Dynamic bandwidth allocation in multi-class IP networks using utility functions.

The Internet needs to evolve from a single-service data network into the multiservice intelligent IP-based network capable of satisfying diverse performance requirements. The way network resources, primarily bandwidth, will be allocated in the future network presents a very important research issue. Bandwidth allocation should be simple to implement and optimally designed to maximise the network performance. The majority of the research on bandwidth allocation in the Internet deals with the problem of bandwidth allocation in a single-service environment, in which the entire Internet traffic is treated as data transfer. This Thesis presents Dynamic Bandwidth Partitioning, a new bandwidth allocation scheme for the multiservice Internet. In this scheme, the link bandwidth is partitioned in order to isolate the different traffic types and at the same time maximise the performance. The partitioning is dynamic; it changes according to a simple ‘additive increase, additive decrease’ linear control algorithm. The information about the change in the partitioning comes from the measured level of network performance. In other words, the Dynamic Bandwidth Partitioning scheme is user-oriented, adaptive and reasonably simple to implement. The contribution of this work is in the introduction of the new bandwidth allocation scheme, and in the metric that was used for the network performance evaluation. This new metric is called connection utility. Connection utility is the assessment of the quality of service level which a user of an Internet application derives from the network performance. It is measured by using utility functions. The significant novelty of this work is in including nonconcave utility functions for real-time traffic classes. Based on the information about the utility of the active traffic on the link, a decision about changes in the bandwidth allocation is made. This Thesis presents the Dynamic Bandwidth Partitioning scheme in detail, including the partitioning algorithm and different utility functions that were used. Through extensive simulation the scheme is compared to several other bandwidth allocation concepts. The results presented here clearly show the network environments in which implementation of the new scheme can prove to be very efficient. Furthermore, the Thesis presents the guidelines for the implementation of the scheme in the MPLS-capable networks.

[1]  K. Sohraby,et al.  Multiservice Loss Models for Broadband Telecommunication Networks [Book Review] , 1996, IEEE Communications Magazine.

[2]  Jon Crowcroft,et al.  Differentiated end-to-end Internet services using a weighted proportional fair sharing TCP , 1998, CCRV.

[3]  Andrew Odlyzko,et al.  Paris Metro pricing: the minimalist differentiated services solution , 1999, 1999 Seventh International Workshop on Quality of Service. IWQoS'99. (Cat. No.98EX354).

[4]  Kihong Park,et al.  On the relationship between file sizes, transport protocols, and self-similar network traffic , 1996, Proceedings of 1996 International Conference on Network Protocols (ICNP-96).

[5]  W. Richard Stevens,et al.  TCP Slow Start, Congestion Avoidance, Fast Retransmit, and Fast Recovery Algorithms , 1997, RFC.

[6]  Domenico Ferrari,et al.  Resource partitioning for real-time communication , 1993, First IEEE Symposium on Global Data Networking.

[7]  Daniel P. Siewiorek,et al.  On quality of service optimization with discrete QoS options , 1999, Proceedings of the Fifth IEEE Real-Time Technology and Applications Symposium.

[8]  Domenico Ferrari,et al.  A dynamic management scheme for real-time connections , 1994, Proceedings of INFOCOM '94 Conference on Computer Communications.

[9]  Van Jacobson,et al.  An Expedited Forwarding PHB , 1999, RFC.

[10]  W. Richard Stevens,et al.  TCP/IP Illustrated, Volume 1: The Protocols , 1994 .

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

[12]  Hui Zhang,et al.  Service disciplines for guaranteed performance service in packet-switching networks , 1995, Proc. IEEE.

[13]  Scott Shenker,et al.  Best-effort versus reservations: a simple comparative analysis , 1998, SIGCOMM '98.

[14]  Klara Nahrstedt,et al.  An overview of quality of service routing for next-generation high-speed networks: problems and solutions , 1998, IEEE Netw..

[15]  Derek McAuley,et al.  Differential QoS and pricing in networks: Where flow control meets game theory , 1999, IEE Proc. Softw..

[16]  Jonathan Walpole,et al.  Control challenges in multi-level adaptive video streaming , 2000, Proceedings of the 39th IEEE Conference on Decision and Control (Cat. No.00CH37187).

[17]  S. Floyd.  A Report on Some Recent Developments in TCP Congestion Control , 2000 .

[18]  Kang G. Shin,et al.  QoS negotiation in real-time systems and its application to automated flight control , 1997, Proceedings Third IEEE Real-Time Technology and Applications Symposium.

[19]  Sally Floyd,et al.  Promoting the use of end-to-end congestion control in the Internet , 1999, TNET.

[20]  Albert G. Greenberg,et al.  Integration of Call Signaling and Resource Management for IP Telephony , 1999, IEEE Internet Comput..

[21]  Albert Banchs,et al.  A scalable share differentiation architecture for elastic and real-time traffic , 2000, 2000 Eighth International Workshop on Quality of Service. IWQoS 2000 (Cat. No.00EX400).

[22]  Ariel Orda,et al.  QoS based routing in networks with inaccurate information: theory and algorithms , 1997, Proceedings of INFOCOM '97.

[23]  Daniel P. Siewiorek,et al.  Practical solutions for QoS-based resource allocation problems , 1998, Proceedings 19th IEEE Real-Time Systems Symposium (Cat. No.98CB36279).

[24]  Eitan Altman,et al.  On the Integration of Best-Effort and Guaranteed Performance Services , 1999, Eur. Trans. Telecommun..

[25]  Raj Jain,et al.  Analysis of the Increase and Decrease Algorithms for Congestion Avoidance in Computer Networks , 1989, Comput. Networks.

[26]  J. Moy,et al.  OSPF: Anatomy of an Internet Routing Protocol , 1998 .

[27]  Michel Mandjes,et al.  Performance evaluation of strategies for integration of elastic and stream traffic , 1999 .

[28]  Husam Osman Awadalla.  Resource management for multimedia traffic over ATM broadband satellite networks , 2000 .

[29]  David L. Black,et al.  Definition of the Differentiated Services Field (DS Field) in the IPv4 and IPv6 Headers , 1998, RFC.

[30]  Zheng Wang,et al.  An Architecture for Differentiated Services , 1998, RFC.

[31]  QUTdN QeO,et al.  Random early detection gateways for congestion avoidance , 1993, TNET.

[32]  Rahul Garg,et al.  Fair bandwidth sharing among virtual networks: a capacity resizing approach , 2000, Proceedings IEEE INFOCOM 2000. Conference on Computer Communications. Nineteenth Annual Joint Conference of the IEEE Computer and Communications Societies (Cat. No.00CH37064).

[33]  Leandros Tassiulas,et al.  Fair allocation of utilities in multirate multicast networks: a framework for unifying diverse fairness objectives , 2002, IEEE Trans. Autom. Control..

[34]  Christian Huitema,et al.  IPv6--the new Internet protocol , 1996 .

[35]  Scott Shenker,et al.  Endpoint admission control: architectural issues and performance , 2000, SIGCOMM.

[36]  Felicia Maria Holness,et al.  Congestion Control Mechanisms within MPLS Networks , 2000 .