Evaluating the influence of multiplexing schemes and buffer implementation on perceived VoIP conversation quality

This work presents a study of RTP multiplexing schemes, which are compared with the normal use of RTP, in terms of experienced quality. Bandwidth saving, latency and packet loss for different options are studied, and some tests of Voice over IP (VoIP) traffic are carried out in order to compare the quality obtained using different implementations of the router buffer. Voice quality is calculated using ITU R-factor, which is a widely accepted quality estimator. The tests show the bandwidth savings of multiplexing, and also the importance of packet size for certain buffers, as latency and packet loss may be affected. The customer’s experience improvement is measured, showing that the use of multiplexing can be interesting in some scenarios, like an enterprise with different offices connected via the Internet. The system is also tested using different numbers of samples per packet, and the distribution of the flows into different tunnels is found to be an important factor in order to achieve an optimal perceived quality for each kind of buffer. Grouping all the flows into a single tunnel will not always be the best solution, as the increase of the number of flows does not improve bandwidth efficiency indefinitely. If the buffer penalizes big packets, it will be better to group the flows into a number of tunnels. The router processing capacity has to be taken into account too, as the limit of packets per second it can manage must not be exceeded. The obtained results show that multiplexing is a good way to improve customer’s experience of VoIP in scenarios where many RTP flows share the same path.     

Controlling mean queuing delay under multi-class bursty and correlated traffic

This paper presents an adaptive queue management scheme to maintain queuing delay in a router at a required level based on a comprehensive analytical model under aggregated Internet traffic flows from various traffic classes. The proposed scheme uses a closed-loop feedback control mechanism to constrain the average queuing delay by regulating traffic arrival rate implicitly through a movable queuing threshold. A discrete-time queuing model is developed to derive the relationship between average queuing delays and queuing thresholds based on a traffic model that models aggregated Internet traffic through superposition of N MMBP-2 arrival processes. The queuing threshold is adjusted dynamically with reference to the relationship derived in the analytical model and also feedback of average queuing delay measurement. Packets are dropped dynamically with respect to the changes of queuing threshold and the packet loss events serve as implicit congestion indicators. Matlab is used to perform queuing analysis and simulation. Statistical evaluation is performed to show the efficiency and accuracy of the analytical and simulation results.     

Impact of background traffic on performance of high-speed TCP variant protocols

This paper examines the effect of background traffic on the performance of existing high-speed TCP variant protocols, namely BIC-TCP, CUBIC, FAST, HSTCP, H-TCP and Scalable TCP. We demonstrate that the stability, link utilization, convergence speed and fairness of the protocols are clearly affected by the variability of flow sizes and round-trip times (RTTs), and the amount of background flows competing with high-speed flows in a bottleneck router. Our findings include: (1) the presence of background traffic with variable flow sizes and RTTs improves the fairness of most high-speed protocols, (2) all protocols except FAST and HSTCP show good intra-protocol fairness regardless of the types of background traffic, (3) HSTCP needs a larger amount of background traffic and more variable traffic than the other protocols to achieve convergence, (4) H-TCP trades stability for fairness; that is, while its fairness is good independent of background traffic types, larger variance in the flow sizes and RTTs of background flows causes the protocol to induce a higher degree of global loss synchronization among competing flows, lowering link utilization and stability, (5) FAST suffers unfairness and instability in small buffer or long delay networks regardless of background traffic types, and (6) the fairness of high-speed protocols depends more on the amount of competing background traffic rather than its rate variability. We also find that the presence of high-speed flows does not greatly reduce the bandwidth usage of background Web traffic.     

Short-circuiting the congestion signaling path for AQM algorithms using reverse flow matching

Recently, we introduced a new congestion signaling method called ACK spoofing, which offers significant benefits over existing methods, such as packet dropping and Explicit Congestion Notification (ECN). Since ACK spoofing requires the router to create a ‘short circuit’ signaling path, by matching marked data packets in a congested buffer with ACK packets belonging to the same flow that are traveling in the opposite direction, the focus of this paper is evaluating the feasibility of reverse flow matching. First, we study the behavior of individual flows from real bi-directional Internet traces to show that ACK spoofing has the potential to significantly reduce the signaling latency for Internet core routers. We then show that reverse flow matching can be implemented at reasonable cost, using essentially the same hardware as the packet filtering logic commonly employed in Layer 2 transparent bridges. Finally, we show that this architecture can be scaled to accommodate worst-case traffic patterns on multi-gigabit links that would render ordinary route caching algorithms completely ineffective.     

