Predictive Model of Solar Irradiance Using Artificial Intelligence: An Indian Subcontinent Case Study

Predictive Model of Solar Irradiance Using Artificial Intelligence: An Indian Subcontinent Case Study

Umang Soni (Netaji Subhash Insitutue of Technology, India), Saksham Gupta (Netaji Subhas Institute of Technology, India), Taranjeet Singh (Netaji Subhas Institute of Technology, India), Yash Vardhan (Netaji Subhas Institute of Technology, India) and Vipul Jain (Victoria University of Wellington, New Zealand)
Copyright: © 2020 |Pages: 18
DOI: 10.4018/IJIRR.2020040105

Abstract

Solar power in India is growing at a tremendous pace. India's solar power capacity is 20 GW and has grown 8-fold since 2014. Assessing the solar potential in India is thus the need of the hour. The objective of this study is to make an optimized prediction model of the monthly potential of solar irradiance of the Indian Subcontinent, by utilizing hour-wise unstructured voluminous (80 million line item) satellite-based data from 609 locations for 15 years. The variables chosen are temperature, pressure, relative humidity, month, year, latitude, longitude, altitude, DHI, DNI, and GHI. Combining predictive models using combinations of SVM, ANN, and RF for factors affecting solar irradiance. This model's performance has been evaluated by its accuracy. Accuracy for DHI, DNI, GHI values on testing data evaluated through the SVM model is 95.11%, 93.25%, and 96.88%, respectively, whereas accuracy evaluated through the ANN model is 94.18%, 91.60%, and 95.90%, respectively. The achieved high prediction accuracy makes the SVM, ANN, and RF model very robust. This model with a sustainable financial model can thus be used to identify major locations to set up solar farms in the present and future and the feasibility of its establishment, wherever local meteorological data measuring facilities are not available in India. Along with the air temperature, air pressure, and humidity predictive interrelation model created to aid the irradiance model this can be used for climate predictions in the Indian sub-continental region.
Article Preview
Top

2. Literature Survey

Benghanem (2012) talked about the prediction model's importance to predict the average of long-term solar radiation (global). But this had its own limitations - bearing these parameters was only possible in selective regions as the overall cost equipment is very high. A method to tackle this problem is by using appropriate empirical relations through the measured parameters at selective locations where appropriate equipment is available. Other parameters like - latitude, relative humidity, longitude, sunshine hours, temperature, relative humidity can be used to find the global solar radiation using different empirical models developed by many researchers.

The classification of the empirical models was done by Besharat et. al. (2013) after they reviewed the available models. The categories of models created by them are Sunshine based, Temperature based and Cloud-based. Ennaceri et al. (2018) investigated potential sites for concentrated solar power installations in Morocco based on direct normal irradiation. A sunshine based model (empirical) was proposed by Quansah et al. (2014). Radiation Model for Solar applications was proposed by Xie et al. (2016). Seven empirical models were used for the calculation process by exploring the Angstrom-Prescott model and the Hargreaves-Samani model. Experiments showed that the Angstrom-Prescott model underestimated global solar radiation for few months (April, May, June, October, and November) and overestimated global solar radiation for few months (December, August, and September). All these models were not suitable for the long-term measurement of solar radiation because the input data were site-specific. Because of all these reasons, most researchers made an attempt to make use of meteorological parameters for Global Solar Radiation prediction. The most common prediction approach which is followed recently is the artificial intelligence (AI) for solar radiation prediction. Sfetsos and Coonick (2000) presented an approach for the forecasting of solar radiation by numerous artificial intelligence based techniques.

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 11: 4 Issues (2021): Forthcoming, Available for Pre-Order
Volume 10: 4 Issues (2020)
Volume 9: 4 Issues (2019)
Volume 8: 4 Issues (2018)
Volume 7: 4 Issues (2017)
Volume 6: 4 Issues (2016)
Volume 5: 4 Issues (2015)
Volume 4: 4 Issues (2014)
Volume 3: 4 Issues (2013)
Volume 2: 4 Issues (2012)
Volume 1: 4 Issues (2011)
View Complete Journal Contents Listing