SOLAR RADIATION FORECASTING USING ADAPTIVE NEURO FUZZY INFERENCE SYSTEM (ANFIS)

Abstract

Hybrid intelligent systems have previously been centered on forecasting solar energy using meteorological data parameters; nevertheless, such forecasting approaches have yielded unreliable results. The goal of this research is to design and develop ANFIS model for forecasting solar energy based on widely shifting environmental factors utilizing experimental data collected in Abuja. This is accomplished by developing a system that predicts solar energy generation using an Artificial Neural Network (ANN) and fuzzy logic. This research examines four Adaptive Neuro Fuzzy Inference System (ANFIS) models that were developed and tested in Abuja, Nigeria, for horizontal sun radiation prediction. These models were generated by varying the number of inputs for each model with the output being solar radiation. Data set of 30 years were collected from the National Space Research Development Agency (NASDRA) and procured for the presented simulation study. Simulation using ANFIS methodology was carried out using MATLAB Tool. The obtained data was divided into two categories: training and testing with training having 70% and testing 30% of the data sets. The simulation results were checked against the data and confirmed to be within allowable limits. The coefficients of determination (R2), correlation coefficient(R), Mean Square Error (MSE), Root Mean Square Error (RMSE) were calculated to demonstrate the effectiveness of the proposed machine learning models. It can be safely concluded that model 4 gave an accurate result with high efficiency and less error.