Mid Sweden University

Queue management and congestion control are important to the robustness and fairness of the Internet. So far, the Active Queue Management (AQM) algorithms show weaknesses to detect and control congestion under dynamically changing network topology. In this paper a new AQM algorithm, termed as an Adaptive AQM (AAQM) is proposed to improve on both fairness and congestion control in heterogeneous networks. The performance of AAQM is compared to those ones of Blue, Drop-tail, RED and REM. The results of the simulations show that AAQM is very promising with respect to responsiveness and robustness in time-varying networks.

One of the main objectives of Active Queue Management (AQM) mechanisms is to provide low delay and low packet loss in best-effort service networks. Nevertheless, AQM algorithms exhibit some weaknesses in the process of congestion detection and congestion whenever we have a dynamic network topology. The paper proposes a new AQM algorithm termed as Adaptive AQM (AAQM) to attain both fairness and congestion control in heterogeneous networks. The performance of AAQM is compared to Blue, Drop-tail, RED and REM using both Reno and Vegas version of TCP. The results based on a large series of simulations with ns (network simulator) indicate that AAQM using Reno is more robust, which means that it is highly responsive to the time-varying state of the network.

The focus of the paper is the implementation of a class of active queue management algorithms (AQM). Their measure of congestion includes packet arrival rate such as REM and Adaptive AQM (AAQM) with respect to a combined input and output queued (CIOQ) switch. The selection of parameters for the congestion controllers at the sources and the AQM scheme at the links prove to be essential for ensuring stability. A structure with one AQM per output port is proposed and consequently followed by the analysis of the constraints on the switch fabric speed imposed by it. A three queue model of a CIOQ switch is developed and simulated to validate the design and compare its performance with a RED queue switch.

This paper studied the performance of the small-packet variant of the TCP Friendly Rate Control protocol in heterogeneous networks. The objective is to maximize system utilization, often called goodput, while maintaining fairness between the nodes. We show that by selecting the right queue size policy, it can be ensured that the bandwidth is fully utilized at a steady state. Additionally, we show that the judicious use of such a policy is beneficial for heterogeneous networks with high packet drop rates.

The Internet architecture is a packet switching technology that allows dynamic sharing of bandwidth among different flows with in an IP network. Packets are stored and forwarded from one node to the next until reaching their destination. Major issues in this integration are congestion control and how to meet different quality of service requirements associated with various services. In other words streaming media quality degrades with increased packet delay and jitter caused by network congestion. To mitigate the impact of network congestion, various techniques have been used to improve multimedia quality and one of those techniques is Active Queue Management (AQM). Access routers require a buffer to hold packets during times of congestion. A large buffer can absorb the bursty arrivals, and this tends to increase the link utilizations but results in higher queuing delays. Traffic burstiness has a considerable negative impact on network performance. AQM is now considered an effective congestion control mechanism for enhancing transport protocol performance over wireless links. In order to have good link utilization, it is necessary for queues to adapt to varying traffic loads. This paper considers a particular scheme which is called Adaptive AQM (AAQM) and studies its performance in the presence of feedback delays and its ability to maintain a small queue length as well as its robustness in the presence of traffic burstiness. The paper also presents a method based on the well-known Markov Modulated Poisson Process (MPP) to capture traffic burstiness and buffer occupancy. To demonstrate the generality of the presented method, an analytic model is described and verified by extensive simulations of different adaptive AQM algorithms. The analysis and simulations show that AAQM outperforms the other AQMs with respect to responsiveness and robustness. © 2011 Rahim Rahmani et al.

We propose Fuzzy Adaptive Active Queue Management Controller (FAAQMC) for dynamic buffer tuning at the router/system-level. The intention of an AQM is to achieve high link utilization without introducing an excessive delay in the Endto-End (E2E) path. For high link utilization it is necessary for queues to adapt to varying traffic loads. The contribution of FAAQMC is to make the Fuzzy Logic Controller (FLC) buffer overflow controller suitable for application over the Internet, where the traffic(i.e., bursty traffic) can change suddenly and the buffer length always cover the queue length adaptively. The desire to eliminate the overestimation effect of standard fuzzy arithmetic in the case of Internet traffic burstiness and preserve the FAAQMC merits the use of this adaptation and learning mechanism.

To achieve self configuring of Active Queue Management based on Fuzzy Logic Controller (FLC), we propose a Fuzzy Adaptive Active Queue Management Controller (FAAQMC). FAAQMC eliminates buffer overflow by adapting the buffer size to the required queue length with a control cycle time shorter than the mean inter-arrival time of a burst. This makes FAAQMC suitable to manage invariant burstiness or self-similar network traffic. © 2009 IEEE.

We propose a Fuzzy Adaptive Active Queue Management Controller (FAAQMC). Its performance objectives are efficient queue utilization, regulated queuing delay, and robustness.   In order to achieve efficient queue utilization, the FAAQMC controls buffer length loading of both time-varying arrival rate and departure rate. The FAAQMC regulates queuing delay by minimize buffering with  small queue lengths. In order to achieve robustness the FAAQMC maintains both resource provisioning and dimensioning performance under varying network conditions including variations in the number of flows, variation in Round Trip Time (RTT), and link capacity. The FAAQMC does so by using a Transformation method with fuzzy sets as numerical representation of uncertain network parameters.