An adaptive artificial neural network model for sizing stand-alone photovoltaic systems: application for isolated sites in Algeria

Abstract

In this paper we investigate, by using an adaptive Artificial Neural Network (ANN), in order to find a suitable model for sizing Stand-Alone Photovoltaic (SAPV) systems, based on a minimum of input data. This model combines Radial Basis Function (RBF) network and Infinite Impulse Response (IIR) filter in order to accelerate the convergence of the network. For the sizing of a photovoltaic (PV) system, we need to determine the optimal sizing coefficients (K PV , K B ). These coefficients allow us to determine the number of solar panels and storage batteries necessary to satisfy a given consumption, especially in isolated sites where the global solar radiation data is not always available and which are considered the most important parameters for sizing a PV system. In this way, the adaptive model was trained to accept and even handle a number of unusual cases, the unknown validation sizing coefficients set produced very set accurate estimation and a correlation coefficient of 98% was obtained between the calculated and that estimated by the RBF-IIR model. This result indicates that the proposed method can be successfully used for the estimation of optimal sizing coefficients of SAPV systems for any locations in Algeria, but the methodology can be generalized using different locations over the world.

Cell modelling and model parameters estimation techniques for photovoltaic simulator application: A review

“…Other PV works involving ANN include (a) characterization of crystalline [99] and CIS modules [100], (b) PV sizing algorithm, (c) simulation of a standalone PV system [101,102] and (d) estimation PV energy yield [103,104].…”

Determination of the Working States of a Hybrid (wind-PV) Energy Generation System using Feed Forward NNs, Probit, and Logit

“…There are many variations of the back propagation algorithm. The simplest implementation of back propagation learning updates the network weights and biases in the direction in which the performance function decreases most rapidly the negative of the gradient 6,13 .…”

ANN-based GA for generating the sizing curve of stand-alone photovoltaic systems

“…Hontroria et al [13], have used a multi-layer perceptron (MLP) for generating the sizing curve of stand-alone PV systems from C S , LLP and K DT , for different Spanish locations, however, the proposed MLP needs as input the yearly cleanness index that is related intimately to the solar radiation, therefore the problem of solar radiation is not resolved. Mellit et al [14,15], have used an artificial neural network (ANN) architecture for estimating of the sizing coefficients of stand-alone PV systems based on the synthetic and measured solar radiation data.…”