Evaluation of Temperature-Based Empirical Models and Machine Learning Techniques to Estimate Daily Global Solar Radiation at Biratnagar Airport, Nepal
Sandeep Dhakal, Yogesh Gautam, Aayush Bhattarai
Abstract
Global solar radiation (GSR) is a critical variable for designing photovoltaic cells, solar furnaces, solar collectors, and other passive solar applications. In Nepal, the high initial cost and subsequent maintenance cost required for the instrument to measure GSR have restricted its applicability all over the country. The current study compares six different temperature-based empirical models, artificial neural network (ANN), and other five different machine learning (ML) models for estimating daily GSR utilizing readily available meteorological data at Biratnagar Airport. Amongst the temperature-based models, the model developed by Fan et al. performs better than the rest with an<mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" id="M1"><mml:msup><mml:mrow><mml:mi>R</mml:mi></mml:mrow><mml:mrow><mml:mn>2</mml:mn></mml:mrow></mml:msup></mml:math>of 0.7498 and RMSE of<mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" id="M2"><mml:mn>2.016</mml:mn><mml:mn>2</mml:mn><mml:mtext> </mml:mtext><mml:msup><mml:mrow><mml:mtext>MJm</mml:mtext></mml:mrow><mml:mrow><mml:mo>−</mml:mo><mml:mn>2</mml:mn></mml:mrow></mml:msup><mml:msup><mml:mrow><mml:mtext>d</mml:mtext></mml:mrow><mml:mrow><mml:mo>−</mml:mo><mml:mn>1</mml:mn></mml:mrow></mml:msup></mml:math>. Feed-forward multilayer perceptron (MLP) is utilized to model daily GSR utilizing extraterrestrial solar radiation, sunshine duration, maximum and minimum ambient temperature, precipitation, and relative humidity as inputs. ANN3 performs better than other ANN models with an<mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" id="M3"><mml:msup><mml:mrow><mml:mi>R</mml:mi></mml:mrow><mml:mrow><mml:mn>2</mml:mn></mml:mrow></mml:msup></mml:math>of 0.8446 and RMSE of<mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" id="M4"><mml:mn>1.4595</mml:mn><mml:mtext> </mml:mtext><mml:msup><mml:mrow><mml:mtext>MJm</mml:mtext></mml:mrow><mml:mrow><mml:mo>−</mml:mo><mml:mn>2</mml:mn></mml:mrow></mml:msup><mml:msup><mml:mrow><mml:mtext>d</mml:mtext></mml:mrow><mml:mrow><mml:mo>−</mml:mo><mml:mn>1</mml:mn></mml:mrow></mml:msup></mml:math>. Likewise, stepwise linear regression performs better than other ML models with an<mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" id="M5"><mml:msup><mml:mrow><mml:mi>R</mml:mi></mml:mrow><mml:mrow><mml:mn>2</mml:mn></mml:mrow></mml:msup></mml:math>of 0.8870 and RMSE of<mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" id="M6"><mml:mn>1.5143</mml:mn><mml:mtext> </mml:mtext><mml:msup><mml:mrow><mml:mtext>MJm</mml:mtext></mml:mrow><mml:mrow><mml:mo>−</mml:mo><mml:mn>2</mml:mn></mml:mrow></mml:msup><mml:msup><mml:mrow><mml:mtext>d</mml:mtext></mml:mrow><mml:mrow><mml:mo>−</mml:mo><mml:mn>1</mml:mn></mml:mrow></mml:msup></mml:math>. Thus, the model developed by Fan et al. is recommended to estimate daily GSR in the region where only ambient temperature data are available. Similarly, a more robust ANN3 and stepwise linear regression models are recommended to estimate daily GSR in the region where data about sunshine duration, maximum and minimum ambient temperature, precipitation, and relative humidity are available.