High Link Utilization Research Articles

GA-based PID active queue management control design for a class of TCP communication networks

Active queue management (AQM) is a key congestion control scheme for reducing packet loss and improving network utilization in TCP/IP networks. This paper proposes a proportional–integral-derivative (PID) controller as an active queue manager for Internet routers. Due to the limitations of packet-dropping probability and the effects of propagation delays in TCP networks, the TCP AQM network was modeled as a time-delayed system with a saturated input. An improved genetic algorithm is employed to derive optimal or near optimal PID controller gains such that a performance index of integrated-absolute error (IAE) is minimized, and thereby a stable queue length, low packet loss, and high link utilization for TCP networks are guaranteed. The performance of the proposed control scheme is evaluated in various network scenarios via a series of numerical simulations.

A fuzzy logic-based AQM for real-time traffic over internet

Autonomic networking has been proposed as an approach to reduce cost and complexity of managing communication functions. An autonomic system is self-configuring, self-optimizing, self-healing and self-protecting. Such a system requires the minimum of administration, primarily involving policy-level management and AI-cognitive models. On the other hand, numerous Active Queue Management (AQM) algorithms have been proposed in the literature to address the problem of congestion in the Internet. Their performance is highly dependent on parameters' setting and tuning. Besides that, most of the AQM algorithms focus on throughput optimization and fail to provide bounded transmission delay while providing high link utilization to popular TCP-based radio/video streaming applications. Tackling the aforementioned concerns, in this paper we propose and evaluate a novel self-configuring AQM algorithm based on fuzzy logic. The proposed approach simplifies significantly the deployment and management of such complex QoS control mechanisms in the Internet providing at the same time a good tradeoff between link utilization and queuing latency. The introduced algorithm is compared with the most efficient adaptive AQM algorithms proposed to date such as ARED, REM, BLUE, PID and LRED. The performance analysis demonstrates that the proposed ''Fast and Autonomic Fuzzy Controller'' (FAFC): (1) minimizes queue fluctuation, (2) optimizes the throughput regardless of the traffic load variation and the presence of unresponsive UDP/RTP based voice and video communications, and (3) suggests the best compromise between link utilization and queuing delay.

Analysis of effect of load-based excess bandwidth reservation on performances of differentiated services in E-PON

Performances of differentiated services in the upstream transmission of Ethernet passive optical network (E-PON) are affected by bandwidth reservation algorithm of an optical network unit, since data packets can be transmitted to an optical line termination only during the reserved transmission window. The effects of time-slot reservation on differentiated services are analysed and an adaptive class-based excess bandwidth reservation algorithm, called service quality pre-engagement (SQP), which reserves a time-slot based on the backlog queue and traffic arrival pattern of class is proposed. SQP applies the prediction-based bandwidth reservation to selected forward reservation classes (FRCs) which are determined by the introduced dynamic FRC selection. The proposed short-term service work-based time-slot reservation and long-term adaptive FRC selection optimise time-slot reservation according to traffic load of class. Analytic and simulation results show that this approach improves the performance of differentiated services, especially in terms of system buffer size, light-load penalty and service fairness, while guaranteeing high link utilisation and throughput.

Rate-Based Active Queue Management for TCP Flows over Wired and Wireless Networks

Current active queue management (AQM) and TCP protocol are designed and tuned to work well on wired networks where packet loss is mainly due to network congestion. In wireless networks, however, communication links suffer from significant transmission bit errors and handoff failures. As a result, the performance of TCP flows is significantly degraded. To mitigate this problem, we analyze existing AQM schemes and propose a rate-based exponential AQM (REAQM) scheme. The proposed REAQM scheme uses the input rate as a primary metric and queue length as the secondary metric. The objectives of REAQM are to stabilize networks with low packet loss, low packet delay, and high link utilization regardless the dynamic of network conditions. We prove the global asymptotic stability of the equilibrium based on Lyapunov theory. Simulation results suggest that REAQM is capable of performing well for TCP flows over both wired and wireless networks, and has comparable implementation complexity as other AQM schemes.

Stability analysis of a novel exponential-RED model with heterogeneous delays

Active Queue Management (AQM) schema provides an early indication of incipient congestion to the sources. However, in developing the AQM schema, there are some urgent problems to be solved, which are how to achieve higher bandwidth utility and smaller queuing delay, keep the stability of congestion control model, and derive some sufficient conditions for the stability. In this paper, we firstly demonstrate that the stability of most of the AQM algorithm is achieved by modifying the packet drop/mark probability function, and then analyze the merit and drawback of RED and its variants. We develop a discrete-time dynamical feedback system model with delay for a TCP/Reno network. By analyzing the dynamical model proposed based on frequency domain, the sufficient conditions are derived. The local stability conditions are validated by some simulation results in ns2. The simulation results show the proposed schema here can achieve the stable average queue length with high link utilization.

