Journal article
EFFICIENT PHOTOVOLTAIC MPPT SYSTEM USING COARSE GAUSSIAN SUPPORT VECTOR MACHINE AND ARTIFICIAL NEURAL NETWORK TECHNIQUES
INTERNATIONAL JOURNAL OF INNOVATIVE COMPUTING INFORMATION AND CONTROL, v 14(1), pp 323-339
01 Feb 2018
Featured in Collection : UN Sustainable Development Goals @ Drexel
Abstract
The use of machine learning techniques for PV system controllers has improved the maximum power point tracking (MPPT) process which increased the PV systems efficiency. However, some of these powerful machine learning techniques such as artificial neural network (ANN) and artificial neuro-fuzzy inference system (ANFIS) still require huge and concise training data for successful MPPT. This paper introduces an innovative maximum power point tracking (MPPT) algorithm that combines two powerful machine learning techniques of coarse-Gaussian support vector machine (CGSVM) and ANN as ANN-CGSVM technique. The results of the proposed MPPT algorithm were compared with that of ANFIS, conventional ANN, and the hybrid of ANN and Perturb&Observe (ANN-PO) results to verify the proposed algorithm performance for MPPT task. This work was implemented to investigate the feasibility of using the combined ANN-CGSVM technique for MPPT and thereafter improve the PV system performance. Two experiments were conducted to determine the ANN-CGSVM efficiency and the convergence speed of the algorithm using Soltech 1STH-215-P photovoltaic (PV) panel with modified CUK DC-DC converter under three different weather conditions. The training data sets were generated using PSIM software. Findings suggest that the ANN-CGSVM technique has a fast-tracking speed and can be used to achieve a reasonable maximum power.
Metrics
Details
- Title
- EFFICIENT PHOTOVOLTAIC MPPT SYSTEM USING COARSE GAUSSIAN SUPPORT VECTOR MACHINE AND ARTIFICIAL NEURAL NETWORK TECHNIQUES
- Creators
- Adedayo Mojeed Farayola - University of JohannesburgAli Nabil Hasan - University of JohannesburgAhmed Ali - University of Johannesburg
- Publication Details
- INTERNATIONAL JOURNAL OF INNOVATIVE COMPUTING INFORMATION AND CONTROL, v 14(1), pp 323-339
- Publisher
- Icic International
- Number of pages
- 17
- Resource Type
- Journal article
- Language
- English
- Academic Unit
- Engineering Leadership and Society/Engineering Technology
- Web of Science ID
- WOS:000428905600022
- Scopus ID
- 2-s2.0-85041119986
- Other Identifier
- 991022004201804721
UN Sustainable Development Goals (SDGs)
This publication has contributed to the advancement of the following goals:
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Web of Science research areas
- Computer Science, Artificial Intelligence