A Markovian Approach to Multipath Data Transfer in Overlay Networks

The use of multipath routing in overlay networks is a promising solution to improve performance and availability of Internet applications, without the replacement of the existing TCP/IP infrastructure. In this paper, we propose an approach to distribute data over multiple overlay paths that is able to improve Quality of Service (QoS) metrics, such as the data transfer time, loss, and throughput. By using the Imbedded Markov Chain technique, we demonstrate that the system under analysis, observed at specific instants, possesses the Markov property. We therefore cast the data distribution problem into the Markov Decision Process (MDP) framework, and design a computationally efficient algorithm named Online Policy Iteration (OPI), to solve the optimization problem on the fly. The proposed approach is applied to the problem of multipath data distribution in various wired/wireless network scenarios, with the objective of minimizing the data transfer time as well as the delay and losses. Through both intensive ns-2 simulations with data collected from real heterogeneous networks and experiments over real networks, we show the superior performance of the proposed traffic control mechanism in comparison with two classical schemes, that are Weighted Round Robin and Join the Shortest Queue.

[1]  Sung-Ju Lee,et al.  Split multipath routing with maximally disjoint paths in ad hoc networks , 2001, ICC 2001. IEEE International Conference on Communications. Conference Record (Cat. No.01CH37240).

[2]  Michalis Faloutsos,et al.  A nonstationary Poisson view of Internet traffic , 2004, IEEE INFOCOM 2004.

[3]  Edward W. Knightly,et al.  Opportunistic traffic scheduling over multiple network paths , 2004, IEEE INFOCOM 2004.

[4]  Leonard Kleinrock,et al.  Queueing Systems: Volume I-Theory , 1975 .

[5]  Krishna R. Pattipati,et al.  Application-layer multipath data transfer via TCP: Schemes and performance tradeoffs , 2007, Perform. Evaluation.

[6]  Anthony D. Joseph,et al.  Choosing an accurate network path model , 2003, SIGMETRICS '03.

[7]  Weiping Zhu,et al.  Improving multipath live streaming performance with Markov Decision Processes , 2007, 2007 International Symposium on Communications and Information Technologies.

[8]  Weiping Zhu,et al.  Modelling Internet End-to-End Loss Behaviours: A New Approach , 2007, First Asia International Conference on Modelling & Simulation (AMS'07).

[9]  Bernd Girod,et al.  Analysis of packet loss for compressed video: does burst-length matter? , 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

[10]  Ness B. Shroff,et al.  Opportunistic transmission scheduling with resource-sharing constraints in wireless networks , 2001, IEEE J. Sel. Areas Commun..

[11]  Anees Shaikh,et al.  A comparison of overlay routing and multihoming route control , 2004, SIGCOMM '04.

[12]  Janardhan R. Iyengar,et al.  Concurrent Multipath Transfer Using SCTP Multihoming Over Independent End-to-End Paths , 2006, IEEE/ACM Transactions on Networking.

[13]  Antonio Pescapè,et al.  Identification of Network Bricks in Heterogeneous Scenarios , 2006, Proceedings. 2006 31st IEEE Conference on Local Computer Networks.

[14]  Huai-Rong Shao,et al.  A new multi-path selection scheme for video streaming on overlay networks , 2004, 2004 IEEE International Conference on Communications (IEEE Cat. No.04CH37577).

[15]  Anees Shaikh,et al.  A measurement-based analysis of multihoming , 2003, SIGCOMM '03.

[16]  P.D. Amer,et al.  Concurrent multipath transfer using transport layer multihoming: performance under varying bandwidth proportions , 2004, IEEE MILCOM 2004. Military Communications Conference, 2004..

[17]  Philippe Owezarski,et al.  Modeling Internet backbone traffic at the flow level , 2003, IEEE Trans. Signal Process..

[18]  Roch Guérin,et al.  Packet-level diversity - from theory to practice: an 802.11-based experimental investigation , 2006, MobiCom '06.

[19]  Jim Kurose,et al.  Multipath Overlay Data Transfer , 2006 .

[20]  Renata Teixeira,et al.  In search of path diversity in ISP networks , 2003, IMC '03.

[21]  Devika Subramanian,et al.  An efficient multipath forwarding method , 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.

[22]  J. Little.  A Proof for the Queuing Formula: L = λW , 1961 .

[23]  Hari Balakrishnan,et al.  Resilient overlay networks , 2001, SOSP.

[24]  Indranil Gupta,et al.  Measurement and modeling of a large-scale overlay for multimedia streaming , 2007, QSHINE.

[25]  M. E. Johnson,et al.  Estimating model discrepancy , 1990 .

[26]  Jennifer Rexford,et al.  Toward internet-wide multipath routing , 2008, IEEE Network.

[27]  Martin L. Puterman,et al.  Markov Decision Processes: Discrete Stochastic Dynamic Programming , 1994 .

[28]  Antonio Pescapè,et al.  End-to-end packet-channel Bayesian model applied to heterogeneous wireless networks , 2005, GLOBECOM '05. IEEE Global Telecommunications Conference, 2005..

[29]  Yin Zhang,et al.  On the constancy of internet path properties , 2001, IMW '01.

[30]  Samir Khuller,et al.  Large-scale data collection: a coordinated approach , 2003, IEEE INFOCOM 2003. Twenty-second Annual Joint Conference of the IEEE Computer and Communications Societies (IEEE Cat. No.03CH37428).

[31]  David G. Andersen,et al.  Improving end-to-end availability using overlay networks , 2004 .

[32]  Jacques Carlier,et al.  Handbook of Scheduling - Algorithms, Models, and Performance Analysis , 2004 .

[33]  Donald F. Towsley,et al.  Exploring the performance benefits of end-to-end path switching , 2004, Proceedings of the 12th IEEE International Conference on Network Protocols, 2004. ICNP 2004..

[34]  Eitan Altman,et al.  Applications of Markov Decision Processes in Communication Networks , 2000 .

[35]  Shang Zhi,et al.  A proof of the queueing formula: L=λW , 2001 .

[36]  Rauf Izmailov,et al.  Fast replication in content distribution overlays , 2005, Proceedings IEEE 24th Annual Joint Conference of the IEEE Computer and Communications Societies..

[37]  J. J. Garcia-Luna-Aceves,et al.  MPATH: a loop-free multipath routing algorithm , 2000, Microprocess. Microsystems.

[38]  Antonio Pescapè,et al.  An approach to the identification of network elements composing heterogeneous end-to-end paths , 2008, Comput. Networks.

[39]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[40]  Antonio Pescapè,et al.  An MDP-Based Approach for Multipath Data Transmission over Wireless Networks , 2008, 2008 IEEE International Conference on Communications.

[41]  Tutomu Murase,et al.  Improved data distribution for multipath TCP communication , 2005, GLOBECOM '05. IEEE Global Telecommunications Conference, 2005..

[42]  Pascal Frossard,et al.  Video Packet Selection and Scheduling for Multipath Streaming , 2007, IEEE Transactions on Multimedia.

[43]  David A. Maltz,et al.  DSR: the dynamic source routing protocol for multihop wireless ad hoc networks , 2001 .

[44]  Weiping Zhu,et al.  A Game Theoretic Framework for Multipath Optimal Data Transfer in Multiuser Overlay Networks , 2008, 2008 IEEE International Conference on Communications.