Enhancements of T-REFWA to mitigate link error-related degradations in hybrid wired/wireless networks

With the on-going wireless access technologies, the Internet has become accessible anytime anywhere. In wireless networks, link errors significantly degrade the performance of the transmission control protocol (TCP). To cope with this issue, this paper improves the recently-proposed terrestrial REFWA (T-REFWA) scheme by adding a new error recovery mechanism to its original design. In the T-REFWA scheme, senders are acknowledged with appropriate sending rates at which an efficient and fair utilization of network resources can be achieved. As the feedback values are computed independently of link errors, senders can keep transmitting data at high rates even in case of link error occurrences. Using this feature, the proposed error recovery mechanism can achieve high throughput in environments with high bit error rates. The throughput is further improved by disabling the exponential backoff algorithm of TCP so that long idle times are avoided in case of link errors. We show through simulations that the proposed method improves TCP performance in high bit error rates. Compared with several TCP variants, the proposed error recovery scheme exhibits higher link utilization and guarantees system fairness for different bit error rates.

Active queue management algorithm considering queue and load states

In this paper, we propose a new AQM algorithm that considers both the average queue length and the estimated packet arrival rate together in order to detect incipient congestion. The proposed algorithm predicts the average queue length and controls it to maintain a certain reference value to achieve high link utilization and low queueing delay. It also has low complexity and easy configuration. Simulation results validate the performance of the proposed algorithm under various environments and show its advantage over other existing AQM algorithms.

Congestion notification and probing mechanisms for endpoint admission control

There has been much interest in admission control schemes that place the burden of admission control decisions on the end users. In these schemes, referred to as Endpoint Admission Control, the decision to join the network is taken by the user, based on the probing of the network using probe packets. Depending on the level of congestion, routers mark the probe packets and thus inform the user of the state of the network. In this paper, we analyze three mechanisms for providing Endpoint Admission Control: virtual-queue marking, random-early marking and tail drop. For each scheme, we analyze the probing duration necessary to guarantee the required QoS and achieve high link utilization. Our main conclusion is that very few probe packets have to be sent when early marking is used, whereas tail drop requires a large number of probe packets.

Lightweight proactive queue management

The quest for better resource control has been the driving force behind Active Queue Management (AQM) research. Random Early Detection (RED), the defacto standard and its variants have been proposed as simple solutions to the AQM problem. These approaches, however, are known to suffer from problems like parameter sensitivity and inability to capture input traffic load fluctuations accurately, thereby resulting in instability. This paper presents a proactive queue management algorithm called PAQMAN that captures input traffic load fluctuations accurately and regulates the queue size around the desirable level. PAQMAN draws from the predictability in the underlying traffic by employing the Recursive Least Squares (RLS) algorithm to forecast the average queue size over the next prediction interval using the average queue size information of the past intervals. The packet drop probability is then computed as a function of this predicted average queue size. The performance of PAQMAN has been evaluated and compared against existing AQM schemes through ns-2 simulations that encompass varying network conditions for networks comprising of single as well as multiple bottleneck links. Simulation results demonstrate that PAQMAN maintains a relatively low queue size, while at the same time achieving high link utilization and low packet loss. Moreover, the computational overhead of PAQMAN is negligible (lightweight) which further justifies its use.

An adaptive bluetooth packet selection and scheduling scheme in interference environments

Bluetooth is a new technology for Wireless Personal Area Networks (WPANs). It intends to eliminate the need of wires and connectors between a variety of devices, like PCs and their peripherals, walkmans and their earphones, etc. Bluetooth provides robust and secure wireless radio communication of both data and voice, even when the devices are not within line-of-sight. Bluetooth employs the 2.4 GHz ISM band, sharing the same band with the Wireless LAN (WLAN) implementing the IEEE 802.11 series standard. While WLANs and WPANs are complementary rather than competing technologies, the likelihood of mutual interference may occur unexpectedly, which may impact the performance of either severely. In this paper, we propose a Bluetooth channel state dependent data segmentation and reassembly (CSD-SAR) scheme and a queue state dependent priority (QSD-PR) scheduling policy. The CSD-SAR maintains a receiving frequency table to predict channel conditions and selects the best packet type and packet size to transmit data. In this way, it not only masks bad frequencies without delaying transmission but also leads to the best performance with high link utilization in error-prone environments. In addition, the QSD-PR also uses the receiving frequency table to avoid bad frequencies and gives a selected master–slave pair, which has more queued data to send between each other, a higher priority to eliminate the wastage of slots. The conventional scheduling policy, Round Robin (RR), yields poor performance with the time division duplex based MAC protocol and results in slot wastage and may not ensure fairness. Simulation results show that our proposed scheme achieves better link utilization and higher throughput with bounded delay compared to the RR scheme in error-free and error-prone environments. Our scheme can also eliminate interference to other wireless networks that share the same spectrum, such as WLANs, by avoiding selecting channels occupied by other networks.

