An approach to dynamically assigning cloud resource considering user demand and benefit of cloud platform

Abstract

Cloud computing, with the features of flexible resource assignment, timely on-demand service and transparent by-quantity pricing, has been widely applied recently. As a new business service model, cloud platform must be capable of satisfying user demand and enhancing quality of service. Therefore, an excellent resource scheduling scheme is requisite to improve the working efficiency of cloud platform and ensure its stability. To achieve the goal of meeting user demand and maximizing the benefit of cloud platform, a dynamic allocation model for cloud resource, which takes into account requirement of users and benefit of cloud platform, is proposed. On the one hand, the concept of user satisfaction is presented to meet the different requirements of different users on time and cost. And a dynamic pricing model is designed to realize the flexible conversion between time and cost, which can instead serve to ensure quality of service and win customer loyalty. On the other hand, genetic algorithm is employed to schedule cloud resources, which can reduce operating cost, shorten makespan, lessen energy consumption, and ensure load balancing, stability and fluency of cloud platform, in order to maximize the benefit of cloud platform as possible. Finally, the results of 5 comparative experiments show that the dynamic pricing model presented is reasonable and the dynamic resource assignment scheme proposed is feasible and efficient.