基于模糊逻辑的高速网络自适应拥塞控制研究

基于模糊逻辑 ,利用自适应拥塞控制机制来预测高速网络 (如Internet中 )的拥塞问题 .把路由器的缓冲系统看作一个非线性离散动态系统 ,利用基于模糊逻辑的控制器来预测源端发送速率的确切值以防止拥塞的发生 .通过对参数向量的调节来估计无法预测的和具有统计波动性的网络通信量 ,并利用Lyapunov分析方法来验证闭环系统的稳定性 .最后 ,以一个仿真例子说明了所提出方法的有效性 .     

Online FPS games: effect of router buffer and multiplexing techniques on subjective quality estimators

First Person Shooters are a genre of online games in which users demand a high interactivity, because the actions and the movements are very fast. They usually generate high rates of small packets which have to be delivered to the server within a deadline. When the traffic of a number of players shares the same link, these flows can be aggregated in order to save bandwidth. Certain multiplexing techniques are able to merge a number of packets, in a similar way to voice trunking, creating a bundle which is transmitted using a tunnel. In addition, the headers of the original packets can be compressed by means of standard algorithms. The characteristics of the buffers of the routers which deliver these bundled packets may have a strong influence on the network impairments (mainly delay, jitter and packet loss) which determine the quality of the game. A subjective quality estimator has been used in order to study the mutual influence of the buffer and multiplexing techniques. Taking into account that there exist buffers which size is measured in terms of bytes, and others measured in packets, both kinds of buffers have been tested, using different sizes. Traces from real game parties have been merged in order to obtain the traffic of 20 simultaneous players sharing the same Internet access. The delay and jitter produced by the buffer of the access router have been obtained using simulations. In general, the quality is expected to be reduced as the background traffic grows, but the results show an anomalous region in which the quality rises with the background traffic amount. Small buffers present better subjective quality results than bigger ones. When the total traffic amount gets above the available bandwidth, the buffers measured in bytes add to the packets a fixed delay, which grows with buffer size. They present a jitter peak when the offered traffic is roughly the link capacity. On the other hand, buffers which size is measured in packets add a smaller delay, but they increase packet loss for gaming traffic. The obtained results illustrate the need of knowing the characteristics of the buffer in order to make the correct decision about traffic multiplexing. As a conclusion, it would be interesting for game developers to identify the behaviour of the router buffer so as to adapt the traffic to it.     

A novel resource scheduling algorithm for QoS-aware services on the Internet

The popularity and availability of Internet connection has opened up the opportunity for network-centric collaborative work that was impossible a few years ago. Contending traffic flows in this collaborative scenario share different kinds of resources such as network links, buffers, and router CPU. The goal should hence be overall fairness in the allocation of multiple resources rather than a specific resource. In this paper, firstly, we present a novel QoS-aware resource scheduling algorithm called Weighted Composite Bandwidth and CPU Scheduler (WCBCS), which jointly allocates the fair share of the link bandwidth as well as processing resource to all competing flows. WCBCS also uses a simple and adaptive online prediction scheme for reliably estimating the processing times of the incoming data packets. Secondly, we present some analytical results, extensive NS-2 simulation work, and experimental results from our implementation on Intel IXP2400 network processor. The simulation and implementation results show that our low complexity scheduling algorithm can efficiently maximise the CPU and bandwidth utilisation while maintaining guaranteed Quality of Service (QoS) for each individual flow.     

