Making greed work in networks: a game-theoretic analysis of switch service disciplines

This paper discusses congestion control from a game-theoretic perspective. There are two basic premises: 1) Users are assumed to be independent and selfish. 2) Central administrative control is exercised only at the network switches. The operating points resulting from selfish user behavior depend crucially on the service disciplines implemented in network switches. This effect is investigated in a simple model consisting of a single exponential server shared by many Poisson sources. We discuss the extent to which one can guarantee, through the choice of switch service disciplines, that these selfish operating points will be efficient and fair. We also discuss to what extent the choice of switch service disciplines can ensure that these selfish operating points are unique and are easily and rapidly accessible by simple self optimization techniques. We show that no service discipline can guarantee optimal efficiency. As for the other properties, we show that the traditional FIFO service discipline guarantees none of these properties, but that a service discipline called fair share guarantees all of them. While the treatment utilizes game-theoretic concepts, no previous knowledge of game theory is assumed.

[1]  E. Maskin The Theory of Implementation in Nash Equilibrium: A Survey , 1983 .

[2]  Jeffrey M. Jaffe,et al.  Bottleneck Flow Control , 1981, IEEE Trans. Commun..

[3]  E. L. Hahne,et al.  Round-Robin Scheduling for Max-Min Fairness in Data Networks , 1991, IEEE J. Sel. Areas Commun..

[4]  K. K. Ramakrishnan,et al.  A binary feedback scheme for congestion avoidance in computer networks with a connectionless network layer , 1988, SIGCOMM '88.

[5]  Beverly A. Sanders,et al.  An Incentive Compatible Flow Control Algorithm for Rate Allocation in Computer Networks , 1988, IEEE Trans. Computers.

[6]  Raj Jain,et al.  A delay-based approach for congestion avoidance in interconnected heterogeneous computer networks , 1989, CCRV.

[7]  Beverly A. Sanders,et al.  An Asynchronous, Distributed Flow Control Algorithm for Rate Allocation in Computer Networks , 1988, IEEE Trans. Computers.

[8]  John B. Nagle,et al.  On Packet Switches with Infinite Storage , 1987, IEEE Trans. Commun..

[9]  Jean Michel Régnier Priority assignment in integrated services networks , 1986 .

[10]  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.

[11]  H. Moulin,et al.  Serial Cost Sharing , 1992 .

[12]  H. Varian,et al.  Theories of Justice Based on Symmetry , 1984 .

[13]  Scott Shenker,et al.  A Theoretical Analysis of Feedback Flow Control , 1990, SIGCOMM.

[14]  Christos Douligeris,et al.  A game theoretic perspective to flow control in telecommunication networks , 1992 .

[15]  Scott Shenker,et al.  Efficient Network Allocations with Selfish Users , 1990, Performance.

[16]  H. Moulin Joint Ownership of a Convex Technology: Comparison of Three Solutions , 1990 .

[17]  Edward G. Coffman,et al.  A Characterization of Waiting Time Performance Realizable by Single-Server Queues , 1980, Oper. Res..

[18]  Aurel A. Lazar,et al.  On the existence of equilibria in noncooperative optimal flow control , 1995, JACM.

[19]  V. Jacobson,et al.  Congestion avoidance and control , 1988, CCRV.

[20]  H. Moulin,et al.  Average Cost Pricing versus Serial Cost Sharing: An Axiomatic Comparison , 1994 .

[21]  Manolis Katevenis,et al.  Fast switching and fair control of congested flow in broadband networks , 1987, IEEE J. Sel. Areas Commun..

[22]  Aurel A. Lazar,et al.  A Game Theoretic Approach to Decentralized Flow Control of Markovian Queueing Networks , 1987, Performance.

[23]  H. Moulin Uniform externalities: Two axioms for fair allocation , 1990 .

[24]  M. Satterthwaite,et al.  Strategy-Proof Allocation Mechanisms at Differentiable Points , 1981 .

[25]  Scott Shenker,et al.  Analysis and simulation of a fair queueing algorithm , 1989, SIGCOMM 1989.