random early detection (red) is one of the most commonly used active queue management (aqm) algorithms that is recommended by ietf for deployment in the network. although red provides low average queuing delay and high throughput at the same time, but effectiveness of red is highly sensitive to the red parameters setting. as network condition varies largely, setting red's parameters with fixed ...

Adaptive RED (ARED) is an active queue management (AQM) designed for congestion responsive traffics such as TCP. ARED aims to keep average queue length around a predefined queue length. If so, average delay will be offered to Internet users and simultaneously high link utilization will be achieved. However, ARED algorithm merely makes the average queue length loosely converge to the target leng...

We consider an M/G/1 queueing system where the customers may leave the queue if their services do not commence before an exponentially distributed random time. The (conditional) offered waiting time distribution is approximated by a gamma distribution via matching the first and second moments of the actual waiting time. Simulation study is conducted to assess the accuracy of the approximation a...

The Adaptive RED proposed by Feng et al . [5] is shown to have small packet delay and queue length variation for long-life TCP traffic such as FTP connection with a large file size. However, a great portion of Internet traffic is shortlife web and UDP traffic. Most web traffic has a small file size and its TCP session is mainly operated in the slow start phase with a small congestion window siz...

Consider the G I / G / i queue partially specified by the first two moments of the interarrival times and service times. Let ?~ be the arrival rate, p the traffic intensity, c, 2 the squared coefficient of variation of the interarrival-time distribution (variance divided by the square of its mean), the c 2 the squared coefficient of variation of the service-time distribution. Kingman [!!] showe...

We consider a network of service stations with different classes of customers where interarrival times and service requirments have ph~e-type distributions, and the service discipline is an arbitrary work-conserving policy. We show that the underlying Markov process is ergodic, if and only if the utilization at eaclt. service station is less than one. We also show, that all the moments of the q...

In Mandelbaum and Yechiali (1979) a simple formula is derived for the expected stationary remaining service time in a FIFO M/G/1 queue, conditional on the number of customers in the system being equal to j, j ≥ 1. Fakinos (1982) derived a similar formula using an alternative method. Here we give a short proof of the formula using rate conservation law (RCL), and generalize to handle higher mome...

Fairness is an inherent and fundamental factor of queue service disciplines in a large variety of queueing applications. Service time variability across jobs is an important factor affecting both system performance and scheduling rules (for example, computer systems that prioritize short jobs over long jobs). Service time variability and its effects on mean response times have been studied exte...

This paper discusses admission control in a two-priority system. The main aim is to evaluate the maximum load that can be admitted to a finite low priority buffer when the constraint on the packet loss ratio is given. To calculate the admissible low priority load we propose the approximate analysis that exploits just two first moments of stochastic processes involved. The method lets us derive ...