Solar System Integrated Smart Grid Utilizing Hybrid Coot-Genetic Algorithm Optimized ANN Controller

Abstract

With the global shift toward sustainable power generation, Hybrid Renewable Energy Sources (HRES) that integrate wind and solar are gaining prominence. While they offer clean energy advantages, its variable nature poses challenges for grid integration, often causing voltage fluctuations and frequency deviations that threaten system stability. To address these issues, this work proposes an Internet-of-Things (IoT)-enabled smart grid framework capable of real-time monitoring of solar, wind, battery and grid parameters. The system employs an Improved High-Gain Q-Boost (IHGQ) converter to enhance the photovoltaic (PV) system output voltage, while performance is further optimized using a Hybrid Coot–Genetic Algorithm (HCGA)-based Artificial Neural Network (ANN) controller, which combines the strengths of Coot Optimization and Genetic Algorithm methods for precise control parameter tuning. IoT-enabled sensors and communication modules ensure accurate, timely data acquisition to support dynamic grid adjustments. Validation through MATLAB/Simulink simulations and a laboratory prototype demonstrates a peak efficiency of 96.66% with a minimal settling time of 0.04 s, enabling efficient energy flow management in the HRES while enhancing grid stability and overall system performance.