Optimizing Microgrid Performance: Integrating Unscented Transformation and Enhanced Cheetah Optimization for Renewable Energy Management

Abstract

The increased integration of renewable energy sources (RESs), such as photovoltaic and wind turbine systems, in microgrids poses significant challenges due to fluctuating weather conditions and load demands. To address these challenges, this study introduces an innovative approach that combines Unscented Transformation (UT) with the Enhanced Cheetah Optimization Algorithm (ECOA) for optimal microgrid management. UT, a robust statistical technique, models nonlinear uncertainties effectively by leveraging sigma points, facilitating accurate decision-making despite variable renewable generation and load conditions. The ECOA, inspired by the adaptive hunting behaviors of cheetahs, is enhanced with stochastic leaps, adaptive chase mechanisms, and cooperative strategies to prevent premature convergence, enabling improved exploration and optimization for unbalanced three-phase distribution networks. This integrated UT-ECOA approach enables simultaneous optimization of continuous and discrete decision variables in the microgrid, efficiently handling uncertainty within RESs and load demands. Results demonstrate that the proposed model significantly improves microgrid performance, achieving a 10% reduction in voltage deviation, a 10.63% decrease in power losses, and an 83.32% reduction in operational costs, especially when demand response (DR) is implemented. These findings validate the model’s efficacy in enhancing microgrid reliability and efficiency, positioning it as a viable solution for optimized performance under uncertain renewable inputs.