Artificial Neural Network Based Simplified One Day Ahead Forecasting of Solar Photovoltaic Power Generation

One Day Ahead Forecasting of Solar Photovoltaic Power Generation

  • Asim Munir Department of Electrical Power Engineering, U.S. Pakistan Centre for Advanced Studies in Energy (USPCASE), National University of Sciences and Technology (NUST), Islamabad, Pakistan
  • Abraiz Khattak Department of Electrical Power Engineering, U.S. Pakistan Centre for Advanced Studies in Energy (USPCASE), National University of Sciences and Technology (NUST), Islamabad, Pakistan
  • Kashif Imran Department of Electrical Power Engineering, U.S. Pakistan Centre for Advanced Studies in Energy (USPCASE), National University of Sciences and Technology (NUST), Islamabad, Pakistan
  • Abasin Ulasyar Department of Electrical Power Engineering, U.S. Pakistan Centre for Advanced Studies in Energy (USPCASE), National University of Sciences and Technology (NUST), Islamabad, Pakistan
  • Azhar Ul Haq Department for Management of Science and Technology Development, Ton Duc Thang University, Ho Chi Minh City, Vietnam
  • Adam Khan Department for Management of Science and Technology Development, Ton Duc Thang University, Ho Chi Minh City, Vietnam Faculty of Electrical & Electronics Engineering, Ton Duc Thang University, Ho Chi Minh City, Vietnam
  • Nasim Ullah Department of Electrical Engineering, College of Electrical and Mechanical Engineering (CEME), National University of Sciences and Technology (NUST), Islamabad, Pakistan
DOI: https://doi.org/10.36909/jer.10425

Abstract

The intermittency of solar energy resources possesses a serious challenge in balancing the power generation and load demand. To enhance the consistency of the system, it is crucial to forecast solar photovoltaic power. Among numerous techniques, Artificial Neural Network (ANN) is an efficient tool that may help to simplify this problem. In this study, all 63 combinations of six input parameters i.e. temperature, dew point, wind speed, cloud cover, relative humidity and pressure are applied one by one to ANN to forecast 24 hours ahead PV generation. The power forecast results are obtained based on weather forecast data of 21 days sampled from the recorded forecasted data of 180 days. To quantify the error between predicted and measured solar PV generation, Root Mean Squared Error (RMSE) is used and results of different input combinations are also compared on basis of this statistical matrix. The analysis showed that the generation is best predicted on two combinations with the first comprising of temperature, dew point, relative humidity and cloud cover while the second consisting of all six parameters. While, some of the three input combinations also resulted in RMSEs as in close proximity of this value.

Published
2021-10-05
Issue
Vol 10 No 1A (2022): Journal of Engineering Research
Section
Electrical Engineering