On the Integration of Best-Effort and Guaranteed Performance Services

One of the main challenges of emerging high speed telecommunication networks is the integration of services. Both ATM as well as the INTERNET have been evolving so as to accomodate both best-effort type traffic (such as file transfer) as well as real time traffic requiring guaranteed performance. The co-existence of these two service types on the same network carries important benefits such as resource sharing between service classes, and the ability of the user to easily select an appropriate service class according to requirements and preferences. These benefits depend on efficient network management and resource sharing strategies. The aim of this paper is twofold. First, we study the performance measures of both service types, as a function of the network management strategy. This study allows us at a second phase to design efficient network management schemes. This includes questions such as whether best-effort traffic should use only bandwidth left-over by the guaranteed performance ones, or whether (and how much) bandwidth needs to be reserved to best-effort traffic. Another management issue that we study is the pricing. We allow for different classes of guaranteed-performance traffic to have different priorities with respect to the rejection probabilities.

[1]  Sean P. Meyn,et al.  Stability and convergence of moments for multiclass queueing networks via fluid limit models , 1995, IEEE Trans. Autom. Control..

[2]  J. Wardrop ROAD PAPER. SOME THEORETICAL ASPECTS OF ROAD TRAFFIC RESEARCH. , 1952 .

[3]  Jonathan Solomon,et al.  Tariffing in the new IP/ATM environment , 1997 .

[4]  Lixia Zhang,et al.  Resource ReSerVation Protocol (RSVP) - Version 1 Functional Specification , 1997, RFC.

[5]  Donald F. Ferguson,et al.  An approach to pricing, optimal allocation and quality of service provisioning in high-speed packet networks , 1995, Proceedings of INFOCOM'95.

[6]  Deborah Estrin,et al.  Pricing in computer networks: motivation, formulation, and example , 1993, TNET.

[7]  Raj Jain,et al.  Erica+: extensions to the erica switch algorithm , 1995 .

[8]  Dilip D. Kandlur,et al.  Provisioning of RSVP-based Services over a Large ATM Network , 1995 .

[9]  Marcel F. Neuts,et al.  Matrix-geometric solutions in stochastic models - an algorithmic approach , 1982 .

[10]  J. G. Wardrop,et al.  Some Theoretical Aspects of Road Traffic Research , 1952 .

[11]  Ariel Orda,et al.  Incentive pricing in multi-class communication networks , 1997, Proceedings of INFOCOM '97.

[12]  Deborah Estrin,et al.  An architectural comparison of ST-II and RSVP , 1994, Proceedings of INFOCOM '94 Conference on Computer Communications.

[13]  Frank Kelly,et al.  Charging and rate control for elastic traffic , 1997, Eur. Trans. Telecommun..

[14]  F. Kelly,et al.  Charging schemes for multiservice networks , 1996 .

[15]  R. Núñez Queija,et al.  Analysis of a multi-server queueing model of ABR , 1996 .

[16]  Jeffrey K. MacKie-Mason,et al.  Pricing Congestible Network Resources (Invited Paper) , 1995, IEEE J. Sel. Areas Commun..

[17]  D. Estrin,et al.  RSVP: a new resource reservation protocol , 1993, IEEE Communications Magazine.

[18]  Sean P. Meyn Transience of Multiclass Queueing Networks Via Fluid Limit Models , 1995 .