A cloud priority-based dynamic online double auction mechanism (PB-DODAM)
- PDF / 1,659,010 Bytes
- 26 Pages / 595 x 791 pts Page_size
- 59 Downloads / 185 Views
Journal of Cloud Computing: Advances, Systems and Applications
RESEARCH
Open Access
A cloud priority-based dynamic online double auction mechanism (PB-DODAM) S. M. Reza Dibaj1*†
, Ali Miri1† and SeyedAkbar Mostafavi2†
Abstract Double auctions are considered to be effective price-scheduling mechanisms to resolve cloud resource allocation and service pricing problems. Most of the classical double auction models use price-based mechanisms in which determination of the winner is based on the prices offered by the agents in the market. In cloud ecosystems, the services offered by cloud service providers are inherently time-constrained and if they are not sold, the allocated resources for the unsold services are wasted. Furthermore, cloud service users have time constraints to complete their tasks, otherwise, they would not need to request these services. These features, perishability and time-criticality, have not received much attention in most classical double auction models. In this paper, we propose a cloud priority-based dynamic online double auction mechanism (PB-DODAM), which is aligned with the dynamic nature of cloud supply and demand and the agents’ time constraints. In PB-DODAM, a heuristic algorithm which prioritizes the agents’ asks and bids based on their overall condition and time constraints for resource allocation and price-scheduling mechanisms is proposed. The proposed mechanism drastically increases resource allocation and traders’ profits in both low-risk and high-risk market conditions by raising the matching rate. Moreover, the proposed mechanism calculates the precise defer time to wait for any urgent or high-priority request without sacrificing the achieved performance in resource allocation and traders’ profits. Based on experimental results in different scenarios, the proposed mechanism outperforms the classical price-based online double auctions in terms of resource allocation efficiency and traders’ profits while fulfilling the double auction’s truthfulness pillar. Keywords: Priority-based dynamic online double suction, Mechanism design, Cloud secondary market, Dynamic resource allocation
Introduction The cloud ecosystem is a business model that needs an appropriate pricing mechanism to satisfy service providers, as well as service users to survive and grow in the current competitive markets [1]. One of the most prevalent pricing methods is an on-demand pricing model. Since in the on-demand pricing model, customers of cloud computing resources have full control over their operational costs, and they can start and end the use of resources according to their needs, the on-demand pricing model is desirable for them [2, 3]. This mechanism *Correspondence: [email protected] † S. M. Reza Dibaj, Ali Miri and SeyedAkbar Mostafavi contributed equally to this work. 1 Department of Computer Science, Ryerson University, Toronto, Canada Full list of author information is available at the end of the article
is not equally able to meet the interests of cloud service providers, as they are inte
Data Loading...
