Resource virtualization methodology for on-demand allocation in cloud computing systems

  • Authors:

  • Xiaojun Chen;Jing Zhang;Junhuai Li;Xiang Li

  • Affiliations:

  • School of Computer Science and Engineering, Xi'an University of Technology, Xi'an, China;School of Computer Science and Engineering, Xi'an University of Technology, Xi'an, China and State Key Laboratory for Manufacturing Systems Engineering, Xi'an Jiaotong University, Xi'an, China;School of Computer Science and Engineering, Xi'an University of Technology, Xi'an, China;School of Computer Science and Engineering, Xi'an University of Technology, Xi'an, China

  • Venue:
  • Service Oriented Computing and Applications
  • Year:
  • 2013

Quantified Score

Hi-index 0.00

Visualization

Abstract

The resources' heterogeneity and unbalanced capability, together with the diversity of resource requirements in cloud computing systems, have produced great contradictions between resources' tight coupling characteristics and user's multi-granularities requirements. We propose a resource virtualization model and its on-demand allocation oriented infrastructure mainly providing computing services to solve that problem. A loosely coupled resource environment centered on resource users is created to complete a mapping from physical view of resources to logic view of resources. Heuristic resource combination algorithm (HRCA) is proposed to transform physical resources to logic resources, which meets two requirements: randomness in combination and fluctuation control to the size of resources granularities. On the basis of the appraisal indexes presented for the on-demand allocation, resource matching algorithm (RMA), targeting at resource satisfaction with the highest resource utilization, is designed to reuse resources. RMA can satisfy users' requirement in limited time and keep resource satisfaction in the highest level in the condition of logic resources granularities being less than their required size. Resource reconfiguration algorithm (RRA) is presented to implement resource matching in the condition that virtual computing resource pool cannot match granularities of resource requirements. RRA assures the lowest resource refusal rate and the greatest resource satisfaction. We verify the effectiveness, performance and accuracy of algorithms in implementing the goal of resource virtualization centered on resource users and on-demand allocation.