An Efficient Resource Allocation Mechanism Based on Dynamic Pricing Reverse Auction for Cloud Workflow Systems

The reverse auction method is widely applied to resource allocation for cloud workflow systems, and it dynamically allocates resources depending on the supply and demand of market. However, during the auction the price of cloud resource is usually fixed, and the resource allocation mechanism cannot adapt to the changeful market. This results in low efficiency of resource utility. In this paper, we first propose a dynamic pricing strategy in reverse auction, and then present an efficient resource allocation mechanism based on dynamic pricing reverse auction. During the auction, providers change resource price according to the trade situation so that the novel mechanism can increase chances of making a deal and improve efficiency of resource utility. In addition, providers improve their competitiveness by lowering price. Simultaneously users are timelier to get resources with the increasing of trade rate. Therefore, users can obtain cheaper resources in shorter time, which decrease monetary cost and completion time for workflow execution. The experiments show that our mechanism can achieve better results in resource utility, monetary cost and completion time compared to BOSS algorithm.