Congestion in networks is considered a serious problem; in order to manage and control this phenomena in early stages before it occurs, a derivation of a new discrete-time queuing network analytical model based on dynamic random early drop (DRED) algorithm is derived to present analytical expressions to calculate three performance measures: average queue length (Qavg,j), packet-loss rate (Ploss,j), and packet dropping probability (pd(j)). Many scenarios can be implemented to analyze the effectiveness and flexibility of the model. We compare between the three queue nodes of the proposed model using the derived performance measures to identify which queue node provides better performance. Results show that queue node one provides highest Qavg,j, Ploss,j, and (pd(j)) than queue nodes two and three, since it has the highest priority than other nodes. All the above results of performance measure are obtained only based on the queuing network setting parameters.
TopIntroduction
Congestion is considered as the main problems in computer networks and data communications systems, which is occurred when the required resources by the sources at a router buffer is more than the available network resources. Congestion has significant role in degrading computer network performance (Kang and Nath, 2004; Welzl, 2005) such as decrease the throughput; obtain high packet queuing delay and packet loss and unfair share of network connections (Braden et al., 1998; Richard, 1997; Welzl, 2004), so many various methods have been developed to control this problem in computer networks (Athuraliya et al., 2001; Aweya et al., 2001; Braden et al., 2001; Feng et al., 99; Feng et al., 2001; Floyd, 2001; Lapsley and Low, 1999; Wydrowski and Zukerman, 2002). The earliest queue congestion control mechanism was the end-to-end Transport Control Protocol (TCP) (Brakmo and Peterson, 1995; Richard, 1997).
When the congestion is detected just only the rate of resources is reduced (Brakmo and Peterson, 1995). Drop-Tail (DT), Random Drop on Full, and Drop Front on Full are Traditional Queue Management (TQM) algorithms, which operate at the designated node, and drop packets only when the queue is full (Braden et al., 1998; Brandauer et al., 2001). TQM have several drawbacks, including, lockout phenomenon, full queues, bias versus burst traffic, and global synchronization, and consequently they contribute in degrading the Internet performance (Feng et al., 2001; Floyd et al., 2001; Welzl, 2005).
Active Queue Management (AQM) algorithms were proposed to overcome some of TQM drawbacks (Athuraliya et al., 2001; Aweya et al., 2001; Braden et al., 2001; Feng et al., 99; Fenget al., 2001; Floyd, 2001; Lapsley and Low, 1999; Wydrowski and Zukerman, 2002). The AQM algorithms have several objectives, which presented as follows:
- 1.
Managing and controlling congestion at routers’ buffers in the network in an early stage.
- 2.
Achieving a satisfactory performance through obtaining high throughput, low queuing delay and loss for packets.
- 3.
Sustaining the queue length as small as possible to prevent building up the router queues.
- 4.
Distributing a fair share of the existing resources among the network connections.