Autonomous smart routing for network QoS

Author

Gelenbe, Erol ; Gellman, Michael ; Lent, Ricardo ; Liu, Peixiang ; Su, Pu

Author_Institution

Dept. of Electr. & Electron. Eng., Imperial Coll., London, UK

fYear

2004

fDate

17-18 May 2004

Firstpage

232

Lastpage

239

Abstract

We present an autonomous adaptive quality of service (QoS) driven network system called a "cognitive packet network" (CPN), which adaptively selects paths so as to offer best effort QoS to the end users based on user defined QoS. CPN uses neural network based reinforcement learning to make routing decisions separately at each node. Measurements on an experimental test-bed are provided to show how the system responds to the choice of QoS goals. We also discuss and evaluate an extension of CPN that uses a genetic algorithm to generate and maintain paths from previously discovered information by matching their "fitness" with respect to the desired QoS.

Keywords

computer networks; genetic algorithms; learning (artificial intelligence); neural nets; quality of service; telecommunication network routing; transport protocols; Internet protocol; adaptive QoS; adaptive packet network; cognitive packet network; network QoS; neural network; quality-of-service; reinforcement learning; smart routing; Computer science; Delay; Educational institutions; Genetic algorithms; Jitter; Learning; Neural networks; Payloads; Quality of service; Routing;

fLanguage

English

Publisher

ieee

Conference_Titel

Autonomic Computing, 2004. Proceedings. International Conference on

Print_ISBN

0-7695-2114-2

Type

conf

DOI

10.1109/ICAC.2004.1301368

Filename

1301368