Reinforcement learning for call admission control and routing in integrated service networks

Peter Marbach; Oliver Mihatsch; Miriam Schulte; John N. Tsitsiklis

Reinforcement learning for call admission control and routing in integrated service networks

Peter Marbach, Oliver Mihatsch, Miriam Schulte, John N. Tsitsiklis

Associate Professorship of Scientific Computing and Uncertainty Quantification

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

17 Scopus citations

Abstract

In integrated service communication networks, an important problem is to exercise call admission control and routing so as to optimally use the network resources. This problem is naturally formulated as a dynamic programming problem, which, however, is too complex to be solved exactly. We use methods of reinforcement learning (RL), together with a decomposition approach, to find call admission control and routing policies. The performance of our policy for a network with approximately 1045 different feature configurations is compared with a commonly used heuristic policy.

Original language	English
Title of host publication	Advances in Neural Information Processing Systems 10 - Proceedings of the 1997 Conference, NIPS 1997
Publisher	Neural information processing systems foundation
Pages	922-928
Number of pages	7
ISBN (Print)	0262100762, 9780262100762
State	Published - 1998
Event	11th Annual Conference on Neural Information Processing Systems, NIPS 1997 - Denver, CO, United States Duration: 1 Dec 1997 → 6 Dec 1997

Publication series

Name	Advances in Neural Information Processing Systems
ISSN (Print)	1049-5258

Conference

Conference	11th Annual Conference on Neural Information Processing Systems, NIPS 1997
Country/Territory	United States
City	Denver, CO
Period	1/12/97 → 6/12/97

Cite this

Marbach, P., Mihatsch, O., Schulte, M., & Tsitsiklis, J. N. (1998). Reinforcement learning for call admission control and routing in integrated service networks. In Advances in Neural Information Processing Systems 10 - Proceedings of the 1997 Conference, NIPS 1997 (pp. 922-928). (Advances in Neural Information Processing Systems). Neural information processing systems foundation.

Marbach, Peter ; Mihatsch, Oliver ; Schulte, Miriam et al. / Reinforcement learning for call admission control and routing in integrated service networks. Advances in Neural Information Processing Systems 10 - Proceedings of the 1997 Conference, NIPS 1997. Neural information processing systems foundation, 1998. pp. 922-928 (Advances in Neural Information Processing Systems).

@inproceedings{b75bb31c2c30428e9064b52e456d13a5,

title = "Reinforcement learning for call admission control and routing in integrated service networks",

abstract = "In integrated service communication networks, an important problem is to exercise call admission control and routing so as to optimally use the network resources. This problem is naturally formulated as a dynamic programming problem, which, however, is too complex to be solved exactly. We use methods of reinforcement learning (RL), together with a decomposition approach, to find call admission control and routing policies. The performance of our policy for a network with approximately 1045 different feature configurations is compared with a commonly used heuristic policy.",

author = "Peter Marbach and Oliver Mihatsch and Miriam Schulte and Tsitsiklis, {John N.}",

year = "1998",

language = "English",

isbn = "0262100762",

series = "Advances in Neural Information Processing Systems",

publisher = "Neural information processing systems foundation",

pages = "922--928",

booktitle = "Advances in Neural Information Processing Systems 10 - Proceedings of the 1997 Conference, NIPS 1997",

note = "11th Annual Conference on Neural Information Processing Systems, NIPS 1997 ; Conference date: 01-12-1997 Through 06-12-1997",

}

Marbach, P, Mihatsch, O, Schulte, M & Tsitsiklis, JN 1998, Reinforcement learning for call admission control and routing in integrated service networks. in Advances in Neural Information Processing Systems 10 - Proceedings of the 1997 Conference, NIPS 1997. Advances in Neural Information Processing Systems, Neural information processing systems foundation, pp. 922-928, 11th Annual Conference on Neural Information Processing Systems, NIPS 1997, Denver, CO, United States, 1/12/97.

Reinforcement learning for call admission control and routing in integrated service networks. / Marbach, Peter; Mihatsch, Oliver; Schulte, Miriam et al.
Advances in Neural Information Processing Systems 10 - Proceedings of the 1997 Conference, NIPS 1997. Neural information processing systems foundation, 1998. p. 922-928 (Advances in Neural Information Processing Systems).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Reinforcement learning for call admission control and routing in integrated service networks

AU - Marbach, Peter

AU - Mihatsch, Oliver

AU - Schulte, Miriam

AU - Tsitsiklis, John N.

PY - 1998

Y1 - 1998

N2 - In integrated service communication networks, an important problem is to exercise call admission control and routing so as to optimally use the network resources. This problem is naturally formulated as a dynamic programming problem, which, however, is too complex to be solved exactly. We use methods of reinforcement learning (RL), together with a decomposition approach, to find call admission control and routing policies. The performance of our policy for a network with approximately 1045 different feature configurations is compared with a commonly used heuristic policy.

AB - In integrated service communication networks, an important problem is to exercise call admission control and routing so as to optimally use the network resources. This problem is naturally formulated as a dynamic programming problem, which, however, is too complex to be solved exactly. We use methods of reinforcement learning (RL), together with a decomposition approach, to find call admission control and routing policies. The performance of our policy for a network with approximately 1045 different feature configurations is compared with a commonly used heuristic policy.

UR - http://www.scopus.com/inward/record.url?scp=84898959706&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84898959706

SN - 0262100762

SN - 9780262100762

T3 - Advances in Neural Information Processing Systems

SP - 922

EP - 928

BT - Advances in Neural Information Processing Systems 10 - Proceedings of the 1997 Conference, NIPS 1997

PB - Neural information processing systems foundation

T2 - 11th Annual Conference on Neural Information Processing Systems, NIPS 1997

Y2 - 1 December 1997 through 6 December 1997

ER -

Reinforcement learning for call admission control and routing in integrated service networks

Abstract

Publication series

Conference

Other files and links

Fingerprint

Cite this