Browse > Article

Internet Roundtrip Delay Prediction Using the Maximum Entropy Principle  

Liu, Peter Xiaoping (Department of Systems and Computer Engineering, Carleton University)
Meng, Max Q-H (Department of Electronic Engineering, Chinese University of Hong Kong)
Gu, Jason (Department of Electrical and Computer Engineering, Dalhousie University)
Publication Information
Journal of Communications and Networks / v.5, no.1, 2003 , pp. 65-72 More about this Journal
Abstract
Internet roundtrip delay/time (RTT) prediction plays an important role in detecting packet losses in reliable transport protocols for traditional web applications and determining proper transmission rates in many rate-based TCP-friendly protocols for Internet-based real-time applications. The widely adopted autoregressive and moving average (ARMA) model with fixed-parameters is shown to be insufficient for all scenarios due to its intrinsic limitation that it filters out all high-frequency components of RTT dynamics. In this paper, we introduce a novel parameter-varying RTT model for Internet roundtrip time prediction based on the information theory and the maximum entropy principle (MEP). Since the coefficients of the proposed RTT model are updated dynamically, the model is adaptive and it tracks RTT dynamics rapidly. The results of our experiments show that the MEP algorithm works better than the ARMA method in both RTT prediction and RTO estimation.
Keywords
Internet; delay; prediction; maximum entropy principle;
Citations & Related Records

Times Cited By Web Of Science : 1  (Related Records In Web of Science)
Times Cited By SCOPUS : 1
연도 인용수 순위
1 V. Jacobson, 'Congestion avoidance and control,' in Proc. ACM SIG-COMM, Stanford, CA, Aug. 1988, pp. 314-329
2 L. Zhang, 'Why TCP timers don't work well,' in Proc. ACM SIGCOMMSymp. Comm., Architectures, and Protocots, Stowe, Vermont, Aug. 1986,pp. 397-405
3 P. Liu et al., 'A novel data transport protocol for Intemet robots,' inPmc. WorId Consress Inteltigent Controt and Automation (WCfCA'02),June 2002, pp. 59-65
4 R. Jain, 'Divergence of timeout algorithms for packet retransmissions,' inProc. Fifth Phoenix Conf. Comp. and Comm., Scottsdale, Arizona, Mar.1986,PP.174-179
5 A. Acharya and J. Saltz, 'A study of Intemet round-trip delay,' TechnicatReport CS-TR-3736, University ofMaryland, Dec. 1996
6 D. D. Clark, RFC 813: Window and acknowtedgement strategy in TCP,July 1988
7 J. UfRnk, 'Can the maximum entropy principle be explained as a con-sistency requirement?,' Studies in History and Philosophy of Modem Physics, 26(3): pp. 223-261, 1995   DOI   ScienceOn
8 E. T. Jaynes, 'Information theory and statistical mechanics I,' Physical Review, 106(4): pp. 620-630, 1957   DOI
9 M. Allman and V. Paxson, 'On estimating end-to-end network path prop-erties,' in Proc. ACM SIGCOM Comput. Commun. Review, 1999, pp. 263-274
10 J.-C. Bolot, 'Characterizina end-to-end packet delay and loss in the Inter-net,' J. High Speed Networks, 2(3): pp. 305-323, 1993
11 K. Goldberg and R. Siegwart (editors), Beyond Webcams: An introductionto ontine robots, The MIT Press, Cambridge, Massachusetts, USA, 2002
12 Available at http://www.topjimmy.net
13 R. Rejaie, M. Handley, and D. Estrin, 'RAP: An end-to-end rate-basedcongesdon control mechanism for realtime streams in the Internet,' inProc. IEEEINF0C0M, New York, NY, Mar. 1999, PP. 1337-1345
14 M. S. Borella et at., 'Self-similarity of Intemet packet delay,' in Proc.[EEEICC'97, Aug. 1997, pp. 513-517
15 Q. Li and D. L. Mills, 'Jitter-based delay-boundary prediction of wide-area networks,' IEEE/ACM Trans. Networking, 9(5): pp. 578-590, 2001   DOI   ScienceOn
16 D. Mills, RFC889: Intemet Delay Experiments, Dec. 1983
17 S. Ployd and K. Fall, 'Promoting the use ofend-to-end congestion controlin the Intemet,' IEEE/ACM Trans. Networking, 7(4): pp. 458-472, 1999   DOI   ScienceOn
18 J. Padhye et al., A TCP-friendty rate adjustment protocot for continuousmedia fIows over best effort network, UMass-CMPSCI Technical ReportTR 98-04, Oct. 1998
19 P. Kam and C. Partridge, 'Improving round-trip time estimates in reliabletransport protocols,' ACM Trans. Computer Systems, 9(4): pp. 365-373,1991
20 D. Kugiumtzis and M. A. Boudourides, 'Chaotic analysis of Internet pingdata,' S0E1S Meeting at Bietefeld, Mar. 27-28, 1998
21 P. Klan and G. Darbellay, 'An information-theoretic adaptive method fortime series forecasting,' Neurat Network WorId, 7(2): pp. 227-238, 1997
22 S. Guiasu and A. Shenitzer, 'Maximum entropy principle,' Mathematicat Intelligencer, 7(1): pp. 42-48, 1985   DOI
23 J. Postel, RFC 793: Transmission controt protocot, available athttp://www.ibiblio.org/pub/docs/rfc/rfc793.txt, Sept. 1981