基于流映射的负载均衡调度算法研究

网络管理者需要能够提供可扩展性、吞吐率保证及报文顺序的高性能路由器体系结构.目前基于Crossbar的集中式路由器体系结构难以实现性能和规模的可扩展,基于两级Mesh网络的负载均衡交换结构成为扩展Internet路由器容量的有效的途径.负载均衡路由器存在严重的报文乱序现象,输出端报文重定序复杂度为O(N2).文中提出一种区域均等的负载均衡交换结构,每k个连续的中间级输入端口划分为一个区域,输入端采用基于流映射的负载分配算法UFFS-k(Uniform Fine-grain Frame Spreading,k为聚合粒度,简称UFFS-k),在k个连续的外部时间槽,以细粒度的方式将同一条流的k个信元分派到固定的映射区域,通过理论证明,该调度策略可获得100%吞吐率并能够保证报文的顺序.为避免流量区域集中现象,采用双循环(dual-rotation)方式构建不同输入端口的流到区域的映射关系;为实现负载在中间级输入端口的均衡分布,每个输入端口维护全局统一视图的流量分布矩阵,UFFS-k调度算法根据流量分布矩阵调度单位帧,可以证明,对任意输出端口j,同一区域OQj队列长度相同且不同区域OQj队列长度至多差1,从而实现了100%负载均衡度.UFFS-k调度算法分布于每个输入端口独立执行,根据流到区域的映射关系及负载分布状态分派信元,模拟结果显示,当聚合粒度k=2时,UFFS-k算法在同类维序算法中表现出最优延迟性能.     

Design of Adaptive PI Rate Controller for Best-Effort Traffic in the Internet Based on Phase Margin

In this paper, we propose an adaptive PI (proportional-integral) rate controller for the AQM (active queue management) router that would support best-effort traffic in the Internet. Unlike most window-based controllers, our rate-based controller design is derived from the classical control theory and it would allow the users to achieve good stability robustness of the AQM control system by specifying a proper phase margin. We also make our controller adaptive by selecting a simple heuristic parameter to monitor the network environment real-time so that the controller would self-tune only when a dramatic change of the network traffic has drifted the monitoring parameter outside its specified interval. Located in the router, the adaptive PI rate controller calculates desirable source window sizes (i.e., source sending rates) based on the instantaneous queue length of the buffer and advertises it to the sources. Our simulations demonstrate that our AQM control system can adapt very well to sudden changes in network environment, thus providing the network with good transient behavior. By making the source sending rate relatively smooth, our adaptive PI rate controller becomes quite suitable for streaming media traffic control in the Internet     

利用路由器自适应限流防御分布拒绝服务攻击

提出一种自适应路由器限流算法防御分布拒绝服务攻击的机制.该算法的关键是由被攻击者要求经挑选的相距k跳(hop)的上游路由器对目的为被攻击者的数据流进行限流,从而将被攻击者的服务支援在各数据流之间达到一种类最大-最小公平的流量分配.还在一个实际的因特网拓扑上针对攻击数据流和合法数据流的不同分布和流量模型考察了算法的效果.结果表明这种以服务器为中心的路由器限流是对抗分布拒绝服务攻击的一种很有前途的方法.     

Dynamic queue level control of TCP/RED systems in AQM routers

One main TCP congestion control objective is, by dynamically adjusting the source window size according to the router queue level, to stabilize the buffer queue length at a given target, thereby achieving predictable queueing delay, reducing packet loss and maximizing link utilization. One difficulty therein is the TCP acknowledging actions will experience a time delay from the router to the source in a TCP system. In this paper, a time-delay control theory is applied to analyze the mechanism of packet-dropping at router and the window-updating in TCP source in TCP congestion control for a TCP/RED dynamic model. We then derive explicit conditions under which the TCP/RED system is asymptotically stable in terms of the instantaneous queue. We discuss the convergence of the buffer queue lengths in the routers. Our results suggest that, if the network parameters satisfy certain conditions, the TCP/RED system is stable and its queue length can converge to any target. We illustrate the theoretical results using ns2 simulations and demonstrate that the network can achieve good performance and converge to the arbitrary target queues.     

