Prediction of photovoltaic panel power output using artificial neural networks learned by heuristic algorithms: A comparative study Sezgisel Algoritma Tabanli Yapay Sinir Aǧlari Kullanilarak Fotovoltaik Panel Güç Çikişlarinin Tahmini: Karşilaştirmali Bir Çalişma

DANDIL E., Gürgen E.

2nd International Conference on Computer Science and Engineering, UBMK 2017, Antalya, Turkey, 5 - 08 October 2017, pp.397-402, (Full Text) identifier

  • Publication Type: Conference Paper / Full Text
  • Doi Number: 10.1109/ubmk.2017.8093423
  • City: Antalya
  • Country: Turkey
  • Page Numbers: pp.397-402
  • Keywords: ANN, Back-propagation, Clonal selection algorithm, Photovoltaic panel, Power prediction, PSO
  • Bilecik Şeyh Edebali University Affiliated: Yes

Abstract

© 2017 IEEE.The prediction of power outputs generated from photovoltaic (PV) systems at different times is necessary for reliable and economical use of solar panels. The prediction of the power output is also very important in terms of factors such as installation of solar panels, guidance of electricity companies, energy management and distribution. In this study, we propose an Artificial Neural Network (ANN) model learned by heuristic algorithms to predict the power outputs obtained from PV panels monthly. It has been seen that ANN trained by Particle Swarm Optimization (PSO) are more successful than methods trained by the Back-Propagation(BP) and Clonal Selection Algorithm (CSA) for prediction of the power outputs obtained from PV panels placed at six different tilt angles.