Comparison between LightGBM and other ML algorithms in PV fault classification

Paulo Monteiro; José Lino; Rui Esteves Araújo; Louelson Costa

doi:10.4108/ew.4865

Authors

Paulo Monteiro University of Porto
José Lino University of Porto
Rui Esteves Araújo University of Porto
Louelson Costa University of Porto

DOI:

https://doi.org/10.4108/ew.4865

Keywords:

Photovoltaic faults, Fault diagnostics, Fault classification, Data-driven, Machine Learning

Abstract

In this paper, the performance analysis of Machine Learning (ML) algorithms for fault analysis in photovoltaic (PV) plants, is given for different algorithms. To make the comparison more relevant, this study is made based on a real dataset. The goal was to use electric and environmental data from a PV system to provide a framework for analysing, comparing, and discussing five ML algorithms, such as: Multilayer Perceptron (MLP), Decision Tree (DT), K-Nearest Neighbors (KNN), Support Vector Machine (SVM) and Light Gradient Boosting Machine (LightGBM). The research findings suggest that an algorithm from the Gradient Boosting family called LightGBM can offer comparable or better performance in fault diagnosis for PV system.

Downloads

Download data is not yet available.

References

Sara Gallardo-Saavedra, Luis Hernandez-Callejo, Oscar Duque-Perez, Quantitative failure rates and modes analysis in photovoltaic plants. Energy, Volume 183, (2019), pp. 825-836, 0360-5442, https://doi.org/10.1016/j.energy.2019.06.185. DOI: https://doi.org/10.1016/j.energy.2019.06.185

Andre Eugenio Lazzaretti, Clayton Hilgemberg da Costa, Marcelo Paludetto Rodrigues, A monitoring system for online fault detection and classification in photovoltaic plants. Sensors (Switzerland), 20:1–30, 9 (2020), https://doi:10.3390/s20174688. DOI: https://doi.org/10.3390/s20174688

Fouzi Harrou and Ying Sun and Bilal Taghezouit and Ahmed Saidi and Mohamed Elkarim Hamlati, Reliable fault detection and diagnosis of photovoltaic systems based on statistical monitoring approaches. Renewable Energy, Elsevier Ltd, (2018), https://doi:10.1016/j.renene.2017.09.048, 18790682. DOI: https://doi.org/10.1016/j.renene.2017.09.048

Paulo Monteiro, Github with Dissertation Scripts, github.com/paulo5930/Dissertation Scripts.

Paulo Monteiro, Pattern Recognition Machine Learning Algorithms for Fault Classification of PV System, Master’s Thesis, Faculty of Engineering of the University of Porto, 02-2023.

Wes McKinney, Python for Data Analysis, 3rd edn. O REILLY, (2022), https://wesmckinney.com/book.

Pauli Virtanen, Ralf Gommers, Travis E. Oliphant, Matt Haberland, Tyler Reddy, David Cournapeau, Evgeni Burovski, et al. Scipy 1.0: fundamental algorithms for scientific computing in python, Nature Methods, 17:261–272, (2020), https://doi.org/10.1038/s41592-019-0686-2. DOI: https://doi.org/10.1038/s41592-020-0772-5

Walter H Delashmit and Michael T Manry, Recent developments in multilayer perceptron neural networks. In Proceedings of the Seventh Annual Memphis Area Engineering and Science Conference, MAESC (2005).

Bahzad Charbuty and Adnan Abdulazeez, Classification based on decision tree algorithm for machine learning. Journal of Applied Science and Technology Trends, 2. 20-28, (2021), https://doi:10.38094/jastt20165 DOI: https://doi.org/10.38094/jastt20165

Sickit Learn developers Homepage, DecisionTreeClassifier, https://scikit-learn.org/stable/modules/generated/sklearn.tree.DecisionTreeClassifier.html, last accessed 2023/10/19.

Gongde Guo, Hui Wang, David Bell, Yaxin Bi, and Kieran Greer. KNN Model- Based Approach in Classification. Lecture Notes in Computer Science 2888, Pages 986 - 996, (2003). DOI: https://doi.org/10.1007/978-3-540-39964-3_62

Jair Cervantes, Farid Garcia-Lamont, Lisbeth Rodríguez-Mazahua, and Asdrubal Lopez. A comprehensive survey on support vector machine classification: Applications, challenges and trends. Neurocomputing, Elsevier B.V., (2020), https://doi:10.1016/j.neucom.2019.10.118. DOI: https://doi.org/10.1016/j.neucom.2019.10.118

Zhi-Hua Zhou: Machine Learning, Springer, Singapore (2021), https://link.springer.com/book/10.1007/978-981-15-1967-3.

Essam Al Daoud: Comparison between xgboost, lightgbm and catboost using a home credit dataset. World Academy of Science, Engineering and Technology, Open Science Index 145, International Journal of Computer, and Information Engineering, 13(1), 6 - 10, (2019).

Guolin Ke, Qi Meng, Thomas Finley, Taifeng Wang, Wei Chen, Weidong Ma, Qiwei Ye, and Tie-Yan Liu, Lightgbm. A highly efficient gradient boosting decision tree, https: //github.com/Microsoft/LightGBM, last accessed 2023/10/19.

LightGBM Homepage, lightgbm. LGBMClassifier, MicrosoftCorporation, https://lightgbm.readthedocs.io/en/latest/pythonapi/lightgbm.LGBMClassifier.html, last accessed 2023/10/19.

Ankit Gupta, Evaluation Metrics For Multi-class Classification, Homepage Gaggle, https://www.kaggle.com/code/nkitgupta/evaluation-metrics-for-multi-class- classification, last accessed 2023/10/19.

Teemu Kanstren, A Look at Precision, Recall, and F1-Score, Towards Data Science Homepage, https://towardsdatascience.com/a-look-at-precision-recall-and- f1-score-36b5fd0dd3ec, last accessed 2023/10/19.

Sarang Narkhede, Understanding Confusion Matrix, Towards Data Science Homepage, https://towardsdatascience.com/understanding-confusion-matrix- a9ad42dcfd62, last accessed 2023/10/19.