Diagnosing faults in a photovoltaic system using the Extra Trees ensemble algorithm

Guy M. Toche Tchio; Joseph Kenfack; Joseph Voufo; Yves Abessolo Mindzie; Blaise Fouedjou Njoya; Sanoussi S. Ouro-Djobo; Guy M. Toche Tchio; Joseph Kenfack; Joseph Voufo; Yves Abessolo Mindzie; Blaise Fouedjou Njoya; Sanoussi S. Ouro-Djobo

doi:10.3934/energy.2024034

AIMS Energy

2024, Volume 12, Issue 4: 727-750. doi: 10.3934/energy.2024034

Previous Article Next Article

Research article Topical Sections

Diagnosing faults in a photovoltaic system using the Extra Trees ensemble algorithm

1.
Regional Center of Excellence for Electricity Management (CERME), University of Lomé, Togo
2.
Solar Energy Laboratory, Department of Physics, Faculty of Sciences, University of Lomé, Togo
3.
Laboratory on Small hydropower and hybrid systems, National Advanced School of Engineering of Yaoundé (NASEY), University of Yaoundé 1, Cameroon

Received: 26 February 2024 Revised: 31 May 2024 Accepted: 06 June 2024 Published: 02 July 2024

The application of machine learning techniques for monitoring and diagnosing faults in photovoltaic (PV) systems has been shown to enhance the reliability of PV power generation. This research introduced a novel machine learning classifier for fault diagnosis in PV systems, utilizing an ensemble algorithm known as extra trees (ETC). The study initially proposed a system with two PV modules and developed a low-cost Arduino-based data logger to gather data from the PV system in free-fault and faulty conditions. Subsequently, the study evaluated six other advanced classifiers for fault diagnosis in PV systems, namely logistic regression (LR), k-nearest neighbor (kNN), support vector machine (SVM), decision tree (DT), AdaBoost, and random forest (RF) models using the collected data from the proposed PV system. The assessment of the various models' performance indicated that the extra trees model exhibits superior classification capabilities for partial shading (PS), open circuit (OCF), partial shading with bypass diode disconnected (PSBD), and combined partial shading with bypass diode disconnected plus open circuit (PSBDOC) faults. The results demonstrated that the new ETC classifier achieves an accuracy of 92%, surpassing the 91%, 87%, 7%, and 59% accuracy of the RF, DT, kNN, and LR classifiers, respectively. This highlights the effectiveness of the extra trees model in enhancing fault detection and classification by distinguishing between open circuits and twin faults. Consequently, these results can be utilized to develop advanced diagnostic tools for photovoltaic systems, thereby improving the reliability of solar technology and accelerating the rate of installation.
- photovoltaics,
- diagnosis,
- extra trees,
- fault,
- data acquisition system
Citation: Guy M. Toche Tchio, Joseph Kenfack, Joseph Voufo, Yves Abessolo Mindzie, Blaise Fouedjou Njoya, Sanoussi S. Ouro-Djobo. Diagnosing faults in a photovoltaic system using the Extra Trees ensemble algorithm[J]. AIMS Energy, 2024, 12(4): 727-750. doi: 10.3934/energy.2024034

Related Papers:

Abstract

The application of machine learning techniques for monitoring and diagnosing faults in photovoltaic (PV) systems has been shown to enhance the reliability of PV power generation. This research introduced a novel machine learning classifier for fault diagnosis in PV systems, utilizing an ensemble algorithm known as extra trees (ETC). The study initially proposed a system with two PV modules and developed a low-cost Arduino-based data logger to gather data from the PV system in free-fault and faulty conditions. Subsequently, the study evaluated six other advanced classifiers for fault diagnosis in PV systems, namely logistic regression (LR), k-nearest neighbor (kNN), support vector machine (SVM), decision tree (DT), AdaBoost, and random forest (RF) models using the collected data from the proposed PV system. The assessment of the various models' performance indicated that the extra trees model exhibits superior classification capabilities for partial shading (PS), open circuit (OCF), partial shading with bypass diode disconnected (PSBD), and combined partial shading with bypass diode disconnected plus open circuit (PSBDOC) faults. The results demonstrated that the new ETC classifier achieves an accuracy of 92%, surpassing the 91%, 87%, 7%, and 59% accuracy of the RF, DT, kNN, and LR classifiers, respectively. This highlights the effectiveness of the extra trees model in enhancing fault detection and classification by distinguishing between open circuits and twin faults. Consequently, these results can be utilized to develop advanced diagnostic tools for photovoltaic systems, thereby improving the reliability of solar technology and accelerating the rate of installation.

