ADSC cloud computing research wins best paper award

4/30/2013 Katie Carr, CSL

ADSC researchers Zhenjie Zhang, Richard Ma, Yin (David) Yang and former ADSC intern Jianbing Ding received the Best Paper Award at the 2013 IEEE International Conference on Cloud Engineering (IC2E) in March.

Written by Katie Carr, CSL

ADSC researchers Zhenjie Zhang, Richard Ma, Yin (David) Yang and former ADSC intern Jianbing Ding received the Best Paper Award at the 2013 IEEE International Conference on Cloud Engineering (IC2E) in March.

Their paper, “ABACUS: An Auction-Based Approach to Cloud Service Differentiation,” describes a new, auction-based resource allocation scheme on the cloud platform. Most existing cloud systems don’t recognize users with different preferences or jobs of different natures. This doesn’t permit the cloud system to provide service differentiation, which allows a company to pay more in order to get better service, such as more space, faster connections or fewer delays. The lack of service differentiation leads to an inefficient allocation of cloud resources.

This figure, MapReduce, explains the architecture of Abacus where virtual machines "map" and "reduce" tasks, which are then auctioned off. Users bid on resources, which are then assigned to jobs.

Abacus is a generic resource management framework that interacts with users to allow them to specify their priorities and job characteristics. Based on this information, Abacus is able to allocate and schedule resources most efficiently.

“A main feature of Abacus is service differentiation, which means that different jobs receive different quality of service, based on the amount of money the owners of the jobs pay to the cloud platform,” Yang said. “Through a carefully designed auction mechanism, Abacus ensures that every job owner’s best bidding strategy is to simply tell their true valuation of the job, thus eliminating the need to play price games.”

To determine pricing of cloud resources, Abacus uses an auction, where users bid more to get more resources, and consequently, better service. Yang added that the auction mechanism ensures nice properties for users, such as monotonicity, which is when a user pays more, they always receive better service, and truth-telling, which is where a user bids on what they can afford, without studying what other users are bidding.

“In a poorly designed auction, each user needs to monitor what others bid and respond accordingly and the price often fluctuates a lot,” Yang said. “Abacus ensures that a user only needs to bid according to her own budget and the price is relatively stable over time.”

As cloud computing is a newly emerging area in the use and delivery of information technology, IC2E is a new conference that seeks to be a forum for researchers and practitioners who are involved in the development of cloud infrastructure and applications.

“Since IC2E is IEEE’s flagship conference on cloud computing, winning the best paper award allows us to enjoy high visibility, which will hopefully lead to many citations to our paper and recognition of the authors, as well as ADSC,” Yang said.

ADSC’s research on cloud computing is in its infancy, with researchers coming from different areas across ADSC. Zhang and Yang bring the perspective of a data management researcher, while Ma contributed from a networking angle. Zhang and Yang gathered initial ideas on how to create an auction mechanism from their previous work on location-based advertising and Ma, who is a game theory background, refined the ideas.

In addition to the award, the researchers will also be submitting an extended version of their paper to a special issue of the IEEE Transactions on Cloud Computing.


Share this story

This story was published April 30, 2013.