Rate-based reliable multicast congestion control

This work address two important challenges in congestion control for reliable multicast: (1) Provably TCP-fairness and (2) Providing scalable feedback. We first present a simple, rate-based, flat-structured scheme, RMCC (Reliable Multicast Congestion Control), that does not rely on router assistance and is readily deployable at end hosts. It is enhanced from a generic scheme originally proposed by Whetten and Cohan. Detailed design of source and receiver mechanisms is described. Next we propose three scalable feedback schemes for RMCC over heterogeneous wired/wireless/mobile networks. Using sampling techniques, these feedback schemes adapt their feedback generation frequency according to network dynamics including congestion status, end host mobility, and packet losses. The RMCC algorithm and the three feedback methods are carefully evaluated through simulation experiments using various network configurations and traffic scenarios. We found that RMCC multicast flow co-exists well with TCP traffic and is TCP-fair. The three feedback schemes are effective in reducing acknowledgments, yet are able to promptly communicate significant network changes.

[1]  Leandros Tassiulas,et al.  Optimization based rate control for multirate multicast sessions , 2001, Proceedings IEEE INFOCOM 2001. Conference on Computer Communications. Twentieth Annual Joint Conference of the IEEE Computer and Communications Society (Cat. No.01CH37213).

[2]  S. Floyd,et al.  Tcp-friendly unicast rate-based flow control , 1997 .

[3]  Richard J. La,et al.  Window-based congestion control with heterogeneous users , 2001, Proceedings IEEE INFOCOM 2001. Conference on Computer Communications. Twentieth Annual Joint Conference of the IEEE Computer and Communications Society (Cat. No.01CH37213).

[4]  Krishan K. Sabnani,et al.  Fundamental observations on multicast congestion control in the Internet , 1999, IEEE INFOCOM '99. Conference on Computer Communications. Proceedings. Eighteenth Annual Joint Conference of the IEEE Computer and Communications Societies. The Future is Now (Cat. No.99CH36320).

[5]  Jon Crowcroft,et al.  TCP-like congestion control for layered multicast data transfer , 1998, Proceedings. IEEE INFOCOM '98, the Conference on Computer Communications. Seventeenth Annual Joint Conference of the IEEE Computer and Communications Societies. Gateway to the 21st Century (Cat. No.98.

[6]  Ernst W. Biersack,et al.  Optimal multicast feedback , 1998, Proceedings. IEEE INFOCOM '98, the Conference on Computer Communications. Seventeenth Annual Joint Conference of the IEEE Computer and Communications Societies. Gateway to the 21st Century (Cat. No.98.

[7]  A. Winsor.  Sampling techniques. , 2000, Nursing times.

[8]  Sally Floyd,et al.  Connections with multiple congested gateways in packet-switched networks part 1: one-way traffic , 1991, CCRV.

[9]  Stefano Giordano,et al.  A measurement based QoS evaluation through traffic sampling , 1998 .

[10]  Donald F. Towsley,et al.  Modeling TCP throughput: a simple model and its empirical validation , 1998, SIGCOMM '98.

[11]  Matthew Mathis,et al.  The macroscopic behavior of the TCP congestion avoidance algorithm , 1997, CCRV.

[12]  Injong Rhee,et al.  MTCP: scalable TCP-like congestion control for reliable multicast , 2002, Comput. Networks.

[13]  Todd Montgomery,et al.  A Loss Tolerant Rate Controller for Reliable Multicast , 1997 .

[14]  Mark Handley,et al.  Strawman Specification for TCP Friendly ( Reliable ) Multicast Congestion Control ( TFMCC ) , 1998 .

[15]  Mark Handley,et al.  Equation-based congestion control for unicast applications , 2000, SIGCOMM.