Comprehensive Evaluation of Machine Learning MPPT Algorithms for a PV System Under Different Weather Conditions
- PDF / 2,182,818 Bytes
- 17 Pages / 595.276 x 790.866 pts Page_size
- 72 Downloads / 208 Views
ORIGINAL ARTICLE
Comprehensive Evaluation of Machine Learning MPPT Algorithms for a PV System Under Different Weather Conditions Mpho Sam Nkambule1 · Ali N. Hasan2 · Ahmed Ali1 · Junhee Hong3 · Zong Woo Geem3 Received: 16 May 2020 / Revised: 16 October 2020 / Accepted: 23 October 2020 © The Korean Institute of Electrical Engineers 2020
Abstract The rapid growth of demand for electrical energy and the depletion of fossil fuels opened the door for renewable energy; with solar energy being one of the most popular sources, as it is considered pollution free, freely available and requires minimal maintenance. This paper investigates the feasibility of using machine learning (ML) based MPPT techniques, to harness maximum power on a PV system under PSC. In this study, certain contributions to the field of PV systems and ML based systems were made by introducing nine (9) ML based MPPT techniques, by presenting three (3) experiments under different weather conditions. Decision Tree (DT), Multivariate Linear Regression (MLR), Gaussian Process Regression (GPR), Weighted K-Nearest Neighbors (WK-NN), Linear Discriminant Analysis (LDA), Bagged Tree (BT), Naïve Bayes classifier (NBC), Support Vector Machine (SVM) and Recurrent Neural Network (RNN) performances are validated and proved using MATLAB SIMULINK simulation software. The experimental results demonstrated that WK-NN performs significantly better when compared with other proposed ML based algorithms. Keywords Maximum power point tracking (MPPT) · Partial shading conditions (PSC) · Machine learning (ML) · DC–DC boost converter
1 Introduction In 1839, the photovoltaic effect was discovered when using sunlight to generate electrical energy by French scientist Edmond Becquerel. He was only 19 years old when he discovered that placing silver chloride in an acidic solution * Zong Woo Geem [email protected] Mpho Sam Nkambule [email protected] Ali N. Hasan [email protected] Ahmed Ali [email protected] Junhee Hong [email protected] 1
Department of Electrical Engineering, University of Johannesburg, Johannesburg, South Africa
2
Depatment of Electrical Engineering, Higher Colleges of Technology, Abu Dhabi, United Arab Emirates
3
Depatment of Energy IT, Gachon University, Seongnam 13120, South Korea
would result in generating current and voltage. The Solar Energy Conversion System has been attracting wide attention as a renewable energy source, due to the increased cost of fossil fuel and its environmental impact. Solar renewable resources are regarded as a cleaner source of energy and they reduce greenhouse gases [1, 2]. In between 1990 and 2019, the Photovoltaic Solar System has grown exponentially worldwide. In 1996, the United States (US) became the first country in history to produce 77 MW of the power through a PV solar system. In about the year 1999, Japan became the world’s leader, producing more solar power than any other country. In the mid-2000s, Germany surpassed Japan to produce over 41GW of solar power. China became the world’s biggest solar power
Data Loading...
