Prediction the photovoltaic system performance via Artificial Neural Network (ANN) Technique

Jumaat, Siti Amely and Mohamed, Abdou Mani and Mohamad Nor, Ahmad Fateh (2024) Prediction the photovoltaic system performance via Artificial Neural Network (ANN) Technique. In: 2024 IEEE 4TH INTERNATIONAL CONFERENCE IN POWER ENGINEERING APPLICATIONS (ICPEA), 2024.

Text P16647_5bd762f237a3f4d9ad575bcb4d02fb1e 5.pdf Download (767kB)

Abstract

Population growth and industrialization are driving up global energy consumption, which is expected to soar in the near future. However, the predominant use of fossil fuels exacerbates environmental pollution and greenhouse gas emissions, which are primary contributors to global warming. To address this, this study proposes an artificial neural network (ANN) model designed to forecast the power output of both monocrystalline and polycrystalline photovoltaic (PV) panels. The aim is to assess the performance and efficiency of these two PV panel types. Data spanning from 2018 to 2020 was gathered, with meteorological parameters serving as input for the ANN model. Polycrystalline panels exhibit higher voltage output, whereas monocrystalline panels typically yield greater current. The model's mean square error (MSE) for training, testing, and validation equated, indicating robust learning during training without overestimation. Both models demonstrate an excellent fit to the data, evident from the correlation coefficient (R) reaching 1. The predicted values closely align with actual trends for both panel types, with insignificant disparities in estimated voltage, current, and power. Overall, the polycrystalline panel outperforms the monocrystalline panel, boasting efficiencies of 0.999% and 0.997%, respectively

Item Type:	Conference or Workshop Item (Paper)
Subjects:	T Technology > T Technology (General)
Divisions:	Faculty of Electrical and Electronic Engineering > Department of Electrical Engineering
Depositing User:	Mrs. Sabarina Che Mat
Date Deposited:	17 Nov 2024 01:36
Last Modified:	17 Nov 2024 01:36
URI:	http://eprints.uthm.edu.my/id/eprint/11686

Actions (login required)

View Item