In this paper, Stochastic Well-formed Nets (SWN) are used to model an optical multi-receiver system and study its performance. A novel approach to resolving packet contention (loss), occurring in optical multi-receiver nodes when the number of packets concurrently reaching the node exceeds the number of available receivers, is presented: it is based on the combined use of fiber delay lines and photonic switches, to temporarily store (delay) optical packets prior to reception. In order to effectively delay the contending packets and improve the multi-receiver throughput three novel control strategies are presented and their performance analyzed using SWN models. Techniques specific to this formalism are applied to cope with the state space explosion problem. A further optimization is achieved by altering the models in such a way that exact performance results can be obtained with reduced computational complexity.
Stochastic Colored Petri Net Models for Rainbow Optical Networks
FRANCESCHINIS, Giuliana Annamaria;
1999-01-01
Abstract
In this paper, Stochastic Well-formed Nets (SWN) are used to model an optical multi-receiver system and study its performance. A novel approach to resolving packet contention (loss), occurring in optical multi-receiver nodes when the number of packets concurrently reaching the node exceeds the number of available receivers, is presented: it is based on the combined use of fiber delay lines and photonic switches, to temporarily store (delay) optical packets prior to reception. In order to effectively delay the contending packets and improve the multi-receiver throughput three novel control strategies are presented and their performance analyzed using SWN models. Techniques specific to this formalism are applied to cope with the state space explosion problem. A further optimization is achieved by altering the models in such a way that exact performance results can be obtained with reduced computational complexity.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.