Sizing of stand-alone photovoltaic power supply system based ongenetic algorithm and neuro-fuzzy: application for isolated areas

摘要

This paper deals with the application of genetic algorithm (GA) and an adaptive neuro-fuzzy inferencescheme (ANFIS), for the prediction of the optimal sizing coefficient of stand-alone photovoltaic supply(SAPVS) systems in remote areas. A database of total solar radiation data for 60 sites in Algeria has beenused to determinethe iso-reliability curves of a PVS system (CA, Cs) for each site. Initially, the GA is usedfor determining theoptimal coefficient (C_(Aop),C_(Sop)) for each site by minimising the optimal cost (objectivefunction). These coefficients allow the determination of the number of PV modules and the capacity of thebattery. Subsequently, an ANFIS is used for the prediction of the optimal coefficient in remote areas basedonly on geographical coordinates. Therefore, 56 couples of C_(A op)andC_(Sop)have been used for the trainingof the network and four couples have been used for testing and validation of the proposed technique. Thesimulation results have been analysed and compared with the alternative techniques. The technique hasbeen applied and tested for Algeria locations, but it can be generalised for any location in the world.