Prediction of hourly solar radiation using temperature and humidity for real-time building energy simulation

Solar radiation is considered one of the most substantial energy sources in our life. This paper discusses how to develop an algorithm to predict real-time hourly solar radiation based on readily available weather data such as temperature and humidity. Artificial Neural Network is one of the most effective technologies for developing algorithms to predict solar radiations. Hidden nodes, learning rates, and epochs are the main three variables. An optimization method is proposed to provide the optimum value of the variables depending on the Coefficient of Variance of the Root Mean Square Error, Normalized Mean Bias Error, and Coefficient of determination.