A Change-of-Measure Approach to Per- Flow Delay Measurement Combining Passive and Active Methods: Mathematical Formulation for CoMPACT Monitor

One problem with active measurement is that, while it is suitable for measuring time-average network performance, it is difficult to measure per-flow quality of service (QoS), which is defined as the average over packets in the flow. To achieve such per-flow QoS measurement, the authors proposed a new technique, called the change- of- measure-based passive/active monitoring (CoMPACT Monitor), which is based on the change-of-measure framework in probability/measure theory and transforms actively obtained information by using passively monitored data. This technique enables us to concurrently measure one-way delay information about individual users, applications, and organizations in detail in a lightweight manner. This paper presents the mathematical formulation for the CoMPACT Monitor and verifies that it works well under some weak conditions. In addition, we investigate its characteristics regarding several implementation issues through simulation and actual network experiments. The results reveal that our technique provides highly qualified estimates involving only a limited amount of extra traffic from active probes.

[1]  S. Asmussen,et al.  Applied Probability and Queues , 1989 .

[2]  Mostafa H. Ammar,et al.  Poisson versus periodic path probing (or, does PASTA matter?) , 2005, IMC '05.

[3]  Keisuke Ishibashi,et al.  PAPER Special Issue on New Technologies in the Internet and their Applications Proposal and Evaluation of Method to Estimate Packet Loss-Rate Using Correlation of Packet Delay and Loss , 2003 .

[4]  Daryl J. Daley,et al.  An Introduction to the Theory of Point Processes , 2013 .

[5]  Jean-Chrysostome Bolot,et al.  Characterizing End-to-End Packet Delay and Loss in the Internet , 1993, J. High Speed Networks.

[6]  Matthew J. Zekauskas,et al.  A One-way Delay Metric for IPPM , 1999, RFC.

[7]  Zhi-Li Zhang,et al.  Practical delay monitoring for ISPs , 2005, CoNEXT '05.

[8]  Sally Floyd,et al.  Wide-Area Traffic: The Failure of Poisson Modeling , 1994, SIGCOMM.

[9]  Vern Paxson,et al.  End-to-end Internet packet dynamics , 1997, SIGCOMM '97.

[10]  François Baccelli,et al.  On optimal probing for delay and loss measurement , 2007, IMC '07.

[11]  JainManish,et al.  End-to-end available bandwidth , 2002 .

[12]  Jin Cao,et al.  Internet Traffic Tends Toward Poisson and Independent as the Load Increases , 2003 .

[13]  Vern Paxson.  End-to-end internet packet dynamics , 1999, TNET.

[14]  John Odentrantz,et al.  Markov Chains: Gibbs Fields, Monte Carlo Simulation, and Queues , 2000, Technometrics.

[15]  Masaki Aida,et al.  CoMPACT-Monitor: change-of-measure based passive/active monitoring weighted active sampling scheme to infer QoS , 2002, Proceedings 2002 Symposium on Applications and the Internet (SAINT) Workshops.

[16]  Thomas Lindh.  Embedded monitoring of QoS parameters in IP-based virtual private networks , 2001, 2001 IEEE/IFIP International Symposium on Integrated Network Management Proceedings. Integrated Network Management VII. Integrated Management Strategies for the New Millennium (Cat. No.01EX470).

[17]  Manish Jain,et al.  End-to-end available bandwidth: measurement methodology, dynamics, and relation with TCP throughput , 2003, TNET.

[18]  Manish Jain,et al.  End-to-end available bandwidth: measurement methodology, dynamics, and relation with TCP throughput , 2002, SIGCOMM 2002.

[19]  P. Glynn,et al.  Independent Sampling of a Stochastic Process , 1998 .

[20]  Toshiaki Miyazaki,et al.  Real-time packet editing using reconfigurable hardware for active networking , 2002, 2002 IEEE International Conference on Field-Programmable Technology, 2002. (FPT). Proceedings..

[21]  Darryl Veitch,et al.  High precision active probing for Internet measurement , 2001 .

[22]  Masaki Aida,et al.  A scalable and lightweight QoS monitoring technique combining passive and active approaches , 2003, IEEE INFOCOM 2003. Twenty-second Annual Joint Conference of the IEEE Computer and Communications Societies (IEEE Cat. No.03CH37428).

[23]  Stefan Savage,et al.  The end-to-end effects of Internet path selection , 1999, SIGCOMM '99.

[24]  François Baccelli,et al.  The Role of PASTA in Network Measurement , 2006, IEEE/ACM Transactions on Networking.

[25]  Sally Floyd,et al.  Wide area traffic: the failure of Poisson modeling , 1995, TNET.

[26]  Vern Paxson,et al.  An architecture for large-scale Internet measurement , 1998, IEEE Commun. Mag..

[27]  Ronald W. Wolff,et al.  Poisson Arrivals See Time Averages , 1982, Oper. Res..

[28]  Thomas Lindh.  A New Approach to Performance Monitoring in IP Networks– combining active and passive methods , 2002 .

[29]  Matthew J. Zekauskas,et al.  A One-way Packet Loss Metric for IPPM , 1999, RFC.

[30]  F. Baccelli,et al.  Elements of Queueing Theory: Palm Martingale Calculus and Stochastic Recurrences , 2010 .

[31]  Vern Paxson,et al.  Framework for IP Performance Metrics , 1998, RFC.

[32]  Thomas Lindh.  A Framework for Embedded Monitoring of QoS Parameters in IP-Based Virtual Private Networks , 2001 .

[33]  Masaki Aida,et al.  Active/passive combination-type performance measurement method using change-of-measure framework , 2002, Global Telecommunications Conference, 2002. GLOBECOM '02. IEEE.