Research On Dynamic Resource Pricing Based On Combinatorial Double Auction In Cloud Environment

With the development of cloud computing, the future way of working and business model will be a fundamental change. Currently market trading mechanism in cloud computing environment is inflexible, and the vast majority of enterprises have adopted a fixed rate pricing model. It is difficult to meet the different needs of users. Therefore, how to manage the resource pricing and distributed resources is always the key issue in cloud environments.In this thesis, the existing resource pricing methods are studied in detail first. Then, the advantages and disadvantages of various pricing methods are analyzed, and the combinatorial double auction model is summarized. Finally, aiming at maximize profit of resources providers and minimize spending of users under the response time of users’service and budget constraints, a new dynamic resource pricing model, based on combinatorial double auction, is proposed. In this model, the users determine their price according to the amount of respond time, and the resource providers ask price considering the workload of the system. The bid will increase when the respond time are increasing, and when the workload of the resource providers is reducing the ask price will reduce.The results of extensive simulation experiments show that the proposed dynamic resource pricing model, based on combinatorial double auction, scheme is better than the fixed pricing scheme. The profit of resource provider is increased by9%and the rate of resource utilization increased by12%.