Call admission control and routing in integrated services networks using neuro-dynamic programming
Authors:
- O. MihatschOMO. Mihatsch
- J.N. TsitsiklisJTJ.N. Tsitsiklis
- 1 February 2000
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal on Selected Areas in Communications
- Vol. 18 (2) , 197-208
Abstract
We consider the problem of call admission control (CAC) and routing in an integrated services network that handles several classes of calls of different value and with different resource requirements. The problem of maximizing the average value of admitted calls per unit time (or of revenue maximization) is naturally formulated as a dynamic programming problem, but is too complex to allow for an exact solution. We use methods of neuro-dynamic programming (NDP) [reinforcement learning (RL)], together with a decomposition approach, to construct dynamic (state-dependent) call admission control and routing policies. These policies are based on state-dependent link costs, and a simulation-based learning method is employed to tune the parameters that define these link costs. A broad set of experiments shows the robustness of our policy and compares its performance with a commonly used heuristic.Keywords
This publication has 13 references indexed in Scilit:
- Computational techniques for accurate performance evaluation of multirate, multihop communication networksIEEE/ACM Transactions on Networking, 1997
- ATM network design and optimization: a multirate loss network frameworkIEEE/ACM Transactions on Networking, 1996
- Multiservice Loss Models for Broadband Telecommunication Networks1995
- On Trunk Reservation in Loss Networks1995
- Call admission and routing in multi-service loss networksIEEE Transactions on Communications, 1994
- Reduced load approximations for multirate loss networksIEEE Transactions on Communications, 1993
- Loss NetworksThe Annals of Applied Probability, 1991
- Optimal Control and Trunk Reservation in Loss NetworksProbability in the Engineering and Informational Sciences, 1990
- Learning to predict by the methods of temporal differencesMachine Learning, 1988
- Routing in circuit-switched networks: optimization, shadow prices and decentralizationAdvances in Applied Probability, 1988