Intelligent control of hybrid energy storage system using NARX-RBF neural network techniques for microgrid energy management

This article presents an energy management strategy (EMS) for a hybrid energy storage system (HESS) within a direct current (DC) microgrid (MG). The system under study comprises a photovoltaic (PV) system and a HESS, which includes a battery energy storage system (BESS) and a supercapacitor (SC). This SC is employed to reduce the effects of high transitional current charge/discharge rates on the BESS, therefore balancing transient power imbalances. The proposed control approach is primarily designed to control battery discharge and charging cycles through the use of a nonlinear autoregressive exogenous input neural network (NARX). The proposed controller can additionally maintain the state of charge (SOC) of the battery within tolerable limits for a long time. The EMS attempts to reduce loads and deep discharges by decreasing PV generation to prolong the life of BESS. With a high gain converter, the radial basis function neural network (RBFNN) is used for maximum power point tracking (MPPT). This technique reduces the input current ripple and the voltage stress on power semiconductor devices to predict the duty cycle value. The RBF achieves an efficiency of 97.25 %. The performance of the proposed algorithm is examined under different irradiations and load variations. MATLAB was used to model 5 KW of the PV generator and the HESS system. The findings show how well the control strategy stabilizes DC bond voltage and lowers HESS-SOC stresses in both transitional and steady-state scenarios.