References

[1]	International Energy Agency. Renewable energy market update—June 2023. Available from: www.iea.org/t & c/.
[2]	Hong YY, Pula RA (2023) Diagnosis of PV faults using digital twin and convolutional mixer with LoRa notification system. Energy Rep 9: 1963–1976. https://doi.org/10.1016/j.egyr.2023.01.011 doi: 10.1016/j.egyr.2023.01.011
[3]	Harrou F, Saidi A, Sun Y, et al. (2021) Monitoring; of photovoltaic systems using improved kernel-based learning schemes. IEEE J Photovoltaics 11: 806–818. https://doi.org/10.1109/JPHOTOV.2021.3057169 doi: 10.1109/JPHOTOV.2021.3057169
[4]	Firth SK, Lomas KJ, Rees SJ (2010) A simple model of PV system performance and its use in fault detection. Sol Energy 84: 624–635. https://doi.org/10.1016/j.solener.2009.08.004 doi: 10.1016/j.solener.2009.08.004
[5]	Bendary AF, Abdelaziz AY, Ismail MM, et al. (2021) Proposed anfis based approach for fault tracking, detection, clearing and rearrangement for photovoltaic system. Sensors 21: 2269. https://doi.org/10.3390/s21072269 doi: 10.3390/s21072269
[6]	Hussain I, Khalil IU, Islam A, et al. (2022) Unified fuzzy logic based approach for detection and classification of PV faults using I-V trend line. Energies 15: 5106. https://doi.org/10.3390/en15145106 doi: 10.3390/en15145106
[7]	Mellit A, Tina GM, Kalogirou SA (2018) Fault detection and diagnosis methods for photovoltaic systems: A review. Renewable Sustainable Energy Rev 91: 1–17. https://doi.org/10.1016/j.rser.2018.03.062 doi: 10.1016/j.rser.2018.03.062
[8]	Boubaker S, Kamel S, Ghazouani N, et al. (2023) Assessment of machine and deep learning approaches for fault diagnosis in photovoltaic systems using infrared thermography. Remote Sens 15: 1686. https://doi.org/10.3390/rs15061686 doi: 10.3390/rs15061686
[9]	Osmani K, Haddad A, Lemenand T, et al. (2023) A critical review of PV systems' faults with the relevant detection methods. Energy Nexus 12: 100257. https://doi.org/10.1016/j.nexus.2023.100257 doi: 10.1016/j.nexus.2023.100257
[10]	Taghezouit B, Harrou F, Sun Y, et al. (2024) Model-based fault detection in photovoltaic systems: A comprehensive review and avenues for enhancement. Results Eng, 21. https://doi.org/10.1016/j.rineng.2024.101835
[11]	Zhao J, Sun Q, Zhou N, et al. (2020) A photovoltaic array fault diagnosis method considering the photovoltaic output deviation characteristics. Int J Photoenergy. https://doi.org/10.1155/2020/2176971
[12]	Garoudja E, Harrou F, Sun Y, et al. (2017) Statistical fault detection in photovoltaic systems. Sol Energy 150: 485–499. https://doi.org/10.1016/j.solener.2017.04.043 doi: 10.1016/j.solener.2017.04.043
[13]	Akram MN, Lotfifard S (2015) Modeling and health monitoring of DC side of photovoltaic array. IEEE Trans Sustainable Energy 6: 1245–1253. https://doi.org/10.1109/TSTE.2015.2425791 doi: 10.1109/TSTE.2015.2425791
[14]	Chine W, Mellit A, Lughi V, et al. (2016) A novel fault diagnosis technique for photovoltaic systems based on artificial neural networks: Renewable Energy 90: 501–512. https://doi.org/10.1016/j.renene.2016.01.036 doi: 10.1016/j.renene.2016.01.036
[15]	Dhimish M, Tyrrell AM (2023) Photovoltaic bypass diode fault detection using artificial neural networks. IEEE Trans Instrum Meas, 72. https://doi.org/10.1109/TIM.2023.3244230
