Applied Chemical Engineering

Smart fault isolation and diagnosis in PV setups utilizing random forest classifiers

Cherifa KARA MOSTEFA KHELIL

Electrical Engineering Department, Djillali Bounaama-Khemis Miliana University, Thniet El Had Street, Khemis Miliana, Ain Defla, 44001, Algeria ; Electronics Department, SET Laboratory, Saad Dahleb Blida 1University, BP 270 Blida, 09000, Algeria

Ihssen HAMZAOUI

Electrical Engineering Department, Djillali Bounaama-Khemis Miliana University, Thniet El Had Street, Khemis Miliana, Ain Defla, 44001, Algeria ; Acoustics and civil engineering laboratory, Djillali Bounaama-Khemis Miliana University, Thniet El Had Street, Khemis Miliana, Ain Defla, 44001, Algeria

Fatma Zohra BAOUCHE

Electrical Engineering Department, Djillali Bounaama-Khemis Miliana University, Thniet El Had Street, Khemis Miliana, Ain Defla, 44001, Algeria ; LESI laboratory, Djillali Bounaama-Khemis Miliana University, Thniet El Had Street, Khemis Miliana, Ain Defla, 44001, Algeria

Mohamed Nadjib BENALLAL

Electrical Engineering Department, Djillali Bounaama-Khemis Miliana University, Thniet El Had Street, Khemis Miliana, Ain Defla, 44001, Algeria

Badia AMROUCHE

Electronics Department, SET Laboratory, Saad Dahleb Blida 1University, BP 270 Blida, 09000, Algeria ; Acoustics and civil engineering laboratory, Djillali Bounaama-Khemis Miliana University, Thniet El Had Street, Khemis Miliana, Ain Defla, 44001, Algeria

Kamel KARA

Electronics Department, SET Laboratory, Saad Dahleb Blida 1University, BP 270 Blida, 09000, Algeria

DOI: https://doi.org/10.59429/ace.v8i2.5659

Keywords: PV setup; faults; isolation; diagnosis; machine learning; random forest classifier

---

Abstract

In the modern era, there has been a growing focus among researchers on the transition from fossil fuels to renewable energy sources, particularly photovoltaic (PV) energy, which is gaining popularity worldwide. As the development and installation of PV systems accelerate globally, it is essential to address the various faults and failures these systems may encounter. Consequently, fault diagnosis and evaluation have emerged as critical areas of study aimed at enhancing performance, improving system efficiency, and reducing maintenance costs and repair times. This paper proposes the use of a Random Forest classifier (RF) for diagnosing short circuit and open circuit faults in PV systems. The classifier is trained using machine learning algorithms to accurately identify different fault types based on real measured data from an experimental PV setup. This data encompasses weather conditions such as cell temperature and solar irradiation, as well as system parameters like current and voltage at the maximum power point, alongside performance metrics. The Random Forest classifier serves as a proactive tool for maintenance and fault diagnosis in PV systems, contributing to better overall performance and reliability. Testing on real-world data from a PV system demonstrates that this approach achieves remarkable accuracy in fault diagnosis, with a precision of 100% for current classification and around 97% for voltage classification, all within a few seconds for each parameter.

---

References

[1]. Kara Mostefa Khelil, C., Amrouche, B., Benyoucef, A. S., Kara, K and Chouder, A. New Intelligent Fault Diagnosis (IFD) Approach for grid-connected photovoltaic systems. J Energy. 2020;211:118591. DOI: 10.1016/j.energy.2020.118591

[2]. Kara Mostefa Khelil, C., Amrouche, B., Kara, K and Chouder, A. The impact of the ANN’s choice on PV systems diagnosis quality. j.enconman. 2021;240: 114278. DOI: 10.1016/j.enconman.2021.114278

[3]. Kara Mostefa Khelil, C., Amrouche, B and Kara K. Fault detection and diagnosis of GCPV systems using bayesian neural network. In Journal of Physics: Conference Series. IOP Publishing. 2022 Mar 1;2208(1):012019. DOI: 10.1088/1742-6596/2208/1/012019

[4]. Li B, Delpha C, Diallo D, Migan-Dubois A. Application of Artificial Neural Networks to photovoltaic fault detection and diagnosis: A review Ren & Sust Ener Rev. 2021;138:110512. DOI: 10.1016/j.rser.2020.110512

[5]. Islam M, R R Masud, A Md Tofael, I A. K. M. Kamrul and Tlemçani M. Artificial Intelligence in Photovoltaic Fault Identification and Diagnosis: A Systematic Review. Energies.2023;16:7417. DOI: 10.3390/en16217417

[6]. Amiri A F, Kichou S, Oudira H, Chouder A and S Santiago. Fault Detection and Diagnosis of a Photovoltaic System Based on Deep Learning Using the Combination of a Convolutional Neural Network (CNN) and Bidirectional Gated Recurrent Unit (Bi-GRU). Sustainability. 2024;16:1012. DOI: 10.3390/su16031012

[7]. Arévalo P, Cano A, Darío B, Jurado F .Fault analysis in clustered microgrids utilizing SVM-CNN and differential protection. j.asoc.2024;164:112031. DOI: 10.1016/j.asoc.2024.112031

[8]. Kara Mostefa Khelil, C., Kara, K and Chouder, A. Fault detection of the photovoltaic system by artificial neural networks. CEEE. 2017; 4:60-65.

[9]. Kara Mostefa Khelil, C., Amrouche, B., Kara, K and Chouder, A. Newfound Intelligent solution for grid connected PV systems diagnosis based on CANFIS algorithm. Tob Regul Sci. 2023; 9(1):3809-3844. DOI: doi.org/10.18001/TRS.9.1.286

[10]. Madeti, S.R and Singh, S.N. Modeling of PV system based on experimental data for fault detection using kNN method. Sol Energy .2018;173:139–51. DOI: 10.1016/j.solener.2018.07.038

[11]. Godfrey B Z, Kara Mostefa Khelil C, Godfrey M G, Taane Z. Identification of PV Fault Classes Using Intelligent Method KNN (K-Nearest Neighbours). IJRSI. 2024;10:1108093. DOI: 10.51244/IJRSI.2024.1108093

[12]. Liao Z, Wang D, Tang L, Ren J, Liu Z. A Heuristic diagnostic method for a PV System: Triple-Layered Particle Swarm Optimization–Back-Propagation Neural Network. Energies. 2017;10: 226. https://doi.org/10.3390/en10020226

[13]. Liu, Y., Zhang, L., & Zhang, L [Random Forest with Class-Balanced Decision Trees for Multi-class Classification. IEEE Transactions on Neural Networks and Learning Systems. 2019; 30(8):2286-2297.

[14]. Somesh, L., Chakravarty, A and Maiti, A. Fault Diagnosis in Power Transmission Line using Decision Tree and Random Forest Classifier. 2022 IEEE 6th International Conference on Condition Assessment Techniques in Electrical Systems (CATCON). 17-19 December 2022.

[15]. Qiang Wang, Thanh-Tung Nguyen, et al An efficient random forests algorithm for high dimensional data classification. Advances in Data Analysis and Classification. 2018; 12: 953–972. DOI: 10.1007/s11634-018-0318-1

[16]. 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. j.enconman. 2024; 301: 18076. DOI: 10.1016/j.enconman.2024.118076

[17]. Zhi-Hua Zhou.(2025). Ensemble Methods Foundation and algorithms second edition. Taylor and Francis group. ISBN: 978-1-032-96061-6. DOI:10.1201/9781003587774.