Optimization Workflow of Hybrid Renewable Energy System Using Hybrid GBDT Controller

Abstract

Hybrid renewable energy systems (HRES), particularly those integrating solar and wind sources, have emerged as promising solutions to the global energy crisis. However, the nonlinear and time-varying characteristics of these resources pose significant challenges to consistently harvesting maximum power. Maximum Power Point Tracking (MPPT) is essential to ensure optimal performance under varying environmental conditions, yet traditional MPPT controllers often suffer from slow dynamic response and fixed step-size limitations. To address these issues, this work introduces an enhanced optimization-driven control strategy that integrates a Gradient Boosting Decision Tree (GBDT) model with an advanced metaheuristic optimization algorithm. The proposed hybrid framework determines the optimal duty cycle of the boost converter in a solar–wind energy system, enabling rapid and accurate convergence to the maximum power point. The method is implemented and evaluated in MATLAB/Simulink, and the results demonstrate significant improvements in tracking speed, stability, and overall power extraction efficiency compared to conventional MPPT techniques