Prediction Model of Photovoltaic Power in Solar Pumping Systems Based on Artificial Intelligence

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.

Analysis of the Use of a Low-Power Photovoltaic System to Power a Water Pumping Station in a Tourist Town

“…Only then should the guarantee of energy supplies from RES be taken care of. The results and conclusions we obtain can be used to further research on and the optimization of the processes of selecting the optimal pump size, pump operation schedules, or pump operation control similar to research carried out on larger facilities with a different work structure [26,30,31], as well as the modernization of water distribution systems: the renovation of pipes or cooperation of the pumping station with the reservoir. The obtained results relate to a PV installation with a permanent structure facing south.…”

“…Tracking can be optimized using a new hybrid FL-INC optimization algorithm for the solar water pumping system [30]. The use of Artificial Neural Networks (ANNs) mathematical modeling has allowed to us predict the power generated in the photovoltaic installation for up to 3 h of pumping water in agriculture [31].…”

Daily Prediction Model of Photovoltaic Power Generation Using a Hybrid Architecture of Recurrent Neural Networks and Shallow Neural Networks

“…Cervera et al [38] present a model that allows forecasting the energy generated in the photovoltaic installations of a solar plant up to 3 hours in advance using deep RNN in a Bayesian structure optimized by a genetic algorithm. It must be considered that each input of the forecast model is a time series, so it is necessary to analyze the seasonality and trend of each input variable.…”

“…From the previous research analyzed, it can be deduced that there is a large number of works that have developed forecasts of photovoltaic energy production ( [3,17,19]), many of which use RNN techniques with LSTM structure ( [20,21,33,36,37,38,42]). Although there are works that combine RNN techniques with statistical methods, such as ARMA, ARIMA, SAR-IMA, and Pearson's coefficients, among others ( [22,26,35]), in most cases, they do not use a large volume of data for model training and validation.…”

Sliding mode controller with fuzzy supervisor for MPPT of Photovoltaic Pumping system

“…In this context, several works are interested to the MPPT algorithms. There exist three big categories of MPPT algorithms, which are known as conventional methods, artificial intelligence and hybrid methods [5,6]. Various works have been interested to PV water pumping system [7,8,9].…”