.2024.118076 (2024).10.1016/j.enconman.2024.118076 DOI

Yu, W., Liu, G., Zhu, L. & Yu, W. Convolutional neural network with feature reconstruction for monitoring mismatched photovoltaic systems. Sol. Energy212, 169–77. 10.1016/j.solener.2020.09.026 (2020).10.1016/j.solener.2020.09.026 DOI

Khan, K. et al. Data-driven green energy extraction: Machine learning-based MPPT control with efficient fault detection method for the hybrid PV-TEG system. Energy Rep.9, 3604–23. 10.1016/j.egyr.2023.02.047 (2023).10.1016/j.egyr.2023.02.047 DOI

Chen, Z., Chen, Y., Wu, L., Cheng, S. & Lin, P. Deep residual network based fault detection and diagnosis of photovoltaic arrays using current-voltage curves and ambient conditions. Energy Convers. Manag.198, 111793. 10.1016/j.enconman.2019.111793 (2019).10.1016/j.enconman.2019.111793 DOI

Chen, S., Yu, J. & Wang, S. One-dimensional convolutional auto-encoder-based feature learning for fault diagnosis of multivariate processes. J. Process Control87, 54–67. 10.1016/j.jprocont.2020.01.004 (2020).10.1016/j.jprocont.2020.01.004 DOI

Gao, W. & Wai, R. J. A novel fault identification method for photovoltaic array via convolutional neural network and residual gated recurrent unit. IEEE Access8, 159493–510. 10.1109/ACCESS.2020.3020296 (2020).10.1109/ACCESS.2020.3020296 DOI

Aziz, F. et al. A novel convolutional neural network-based approach for fault classification in photovoltaic arrays. IEEE Access8, 41889–904. 10.1109/ACCESS.2020.2977116 (2020).10.1109/ACCESS.2020.2977116 DOI

Lu, X. et al. Fault diagnosis for photovoltaic array based on convolutional neural network and electrical time series graph. Energy Convers. Manag.196, 950–65. 10.1016/j.enconman.2019.06.062 (2019).10.1016/j.enconman.2019.06.062 DOI

Lu, S., Sirojan, T., Phung, B. T., Zhang, D. & Ambikairajah, E. DA-DCGAN: An effective methodology for DC series arc fault diagnosis in photovoltaic systems. IEEE Access7, 45831–40. 10.1109/ACCESS.2019.2909267 (2019).10.1109/ACCESS.2019.2909267 DOI

Liu, G., Zhu, L., Yu, W. & Yu, W. Image formation, deep learning, and physical implication of multiple time-series one-dimensional signals: Method and application. IEEE Trans. Indus. Inf.17(7), 4566–74 (2020).10.1109/TII.2020.3018496 DOI

Hong, Y. Y. & Pula, R. A. Diagnosis of PV faults using digital twin and convolutional mixer with LoRa notification system. Energy Rep.9, 1963–76. 10.1016/j.egyr.2023.01.011 (2023).10.1016/j.egyr.2023.01.011 DOI

Korkmaz, D. & Acikgoz, H. An efficient fault classification method in solar photovoltaic modules using transfer learning and multi-scale convolutional neural network. Eng. Appl. Artif. Intell.113, 104959. 10.1016/j.engappai.2022.104959 (2022).10.1016/j.engappai.2022.104959 DOI

Lin, P. et al. Compound fault diagnosis model for Photovoltaic array using multi-scale SE-ResNet. Sustain. Energy Technol. Assess.50, 101785. 10.1016/j.seta.2021.101785 (2022).10.1016/j.seta.2021.101785 DOI

Kellil, N., Aissat, A. & Mellit, A. Fault diagnosis of photovoltaic modules using deep neural networks and infrared images under Algerian climatic conditions. Energy263, 125902. 10.1016/j.energy.2022.125902 (2023).10.1016/j.energy.2022.125902 DOI

Pan, P., Mandal, R. K. & Redoy AkandaRahman, M. M. Fault classification with convolutional neural networks for microgrid systems. Int. Trans. Electr. Energy Syst.20(1), 8431450. 10.1155/2022/8431450 (2022).10.1155/2022/8431450 DOI

