ESTIMASI INTENSITAS RADIASI MATAHARI DENGAN MENGGUNAKAN JARINGAN SYARAF TIRUAN BACKPRPAGATION DI KOTA JAYAPURA

Abstract

Eastern Indonesia has enormous potential for solar energy. For the utilization of this energy, data on the intensity of solar radiation is needed that can describe the availability of solar energy that can be utilized. Information on the availability of solar energy will be used to estimate the intensity of solar radiation, so that the use of solar energy can be optimal. In this study, the intensity of solar radiation was estimated. The data used to estimate the intensity of solar radiation were air temperature, humidity, duration of solar radiation, and rainfall. The method used in this study is an artificial neural network (ANN) with backpropagation training. This study uses variations in the number of neurons in 1 hidden layer to get the best group based on the RMSE value and correlation. The best group from each training simulation is then used to estimate solar radiation. The estimation results for the city of Jayapura have an RMSE value of 1,970 kWh/m2. The solar radiation received in the Jayapura area has a high enough potential to be used as alternative energy with an average monthly radiation value of 4,5 kWh/m2.