An Enhanced Hybrid Genetic Algorithm And Particle Swarm Optimization Based on Small Position Values for Tasks Scheduling in Cloud

Cloud computing is becoming irresistible considering its benefits, such as low maintenance, up-front costs and ease of scaling. On the other hand, the proliferation of cloud users is causing the expansion of more data centres that require a lot of power. As such, it triggered the problem of energy consumption in data centre storage systems and emission of carbon footprints in the cloud environments. To mitigate the problems, many approaches based on hybrid GA-PSO were proposed in the literature for tasks scheduling in the cloud infrastructure to efficiently manage cloud resources, enhance energy efficiency and quality of service (QoS). The already discussed GA-PSO typically applied randomization in generating initial population. However, in solving tasks scheduling problems, randomness slows convergence speed of the algorithm. In this paper, we propose an enhanced hybrid of Genetic algorithm (GA) and Particle Swarm Optimization (PSO) (GA-PSO) by applying small position values (SPV) to generate initial population to deviate from the limitation of the randomness and improve convergence speed. The proposed enhance GA-PSO with SPV is applied to efficiently schedule tasks to cloud computing resources. The result indicated that the propose GA-PSO perform better than the classical hybrid GA-PSO algorithm in terms of makespan and resource utilization.