Hybrid Intelligent Control of Cascaded H-Bridge Multilevel Inverter for Solar PV Systems Using Neural Network-Based MPPT, PID–TCSC, and IWD Optimization

Abstract

This paper presents a hybrid intelligent control approach for a Cascaded H-Bridge Multilevel Inverter (CHB–MLI) integrated with a solar photovoltaic (PV) system to achieve enhanced power quality, transient stability, and fault tolerance under grid-connected conditions. The system combines three coordinated control layers: a Neural Network (NN)-based Maximum Power Point Tracking (MPPT) algorithm for optimal solar energy extraction, a Proportional–Integral–Derivative (PID)-controlled Thyristor Controlled Series Capacitor (TCSC) for voltage stabilization during transient disturbances, and an Intelligent Water Drop (IWD) optimization algorithm for adaptive PQ improvement under unsymmetrical fault conditions. A detailed MATLAB/Simulink model incorporating bidirectional switches, cascaded transformers, and 11-level inverter topology was developed to validate system performance. The NN-MPPT enhanced tracking accuracy and efficiency from 94.5% to 98.6%, maintaining THD below 5%; the PID–TCSC reduced voltage deviation by over 80% and settling time by 60% while improving damping ratio by 150%; and the IWD optimization minimized THD, voltage unbalance, and reactive power deviation by over 60% during L–G, L–L, and L–L–G faults. Simulation results confirm that the proposed hybrid NN–PID–IWD control architecture provides superior efficiency, stability, and PQ performance compared to conventional MPPT and control methods, making it a robust and scalable solution for next-generation grid-connected solar PV systems.