Access Type

Open Access Dissertation

Date of Award

January 2013

Degree Type


Degree Name



Computer Science

First Advisor

Daniel Grosu


Current cloud providers use fixed-price based mechanisms to allocate Virtual Machine (VM) instances to their users. But economic theory states that when there are large amount of resources to be allocated to large number of users, auctions are the most efficient allocation mechanisms. Auctions achieve efficiency of allocation and also maximize the providers' revenue, which a fixed-price based mechanism is unable to do. We argue that combinatorial auctions are best suited for the problem of VM provisioning and allocation in clouds, since they provide the users with the most flexible way to express their requirements. In combinatorial auctions, users bid for bundles of items rather than individual ones, therefore they are able to express whether the items they require are complementary to each other. The objective of this Ph.D. dissertation is to design, study, and implement combinatorial auction-based mechanisms for efficient provisioning and allocation of VM instances in clouds. The central hypothesis is that allocation efficiency and revenue maximization can be obtained by inducing users to fully express and truthfully report their preferences to the system. The rationale for our research is that, once efficient resource provisioning and allocation mechanisms that take into account the incentives of the users and cloud providers are developed and implemented, it will become more efficient to utilize cloud computing environments for solving challenging problems in business, science and engineering. In this dissertation, we present three combinatorial auction-based offline mechanisms to provision and allocation VM instances in clouds. We also present an online mechanism for dynamic provisioning of virtual machine instances in clouds. Finally, we designed an efficient bidding algorithm to assist users submitting bids to combinatorial auction-based mechanisms to execute parallel jobs the cloud. We outline our contribution and possible direction for future research in this field.