Rate-based proportional–integral control scheme for active queue management

Most high-speed links do not have adequate buffering and as a result Active Queue Management (AQM) schemes that utilize queue size information for congestion control cannot be effectively applied on these links. A high-speed link will, typically, have small buffers in relation to the bandwidth-delay product of the link. In this paper we argue that rate-based AQM schemes be used for such links. The goal here is to match the aggregate rate of the active TCP connections to the available capacity while maintaining minimal queue size and high link utilization. The AQM scheme described here employs a Proportional–Integral (PI) control strategy and explicitly takes into account the time delay in the control process. Copyright © 2006 John Wiley & Sons, Ltd.

A Load-Adaptive Active Queue Management Algorithm

Random Early Detection (RED) is the active queue management (AQM) algorithm recommended by IETF. Unfortunately, it is identified that RED is difficult to configure its parameters and the average queue length of RED is closely related to the load level. ARED (adaptive RED) is the adaptive version of RED. ARED dynamically adjust maximum packet marking probability according to the average queue length to make average queue length stable, but it still suffers from unstable instantaneous queue length and performance degradation under dynamic traffic conditions. In this paper, the cause of such problems of ARED is analyzed and a load adaptive active queue management scheme called LARED (load adaptive RED) is proposed. LARED features in adapting the load level of bottleneck link as well as quick response to queue length dynamics. Analysis and simulation results show that, compared with ARED and other AQM algorithms, LARED brings more stable queue dynamics; while keeping high link utilization and low queuing delay, it presents good responsiveness and robustness in various traffic conditions.

Traffic scheduling solutions with QoS support for an input-buffered multimedia router

Quality of service (QoS) support in local and cluster area environments has become an issue of great interest in recent years. Most current high-performance interconnection solutions for these environments have been designed to enhance conventional best-effort traffic performance, but are not well-suited to the special requirements of the new multimedia applications. The multimedia router (MMR) aims at offering hardware-based QoS support within a compact interconnection component. One of the key elements in the MMR architecture is the algorithms used in traffic scheduling. These algorithms are responsible for the order in which information is forwarded through the internal switch. Thus, they are closely related to the QoS-provisioning mechanisms. In this paper, several traffic scheduling algorithms developed for the MMR architecture are described. Their general organization is motivated by chances for parallelization and pipelining, while providing the necessary support both to multimedia flows and to best-effort traffic. Performance evaluation results show that the QoS requirements of different connections are met, in spite of the presence of best-effort traffic, while achieving high link utilizations.

A consolidation algorithm for multicast service using proportional control and neural network predictive techniques

With the increase of multicast data applications, research interests have been focused on the design of congestion control scheme for multicast communications. One challenge comes from the heterogeneous multicast receivers, especially those with large propagation delays, which means the feedbacks arriving at the source node are somewhat outdated and harmful to the control actions. To attack this problem, this paper describes a novel multicast congestion control scheme, which is based on the proportional plus neural network (PNN) predictive technique. The congestion controller is located at the multicast source and uses the explicit rate algorithm to regulate the transmission rate. This network-assisted property is different from the existed control schemes in that the multicast source is able to predict the available bandwidth at those receiver nodes for which the back control packets experience very long propagation delay and possibly cause irresponsiveness of a multicast flow. The proposed control scheme is more responsive to the network status thus the rate adaptation can be made in a timely manner for the sender to react to the network congestion quickly. Simulation results demonstrate the efficiency of the proposed scheme in terms of fast response, high link utilization and stable buffer occupancy.

