This article presents a novel solar radiation prediction approach using artificial neural networks. The developed model predicts three meteorological variables using sunshine ratio, day number, and location coordinates. These meteorological variables are solar energy, ambient temperature, and relative humidity. However, three statistical values are used to evaluate the proposed model. These statistical values are mean absolute percentage error, mean bias error, and root mean square error. Based on the results, the developed model predicts accurately the three meteorological variables. The mean absolute percentage error, root mean square error, and mean bias error in predicting solar radiation are 1.3%, 5.8 (1.8%), and 0.9 (0.3%), respectively. While the mean absolute percentage error, root mean square error, and mean bias error values for ambient temperature prediction are 1.3%, 0.4 (1.7%), and 0.1 (0.4%). In addition, the mean absolute percentage error, root mean square error, and mean bias error values in relative humidity prediction are 3.2%, 3.2, and 0.2.
This article presents a method for optimizing the tilt angle of photovoltaic module/array installed in the five sites in Malaysia. The optimization method is based on the Liu and Jordan model for solar energy incident on a tilt surface considering monthly and seasonal tilt angles. The optimization results showed that a seasonal optimum tilt angle change is recommended for the peninsular Malaysia, while a monthly optimum tilt angle change is recommended for east Malaysia comprising the states of Sabah and Sarawak. By applying the monthly optimum tilt angle, the collected yields by the PV module/array in Kuala Lumpur, Johor Bharu, Ipoh, Kuching, and Alor Setar increased by 5.03, 5.02, 5.65, 7.96, and 6.13%, respectively. On the other hand, applying the seasonal optimum tilt angle for the same regions increased the collected yields by 4.54, 4.58, 5.70, 4.11, and 5.85%, respectively.