CLUSTERING-ENHANCED MOPSO FOR UAV-BS PLACEMENT IN DISASTERAFFECTED SMART GRID NETWORKS

Natural disasters pose a significant threat to smart grid infrastructure, often causing simultaneous failures in both power and communication systems. These disruptions fragment the grid into isolated microgrids, or "islands," hindering coordinated restoration efforts. To address this challenge, we propose a novel multi-objective optimization framework for the strategic placement of unmanned aerial vehicle base stations (UAV-BSs) in disaster-stricken environments. UAV-BSs serve as mobile relay nodes, enabling temporary communication between power sources (PSs) and static base stations (SBSs), thereby facilitating grid reintegration. Our method jointly optimizes the 3D placement of UAV-BSs&mdashhorizontal coordinates and altitude&mdashwhile balancing five conflicting objectives: minimizing the number of UAV-BSs, reducing the number of unserved PSs (NAPS), maximizing system throughput, maximizing energy efficiency, and ensuring full interconnection of islands. We introduce an enhanced multi-objective particle swarm optimization (MOPSO) algorithm with clustering-based initialization to improve convergence and solution quality. Simulation results on synthetic disaster scenarios and the Simbench dataset demonstrate the effectiveness of our approach in achieving robust, energy-efficient, and cost-effective UAV-BS deployment for smart grid recovery.