Modeling and Prediction of the Internet End-to-end Delay using Recurrent Neural Networks

This paper focuses on modeling and predicting the Internet end-to-end (e2e) delay multi-step ahead using Recurrent Neural Networks (RNNs). In this work, Round- Trip Time (RTT) is used as the basic metric to forecast the Internet e2e delay. A method for delay prediction model is developed using RNNs, able to model nonlinear systems. By observing the delay between two Internet nodes, RTT data has been collected as a time series during several days. Then this discrete-time series data has been organized into two parts, the first one is used as a training/learning set of the RNN, whereas the rest of data is used for the testing/evaluation of the RNN performance. To achieve this purpose, a learning phase has been performed to provide a mathematical characterization of RTT during one or several reference days. The test phase consists of iteratively forecasting RTT acquired during the test day. Simulation results illustrate that the suggested model is adaptive and it tracks RTT dynamics rapidly and accurately, even for long time ahead prediction.

[1]  Ming Yang,et al.  Predicting Internet end-to-end delay: an overview , 2004, Thirty-Sixth Southeastern Symposium on System Theory, 2004. Proceedings of the.

[2]  Griff L. Bilbro,et al.  Improved delay prediction for on-chip buses , 1999, DAC '99.

[3]  Shahram Payandeh,et al.  A model for time-delays for teleoperation over the Internet , 2001, Proceedings 2001 IEEE International Symposium on Computational Intelligence in Robotics and Automation (Cat. No.01EX515).

[4]  Hiroyuki Ohsaki,et al.  Modeling end-to-end packet delay dynamics of the internet using system identification , 2001 .

[5]  Ming Yang,et al.  Predicting Internet End-to-End Delay: A Multiple-Model Approach , 2005, Proceedings IEEE INFOCOM 2006. 25TH IEEE International Conference on Computer Communications.

[6]  Jean-Chrysostome Bolot,et al.  End-to-end packet delay and loss behavior in the internet , 1993, SIGCOMM '93.

[7]  Alexander G. Parlos,et al.  Identification of the Internet end-to-end delay dynamics using multi-step neuro-predictors , 2002, Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290).

[8]  Sunil Kalidindi,et al.  Surveyor: An Infrastructure For Internet Performance Measurements , 1999 .

[9]  Bharat K. Bhargava,et al.  A round trip time and time-out aware traffic conditioner for differentiated services networks , 2002, 2002 IEEE International Conference on Communications. Conference Proceedings. ICC 2002 (Cat. No.02CH37333).

[10]  Ying Zhang,et al.  A Measurement Study of Internet Delay Asymmetry , 2008, PAM.

[11]  David L. Mills,et al.  Internet Engineering Task Force (ietf) Network Time Protocol Version 4: Protocol and Algorithms Specification , 2010 .

[12]  Antonio Pescapè,et al.  Long Horizon End-to-End Delay Forecasts: A Multi-Step-Ahead Hybrid Approach , 2007, 2007 12th IEEE Symposium on Computers and Communications.

[13]  Moncef Tagina,et al.  VFAST TCP: An improvement of FAST TCP , 2008, Tenth International Conference on Computer Modeling and Simulation (uksim 2008).

[14]  Shahram Payandeh,et al.  A delay prediction approach for teleoperation over the Internet , 2002, Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292).

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

[16]  Ah Chung Tsoi,et al.  Universal Approximation Using Feedforward Neural Networks: A Survey of Some Existing Methods, and Some New Results , 1998, Neural Networks.

[17]  Paolo Fiorini,et al.  A Design and Control Environment for Internet-Based Telerobotics , 1998, Int. J. Robotics Res..

[18]  Cheng Jin,et al.  FAST TCP: Motivation, Architecture, Algorithms, Performance , 2006, IEEE/ACM Transactions on Networking.

[19]  Thomas B. Sheridan,et al.  Space teleoperation through time delay: review and prognosis , 1993, IEEE Trans. Robotics Autom..

[20]  Sally Floyd,et al.  HighSpeed TCP for Large Congestion Windows , 2003, RFC.

[21]  David L. Mills,et al.  Simple Network Time Protocol (SNTP) Version 4 for IPv4, IPv6 and OSI , 1996, RFC.

[22]  Larry L. Peterson,et al.  TCP Vegas: End to End Congestion Avoidance on a Global Internet , 1995, IEEE J. Sel. Areas Commun..

[23]  Nageswara S. V. Rao.  Overlay networks of in situ instruments for probabilistic guarantees on message delays in wide-area networks , 2004, IEEE Journal on Selected Areas in Communications.

[24]  Zhihao Guo,et al.  Delay Prediction for Intelligent Routing in Wireless Networks Using Neural Networks , 2006, 2006 IEEE International Conference on Networking, Sensing and Control.

[25]  Michael S. Borella.  Measurement and interpretation of Internet packet loss , 2000, Journal of Communications and Networks.

[26]  Peter Xiaoping Liu,et al.  End-to-end delay boundary prediction using maximum entropy principle (MEP) for internet-based teleoperation , 2002, Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292).

[27]  Ren Wang,et al.  TCP Westwood: congestion window control using bandwidth estimation , 2001, GLOBECOM'01. IEEE Global Telecommunications Conference (Cat. No.01CH37270).

[28]  Yuechao Wang,et al.  The control oriented QoS: analysis and prediction , 2001, Proceedings 2001 ICRA. IEEE International Conference on Robotics and Automation (Cat. No.01CH37164).

[29]  Van Jacobson,et al.  Congestion avoidance and control , 1988, SIGCOMM '88.