The use of learning algorithms in ATM networks call admission control problem: a methodology

Abstract Call Admission Control (CAC) is one of the most fundamental preventive congestion control mechanisms in Asynchronous Transfer Mode (ATM) networks. Several mathematical approaches that have been proposed in the literature, which usually estimate the equivalent bandwidth that is required, achieve conservative approximations that result in reduced statistical gain and thus, in under-utilisation of the network resources. In this study, a new methodology is proposed which uses a Learning Automaton (LA) in combination with equivalent bandwidth approximations to reduce the percentage of overestimation. The learning algorithm that is used attempts to predict in real-time if a call-request should be accepted or not receiving as feedback a function of an estimate of the equivalent bandwidth. As will be shown, the proposed mechanism, whose hardware implementation is feasible, exhibits remarkable statistical gain compared with some classical CAC schemes of the literature and distinct improvement of the equivalent bandwidth approximations. Finally, some issues for extending this work are also discussed.

[1]  Rae-Hong Park,et al.  Connection admission control for video traffic using modified equivalent capacity , 1995, Proceedings of GLOBECOM '95.

[2]  R.J.T. Morris,et al.  Neural network control of communications systems , 1994, IEEE Trans. Neural Networks.

[3]  Athanasios V. Vasilakos,et al.  On the use of a stochastic estimator learning algorithm to the ATM routing problem: a methodology , 1998, Comput. Commun..

[4]  Gunnar Karlsson,et al.  Performance models of statistical multiplexing in packet video communications , 1988, IEEE Trans. Commun..

[5]  A. Hiramatsu.  ATM call admission control using a neural network trained with a virtual output buffer method , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

[6]  Hamid Ahmadi,et al.  Equivalent Capacity and Its Application to Bandwidth Allocation in High-Speed Networks , 1991, IEEE J. Sel. Areas Commun..

[7]  Kumpati S. Narendra,et al.  Learning Automata - A Survey , 1974, IEEE Trans. Syst. Man Cybern..

[8]  Georgios I. Papadimitriou.  A New Approach to the Design of Reinforcement Schemes for Learning Automata: Stochastic Estimator Learning Algorithms , 1994, IEEE Trans. Knowl. Data Eng..

[9]  Debasis Mitra,et al.  Effective bandwidth of general Markovian traffic sources and admission control of high speed networks , 1993, TNET.

[10]  Hiroshi Saito,et al.  Call admission control in an ATM network using upper bound of cell loss probability , 1992, IEEE Trans. Commun..

[11]  Raif O. Onvural,et al.  Asynchronous Transfer Mode Networks , 1993 .

[12]  Ioannis Ch. Paschalidis,et al.  Congestion avoidance for ATM networks , 1994, Comput. Commun..

[13]  T. V. Lakshman,et al.  Fundamental Bounds and Approximations for ATM Multiplexers with Applications to Video Teleconferencing , 1995, IEEE J. Sel. Areas Commun..

[14]  J.E. Neves,et al.  B-ISDN connection admission control and routing strategy with traffic prediction by neural networks , 1994, Proceedings of ICC/SUPERCOMM'94 - 1994 International Conference on Communications.

[15]  G.I. Stassinopoulos,et al.  Leaky bucket mechanism with learning algorithm for ATM traffic policing , 1997, Proceedings Second IEEE Symposium on Computer and Communications.

[16]  Ness B. Shroff,et al.  Improved loss calculations at an ATM multiplexer , 1998, TNET.

[17]  Alex Aussem.  Call admission control in ATM networks with the random neural network , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

[18]  Chen-Shang Chang,et al.  Effective Bandwith in High-Speed Digital Networks , 1995, IEEE J. Sel. Areas Commun..

[19]  Zbigniew Dziong,et al.  A framework for bandwidth management in ATM networks—aggregate equivalent bandwidth estimation approach , 1997, TNET.

[20]  Luigi Fratta,et al.  ATM: bandwidth assignment and bandwidth enforcement policies , 1989, IEEE Global Telecommunications Conference, 1989, and Exhibition. 'Communications Technology for the 1990s and Beyond.

[21]  Jean C. Walrand,et al.  Resource Management in Wide-Area ATM Networks Using Effective Bandwiths , 1995, IEEE J. Sel. Areas Commun..

[22]  Harry G. Perros,et al.  Call admission control schemes: a review , 1996, IEEE Commun. Mag..

[23]  Ward Whitt,et al.  Effective bandwidths with priorities , 1998, TNET.

[24]  Khosrow Sohraby.  Heavy traffic multiplexing behavior of highly-bursty heterogeneous sources and their admission control in high-speed networks , 1992, [Conference Record] GLOBECOM '92 - Communications for Global Users: IEEE.

[25]  Atsushi Hiramatsu,et al.  ATM communications network control by neural networks , 1990, IEEE Trans. Neural Networks.

[26]  Shigeo Shioda,et al.  Real-time cell loss ratio estimation and its applications to ATM traffic controls , 1997, Proceedings of INFOCOM '97.

[27]  Debasis Mitra,et al.  A New Approach for Allocating Buffers and Bandwidth to Heterogeneous Regulated Traffic in an ATM Node , 1995, IEEE J. Sel. Areas Commun..

[28]  Raif O. Onvural,et al.  Asynchronous Transfer Mode Networks: Performance Issues, Second Edition , 1993 .

[29]  Athanasios V. Vasilakos,et al.  LB-SELA: Rate-Based Access Control for ATM Networks , 1998, Comput. Networks.

[30]  Chung-Ju Chang,et al.  PSD-based neural-net connection admission control , 1997, Proceedings of INFOCOM '97.

[31]  Tarek N. Saadawi,et al.  A Neurocomputing Controller for Bandwith Allocation in ATM Networks , 1997, IEEE J. Sel. Areas Commun..

[32]  Athanasios V. Vasilakos,et al.  A new approach to the design of reinforcement schemes for learning automata: Stochastic estimator learning algorithm , 1995, Neurocomputing.

[33]  M. Decina,et al.  Bandwidth assignment and virtual call blocking in ATM networks , 1990, Proceedings. IEEE INFOCOM '90: Ninth Annual Joint Conference of the IEEE Computer and Communications Societies@m_The Multiple Facets of Integration.

[34]  W. J. Poppelbaum,et al.  Stochastic and deterministic averaging processors , 1981 .