Maximum power point tracking and power flow management of hybrid renewable energy system with partial shading capability: A hybrid technique

A grid connected hybrid energy system combining wind turbine (WT) and photovoltaic (PV) array generating system with energy storage system to supply continuous power to the load using hybrid technique is exhibited in this dissertation. The proposed hybrid technique is the joint execution of both the binary chaotic crow search optimizer (BCCSO) with grey wolf optimizer and random forest algorithm (GWORFA) and hence it is named as BCCSO-GWORFA technique. The main aim of the proposal is to optimally track the maximum power point tracking (MPPT) and to maintain the power flow of the grid connected HRES. Here, the BCCSO-based MPPT procedure optimizes the exact duty cycles required for the DC-DC converter of the PV under partial shading conditions and WT system under variable speed conditions based on the voltage and current parameters. On the other hand, the grey wolf optimizer (GWO) learning procedure-based random forest algorithm (RFA) predicts the control signals of the voltage source inverter (VSI) based on the active and reactive power variations available in the load side. To predict the control parameters, the proposed technique considers power balance constraints like RES accessibility, storage element state of charge, and load side power demand. The proposed strategy is implemented in MATLAB/Simulink working platform. The performance of the HRES is assessed by utilizing the comparison analysis with the existing techniques. The comparison results invariably prove the proposed hybrid technique effectiveness and confirm its potential to solve the related issues with efficiency of 99.5%.