Equivalent bandwidth characterization for real‐time CAC in ATM networks

Article type: Research Article

Authors: Ramaswamy, S. | Ono‐Tesfaye, T. | Armstrong, W.W. | Gburzynski, P.^;

Affiliations: Department of Computing Science, 615 GSB, University of Alberta, Edmonton, AB, T6G 2H1, Canada Tel: +1 403 492 2347; Fax: +1 403 492 1071 E‐mail: [email protected]; URL: http://www.cs.ualberta.ca/˜pawel

Note: [] Corresponding author.

Abstract: Many call admission control schemes for ATM‐type networks are based on the concept of effective bandwidth (\mathit{EB}). Most such schemes focus on the cell loss rate as the exclusive QoS metric and therefore base their \mathit{EB} on cell‐loss rate approximations. We use simulation data to train an adaptive logic network (ALN) to estimate cell loss and delay; these estimates can then be used to compute effective bandwidths to satisfy both cell loss and delay. The simulation data is also used to develop regression models for cell loss and delay. We compare the accuracy of the ALN and regression models with that of the well‐known fluid‐flow model by Anick et al. Results indicate that the ALN and regression models are computationally simple and sufficiently accurate for practical use.

Keywords: Neural networks, regression analysis, ATM networks, call admission, bandwidth characterization

Journal: Journal of High Speed Networks, vol. 7, no. 1, pp. 1-25, 1998