Enhancing Steady-State power flow optimization in smart grids with a hybrid converter using GBDT-HBA technique

Optimizing steady-state power flow (PF) in Smart Grids (SGs) poses a significant challenge due to the complex interplay of various energy sources, converters, and control mechanisms. Conventional optimization methods often face limitations in terms of efficiency, flexibility, and steady-state error reduction. This manuscript proposes a hybrid technique to optimize steady-state power flow within Smart Grids (SGs) by combining DC/DC converters with DC/AC inverters. The proposed method combines the gradient boosting decision tree (GBDT) and Honey Badger Algorithm (HBA) commonly known as the GBDT-HBA method. The HBA is used to improve the control parameters of the hybrid converter. The GBDT is used to predict the control parameters. Among the generation source and microgrid (MG) system, the energy flow is assessed with energy routers. The proposed technique shows a higher efficiency of 96%, low steady-state error of 0.513 %, and less THD of 2.52 % compared to other existing Salp Swarm Algorithm (SSA), Ant Lion Optimization (ALO), particle swarm optimization (PSO), techniques.