Dynamic queue length thresholds for shared-memory packet switches
IEEE/ACM Transactions on Networking (TON)
On the Exact Analysis of a Discrete-Time Queueing System with Autoregressive Inputs
Queueing Systems: Theory and Applications
IEEE Journal on Selected Areas in Communications
Time and space priority in a partially shared priority queue
Proceedings of the 5th International Conference on Queueing Theory and Network Applications
| Hi-index | 0.01 |
We analyze a multi-server priority queueing system with partial buffer sharing, where the input is a discrete autoregressive process of order 1 (DAR(1)) which is known as a good mathematical model for a VBR-coded teleconference video traffic. We assume that arriving packets are classified into two priority classes, say, high priority class and low priority class based on their importance. A threshold T is set to limit the accessibility of low priority packets to the buffer. When the partial buffer sharing is applied to the real time traffic such as teleconference video traffic, it is known that it can decrease the queueing delay at the expense of the loss of low priority packets which is less important. Since the queueing delay is more important than the loss probability for real time traffic, it is important to analyze the queueing delay of DAR(1) arrivals under the partial buffer sharing policy. Based on the Wiener-Hopf factorization of the GI/GI/1 queue, we obtain the waiting time distribution of a packet which is not discarded at its arrival in the steady state. Numerical examples are provided to show the feasibility of our analysis. We also show that the partial buffer sharing policy significantly decreases the waiting time as the value of threshold increases.