Title: Application of Artificial Neural Network to Predict Annual Global Solar Radiation for PV System's Sizing in UUM Area, Malaysia.

Year of Publication: Jan - 2015
Page Numbers: 10-17
Authors: Sanusi Yekinni Kolawole , Ojeniyi Adegoke, Sunmonu Lukman Ayobami
Conference Name: The International Conference on Electrical and Bio-medical Engineering, Clean Energy and Green Computing (EBECEGC2015)
- United Arab Emirates


The knowledge and estimation of global solar radiation are very crucial in application of photovoltaic (PV) solar system at a particular location. Estimation of global solar radiation at University Utara Malaysia (UUM) area, Malaysia, (Latitude 60N and longitude 1000E) was carried out in this study. The artificial neural network model was used to predict the global solar radiation based on the available simple atmospheric parameters of ambient temperature. The statistical analyses were employed to validate the results obtained from the model. It is deduced from the results obtained that the values of the measured global solar radiation and the estimated values from artificial neural network model have a very close agreement and therefore, have been suggested to be utilized very efficiently in the prediction of the performance of global solar radiation for photovoltaic system application in UUM area and its environs. The values of mean bias error, root mean square error and mean percentage error are 0.00062, 0.00812 and -0.813 respectively. This confirmed the strong capacity of using the model to estimate global solar radiation in the study area for photovoltaic system utilization.