STAR: Strategy-Proof Double Auctions for Multi-Cloud, Multi-Tenant Bandwidth Reservation

Abstract

Bandwidth reservation has been recognized as a value-added service to the cloud provider in recent years. We consider an open market of cloud bandwidth reservation, in which cloud providers offer bandwidth reservation services to cloud tenants, especially online streaming service providers, who have strict requirements on the amount of bandwidth to guarantee their quality of services. In this paper, we model the open market as a double-sided auction, and propose the first family of STrategy-proof double Auctions for multi-cloud, multi-tenant bandwidth Reservation (STAR). STAR contains two auction mechanisms. The first one, STAR-Grouping, divides the tenants into groups by a bid-independent way, and carefully matches the cloud providers with the tenant groups to form good trades. The second one, STAR-Padding, greedily matches the cloud providers with the tenants, and fills the partially reserved cloud provider(s) with a novel virtual padding tenant who can be a component of the auctioneer. Our analysis shows that both of the two auction mechanisms achieve strategy-proofness and ex-post budget balance. Our evaluation results show that they achieve good performance in terms of social welfare, cloud bandwidth utilization, and tenant satisfaction ratio.

BIGhybrid: a simulator for MapReduce applications in hybrid distributed infrastructures validated with the Grid5000 experimental platform

“…The authors state that, for instance, it is possible to have multiple execution paths for carrying out an MR job in this scenario, and the performance can carry out a great deal. Nevertheless, a popular MR open source, like Hadoop, does not support this feature naturally, and the major Cloud Service Providers (CSPs) do not usually provide a bandwidth guarantee [24].These problems can be overcome by means of a hybrid infrastructure, if there is a file system that supports the incremental updates and highly concurrent data sharing, such as BlobSeer. The solution involves integrating BlobSeer into a DFS on Hadoop by making use of Cloud environment.…”

Resource Management in Cloud Networking Using Economic Analysis and Pricing Models: A Survey

“…The winner determination problem is NP-hard, and the anytime search algorithm [193] can be used which leads to a feasible solution at any time for the bandwidth allocation. However, the joint allocation of bandwidth and other network resources, e.g., base stations and [190] Double auction Cloud providers…”

“…However, the assumption that each gateway knows the bid value of others is not realistic. One shortcoming of the approach in [194] is that the service provider may redistribute bandwidth for all gateways even if • Achieve low computational complexity • Guarantee workflow deadline • Have unreliability in spot instances [162] • Be easy to be implemented • Not use market factors [85] • Achieve win-win solution • Have slow convergence [186] • Address the workload elasticity of users • Be challenging to determine of users' behavior [190] • Support multiple cloud providers and multiple cloud tenants…”

Towards Incentive-Compatible Pricing for Bandwidth Reservation in Community Network Clouds

“…Community networks solve this problem to a large extent through social mechanisms like enforcing reciprocal sharing agreements [1]. Bandwidth reservation has also been under focus recently in the grid systems [4], and in public clouds, both for internal bandwidth within data centre networks [6], and external bandwidth [5,15,20] to the Internet.…”

“…Recent work has explored auctions for incentivizing bandwidth sharing in community networks [18,21], and allocating bandwidth in public clouds [5,15,20] and grid systems [4]. However, the problem of bandwidth allocation for applications in community network clouds has largely been unexplored to the best of our knowledge.…”