• Adaptive ANN-HHO for voltage regulation and loss minimization. • Gradient-informed boosting improves convergence and stability. • Multi-objective constraints in hybrid AC/DC microgrids. • Validated on 9-bus system under balanced and unbalanced loads. This paper introduces an enhanced Artificial Neural Network-Harris Hawks Optimization (ANN–HHO) framework for voltage regulation and power losses minimization in a 9-bus hybrid AC/DC microgrid with a 100 kW photovoltaic (PV) subsystem. The proposed controller optimizes the inverter duty cycle to achieve optimal power flow and maintain voltage stability within strict limits ( ± 5% of nominal base voltage 230 V) under balanced and unbalanced load conditions. Key enhancements are introduced to the standard HHO, including a variance-based adaptive weighting mechanism for multi-objective balance, ANN-weight-normalized constraint penalties, and a gradient-informed energy boosting strategy that dynamically refines the HHO exploration–exploitation equilibrium. The framework is validated through 24-h MATLAB/Simulink simulations under time-varying load conditions. The results demonstrate the effectiveness of the proposed adaptive optimization framework in enhancing efficiency, voltage stability, and dynamic performance of hybrid AC/DC microgrids, and show improved performance over the traditional method. The proposed method achieves voltage regulation within 0.95–1.05 pu, improves active power performance by up to 18.5%, enhances reactive power support exceeding 60% at critical buses, and reduces line power losses by 85% on average, with stable and efficient operation. The findings provide a robust foundation for future developments incorporating multi-source integration and advanced AI-based control.
Kamoona et al. (Fri,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: