Prediction of the Electricity Generation of a 60-kW Photovoltaic System with Intelligent Models ANFIS and Optimized ANFIS-PSO

The development and constant improvement of accurate predictive models electricity generation from photovoltaic systems provide valuable planning tools for designers, producers, self-consumers. In this research, an adaptive neuro-fuzzy inference model (ANFIS) was developed, which is intelligent hybrid that integrates the ability to learn by itself provided neural networks function language expression, how fuzzy logic infers, ANFIS optimized particle swarm algorithm, both with a capacity about eight months. were developed using Matlab® software trained four input variables (solar radiation, module temperature, ambient wind speed) electrical power generated (PV) system as output variable. models’ predictions compared experimental data evaluated rigorous statistical metrics, obtaining results RMSE = 1.79 kW, RMSPE 3.075, MAE 0.864 MAPE 1.47% ANFIS, 0.754 1.29, 0.325 0.556% ANFIS-PSO, respectively. evaluations indicate have good capacity. However, PSO integration into allows improving capability behavior system, provides better tool.