Adaptive neuro-fuzzy approach for prediction of global solar radiation for 25 cities falling under seven Köppen climatic zones
by Vinay Anand Tikkiwal; Sajai Vir Singh; Dinesh Bisht; Hari Om Gupta
International Journal of Computer Aided Engineering and Technology (IJCAET), Vol. 15, No. 4, 2021

Abstract: Estimation of solar energy is essential for the identification of suitable locations for solar-based energy systems and their optimal sizing. In this work, capability of adaptive neuro-fuzzy inference system (ANFIS) for the estimation of global solar radiation has been investigated for 25 different locations in India. Using geographical parameters like latitude, longitude and altitude, along with meteorological parameters such as sunshine duration, temperature as inputs, five ANFIS models have been developed. The relevant significance of input parameters with respect to global solar radiation has been evaluated using the regression method. The accuracy of prediction for the models has been evaluated using standard statistical indicators including mean absolute percentage error (MAPE), mean bias error (MBE), root mean square error (RMSE) and t-statistic. The models have been ranked using the rank score method. For the best ANFIS model, MAPE = 9.7%, RMSE = 0.80 and MBE = 6.6E-06 were obtained. The results indicate that the developed models have good prediction accuracy for cities having starkly different climates.

Online publication date: Wed, 27-Oct-2021

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Computer Aided Engineering and Technology (IJCAET):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com