[16]	Kumar R, Sharma N, Chahat, et al. (2024) Prediction of jet impingement solar thermal air collector thermohydraulic performance using soft computing techniques. Case Stud Therm Eng, 55. https://doi.org/10.1016/j.csite.2024.104144
[17]	Madeti SR, Singh SN (2018) Modeling of PV system based on experimental data for fault detection using kNN method. Sol Energy 173: 139–151. https://doi.org/10.1016/j.solener.2018.07.038 doi: 10.1016/j.solener.2018.07.038
[18]	Eskandari A, Milimonfared J, Aghaei M (2020) Optimization of SVM classifier using grid search method for line-line fault detection of photovoltaic systems. IEEE Photovoltaic Specialists Conference, 1134–1137. https://doi.org/10.1109/PVSC45281.2020.9300846
[19]	Wang J, Gao D, Zhu S, et al. (2019) Fault diagnosis method of photovoltaic array based on support vector machine. Energy Sources 45: 5380–5395. https://doi.org/10.1080/15567036.2019.1671557 doi: 10.1080/15567036.2019.1671557
[20]	Harrou F, Dairi A, Taghezouit B, et al. (2018) An unsupervised monitoring procedure for detecting anomalies in photovoltaic systems using a one-class Support Vector Machine. Sol Energy 179: 48–58. https://doi.org/10.1016/j.solener.2018.12.045 doi: 10.1016/j.solener.2018.12.045
[21]	Mellit A, Zayane C, Boubaker S, et al. (2023) A sustainable fault diagnosis approach for photovoltaic systems based on stacking-based ensemble learning methods. Mathematics 11: 936. https://doi.org/10.3390/math11040936 doi: 10.3390/math11040936
[22]	Harrou F, Taghezouit B, Khadraoui S, et al. (2022) Ensemble learning techniques-based monitoring charts for fault detection in photovoltaic systems. Energies 15: 6716. https://doi.org/10.3390/en15186716 doi: 10.3390/en15186716
[23]	Benkercha R, Moulahoum S (2018) Fault detection and diagnosis based on C4.5 decision tree algorithm for grid connected PV system. Sol Energy 173: 610–634. https://doi.org/10.1016/j.solener.2018.07.089 doi: 10.1016/j.solener.2018.07.089
[24]	Gong S, Wu X, Zhang Z (2020) Fault diagnosis method of photovoltaic array based on random forest algorithm. 2020 39th Chinese Control Conference (CCC), 4249–4425. https://doi.org/10.23919/CCC50068.2020.9189016
[25]	Ghoneim SSM, Rashed AE, Elkalashy NI (2021) Fault detection algorithms for achieving service continuity in photovoltaic farms. Intell Autom Soft Comput 30: 467–479. https://doi.org/10.32604/iasc.2021.016681 doi: 10.32604/iasc.2021.016681
[26]	Sharma N, Thakur MS, Kumar R, et al. (2022) Assessing waste marble powder impact on concrete flexural strength using gaussian process, SVM, and ANFIS. Processes 10: 2745. https://doi.org/10.3390/pr10122745 doi: 10.3390/pr10122745
[27]	Puri D, Kumar R, Kumar S, et al. (2024) Performance analysis and modelling of circular jets aeration in an open channel using soft computing techniques. Sci Rep, 14. https://doi.org/10.1038/s41598-024-53407-3
[28]	Mathew TE (2022) An optimized extremely randomized tree model for breast cancer classification. J Theor Appl Inf Technol. Available from: www.jatit.org.
[29]	Mahkya DAl, Notodiputro KA, Sartono B (2022) Extra trees method for stock price forecasting with rolling origin accuracy evaluation. Media Stat 15: 36–47. https://doi.org/10.14710/medstat.15.1.36-47 doi: 10.14710/medstat.15.1.36-47
[30]	Almohammed F, Thakur MS, Lee D, et al. (2024) Flexural and split tensile strength of concrete with basalt fiber: An experimental and computational analysis. Constr Build Mater, 414. https://doi.org/10.1016/j.conbuildmat.2024.134936
