Energy and Time Efficient Task Scheduling in Cloud Computing Using a Hybrid Genetic Algorithm - Approach

Abstract

Efficient task scheduling in cloud computing is a challenging problem, particularly when multiple competing objectives such as execution time, power consumption, and resource utilization must be optimized simultaneously. Traditional metaheuristic algorithms like Genetic Algorithms (GA) and Multi-Objective Particle Swarm Optimization (MOPSO) have been widely applied, but they suffer from drawbacks including premature convergence, limited diversity preservation, and difficulty in maintaining a well-distributed Pareto front. This paper proposes a hybrid GA-MOPSO algorithm in which GA’s crossover and mutation operators are embedded directly into the MOPSO updating process. Unlike conventional sequential or loosely coupled hybrids, our design allows GA to dynamically inject new genetic diversity into the swarm at each iteration, thereby preventing stagnation and guiding particles towards unexplored regions of the Pareto front. This integration preserves MOPSO’s fast convergence while enhancing diversity and solution quality through GA’s exploration capabilities. Simulation results on benchmark cloud scheduling scenarios demonstrate that the proposed algorithm consistently outperforms standalone GA and MOPSO in terms of makespan, energy efficiency, and average response ratio. These results prove the effectiveness of the proposed hybrid approach in multi-objective scheduling problems of cloud environment.