Lightpath requests processing in flexible packet switching optical networks using reinforcement learning

Author

Razo-Zapata, Ivan S. ; Castanon, Gerardo ; Mex-Perera, Carlos

Author_Institution

Dept. of Electr. & Comput. Eng., Tecnol. de Monterrey, Monterrey, Mexico

fYear

2013

fDate

23-27 June 2013

Firstpage

1

Lastpage

4

Abstract

We present a self-adaptive framework to process lightpath requests on a packet switching optical network. Our framework takes care of issues regarding lightpath setting up, resource reservation and load balancing. The framework is composed of a dimensioning phase that adds up new resources to an initial topology and a learning phase that provides routing intelligence to efficiently use the dimensioned resources. The proposed framework is tested on a realistic topology achieving a probability of packet loss of 1×10^-4.

Keywords

learning (artificial intelligence); optical fibre networks; optical switches; packet switching; telecommunication computing; telecommunication network routing; telecommunication network topology; dimensioning phase; flexible packet switching optical network; lightpath request processing; lightpath requests processing; load balancing; reinforcement learning; resource reservation; routing intelligence; self-adaptive framework; topology; Network topology; Optical fiber networks; Optical fibers; Optical packet switching; Packet loss; Routing; dimensioning; learning; lightpath requests; packet loss; service-oriented optical networks;

fLanguage

English

Publisher

ieee

Conference_Titel

Transparent Optical Networks (ICTON), 2013 15th International Conference on

Conference_Location

Cartagena

ISSN

2161-2056

Type

conf

DOI

10.1109/ICTON.2013.6602872

Filename

6602872