[31]	Saeed U, Jan SU, Lee YD, et al. (2020) Fault diagnosis based on extremely randomized trees in wireless sensor networks. Reliab Eng Syst Saf, 205. https://doi.org/10.1016/j.ress.2020.107284
[32]	Toche Tchio GM, Kenfack J, Kassegne D, et al. (2024) A comprehensive review of supervised learning algorithms for the diagnosis of photovoltaic systems, proposing a new approach using an ensemble learning algorithm. Appl Sci 14: 2072. https://doi.org/10.3390/app14052072 doi: 10.3390/app14052072
[33]	Geurts P, Ernst D, Wehenkel L (2006) Extremely randomized trees. Mach Learn 63: 3–42. https://doi.org/10.1007/s10994-006-6226-1 doi: 10.1007/s10994-006-6226-1
[34]	Maghami MR, Mutambara AGO (2022) Challenges associated with hybrid energy systems: An artificial intelligence solution. Energy Rep 9: 924–940. https://doi.org/10.1016/j.egyr.2022.11.195 doi: 10.1016/j.egyr.2022.11.195
[35]	Pei T, Hao X (2019) A fault detection method for photovoltaic systems based on voltage and current observation and evaluation. Energies 12: 1712. https://doi.org/10.3390/en12091712 doi: 10.3390/en12091712
[36]	Khalil IU, Ul-Haq A, Mahmoud Y, et al. (2020) Comparative analysis of photovoltaic faults and performance evaluation of its detection techniques. IEEE Access 8: 26676–26700 https://doi.org/10.1109/ACCESS.2020.2970531
[37]	Dhimish M, Tyrrell AM (2018) Photovoltaic bypass diode fault detection using artificial neural networks. IEEE Trans Instrum Meas 72: 1–10. https://doi.org/10.1109/TIM.2023.3244230 doi: 10.1109/TIM.2023.3244230
[38]	Dhakshinamoorthy M, Sundaram K, Murugesan P, et al. (2022) Bypass diode and photovoltaic module failure analysis of 1.5 kW solar PV array. Energy Sources 44: 4000–4015. https://doi.org/10.1080/15567036.2022.2072023
[39]	Platon R, Martel J, Woodruff N, et al. (2015) Online fault detection in PV systems. IEEE Trans Sustainable Energy 6: 1200–1207. https://doi.org/10.1109/TSTE.2015.2421447 doi: 10.1109/TSTE.2015.2421447
[40]	Guerriero P, Piegari L, Rizzo R, et al. (2017) Mismatch based diagnosis of PV fields relying on monitored string currents. Int J Photoenergy. https://doi.org/10.1155/2017/2834685
[41]	Roger PY, Emilio CCJ, Rubén RH (2021) Fault diagnostic methodology for grid-connected photovoltaic systems. J La Multiapp 2: 10–30. https://doi.org/10.37899/journallamultiapp.v2i2.339 doi: 10.37899/journallamultiapp.v2i2.339
[42]	Berghout T, Benbouzid M, Bentrcia T, et al. (2021) Machine learning-based condition monitoring for PV systems: State of the art and future prospects. Energies 14: 6316. https://doi.org/10.3390/en14196316 doi: 10.3390/en14196316
[43]	Lodhi E, Wang FY, Xiong G, et al. (2023) A novel deep stack-based ensemble learning approach for fault detection and classification in photovoltaic arrays. Remote Sens 15: 1277. https://doi.org/10.3390/rs15051277 doi: 10.3390/rs15051277
[44]	Goude Y (1996) Methodes d'ensemble et forets aléatoires. Available from: https://www.imo.universite-paris-saclay.fr/~yannig.goude/Materials/ProjetMLF/rf_web.html.
[45]	Camana Acosta MR, Ahmed S, Garcia CE, et al. (2020) Extremely randomized trees-based scheme for stealthy cyber-attack detection in smart grid networks. IEEE Access 8: 19921–19933. https://doi.org/10.1109/ACCESS.2020.2968934 doi: 10.1109/ACCESS.2020.2968934

Reader Comments

Your name:*

Email:*
© 2024 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)