GreedEx—a scalable clearing mechanism for utility computing

Scheduling becomes key in dynamic and heterogeneous utility computing settings. Market-based scheduling offers to increase efficiency of the resource allocation and provides incentives to offer computer resources and services. Current market mechanisms, however, are inefficient and computationally intractable in large-scale settings.The contribution of this paper is the proposal as well as analytical and numerical evaluation of GreedEx, an exchange for clearing utility computing markets, based on a greedy heuristic, that does achieve a distinct trade-off: GreedEx obtains fast and near-optimal resource allocations while generating prices that are truthful on the demand-side and approximately truthful on the supply-side.

[1]  David C. Parkes,et al.  Achieving Budget-Balance with Vickrey-Based Payment Schemes in Combinatorial Exchanges , 2001 .

[2]  M. Wellman,et al.  Automated Markets and Trading Agents , 2007 .

[3]  Noam Nisan,et al.  Truthful approximation mechanisms for restricted combinatorial auctions , 2008, Games Econ. Behav..

[4]  Amin Vahdat,et al.  Resource Allocation in Federated Distributed Computing Infrastructures , 2004 .

[5]  Dirk Neumann,et al.  Automated bidding for trading grid services , 2006, ECIS.

[6]  Yoav Shoham,et al.  Truth revelation in approximately efficient combinatorial auctions , 2002, EC '99.

[7]  Ian T. Foster.  Globus Toolkit Version 4: Software for Service-Oriented Systems , 2005, NPC.

[8]  David E. Culler,et al.  Market-based Proportional Resource Sharing for Clusters , 2000 .

[9]  N. Nisan,et al.  The POPCORN market—an online market for computational resources , 1998, ICE '98.

[10]  Leigh Tesfatsion,et al.  Agent-Based Computational Economics: Growing Economies From the Bottom Up , 2002, Artificial Life.

[11]  Michael A. Rappa,et al.  The utility business model and the future of computing services , 2004, IBM Syst. J..

[12]  Dirk Neumann,et al.  A Truthful Heuristic for Efficient Scheduling in Network-Centric Grid OS , 2007, ECIS.

[13]  David Levine,et al.  CABOB: A Fast Optimal Algorithm for Combinatorial Auctions , 2001, IJCAI.

[14]  Warren Smith,et al.  Predicting Application Run Times Using Historical Information , 1998, JSSPP.

[15]  Olov Schelén,et al.  Advance reservations for predictive service in the Internet , 1997, Multimedia Systems.

[16]  Tad Hogg,et al.  Spawn: A Distributed Computational Economy , 1992, IEEE Trans. Software Eng..

[17]  N. Carr.  IT doesn't matter , 2003, IEEE Engineering Management Review.

[18]  Dror G. Feitelson,et al.  Workload Modeling for Performance Evaluation , 2002, Performance.

[19]  Dirk Neumann,et al.  Trading grid services - a multi-attribute combinatorial approach , 2008, Eur. J. Oper. Res..

[20]  Noam Nisan,et al.  Truthful approximation mechanisms for restricted combinatorial auctions: extended abstract , 2002, AAAI 2002.

[21]  Rainer Kolisch,et al.  Project Scheduling Under Partially Renewable Resource Constraints , 1999 .

[22]  Jan Stallaert,et al.  A Market Design for Grid Computing , 2008, INFORMS J. Comput..