An Approximation Method Of Optimal Scheduling For Multicommodity Flows In Cloud-Service Scenarios. Issue 1 (2nd January 2016)

• Record Type: Journal Article
• Authors: Huang, Dong; Yang, Yong; Tang, Lun; Zhang, Ju; Wang, Xiang
• Is Part Of: Intelligent automation & soft computing. Volume 22:Issue 1(2016)
• Page Start: 143
• Page End: 152
• Publication Date: 2016-01-02
• Subjects: Multicommodity flows -- Communication network -- Optimal approximation method -- Cloud computing; Artificial intelligence -- Periodicals; Intelligent control systems -- Periodicals; 003.5
• DOI: 10.1080/10798587.2015.1048967
• Languages: English
• ISSNs: 1079-8587

Abstract

Abstract: With limited physical and virtual resources in cloud computing systems, it is not feasible to successively expand network infrastructure to adequately support the rapid growth in service. So the pervasive boundary in communication networks is that of allocating bandwidth to satisfy a given collection of service requests is hard to reach. In situations where there is limited network capacity but plethory of requests, the current optimal methodology of the choice of which requests to satisfy, thereby resulting in congestion and low utilization rate. It is imperative to develop new efficient scheduling methods. In this paper, we demonstrate these concepts through a case test study of scheduling for multicommodity flows in cloud-service environment by successive heuristics algorithms, and the heuristic solutions are then compared with the related network performance metrics obtained using the presented model. The effectiveness of the new technique was evaluated by comparison to the differentiated cost utilization and the comparison indicates that substantial improvements are possible. Then the lower cost of deployment on the cloud-computing systems can be justified. Moreover, developing an approximation optimization model can be beneficial to the communication network planning.