Hardware design and implementation of packet fair queuing algorithms for the quality of service support in the high-speed internet

The increasing amount of real-time traffic carried over the Internet requires end-to-end quality of service (QoS) support. To this end, the QoS Schedulers, that are implemented in routers, assign the available bandwidth resources to packet flows according to their respective allocated rates. Packet Fair Queuing (PFQ) schedulers can provide fair service and low end-to-end delay bound to the traffic flows. However, they have higher implementation complexity compared to other algorithms, because of the requirements of tracking the system state, and searching for the packet to get service among all flows, that are queued at the outgoing interface. QoS scheduling is a data plane functionality, which requires hardware implementation for high speed router interfaces. The previous works on hardware implementation of PFQ schedulers are specific to certain algorithms, and they do not provide any results on real hardware platforms. In this paper, we present a general hardware design framework for PFQ schedulers, and apply this framework to the WF²Q+ PFQ algorithm to demonstrate its properties. We carry out the entire implementation of the WF²Q+ algorithm on an FPGA, and evaluate its performance with real traffic flows. In addition, we implement WFQ as a second PFQ algorithm to demonstrate the generality of the framework.     

基于分形散粒噪声的天基网络流量生成

为在天基网络中进行应用级开发与研究,需要对背景业务流量进行建模并实时生成。本文提出了一种基于分形散粒噪声的卫星网络聚合背景流量生成算法,该算法根据星间链路的差错特性、星上路由器随机丢弃策略、星间路由往返时延抖动特性、拥塞控制策略,对单个流的速率波动进行建模,进而使用分形散粒噪声过程对天基组网中的聚合业务务流量进行模拟生成。本文在空间综合信息网络仿真环境中使用该算法对SCPS-VJ空间传输控制协议聚合流量进行了模拟生成。仿真结果表明,该算法能够生成符合空间网络
特性的背景流量。     

快速数据包分流算法研究

基于“流”的数据包分类算法已经在第四层交换等领域中得到了应用,该类算法的特点是流表的容量大,流表的更新速度较快.“快速的数据包分流算法”采用了散列算法的基本思想,并引入了流的局部性原理来加速散列查找的过程,用软件对该算法进行了仿真测试,并在最后从时间复杂度和空间复杂度两个方面对其进行了性能分析.实验结果表明,该算法具有良好的时间复杂度和空间复杂度,可以实现快速的分流.     

A Lightweight Fairness-Driven AQM for Regulating Bandwidth Utilization in Best-Effort Routers

The end-to-end congestion control mechanism of transmission control protocol (TCP) is critical to the robustness and fairness of the best-effort Internet. Since it is no longer practical to rely on end-systems to cooperatively deploy congestion control mechanisms, the network itself must now participate in regulating its own resource utilization. To that end, fairness-driven active queue management (AQM) is promising in sharing the scarce bandwidth among competing flows in a fair manner. However, most of the existing fairness-driven AQM schemes cannot provide efficient and fair bandwidth allocation while being scalable. This paper presents a novel fairness-driven AQM scheme, called CHORD (CHOKe with recent drop history) that seeks to maximize fair bandwidth sharing among aggregate flows while retaining the scalability in terms of the minimum possible state space and per-packet processing costs. Fairness is enforced by identifying and restricting high-bandwidth unresponsive flows at the time of congestion with a lightweight control function. The identification mechanism consists of a fixed-size cache to capture the history of recent drops with a state space equal to the size of the cache. The restriction mechanism is stateless with two matching trial phases and an adaptive drawing factor to take a strong punitive measure against the identified high-bandwidth unresponsive flows in proportion to the average buffer occupancy. Comprehensive performance evaluation indicates that among other well-known AQM schemes of comparable complexities, CHORD provides enhanced TCP goodput and intra-protocol fairness and is well-suited for fair bandwidth allocation to aggregate traffic across a wide range of packet and buffer sizes at a bottleneck router.     