Latoui, A. & Daachi, M. E. Real-time monitoring of partial shading in large PV plants using Convolutional Neural Network. Sol. Energy253, 428–38. 10.1016/j.solener.2023.02.041 (2023).10.1016/j.solener.2023.02.041 DOI

Qu, J., Sun, Q., Qian, Z., Wei, L. & Zareipour, H. Fault diagnosis for PV arrays considering dust impact based on transformed graphical features of characteristic curves and convolutional neural network with CBAM modules. Appl. Energy355, 122252. 10.1016/j.apenergy.2023.122252 (2024).10.1016/j.apenergy.2023.122252 DOI

Gong, B., An, A., Shi, Y. & Zhang, X. Fast fault detection method for photovoltaic arrays with adaptive deep multiscale feature enhancement. Appl. Energy353, 122071. 10.1016/j.apenergy.2023.122071 (2024).10.1016/j.apenergy.2023.122071 DOI

Bakdi, A., Guichi, A., Mekhilef, S. & Bounoua, W. GPVS-Faults: Experimental Data for fault scenarios in grid-connected PV systems under MPPT and IPPT modes. Mendeley10.17632/n76t439f65.1 (2020).10.17632/n76t439f65.1 DOI

Howard, A. G. et al. Mobilenets: Efficient convolutional neural networks for mobile vision applications. arX. Prepr. arX.10.48550/arXiv.1704.04861 (2017).10.48550/arXiv.1704.04861 DOI

Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A. Going deeper with convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition 2015 10.48550/arXiv.1409.4842

Zoph, B., Vasudevan, V., Shlens, J., Le, Q. V. Learning transferable architectures for scalable image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition 2018 (pp. 8697-8710). 10.48550/arXiv.1707.07012

Deng, J. et al. Imagenet: A large-scale hierarchical image database. IEEE Conf. Comput. Vis. Pattern Recognit.2009, 248–255 (2009).

Li, Z., Liu, F., Yang, W., Peng, S. & Zhou, J. A survey of convolutional neural networks: Analysis, applications, and prospects. IEEE Trans. Neural Netw. Learn. Syst.33(12), 6999–7019. 10.1109/TNNLS.2021.3084827 (2021).10.1109/TNNLS.2021.3084827 PubMed DOI

Ayadi, W., Elhamzi, W., Charfi, I. & Atri, M. Deep CNN for brain tumor classification. Neural Process. Lett.53(1), 671–700. 10.1007/s11063-020-10398-2 (2021).10.1007/s11063-020-10398-2 DOI

Alzubaidi, L. et al. Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions. J. Big Data8, 1–74. 10.1186/s40537-021-00444-8 (2021). 10.1186/s40537-021-00444-8 PubMed DOI PMC

Wang, M. H., Hung, C. C., Lu, S. D., Lin, Z. H. & Kuo, C. C. Fault diagnosis for PV modules based on alexnet and symmetrized dot pattern. Energies16(22), 7563. 10.3390/en16227563 (2023).10.3390/en16227563 DOI

Dileep, P., Das, D., Bora, P. K. Dense layer dropout based CNN architecture for automatic modulation classification. In 2020 National conference on communications (NCC) 2020 Feb 21 (pp. 1–5). IEEE. 10.1109/NCC48643.2020.9055989

Memon, S. A. et al. A machine-learning-based robust classification method for PV panel faults. Sensors22(21), 8515. 10.3390/s22218515 (2022). 10.3390/s22218515 PubMed DOI PMC

Azizi, M., Aickelin, U., Khorshidi, H. A. & Baghalzadeh, S. M. Energy valley optimizer: A novel metaheuristic algorithm for global and engineering optimization. Sci. Rep.13(1), 226. 10.1038/s41598-022-27344-y (2023). 10.1038/s41598-022-27344-y PubMed DOI PMC

Prediction of power conversion efficiency parameter of inverted organic solar cells using artificial intelligence techniques