SAVQ: stabilized adaptive virtual queue management algorithm

We observe that the desired utilization parameter /spl gamma/ in AVQ algorithm has an influence on the dynamics of queue and link utilization. It is difficult to achieve a fast system response and high link utilization simultaneously using a constant value /spl gamma/. An adaptive setting method for /spl gamma/ is proposed according to the instantaneous queue size and the given reference queue value. This new algorithm, called stabilized AVQ (SAVQ), stabilizes the dynamics of queue maintaining a high link utilization.

Joint local delivery and congestion control framework for reliable multicast

The use of a server-based loss recovery technique for reliable multicast can significantly improve the system performance in terms of loss recovery latency and bandwidth consumption. Appropriate congestion control mechanisms are necessary to provide fairness and to maintain a high network throughput and link utilisation. In reliable multicast protocol design the loss recovery associated with data delivery and congestion control are not independent issues and should be addressed simultaneously. This suggests that a server-based loss recovery technique allied with congestion control could have potential in addressing the challenges of scalabililty and heterogeneity for reliable multicast in a best-effort network. The authors propose a new framework which jointly performs local delivery and congestion control (LDCC). In this framework, delivery and control servers (DCSs) collocated with routers perform LDCC functions. Each DCS and its serving receivers form a local DCS region according to a tree topology. With proper acknowledgment processing and buffer management, packet loss can be efficiently recovered locally. Also, the overall throughput degradation caused by the interference of neighbouring regions can be minimised by local congestion control. NS-2 simulations are used to demonstrate that the framework can achieve a significantly lower loss recovery latency without sacrificing the network throughput, compared to existing approaches such as AER/NCA. It is also shown using fairness tests that the proposed framework is TCP-compatible.

Fractional Lambda Switching Principles of Operation and Performance Issues

This article introduces fractional lambda (λ) switching (FλS) and studies its blocking issues. FλS uses a global common time reference (CTR) for implementing pipeline forwarding (PF) inside the network. A global CTR is conveniently realized with the UTC (coordinated universal time) standard. Resource reservation over an FλS network requires a schedule. As in other scheduling cases, a call may not be accepted, even though there is enough capacity, because the schedule is not available—the call is then considered blocked. This work studies the probability of call blocking as a function of link utilization. The results show that (especially if multiple-wavelength division multiplexing channels are deployed on optical links between fractional λ switches) high-link utilization can be achieved with negligible call blocking, even when the switching fabric is a Banyan network.

Performance Evaluation of TCP over Optical Channels and Heterogeneous Networks

Next generation optical networks will soon provide users the capability to request and obtain end-to-end all optical 10 Gbps channels on demand. Individual users will use these channels to exchange large amounts of data and support applications for scientific collaborative work. These new applications, which expect steady transfer rates in the order of Gbps, will very likely use either TCP or a new transport layer protocol as the end-to-end communication protocol. In this paper, we investigate the performance of TCP and newer TCP versions over High Bandwidth Delay Product Channels (HBDPC), such as the on demand optical channels described above. In addition, we investigate the performance of these new TCP versions over wireless networks and according to old issues such as fairness. This is particularly important to make adoption decisions. Using simulations, we show that (1) the window-based mechanism of current TCP implementations is not suitable to achieve high link utilization and (2) congestion control mechanisms, such as the one utilized by TCP Vegas and Westwood are more appropriate and provide better performance. We also show that new TCP proposals, although perform better than current TCP versions, they still perform worse than TCP Vegas. In addition, we found that even though these newer versions improve TCP's performance over their original counterparts in HBDPC, they still have performance problems in wireless networks and present worse fairness problems than their old counterparts. We conclude that all these versions are still based on TCP's AIMD strategy or similar and therefore continue to be fairly blind in the way they increase and decrease their transmission rates. TCP will not be able to utilize the foreseen optical infrastructure adequately and support future applications if not redesigned to scale.

Modified RED gateways under bursty traffic

We propose modified random early detection (MRED) gateways for congestion avoidance in TCP/IP networks. MRED aims at providing better control over the burstiness level while remaining the advantages of RED. We use ns2 to simulate a series of network configurations and the numerical results demonstrate that MRED can achieve higher link utilization compared to RED without sacrificing its advantages in all simulation scenarios. The improvement becomes more significant under bursty traffic.

Quality-oriented adaptation scheme for video-on-demand

A new quality-oriented adaptation scheme (QOAS) is proposed in which the adaptation of streamed video is based on end-user perceived quality information. QOAS has been tested in a simulated local multi-service IP network with various types, sizes and shapes of background traffic. Test results show good end-user perceived quality and high link utilisation with very low loss rates. In addition, the performance of QOAS is very close to that of an ideal adaptive system in all traffic conditions.