Energy-efficient resource allocation in fog computing using hybrid genetic algorithm-based VM consolidation

Fog computing brings cloud-like services closer to data sources, improving responsiveness but also introducing challenges like high energy consumption and inefficient resource use. To tackle this, VM consolidation using live migration is employed to enhance energy efficiency and resource management. This paper introduces a hybrid Genetic Algorithm model that combines various selection strategies—Tournament, Rank, SUS, Truncation, and Roulette-Wheel—to optimize CPU and memory usage during VM consolidation. By using heuristics for population generation, fitness evaluation, and load balancing, the model minimizes active physical machines and adapts to workload changes, improving efficiency in fog data centers.