Comparative performance study of space priority mechanisms for ATM networks

Kröner, Hans

doi:10.1109/infcom.1990.91367

Cited by 95 publications

(32 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Threshold-based Push-out and Probabilistic Push-out schemes [7] have been found to provide more flexibility in tuning the cell loss probability but their implementation seems to be complex while still having the restriction that the class with strict cell loss requirement is the one with the low cell delay requirement. Comparisons between various space-priority schemes are presented in [8][9][10]. It turns out that such schemes are fairly effective in inducing fairly different cell loss rates for the differentiated applications (differences of several orders of magnitude are achievable).…”

Section: Introductionmentioning

confidence: 99%

Study of a scheduling policy for diverse deadline-based quality of service

Stavrakakis

Chen²

2000

Performance Evaluation

View full text Add to dashboard Cite

One of the most challenging problems in ATM network design is providing diversified Quality of Service (QoS) to applications with distinct characteristics. Buffer management schemes can play a significant role in providing the necessary diversification through the employed cell admission and service policy. A flexible priority service policy for two applications (classes) with strict -and in general distinct -deadlines and different deadline violation rates is studied in this paper. The proposed policy is a generalization of the shortest time to extinction (STE) policy (or the Earliest Due Date policy which discards expired cells), which is more flexible in providing diversified QoS. The relationship of this policy to other standard ones is also discussed. A flexible numerical analysis is presented for the derivation of performance measures such as cell loss, mean cell-delay and the tail of the cell-delay probability distribution for each class. Numerical results illustrate the effectiveness of the studied priority scheme. Finally, a low-complexity implementation scheme is proposed, which does not require time-stamp-based sorting.

show abstract

Section: Introductionmentioning

confidence: 99%

Study of a scheduling policy for diverse deadline-based quality of service

Stavrakakis

Chen²

2000

Performance Evaluation

View full text Add to dashboard Cite

show abstract

“…has extended this analysis to the two class model with shared buffer. Finally, we mention that a performance model with partial buffer sharing has been analyzed by Kroner (1990).…”

Section: Introductionmentioning

confidence: 99%

Delay and overflow of discrete-time priority queue with burst arrivals and partial buffer sharing

Yamashita

1998

Performance and Management of Complex Communication Networks

View full text Add to dashboard Cite

We study a discrete-time, single-server queue with partial buffer sharing. There are two priority classes of jobs. Though class 1 jobs in the queue have higher priority for the next service than any of class 2 jobs, class 2 jobs are allowed to occupy their own part of buffer when the shared part of buffer is full. We characterize a bursty arrival process using bursts which consist of the same class of jobs. Once the first job of a burst arrives at the queue, the successive jobs will arrive on every time slot until the last job of the burst arrives. The numbers of jobs of a burst and the inter-arrival times of bursts are assumed to be i.i.d., respectively, and the service time is assumed to be equal to one slot. This model targets the buffer management to meet the quality of service requirments of different traffic types as video, voice and data in ATM multiplexer. In particular, class 1 jobs may correspond to cells with the strict delay requirments. On the other hand, class 2 jobs may correspond to cells with the strict cell loss requirments. We propose an efficient numerical method to exactly obtain the job loss probability, the waiting time distribution and the mean queue length. Some numerical examples are also given.

show abstract

“…They observe a tagged low priority packet from joining until leaving the system and derive the probabilities that this packet will either be served or discarded from the system. Kroner [7] presents a method to compute the loss probabilities of an MI, MZ/G/l/N push-out system with FIFO service discipline. He considers three different space priority mechanisms, namely, push-out scheme, partial buffer sharing, and the scheme with a separate route for each traffic class, and determines the push-out scheme as the best scheme in terms of loss probabilities.…”

Section: Introductionmentioning

confidence: 99%

A finite buffer two class queue with different scheduling and push-out schemes

Cheng

Akyildiz²

1992

[Proceedings] IEEE INFOCOM '92: The Conference on Computer Communications

View full text Add to dashboard Cite

We analyze an M I , M2/G1,G2/1/N queue with different scheduling and push-out scheme in this paper. Our work is motivated by the study of the performance of an output link of ATM switches with two-class priority traffics. The queueing model developed in this paper is more general than that of the output link of ATM switches with two-class priority traffics. We can have general service time distributions for classes 1 and 2, and a general service discipline function, al(z,j), with a l ( i , j ) being the probability that a class 1 packet will be served, given that there are i class 1 and j class 2 packets waiting for service. We obtain an exact solution for loss probabilities for classes 1 and 2, the queue length distribution and the mean waiting time for class 1 and an approximate calculation for the queue length distribution and mean waiting time for class 2. We show that our approximation is an upper bound and the error due to the approximation is very small when the loss probability of class 2 is small (e.g., 5 0.01).

show abstract

Comparative performance study of space priority mechanisms for ATM networks

Cited by 95 publications

References 6 publications

Study of a scheduling policy for diverse deadline-based quality of service

Study of a scheduling policy for diverse deadline-based quality of service

Delay and overflow of discrete-time priority queue with burst arrivals and partial buffer sharing

A finite buffer two class queue with different scheduling and push-out schemes

Contact Info

Product

Resources

About