A differentiated services architecture for multimedia streaming in next generation Internet

This paper presents a Differentiated Services (Diffserv or DS) architecture for multimedia streaming applications. Specifically, we define two types of services in the context of Assured Forwarding (AF) per hop behavior (PHB) that are differentiated in terms of reliability of packet delivery: the High Reliable (HR) service and the Less Assured (LA) service. We propose a novel node mechanism called Selective Pushout with Random Early Detection (SPRED) that is capable of simultaneously achieving the following four objectives: (1) a core router does not maintain any state information for each flow (i.e., core-stateless); (2) the packet sequence within each flow is not re-ordered at a node; (3) packets from HR service are delivered more reliably than packets from LA service at a node during congestion; and (4) packets from TCP traffic are dropped randomly to avoid global synchronization during congestion. We show that SPRED is a generalized buffer management algorithm of both tail-dropping and Random Early Detection (RED), and combines the best features of pushout (PO), RED and RED with In/Out (RIO) mechanisms. Simulation results demonstrate that under the same link speed and network topology, network nodes employing our Diffserv architecture have substantial performance improvement over the current Best Effort (BE) Internet architecture for multimedia streaming applications.     

Splitting and merging of packet traffic: Measurement and modelling

This paper concerns the modelling of Internet packet traffic. In previous work we showed that a Bartlett–Lewis point process, as a model of packet arrivals on backbone links, enjoys strong physical backing and can predict key features. It is based on the surprising empirical observation that flows can often be considered independent for the purpose of modelling packet arrival times. We extend this work in two ways by using a unique dataset obtained from an experiment where all the packets crossing a backbone router are captured. First, this enables an examination of the validity of the fundamental assumptions underlying the model across several links, covering a large range of bandwidths and utilization levels. Second, we extend the model from links to a network node, by examining the merging and splitting properties of the (sub)streams through the router, and mapping these to the merging and splitting properties of the model. We show how the model can, in most cases, capture the observed multiplexing and demultiplexing behaviour of the router, opening up the possibility of its use for understanding traffic flows in networks. We show that failures in the model cannot be accounted for simply through considering utilisation levels, and explain how they can in fact be used as a detector of upstream bottlenecks and traffic shaping.     

小缓存对网络实时业务的影响

论述基于TCP协议模型的各种骨干路由器缓存容量研究成果。针对网络实时视频业务的发展,研究小缓存对网络实时视频流的影响,总结小缓存存在的不足,利用网络仿真工具NS2分析小缓存对网络性能的影响。实验结果表明,当链路利用率较低时,小缓存能够满足实时业务的性能要求。     

Traffic measurement and analysis in an ATM-based internet backbone

This paper reports our measurements and analysis of traffic characteristics in an Internet backbone ATM network. In order to utilize network resource efficiently while satisfying the quality of service requirement, it is important to understand the traffic characteristics. We therefore monitored the traffic from the flow or application level to the cell level on a link between NTT's Open Computer Network (OCN) and the Science Information Network (SINET), which are two of the largest Internet backbone ATM-based networks in Japan. Using the monitored traffic, we also evaluated the performance of the aggregate traffic by real-time simulation. Results show that the performance (cell loss ratio) greatly depended not only on link utilization but also on the number of flows, flow size, and traffic composition in terms of applications. We also found that the degree of self-similarity in the Internet backbone was not large. In addition, we clarified that more statistical multiplexing gain could be obtained in the Internet backbone when more flows were multiplexed onto a link.     

A measurement-based study on the correlations of inter-domain Internet application flows

Internet traffic characterization has a profound impact on network engineering and traffic identification. Existing studies are often carried out on a per-flow basis, focusing on the properties of individual flows. In this paper, we study the interaction of Internet traffic flows and network features from a complex network perspective, focusing on six types of applications: P2P file sharing, P2P stream, HTTP, instant messaging, online games and abnormal traffic. With large-volume traffic flow records collected through proprietary line-speed hardware-based monitors, we construct flow graphs of these different application types. Based on the flow graphs, we calculate the correlation coefficients on various properties for individual or multiple applications. Our studies on associativity among degree and strength of individual hosts and connected nodes reveal distinct correlative behavior of different types of applications. Especially, the correlations of P2P applications are observed to be much stronger than those of the other applications. We also investigate the correlations between different types of applications, and observe that HTTP has remarkably different correlations from those of the two P2P applications due to the fact that multiple application types rely on HTTP. Finally, we study the dynamics of correlations for a period of 24 h and reveal a few interesting trends. We believe that our work which focuses on the assortativities of Internet applications provides insightful understanding on Internet traffic classification of up-to-date applications and will be helpful for Internet traffic classification and engineering.