Cost Efficient Scheduling Through Auction Mechanism in Cloud Computing

Abstract

Cloud resources provided different types of virtual machine (VM) instances that are assigned to users for particular periods of time. Currently, the process of VM scheduling in Cloud environments is determined by fixed-price scheduling algorithm in which the user pays a fixed amount per unit time in order to obtain the resources. However, such scheduling algorithm is not effective for Cloud since the Cloud’s resources are dynamically allocated and released. To address this issue, an adaptive scheduling algorithm for VM allocation in Cloud environments is proposed. Our market-based scheduling algorithm uses the principle of auction mechanism in order to increase the Cloud providers’ and uses’ satisfaction. Moreover, the scheduling algorithm considers other factors such as auction deadline and network bandwidth with the aim of enhancing the resources utilization and the quality of service (QoS) in Cloud. The simulation experimental results show that the adaptive auction-based scheduling is able to effectively enhance quality of service, profit of Cloud service provider and resource utilization.