Scheduling Problems For Cloud Computing

Abstract

Abstract. Cloud computing, the long-held dream of computing as a utility, has the potential to transform a large part of the IT industry, making software even more attractive as a service and shaping the way in which hardware is designed and purchased. From the theoretical aspect, we mainly accomplish three research issues. Firstly, we solve the resource allocation problem in the user-level of cloud scheduling. We propose game theoretical algorithms for user bidding and auctioneer pricing.With Bayesian learning prediction, resource allocation can reach Nash equilibrium among non-cooperative users even though common knowledge is insufficient. Secondly, we address the task scheduling problem in the system-level of cloud scheduling. We prove a new utilization bound to settle on-line schedulability test considering the sequential feature of MapReduce. We deduce the relationship between cluster utilization bound and the ratio of Map to Reduce. This new schedulable bound with segmentation uplifts classical bound which is most used in industry.