Estimation Of Solar Radiation By Artificial Neural Network Model
-In this paper artificial neural Networks is used for predicting solar global radiation by using meteorological
parameters. Seven meteorological parameters is considered for 14 cities to estimate solar radiation. The inputs are wind
speed, rainfall, sunshine duration, temperature, vapour pressure, humidity, and rainy day. The ANN model is based on the
feed forward multilayer perception model with seven inputs and one output. Based on the results, the average MAPE,
mean bias error for the predicted global solar irradiation are 3.99%and 2.96%.The results shown a better accuracy than
other conventional prediction models. The results of these models have shown the capability of ANN models for predicting
solar radiation in the locations that there is no any measurement.
Index Terms- Global Radiation, Solar Radiation, Artificial Neural Networks, Meteorological Parameters, Forecasting.