Abstract
The rapid growth of streaming media puts great demand on network traffic smoothness. The traffic sawtooth waving caused by typical TCP congestion control method based on sending/congestion window and AIMD (Additive Increase and Multiplicative Decrease) constrains the transmission performance and the QoS (quality of service) of streaming media. To solve these problems, this paper proposes a unilateral TCP optimization method – TCP traffic smoothing algorithm based on rate pacing (TCP-SRP). Instead of using the traditional method based on window + AIMD, TCP-SRP achieves congestion control by pacing the packet transmission rate in order to avoiding the sawtooth waving and improving the smoothness. Further, TCP-SRP deals with packet loss and time out events via packet-loss event probability and time-out backoff strategy. Moreover, TCP-SRP enhances the bandwidth competitiveness in heavy congestion situation by improving the packet-loss event sensitivity. The experiment proves that, compared with TCP NewReno, the traffic smoothness of TCP-SRP increases by 26.5 %–38.6 % which gets even better in heavy congestion situation. The TCP friendliness of TCP-SRP is 0.36–0.58 which indicates good inter-protocol fairness.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Sun, W.: Research on some problems of TCP friendly rate control protocol for streaming media. Ph.D. dissertation, Department of Information Science and Engineering, Northeastern University, Shenyang, China (2010)
Tulu, B., Chatterjee, S.: Internet-based telemedicine: an empirical investigation of objective and subjective video quality. Decis. Support Syst. 45(4), 681–696 (2008)
Ghobadi, M., Ganjali, Y.: TCP pacing in data center networks. In: 2013 IEEE 21st Annual Symposium on High-Performance Interconnects, IEEE Computer Society, pp. 25–32 (2013)
Alizadeh, M., Greenberg, A., Maltz, D.A.: DCTCP: efficient packet transport for the commoditized data center. ACM Sigcomm Comput. Commun. Rev. 40(4), 63–74 (2010)
Handley, M., Floyd, S., Padhye, J.: TCP friendly rate control (TFRC): protocol specification. Sonstiges 1, 146–159 (2003)
Volkan, O., Injong, R., Yung, Y.: TEAR: TCP emulation at receivers – flow control for multimedia streaming. Department of Computer Science, pp. 1–24 (2000)
Liu, Y.H., Hu, Y., Zhang, G.Z.: Study on TCP-friendly protocol in self-similar traffic network. Chin. J. Comput. 27(1), 42–51 (2004)
Kohler, E., Handley, M., Floyd, S.: Datagram congestion control protocol (DCCP). Internet Draft Internet Eng. Task Force, RFC 4340(4), 206–207 (2006)
Zhang, J., Ren, F., Tang, L.: Modeling and solving TCP Incast problem in data center networks. IEEE Trans. Parallel Distrib. Syst. 26(2), 478–491 (2015)
Floyd, S., Handley, M., Padhye, J.: Equation-based congestion control for unicast applications. ACM Sigcomm Comput. Commun. Rev. 30(4), 43–54 (2000)
Padhye, J., Firoiu, V., Towsley, D.F.: Modeling TCP Reno performance: a simple model and its empirical validation. IEEE/ACM Trans. Network. 8(2), 133–145 (2000)
Floyd, S., Henderson, T.: The NewReno modification to TCP’s fast recovery algorithm. Expires 345(2), 414–418 (1999)
Sun, W., Wen, T., Feng, Z.: Steady state throughput modeling of TCP NewReno. J. Comput. Res. Develop. 47(3), 398–406 (2010)
Zhang, B., Yang, J.H., Wu, J.P.: Survey and analysis on the internet traffic model. J. Softw. 22(1), 115–131 (2011)
Ren, F.Y., Lin, C., Liu, W.D.: Congestion control in IP network. Chin. J. Comput. 26(9), 1025–1034 (2003)
Jiang, X., Wu, C.M., Jiang, M.: A congestion aware slow-start algorithm for TFRC protocol. Acta Electronica Sin. 37(5), 1025–1029 (2009)
Jiang, M., Wu, C.M., Zhang, W.: Research of the algorithm to improve fairness and smoothness of TFRC protocol. Acta Electronica Sin. 37(8), 1723–1727 (2009)
Aggarwal, A., Savage, S., Anderson, T.: Understanding the performance of TCP pacing. IEEE Comm. Lett. 3, 1157–1165 (2006)
Li, Q.M., Xu, M.W., Yan, H.: A novel network congestion forecast method. J. Syst. Simul. 18(8), 2101–2104 (2006)
Li, S.Y., Xu, D., Liu, Q.: Study on self-similarity traffic prediction and network congestion control. J. Syst. Simul. 21(21), 6935–6939 (2009)
Wang, Y., Zhao, Q.C., Zheng, D.Z.: TCP congestion control algorithm on self-similar traffic network. J. Commun. 22(5), 31–38 (2001)
Widmer, J., Handley, M.: Extending equation-based congestion control to multicast applications. In: ACM Sigcomm, pp. 275–285 (2001)
Widmer, J., Denda, R., Mauve, M.: A survey on TCP-friendly congestion control. IEEE Netw. 15(3), 28–37 (2001)
Hassan, S., Kara, M.: Simulation-based performance comparison of TCP-friendly congestion control protocols. In: Proceedings of the 16th Annual UK Performance Engineering Workshop, pp. 1–11 (2000)
Acknowledgments
This research is supported by the “Strategic Priority Research Program” of the Chinese Academy of Sciences (No. XDA06010302).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Shang, Q., Wang, J., Chen, X. (2016). A TCP Traffic Smoothing Algorithm Based on Rate Pacing. In: Gervasi, O., et al. Computational Science and Its Applications – ICCSA 2016. ICCSA 2016. Lecture Notes in Computer Science(), vol 9786. Springer, Cham. https://doi.org/10.1007/978-3-319-42085-1_47
Download citation
DOI: https://doi.org/10.1007/978-3-319-42085-1_47
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-42084-4
Online ISBN: 978-3-319-42085-1
eBook Packages: Computer ScienceComputer Science (R0)