A Comparative Analysis of Meta-heuristic Algorithms for Energy Management in Smart Grids

Abstract

—Motivated by the ever-increasing demand for energy and guided by economic and environmental considerations, the smart grid represents a future of tremendous opportunities. It must evolve to seamlessly incorporate the intermittent and decentralized production of renewable energies. This paper con ducts a comprehensive analysis of four well-known meta-heuristic algorithms utilized for addressing energy management challenges in smart grids: Particle Swarm Optimization (PSO), Gorilla Troop Optimizer (GTO), Manta Ray Foraging Optimization (MRFO), and Bald Eagle Search (BES). The study evaluates the performance of each algorithm in terms of solution quality, convergence speed, and efficiency. The experiments specifically examine the adaptability of the algorithms to dynamic changes and their ability to optimize energy utilization within a real-world smart grid scenario.