作者: Ivan S. Razo-Zapata , Gerardo Castanon , Carlos Mex-Perera
DOI: 10.1109/ICTON.2013.6602872
关键词: Reservation 、 Computer science 、 Optical switch 、 Packet switching 、 Network topology 、 Computer network 、 Distributed computing 、 Packet loss 、 Reinforcement learning 、 Load balancing (computing) 、 Dimensioning
摘要: We present a self-adaptive framework to process lightpath requests on packet switching optical network. Our takes care of issues regarding setting up, resource reservation and load balancing. The is composed dimensioning phase that adds up new resources an initial topology learning provides routing intelligence efficiently use the dimensioned resources. proposed tested realistic achieving probability loss 1×10-4.