Prediction Model of Photovoltaic Power in Solar Pumping Systems Based on Artificial Intelligence
Jorge Cervera-Gascó, R. González Perea, J. Montero, M. Moreno
Abstract
Photovoltaic solar energy is becoming very important globally due the benefits of their use. Climate change is resulting in frequent climatic variations that have a direct effect on the energy production in photovoltaic installations, so their good management is essential. This can be a big problem, for example, in photovoltaic pumping systems where irrigated crops can be affected due to lack of water. In this work, a PREPOSOL (PREdiction of POwer in SOLar installations) model was developed in MATLAB® software, which allowed to predict the power generated in the photovoltaic installations up to 3 h in advance using Artificial Neural Networks (ANNs) in a Bayesian framework with Genetic Algorithms. Despite that the PREPOSOL model can be implemented for other activities with photovoltaic solar energy, in this case, it was applied to photovoltaic pumping systems. The results showed that the model estimated the generated power with a relative error (RE) and R2 of 8.10 and 0.9157, respectively. Moreover, a representative example concerning irrigation programming is presented, which allowed adequate management. The methodology was calibrated and validated in a high-power and complex photovoltaic pumping system in Albacete, Spain.