Renewable energy has received a lot of attention in the previous two decadeswhen it comes to meeting electrical needs in the home, industrial, andagricultural sectors. Solar forecasting is critical for the efficient operation,scheduling, and balancing of energy generation by standalone and grid-connected solar PV systems. A variety of models and methods have beendeveloped in the literature to forecast solar irradiance. This paper provides ananalysis of the techniques used in the literature to forecast solar irradiance.The main focus of the study is to investigate the influence of meteorologicalvariables, time horizons, climatic zone, pre-processing technique, optimiza-tion & sample size on the complexity and accuracy of the model. Due to theirnonlinear complicated problem solving skills, artificial neural network basedmodels outperform other models in the literature. Hybridizing the two modelsor performing pre-processing on the input data can improve their accuracyeven more. It also addresses the various main constituents that influence amodel’s accuracy. The paper provides key findings based on studied literatureto select the optimal model for a specific site. This paper also discussesthe metrics used to measure the efficiency of forecasted model. It has beenobserved that the proper selection of training and testing period also enhancethe accuracy of the model.