Adaptive fuzzy logic control based optimal Hopfield neural network of standalone photovoltaic system with battery storage

Abstract

This paper presents the optimized Hopfield Neural Network (HFNN) based Fuzzy Logic Control (FLC) Maximum Power Tracking structure for a renewable Photovoltaic (PV) system under changing climatic conditions. Changing climatic condition of photovoltaic panel yield multiple local and global maximum power points, which creates tracing of the extreme power which is a problematic task. Most of existing traditional techniques fail to operate accurately under this changing weather condition. This paper advances the technique by considering wide search and changing climate so that the designed HFNN trace the maximum power for the entire situation. It is verified for dissimilar weather condition through simulation and proved experimentally. In this paper, the major merit of using optimized new FLC is also presented. HFNN neurons are optimized using new FLC. Comparative tests have been conducted for conventional Perturb and Observe and Incremental Conductance methods. From the outcomes of the simulation results, it is measured that the HFNN technique decreases error and it contributes quick reaction to climatic variations. Moreover, it does not need any external fine-tuning of the structure, unlike existing traditional FLC technique, wherein the regulator gain components want to be altered when solar illumination varies.