Solar irradiation forecasting technologies: A review

Abstract

Renewable energy has received a lot of attention in the previous two decades when it comes to meeting electrical needs in the home, industrial, and agricultural sectors. Solar forecasting is critical for the efficient operation, scheduling, and balancing of energy generation by standalone and gridconnected solar PV systems. A variety of models and methods have been developed in the literature to forecast solar irradiance. This paper provides an analysis of the techniques used in the literature to forecast solar irradiance. The main focus of the study is to investigate the influence of meteorological variables, time horizons, climatic zone, pre-processing technique, optimization & sample size on the complexity and accuracy of the model. Due to their nonlinear complicated problem solving skills, artificial neural network based models outperform other models in the literature. Hybridizing the two models or performing pre-processing on the input data can improve their accuracy even more. It also addresses the various main constituents that influence a model s accuracy. The paper provides key findings based on studied literature to select the optimal model for a specific site. This paper also discusses the metrics used to measure the efficiency of forecasted model. It has been observed that the proper selection of training and testing period also enhance the accuracy of the model.