Using Machine Learning for Analysis a Database Outdoor Monitoring of Photovoltaic System

Authors

  • Hichem Hafdaoui Centre de Développement des Energies Renouvelables ,CDER, 16340, Algiers, Algeria
  • El Amin Kouadri Boudjelthia cder
  • Salim Bouchakour
  • Nasreddine Belhaouas

Abstract

: In this paper we propose a new method for analyzing the performance of photovoltaic system using classification, the monitoring of photovoltaic module (150 W) was controlled and analyzed, the system was deployed in Algiers over a long period (80 days), one of the most important difficulties faced by researchers is collecting and analyzing the results of monitoring for a long period, so in this paper we proposed a method for analyzing results by classification using SVM Classifier. More specifically, we regrouping a data variable to multiclass for according and analyzing using SVM. We have presented thoroughly all the calculation steps. Based on the application of artificial intelligence (classification), recorded data, the power output for a given solar panels technology, types and small or large stations under any seasons can be analyzed and treated easily. The several measurements in our laboratory was investigated based on data acquisition (Keysight 34972A).The system collects the measurements from the various sensors. The measurement system was taken the data between 05h00 to 21h00 with irradiation of 50 W/m2 which is starting point, however in 0 to 50 W/m2 the system cannot detect any photovoltaic effect. Results predict that the performance ratio (PR) from a Poly-crystalline panel was around 85.28 % for a different season’s exposure and 727 point analyzes at irradiation of 850-950 W/m2 in same time 14h00-15h00 . The temperature of solar panel are also calculated and compared in different irradiation and time.

Downloads

Download data is not yet available.

Downloads

Published

29-11-2022

Issue

Section

Articles

How to Cite

Hafdaoui, H., Kouadri Boudjelthia, E. A., Bouchakour, S. ., & Belhaouas, N. . (2022). Using Machine Learning for Analysis a Database Outdoor Monitoring of Photovoltaic System. International Journal of Integrated Engineering, 14(6), 275-280. https://penerbit.uthm.edu.my/ojs/index.php/ijie/article/view/10520