An Enhanced BPSO based Approach for Service Placement in Hybrid Cloud
Due to the challenges of competition and the rapidly evolving market, companies need to be innovative and agile, particularly in regard of web applications as used by customers. Nowadays, hybrid cloud stands as an attractive solution as organizations tend to use a combination of private and public cloud implementations, in accordance with their appropriate needs to profitably apply the available resources and speed of execution. In such a case, deploying the new applications would certainly entail opting for placing and consecrating some components to the private cloud option, while reserving some others to the public cloud option. In this respect, our primary goal in this paper consists in minimizing the extra costs likely to be incurred by applying the public cloud related options, along with those costs involved in maintaining communication between the private cloud system and the public cloud framework. As for our second targeted objective, it lies in reducing the decision process relating to the execution time, necessary for selecting the optimal service placement solution. For this purpose, a novel Binary Particle Swarm Optimization (BPSO) based approach is proposed, useful for an effective service placement optimization within hybrid cloud to take place. Using a real benchmark, the experimental results appear to reveal that our proposed approach reached results that outperform those documented in the state of the art both in terms of cost and time.
READ FULL TEXT