An Economic Framework for Resource Allocation in Ad-hoc Grids

Doctoral thesis English OPEN
Pourebrahimi, B. (2009)

In this dissertation, we present an economic framework to study and develop different market-based mechanisms for resource allocation in an ad-hoc Grid. Such an economic framework helps to understand the impact of certain choices and explores what are the suitable mechanisms from Grid user/owner perspectives under given circumstances. We focus on resource allocation in a Grid-based environment in the case where some resources are lying idle and could be linked with overloaded nodes in a network. In such networks, the resources are neither necessarily dedicated nor have predictable availability at any point in time. We call such networks ad-hoc Grids. Self-interested nodes in ad-hoc Grids are considered as consumers (buyers) and producers (sellers) of resources within the economic framework. Consumers and producers of resources are autonomous agents that cooperate through a simple, single metric namely the price that summarizes the global state of a network in a number. The price represents all the available information that may reside at the level of the individual nodes and that is not necessarily shared among them. A middle agent, named the matchmaker, sets up a mutual agreement between consumer and producer agents based on the price by employing economic mechanisms such as auctions. The transaction is established when the consumer and producer constraints such as resource quantity, time, and budget are met. In this dissertation, we study market-based resource allocation mechanisms at macro and micro levels. Macroeconomics addresses the behavior of an economy at the aggregate level and microeconomics describes the individual behavior. At the macro level, we compare different economic models as the matchmaking mechanisms. We study the impact of choosing particular auction mechanisms in the framework. At the micro-level, we study different pricing mechanisms and investigate the effect of introducing money and budget constraints. Furthermore, we analyze different bidding strategies that help agents to better achieve their objectives under varying constraints.
  • References (77)
    77 references, page 1 of 8

    [24] Murshed M. Buyya, R. Gridsim: A toolkit for the modeling and simulation of distributed resource management and scheduling for grid computing. Concurrency and Computation: Practice and Experience, 14(13-15):1175-1220, 2002.

    [25] R. Buyya, D. Abramson, and J. Giddy. Nimrod/g: an architecture for a resource management and scheduling system in a global computational grid. In Proceedings of The Fourth International Conference on High Performance Computing in Asia-Pacific Region (HPC Asia 2000), USA, 2000. IEEE Computer Society Press.

    [26] R. Buyya, D. Abramson, Jonathan Giddy, and Heinz Stockinger. Economic models for resource management and scheduling in grid computing. Concurrency and Computation: Practice and Experience, 14(13-15):1507-1542, 2002.

    [27] R. Buyya, D. Abramson, and S. Venugopal. The grid economy. Special Issue on Grid Computing, Proceedings of the IEEE, 93:698-714, 2005.

    [28] Rajkumar Buyya, David Abramson, and Jonathan Giddy. An economy driven resource management architecture for global computational power grids. In PDPTA, 2000.

    [29] Junwei Cao, Daniel P. Spooner, Stephen A. Jarvis, and Graham R. Nudd. Grid load balancing using intelligent agents. Future Gener. Comput. Syst., 21(1):135-149, 2005.

    [30] H. Casanova and J. Dongarra. Netsolve: A network server for solving computational science problems. Technical report, University of Tennessee, Knoxville, TN, USA, 1995.

    [31] Shang-Wen Cheng, David Garlan, Bradley Schmerl, Peter Steenkiste, and Ningning Hu. Software architecture-based adaptation for grid computing. In Proceedings of the 11th IEEE Int. Symposium on High Performance Distributed Computing, page 389, Washington, DC, USA, 2002. IEEE Computer Society.

    [32] Ian Clarke, Oskar Sandberg, Brandon Wiley, and Theodore W. Hong. Freenet: A distributed anonymous information storage and retrieval system. Lecture Notes in Computer Science, 2009:46+, 2001.

    [33] Scott H. Clearwater, editor. Market-based control: a paradigm for distributed resource allocation. World Scientific Publishing Co., Inc., River Edge, NJ, USA, 1996.

  • Metrics
    No metrics available
Share - Bookmark

  • Download from
    TU Delft Repository via NARCIS (Doctoral thesis, 2009)
  • Cite this publication