Hybrid microgrid optimization for smart cities using Botox algorithm and motif-based heterogeneous attention network

Abstract

Hybrid Microgrid Systems (HMGSs), which integrate solar, wind, biomass, and conventional power grid (PG) resources, are essential for developing sustainable, efficient, and resilient energy infrastructures in smart cities. However, their large-scale deployment is challenged by grid stability issues, energy management (EM) complexities, and storage limitations, particularly when renewable energy (RE) output is insufficient or highly variable. To overcome these drawbacks, this paper suggests a hybrid BOA-MBHAN technique that incorporates the Botox Optimization Algorithm (BOA) with a Motif-Based Heterogeneous Graph Attention Network (MBHAN). The framework enhances the economic, operational, and environmental performance of HMGSs by improving energy distribution, increasing reliability, and reducing both the Levelized Cost of Energy (LCOE) and carbon emissions. BOA has been used in adaptive control and optimization of grid stability through dynamic response to changes in power supply and MBHAN is used to predict the system performance under different operating conditions to maintain balanced energy demand and optimal energy flow. The suggested approach is implemented in MATLAB and compared to existing approaches, such as African Vultures Optimization Approach (AVOA), Modified Bio-Inspired Optimization Algorithm (MBIOA), Particle Swarm Optimization (PSO), Grasshopper Optimization Algorithm (GOA), and Adaptive Local Attractor-based Quantum Behaved PSO (ALA-QPSO). Comparative outcomes prove that the BOA-MBHAN framework improves cost-effectiveness and environmental sustainability, achieving an LCOE as low as $0.30/kWh and reducing CO₂ emissions to 199,016 kg/year, outperforming all competing techniques. These results validate the framework’s potential to support smarter, cleaner, and more resilient urban energy systems.