Comparative analysis of random early detection (RED) and virtual output queue (VOQ) algorithms in differentiated services network

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 values is not an efficient solution. We propose a new method to dynamically tuning RED's parameters. For this purpose, we compute the rate of which the queue is occupied and consider it as a congestion metric that will be forecasted when the queue is overloaded. This meter is used to dynamically setting RED parameters. The simulation results show the effectiveness of the proposed method. According to the results, we achieve a significantly higher utilization and less packet loss comparing to original RED algorithm in dynamic conditions of the network.

In Internet gateways with active queue management, effective algorithms are often used to enhance the traffic flows through the gateway. The random early detection (RED) algorithm is a widely used algorithm for controlling the transmission control protocol (TCP) flows. Specifically, the RED algorithm has deliberately introduced randomness into the explicit congestion notification (ECN) marking mechanism in order to enhance the fairness and to avoid synchronization of TCP flows through the gateway. As randomness plays a key role in providing better performance for RED gateways than the DropTail gateways, knowledge of the effect of the random mechanism is important to the understanding the behavior of the system. The fluid flow model (FFM), ignoring the randomness of ECN markings, has provided a fast alternative to the slow ns-2 network simulation tool in studying the TCP flow in the RED gateway. In this brief, the random ECN marking mechanism in RED gateways has been studied. The randomness of the RED ECN marking algorithm is implemented into the FFM. Verified using ns-2 simulations, the proposed model shows better dynamical performance than FFM in both the single-bottleneck dumbbell network and in networks with interactive bottlenecks.

Congestion control in Cluster Wireless Sensor Networks (CWSNs) has drawn widespread attention and research interests. The increasing number of nodes and scale of networks cause more complex congestion control and management. Active Queue Management (AQM) is one of the major congestion control approaches in CWSNs, and Random Early Detection (RED) algorithm is commonly used to achieve high utilization in AQM. However, traditional RED algorithm depends exclusively on source-side control, which is insufficient to maintain efficiency and state stability. Specifically, when congestion occurs, deficiency of feedback will hinder the instability of the system. In this paper, we adopt the Additive-Increase Multiplicative-Decrease (AIMD) adjustment scheme and propose an improved RED algorithm by using neighbor feedback and scheduling scheme. The congestion control model is presented, which is a linear system with a non-linear feedback, and modeled by Lur’e type system. In the context of delayed Lur’e dynamical network, we adopt the concept of cluster synchronization and show that the congestion controlled system is able to achieve cluster synchronization. Sufficient conditions are derived by applying Lyapunov-Krasovskii functionals. Numerical examples are investigated to validate the effectiveness of the congestion control algorithm and the stability of the network.

Active queue management (AQM) algorithm is the key technology of congestion control for routers recommended by IETF. AQM provides a main way to avoid Internet congestion combined with TCP. Random Early Detection (RED), recommended by AQM as the default algorithm for routers of NGN, has become the research hotspot nowadays. In this paper, we proposes an improved RED algorithm named ERED (Enhanced RED) based on the study of existing RED, congestion detection and congestion avoidance. A serial of simulation had been done based on NS2 simulator. The experimental results indicate that the packet loss and stability are better than RED algorithm. The comparison of packet numbers and packet loss numbers under different congestion condition shows that the packet loss and link utilization of ERED are better than RED, which enhances the adaptability of RED algorithm.

Random Early Detection(RED) algorithm of Active Queue Management(AQM) is a well-known link congestion control algorithm. Based on analyzing the linear RED algorithm this paper proposes a nonlinear feedback method of composite curves which used to notify end system congestion state feedback mechanism. When the new mechanism is applied to the queue management process of the router buffer, the result of the simulations indicate the effectiveness of the new algorithm. Therefore more effective congestion control target is achieved.

Schemes described in the literature on network congestion management are in general based on queue management. It is widely accepted that Poisson model is not sufficient to characterize the traffic in current Internet. In this paper, we present an alternate RED (Random Early Detection) algorithm for traffic congestion management in IP networks having self-similar (SS) input. We first discuss the basic scheme of Normal and Gentle RED as proposed by Floyd et.al., for the Poisson input model, and then explain piecewise RED, an extension of Gentle RED and Exponential RED - a new AQM proposed by us. We then explain the modification to these algorithms that we propose for the self-similar IP traffic input. Our modification takes into consideration probability values corresponding to the average queue lengths for computing the marking/dropping probability. Verification of the algorithms proposed viz., Normal SS RED and Exponential SS RED, vis-a-vis that of Floyd has been done using simulated self-similar traffic. Results of the verification have been discussed in the paper.

Random Early Detection(RED) is a network congestion control algorithm which calculates the packet-lossratio according to current length of average queue. This paper describes an improved RED algorithm: Firstly, predicts network flows with RBF neural Network in order to forecast queue length much earlier, and then, fits the Packet-loss-ratio of RED algorithm according to some special points using curve fitting method, therefore, controls nonlinear network congestion. From our simulation, it can be concluded that the algorithm avoids congestion more efficiently.

