2006
P.G. Sarigiannidis; G.I. Papadimitriou; A.S. Pomportsis
CS-POSA: A high performance scheduling algorithm for WDM star networks Journal Article
In: Photonic Network Communications, vol. 11, no. 2, pp. 211-227, 2006.
Abstract | BibTeX | Tags: Optical WDM networks, Reservation, Scheduling, Star topology, Traffic prediction | Links:
@article{Sarigiannidis2006211,
title = {CS-POSA: A high performance scheduling algorithm for WDM star networks},
author = { P.G. Sarigiannidis and G.I. Papadimitriou and A.S. Pomportsis},
url = {https://www.researchgate.net/publication/225152613_CS-POSA_A_high_performance_scheduling_algorithm_for_WDM_star_networks},
doi = {10.1007/s11107-005-6024-x},
year = {2006},
date = {2006-01-01},
journal = {Photonic Network Communications},
volume = {11},
number = {2},
pages = {211-227},
abstract = {In this paper a new packet scheduling algorithm for WDM star networks is introduced. The protocol adopted is pre-transmission coordination-based and packet collisions have been eliminated due to predetermination of the timeslots each node transmits in a demand matrix. The requests of the transmitted packets are predicted through Markov chains in order to reduce the calculation time of the final scheduling matrix. This is accomplished by pipelining the schedule computation. The innovation that this algorithm introduces is to modify the service sequence of the node. The proposed algorithm is studied via extensive simulation results and it is proved that changing the sequence that nodes transmit, from the node with the largest number of requests to the node with the fewest requests, that there is an increase in the throughput of the network, with a minimum (almost zero) cost in mean time delay and in delay variance. © Springer Science + Business Media, Inc. 2006.},
keywords = {Optical WDM networks, Reservation, Scheduling, Star topology, Traffic prediction},
pubstate = {published},
tppubtype = {article}
}
In this paper a new packet scheduling algorithm for WDM star networks is introduced. The protocol adopted is pre-transmission coordination-based and packet collisions have been eliminated due to predetermination of the timeslots each node transmits in a demand matrix. The requests of the transmitted packets are predicted through Markov chains in order to reduce the calculation time of the final scheduling matrix. This is accomplished by pipelining the schedule computation. The innovation that this algorithm introduces is to modify the service sequence of the node. The proposed algorithm is studied via extensive simulation results and it is proved that changing the sequence that nodes transmit, from the node with the largest number of requests to the node with the fewest requests, that there is an increase in the throughput of the network, with a minimum (almost zero) cost in mean time delay and in delay variance. © Springer Science + Business Media, Inc. 2006.
Address
Internet of Things and Applications Lab
Department of Electrical and Computer Engineering
University of Western Macedonia Campus
ZEP Area, Kozani 50100
Greece
Contact Information
tel: +30 2461 056527
Email: ithaca@uowm.gr