Fast circuit switching for the next generation of high performance networks

Bohm, Christer; Hidell, Markus; Lindgren, Per; Ramfelt, Lars; Sjödin, Peter

doi:10.1109/49.481937

Cited by 22 publications

(8 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…C IRCUIT-SWITCHED (CS) networks have been pervasive in telephony and it is envisaged that they will have a renewed role in future optical networks [1]. CS networks with alternate routing are examples of overflow loss networks which form an important class of network models.…”

Section: Introductionmentioning

confidence: 99%

Enhanced Blocking Probability Evaluation Method for Circuit-Switched Trunk Reservation Networks

et al. 2007

View full text Add to dashboard Cite

Abstract-We consider the problem of estimating steady-state blocking probability for circuit-switched networks that allow alternate routing with particular emphasis on networks protected by trunk reservation. We use a recently proposed blocking probability estimate, the Overflow Priority Classification Approximation (OPCA) as an alternative to the currently used Erlang's Fixed-Point Approximation (EFPA). We demonstrate empirically that OPCA provides a better blocking estimate than EFPA for circuit-switched networks with alternate routing, that are reasonably protected by trunk reservation.

show abstract

Section: Introductionmentioning

confidence: 99%

Enhanced Blocking Probability Evaluation Method for Circuit-Switched Trunk Reservation Networks

et al. 2007

View full text Add to dashboard Cite

show abstract

“…The total medium capacity is shared by all connected nodes using time division multiplexing. Previous proposals and implementations [5,6] are based on dual-bus topology.…”

Section: Introductionmentioning

confidence: 99%

“…In the basic set-up time channel allocation algorithm of DTM (KTH algorithm) [5,6], the request or of nodes during channel allocation is based on the closest first algorithm. We proposed two other request orders in [1,3,4] and carried out a performance evaluation study focusing on the fairness of the three variants, which are: -Closest First: KTH-CF algorithm [6] It operates according to the closest first rule.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Smoothing Algorithms for DTM Networks

Antal¹,

Molnár

2000

Telecommunication Network Intelligence

View full text Add to dashboard Cite

Abstract:Previous studies of Dynamic Synchronous Transfer Mode (OTM), which is based on multi-access dual fiber bus, showed that it could be a viable technology in the future. This paper points out that the characteristics of active and passive nodes are not balanced and the performance of the network can be increased by decreasing the need for slot allocation during call set-up. We propose a new type of smoothing algorithms, which is a new channel allocation algorithm that improves the fairness of DTM network with proper priority settings and the performance of channel allocation in ordinary operating conditions. Results are based on simulation, which was carried out by a self-developed simulator.

show abstract

“…No extra latency is required to return the result of the algorithm, which had been the case if, e.g., a master had calculated it. Other motivations to use a distributed algorithm can be found in [24]. Smarter algorithms can be implemented to get higher bandwidth utilization, but at the cost of complexity.…”

Section: Distributed §Lot-allocation Algorithmmentioning

confidence: 99%

Time-deterministic WDM star network for massively parallel computing in radar systems

Jönsson

Åhlander²,

Taveniku³

et al.

Proceedings of Massively Parallel Processing Using Optical Interconnections

View full text Add to dashboard Cite

In massively parallel computer systems for embedded real-time applications there are normally very high bandwidth demands on the interconnection network. Other important properties are time-deterministic latency and services to guarantee that deadlines are met. In this paper we analyze how these properties vary with the design parameters for a passive optical star network, specifically when used in a massively parallel radar signal processing system. The aggregated bandwidth and computational power of the radar system are approximately 45 Gbh and 100 GOPS, respectively. The analysis is focused on the medium access control protocol, called TD-TWDMA, for the time and wavelength multiplexed network. It is concluded that the proposed network is very well suited to this kind of signal-processing applications. We also present a new distributed slot-allocation algorithm with real-time properties.

show abstract

Fast circuit switching for the next generation of high performance networks

Cited by 22 publications

References 18 publications

Enhanced Blocking Probability Evaluation Method for Circuit-Switched Trunk Reservation Networks

Enhanced Blocking Probability Evaluation Method for Circuit-Switched Trunk Reservation Networks

Smoothing Algorithms for DTM Networks

Time-deterministic WDM star network for massively parallel computing in radar systems

Contact Info

Product

Resources

About