Logo image
Back
Optimization of PV Systems Using Data Mining and Regression Learner MPPT Techniques
Journal article   Open access

Optimization of PV Systems Using Data Mining and Regression Learner MPPT Techniques

Adedayo M. Farayola, Ali N Hasan and Ahmed Ali
Indonesian Journal of Electrical Engineering and Computer Science, v 10(3), pp 1080-1089
01 Jun 2018
DOI: https://doi.org/10.11591/ijeecs.v10.i3.pp1080-1089
url
https://doi.org/10.11591/ijeecs.v10.i3.pp1080-1089View
Published, Version of Record (VoR)Open Access (License Unspecified),  Open

Abstract

Supervised machine learning techniques such as artificial neural network (ANN) and ANFIS are powerful tools used to track the maximum power point (MPPT) in photovoltaic systems. However, these offline MPPT techniques still require large and accurate training data sets for successful tracking. This paper presents an innovative use of rational quadratic gaussian process regression (RQGPR) technique to generate the large and very accurate training data required for MPPT task. To confirm the effectiveness of the RQGPR technique, the combination of ANN and RQGPR as ANN-RQGPR technique results were compared with the conventional ANN technique results, and that of combined ANN and linear support vector machine regression as ANN-LSVM technique results under different weather conditions. Results show that ANN-RQGPR technique produced the overall best result and with an improved performance. 

Metrics

6 Record Views
23 citations in Scopus

Details

Logo image