Implementing machine learning to characterize solar cells and optimize their efficiency
DOI:
https://doi.org/10.38152/bjtv7n4-005Keywords:
Maximum Power Point Traking MPPT, optimization, machine learning, Artificial Intelligence, solar energyAbstract
Artificial intelligence (AI) has evolved into an indispensable component across various sectors, with a particular emphasis on employing machine learning techniques. This integration of AI technologies holds significant importance, especially in the realm of renewable energy, given its positive ecological impact and its role as a sustainable energy source to fulfill our energy needs. The field of solar energy is undergoing continual research and development, with a dedicated focus on applying various machine learning techniques to optimize energy production. One such area of investigation pertains to Maximum Power Point Tracking (MPPT). In this study, we have implemented a machine learning algorithm, specifically a regression tree, using a novel dataset derived from experimental measurements. Our approach yielded a commendable accuracy score of 96%. Our primary objective revolves around the meticulous construction of a database through precise experimental measurements, which serves as the foundational cornerstone of the machine learning process. This dataset is then utilized to develop and train a machine learning model that can predict values pertinent to our research. Finally, we deploy this model within a dedicated platform to facilitate the attainment of the Maximum Power Point, a crucial component in the optimization of solar energy systems.
References
N.H. Djilali Hamida, Maximum Power Point Tracking Of Photovoltaic Panel Using Machine Learning, National Polytechnic School of Oran, Algeria, Thesis, Jul. 2022.
Mahmud Ahmed Sasi, Fuzzy Logic Control of MPPT Controller for PV Systems. Thesis, May.2017 https://core.ac.uk/download/pdf/154914752.pdf
S.Ma, M. Chen, J. Wu. Huo, L. Huang, Augmented Nonlinear Controller For Maximum Power-Point Tracking With Artificial Neural Network In Grid-Connected Photovoltaic Systems. Energies,
vol. 9 n.12, 2016, pp. 1005-1028.
https://doi.org/10.3390/en9121005
Lalit Kumar Narwat and Javed Dhillon, Design and Operation of Fuzzy Logic Based MPPT Controller under Uncertain Condition, Journal of Physics: Conference Series, Volume 1854, International Conference on Future of Engineering Systems and Technologies (FEST) 2020 18-19 December 2020, Greater Noida, Delhi/NCR, India. DOI 10.1088/1742-6596/1854/1/012035
Giuseppe Bonaccorso, Machine-learning algorithms. July 2017, ISBN 978-1-78588-962-2
https://balasahebtarle.files.wordpress.com/2020/01/machine-learning-algorithms_text-book.pdf
Sahir Rai Bhatnagar, Introduction to Regression Trees. February 19st, 2018
https://sahirbhatnagar.com/assets/pdf/cart_animation_EN_Feb19_Final.pdf
Gareth James, Daniela Witten, Trevor Hastie, Robert Tibshirani, An Introduction to Statistical Learning. August, 4st, 2021.Second Edition.
Saharia, Barnam. A comparative study on converter topologies for maximum power point tracking application in photovoltaic generation. Journal of Renewable and Sustainable Energy (2014).
DOI: 10.1063/1.4900579
Moacyr A. G. de Brito; Leonardo P. Sampaio; G. Luigi; Guilherme A. e Melo; Carlos A. Canesin. Comparative analysis of MPPT techniques for PV applications. 3rd International Conference on Clean Electrical Power: Renewable Energy Resources Impact, ICCEP 2011. DOI:10.1109/ICCEP.2011.6036361
R.Salviati, MPPT algorithm based on artificial neural network for PV system. https://thesis.unipd.it/retrieve/9ddf2c62-1d9c-4648-9630-ed3edcc08c1c/Salviati_Riccardo_1183982.pdf
El-Ahmar, Mohamed & Ahmed, Abou-Hashema & Hemeida, Ashraf, mathematical modeling of Photovoltaic module and evalute the effect of varoiusparamenters on its performance. DOI:10.1109/MEPCON.2016.7836976
N. Mazouz, A.MIDOUN Implementation of a Converter DC / DC Controlled by VMC and PCM in a Photovoltaic System, International Journal of Applied Engineering Research. Volume 11, Number 23 (2016) pp. 11595-11604.
Taiwo Oladipupo Ayodele, Types of Machine Learning Algorithms. February 1st, 2010 DOI: 10.5772/9385
Arjav Harjai, A. Bhardwaj, Mrutyunjaya Sandhibigraha, Study of Maximum Power point Tracking (MPPT), Techniques in a Solar Photovoltaic Array 2011. https://core.ac.uk/download/pdf/53187734.pdf
Putri, Ratna&Wibowo, Sapto&Rifa’i, Muhamad (2015). Maximum Power Point Tracking for Photovoltaic Using Incremental Conductance Method. Energy Procedia. https://doi.org/10.1016/j.egypro.2015.03.228
Praveen Kumar Mishra1, Prabhakar Tiwari2. Incremental conductance MPPT in grid connected PV system. International Journal of Engineering, Science and Technology. Jul 9, 2021 DOI:10.4314/ijest.v13i1.21S
N. Mazouz, A. Midoun: Control of a DC/DC converter by fuzzy controller for a solar pumping system. ELSEVIER, Electrical Power and Energy Systems, JEPE 1492, 27 August 2011, No. of Pages 9. doi:10.1016/j.ijepes.2011.06.016
