Abstract
This letter reports a study of a hybrid burst assembly and a hybrid burst loss recovery scheme
(delay-based burst assembly and hybrid loss recovery (DBAHLR)) which selectively employs proactive or reactive
loss recovery techniques depending on the classification of traffic into short term and long term,
respectively. Traffic prediction and segregation of optical burst switching network flows into the long term
and short term are conducted based on predicted link holding times using the hidden Markov model (HMM). The
hybrid burst assembly implemented in DBAHLR uses a consecutive average-based burst assembly to handle jitter
reduction necessary in real-time applications, with variations in burst sizes due to the non-monotonic nature
of the average delay handled by additional burst length thresholding. This dynamic hybrid approach based on
HMM prediction provides overall a lower blocking probability and delay and more throughput when compared with
forward segment redundancy mechanism or purely HMM prediction-based adaptive burst sizing and wavelength
allocation (HMM-TP).
© 2014 Chinese Optics Letters
PDF Article
More Like This
Cited By
You do not have subscription access to this journal. Cited by links are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.
Contact your librarian or system administrator
or
Login to access Optica Member Subscription