Effects of an asynchronous resource allocation protocol on end-to-end service provision

In this paper we present a protocol for acquiring resource bundles from autonomously operating markets and discuss results of experiments that were performed to quantify the protocol performance at high loads. A major finding from from our experiments is that an application class may be penalized by experiencing delays in accessing a shared resource as a result of overload on resources used by other application classes, which are unknown to this class. In turn, these delays may cause under-utilization of other resources used by this application class. Moreover, we illustrate how such effects can emerge by varying the relative occurrence frequencies application classes, but without changing aggregate load of the system.

[1]  Michael P. Wellman,et al.  The Michigan Internet AuctionBot: a configurable auction server for human and software agents , 1998, AGENTS '98.

[2]  Michael P. Wellman,et al.  Market-oriented programming: some early lessons , 1996 .

[3]  Michael P. Wellman,et al.  A Simple Computational Market for Network Information Services , 1995, ICMAS.

[4]  S. Clearwater Market-based control: a paradigm for distributed resource allocation , 1996 .

[5]  Donald F. Ferguson,et al.  An economy for managing replicated data in autonomous decentralized systems , 1993, Proceedings ISAD 93: International Symposium on Autonomous Decentralized Systems.

[6]  K. Mani Chandy,et al.  A General Resource Reservation Framework for Scientific Computing , 1997, ISCOPE.

[7]  Bernardo A. Huberman,et al.  The ecology of computation , 1988, Digest of Papers. COMPCON Spring 89. Thirty-Fourth IEEE Computer Society International Conference: Intellectual Leverage.

[8]  Michael P. Wellman,et al.  The Auction Manager: Market Middleware for Large-Scale Electronic Commerce , 1998, USENIX Workshop on Electronic Commerce.

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

[10]  Dale O. Stahl The Inefficiency of Auctions in Dynamic Stochastic Environments , 1997 .

[11]  Patrick Valduriez,et al.  Principles of Distributed Database Systems , 1990 .

[12]  Donald F. Ferguson,et al.  An economy for flow control in computer networks , 1989, IEEE INFOCOM '89, Proceedings of the Eighth Annual Joint Conference of the IEEE Computer and Communications Societies.

[13]  Michael P. Wellman,et al.  The WALRAS Algorithm: A Convergent Distributed Implementation of General Equilibrium Outcomes , 1998 .

[14]  Maria L. Gini,et al.  A market architecture for multi-agent contracting , 1998, AGENTS '98.

[15]  J. Eriksson,et al.  Information and interaction in marketspace: towards an open agent-based market infrastructure , 1996 .

[16]  Manolis Marazakis,et al.  The Aurora Architecture for Developing Network-Centric Applications by Dynamic Composition of Servic , 1997 .