Browsing by Subject "Fiber delay line (FDL)"
Now showing 1 - 2 of 2
- Results Per Page
- Sort Options
Item Open Access Dimensioning shared-per-node recirculating fiber delay line buffers in an optical packet switch(Elsevier, 2013) Akar, N.; Gunalay, Y.Optical buffering based on fiber delay lines (FDLs) has been proposed as a means for contention resolution in an optical packet switch. In this article, we propose a queuing model for feedback-type shared-per-node recirculating FDL optical buffers in asynchronous optical switching nodes. In this model, optical packets are allowed to recirculate over FDLs as long as the total number of recirculations is less than a pre-determined limit to meet signal loss requirements. Markov Modulated Poisson Process (MMPP)-based overflow traffic models and fixed-point iterations are employed to provide an approximate analysis procedure to obtain blocking probabilities as a function of various buffer parameters in the system when the packet arrival process at the optical switch is Poisson. The proposed algorithm is numerically efficient and accurate especially in a certain regime identified with relatively long and variably-sized FDLs, making it possible to dimension optical buffers in next-generation optical packet switching systems.Item Open Access Exact analysis of single-wavelength optical buffers with feedback markov fluid queues(Optical Society of America, 2009-10-15) Kankaya H. E.; Akar, N.Optical buffering via fiber delay lines is used for contention resolution in optical packet and optical burst switching nodes. This article addresses the problem of exactly finding the blocking probabilities in an asynchronous single-wavelength optical buffer. Packet lengths are assumed to be variable and modeled by phase-type distributions, whereas the packet arrival process is modeled by a Markovian arrival process that can capture autocorrelations in interarrival times. The exact solution is based on the theory of feedback fluid queues for which we propose numerically efficient and stable algorithms. We not only find the packet blocking probabilities but also the entire distribution of the unfinished work in this system from which all performance measures of interest can be derived.