In this paper, we propose a parameter optimization method for RIO (RED (Random Early Detection) with In and Out) scheme for Assured Service (AS) in Differentiated Services (DiffServ). The RIO was proposed to use to ensure the expected capacity specified by the traffic profile. However, in order to optimize the QoS (Quality of Service) performance for the AS in DiffServ in terms of maximum tolerable latency, link utilization, etc., the RIO policy should be operated considerately. Therefore, in order to guarantee the maximum delay for each AS subclass in DiffServ, the proposed scheme differentiates the assigned bandwidth to each subclass efficiently. In addition, we propose a configuration method for the RIO and the admission control criterion considering the allocated bandwidth to each subclass and the corresponding buffer size to increase the throughput for the In-profile traffic and the link utilization. Simulation results show that the capacity for the AS can be effectively estimated by using the proposed method and the throughput for the In-profile traffic and the link utilization can be improved remarkably by applying the optimized RIO parameter set. <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup>

Low‐rate denial of service (LDoS) attacks exploit the congestion control mechanism to degrade the network quality of service. As a classic active queue management algorithm, random early detection (RED) algorithm is widely used to avoid network congestion. However, RED is vulnerable to LDoS attacks. LDoS attacks with well‐configured attack parameters force RED queue to fluctuate severely, thereby throttling transmission control protocol (TCP) senders’ sending rate. A feedback control model is proposed to describe the process of the congestion control, by which the congestion window and queue behaviours are analysed combined. After that, a two‐dimensional queue distribution model composed of the instantaneous queue and the average queue is designed to extract the attack feature. Moreover then, a combination of a simple distance‐based approach and an adaptive threshold algorithm is proposed to detect every LDoS attack burst. Test results of network simulator (NS)‐2 simulation and test‐bed experiments indicate that the proposed detection strategy can almost completely detect LDoS attack bursts and is especially robust to legitimate short bursts.

Congestion lowers the network utilization, throughput which causes very large queuing delays, data loss and degrades quality of service. In this paper the technique Random Early Detection (RED) has been studied in more details and other queuing techniques have been derived in general in order to solve congestion problem in the computer networks. The simulation program has been built using C++ language to simulate Random Early Detection (RED) algorithm which gave a detailed result about the algorithm

ZigBee is a sensor based IEEE 802.15.4 wireless standard. ZigBee has taken a role in the utilization of wireless network for diverse applications in home, office or industrial automation. The vast use of ZigBee devices which bring forth a huge application traffic. ZigBee Coordinator processes the application traffic. This traffic waits to be executed in the Coordinator queue. Routers transfer the application traffic to the destination. These huge application traffic can be a cause of queuing drop which reduces throughput as well as increases delay. An active queue management is in demand for ZigBee Coordinator. In this paper, Random Early Detection (RED) algorithm is applied to maintain Coordinator queue for gaining high throughput as the lowest possible delay and data packet dropped. The simulation results show the performance of RED enabled network parameters are better. This analysis will be a convenient direction for the further development of ZigBee network.

The virtual output queue (VOQ) has been used in input queued and input-output queued packet switches which require switch plane scheduling algorithms to achieve high throughput. However, existing scheduling algorithms such as iSLIP are designed for scheduling fixed size cell units and introduce unfairness in packet latency among VOQs if used for scheduling variable sized packet units. A self-optimized latency (SOL) scheduling algorithm is proposed to deal with scheduling variable-length packets. The SOL is a credit-based scheduling algorithm which assigns a credit flow for each VOQ. During operation, the SOL examines credit flows to grant access to VOQs through the switch plane. Moreover, the SOL also works in conjunction with an average packet length scheduling concept to modify credit flows based on size of packets transferred through the switch plane in order to increase fairness among VOQs. Simulation results show that the SOL scheduling algorithm in a switch plane significantly reduces the packet latency compared to iSLIP scheduling algorithm.

In this paper, we propose a QoS-enabled VPN architecture supporting a new service level agreement (SLA), called mu SLA to allow customer to specify QoS requirement. Such a QoS requirement is in terms of VPN total bandwidth and real-time micro-flow bandwidth. The proposed architecture is based on VPN hose model over DiffServ network and on logical bandwidth partitions at edge routers into various classes of micro-flow aggregations. State information of micro-flow at edge routers provides fine granularity of QoS control. A dynamic bandwidth prediction technique, normalized least mean square error (NLMS) linear predictor, is used to help the efficient resource sharing between real-time and best-effort services within each VPN. Simulation results done by network simulator 2 (NS-2) show that the proposed architecture guarantees VPN real-time micro-flows with bandwidth and quality improvement

Virtual output queue (VOQ) architecture is commonly used for avoiding head-of-line blocking in input-queued switches. Many algorithms have been developed for transferring the cells from the VOQs to the output ports. Traditional iterative algorithms such as iSLIP and DRRM, achieve 100% throughput under uniform traffic. but under non-uniform traffic, throughput drops significantly. Recently, a new paradigm of exhaustive matching (EM) has been introduced for handling non-uniform traffic while preserving the complexity of traditional iterative algorithms. In EM, a VOQ is served continuously until it becomes empty. Only the input ports that have finished serving a VOQ look for a new match. This strategy produces very good throughput and delay performance in uniform and non-uniform traffic. However under some traffic patterns, there is a starvation problem when a VOQ occupies an output port for an extended period of time. This problem can be eliminated by providing a priority service for a VOQ that has waited an excessively long time. The resulting algorithm, prioritized EM (PEM), eliminates starvation and achieves very high throughput for many traffic patterns.

We describe a novel method for scheduling highspeed network switches. The targeted architecture is an input-buffered switch with a non-blocking switch fabric. The input buffers are organized as virtual output queues to avoid head-of-line blocking. The task of the scheduler is to decide when the input ports can forward packets from the virtual output queues to the corresponding output ports. Our Least Choice First (LCF) scheduling method selects the input and output ports to be matched by prioritizing the input ports according to the number of virtual output queues that contain packets: The fewer virtual output queues with packets, the higher- the scheduling priority, of the input port. This way the number- of switch connections and, with it, switch throughput is maximized. Fairness is provided through the addition of a round-robin algorithm. We present two alternative implementations: A central implementation intended for narrow, switches and a distributed implementation based on an iterative algorithm intended for wide switches. The simulation results show that the LCF scheduler outperforms other scheduling methods such as the parallel iterative matcher, iSLIP, and the wave front arbiter.