Machine Learning-Based Automated Dust Detection on Solar Panels: A Comparative Study
DOI:
https://doi.org/10.21467/proceedings.7.6.61Keywords:
Solar panel dust detection, Machine learning, Logistic regressionAbstract
Dust accumulation can significantly impair the efficiency of solar panels, which require frequent sustentation and a decrease in power output. The aim of this study to use machine learning models for differentiating between dusty and clean solar panels using an image dataset. Dataset consists of solar panel images, whose features are extracted and processed. The evaluation of the three classification models - Discriminant Analysis, Decision Trees, and Logistic Regression - was carried out using Accuracy and Area Under the Curve (AUC) metrics. The findings reveal that Discriminant Analysis attained higher classification accuracy, whereas Logistic Regression demonstrated the highest AUC performance. This research provides promising perspectives on the application of machine learning methods for efficient and automated dust detection on solar panels.
References
[1] Kaggle Solar Panel Images Dataset Online Available https www kaggle com
[2] M Mani and R Pillai Impact of dust on solar photovoltaic performance Research status challenges and recommendations Renewable and Sustainable Energy Reviews vol 14 no 9 pp 3124 3131 2010
[3] M Sayyah M N Horenstein and M K Mazumder Energy yield loss caused by dust deposition on photovoltaic panels Solar Energy vol 107 pp 576 604 2014
[4] M Ilse Robotic cleaning of PV panels Technology overview Solar Energy vol 158 pp 644 658 2017
[5] Y Du X Li and Y Chen Machine learning based fault diagnosis for photovoltaic systems A review IEEE Access vol 8 pp 18072 18088 2020
[6] M Alam M Syed and R Ahmad Deep learning based solar panel cleanliness detection using image classification Journal of Cleaner Production vol 279 2021
[7] T Hastie R Tibshirani and J Friedman The Elements of Statistical Learning Springer 2009
[8] D W Hosmer S Lemeshow and R X Sturdivant Applied Logistic Regression Wiley 2013
[9] J R Quinlan Induction of decision trees Machine Learning vol 1 no 1 pp 81 106 1986
[10] R A Johnson and D W Wichern Applied Multivariate Statistical Analysis Pearson 2013
[11] H Zhang Edge detection methods in image processing IEEE Access vol 7 pp 167062 167071 2019
[12] R M Haralick Statistical and structural approaches to texture Proceedings of the IEEE vol 67 no 5 pp 786 804 1979
[13] T Fawcett An introduction to ROC analysis Pattern Recognition Letters vol 27 no 8 pp 861 874 2006
[14] S Mekhilef R Saidur and A Safari A review on solar energy use in industries Renewable and Sustainable Energy Reviews vol 15 no 4 pp 1777 1790 2011
[15] A Hassan Dust and soiling impact on PV systems IEEE Journal of Photovoltaics vol 9 no 3 pp 837 847 2019
[16] A A M Sayigh Effect of dust on the performance of PV panels Renewable Energy vol 3 no 6 7 pp 585 590 1993
[17] M Ghazi A review on the effect of dust on solar photovoltaic systems Renewable and Sustainable Energy Reviews vol 33 pp 742 751 2014
[18] S Sharma and D Jain Performance analysis of classification algorithms for solar panel image classification International Journal of Computer Applications vol 182 no 30 pp 1 6 2019
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
