Application of neural networks and genetic algorithms for sizing of photovoltaic systems

In this paper, an artificial neural network-based genetic algorithm (ANN-GA) model was developed for generating the sizing curve of stand-alone photovoltaic (SAPV) systems. Firstly, a numerical method is used for generating the sizing curves for different loss of load probability (LLP) corresponding to 40 sites located in Algeria. The inputs of ANN-GA are the geographical coordinates (Lat, Lon and Alt) and the LLP while the output is the sizing curve represented by CA=f(CS). Subsequently, the proposed ANN-GA model has been trained by using a set of 36 sites, whereas data for 4 sites which are not included in the training dataset have been used for testing the ANN-GA model. The results obtained are compared and tested with those of the numerical method. In addition, two new regression models have been developed and compared with the conventional regression models. The results show that, the proposed exponential regression model with three coefficients presents more accurate results than the conventional regression models. A new ANN has been used for predicting the sizing coefficients for the best regression model. These coefficients can be used for developing the sizing curve in different locations in Algeria. The results obtained showed that the coefficient of multiple determination (R2) is 0.9998, which can be considered as very promising.