A new traffic model for backbone networks and its application to performance analysis

In this paper, we present a new traffic model constructed from a random number of shifting level processes (SLP) aggregated over time, in which the lengths of the active periods of the SLP are of Pareto or truncated Pareto distribution. For both cases, the model has been proved to be asymptotically second‐order self‐similar. However, based on extensive traffic data we collected from a backbone network, we find that the active periods of the constructing SLPs can be approximated better by a truncated Pareto distribution, instead of the Pareto distribution as assumed in existing traffic model constructions. The queueing problem of a single server fed with a traffic described by the model is equivalently converted to a problem with a traffic described by Norros' model. For the tail probability of the queue length distribution, an approximate expression and upper bound have been found in terms of large deviation estimates and are mathematically more tractable than existing results. The effectiveness of the traffic model and performance results are demonstrated by our simulations and experimental studies on a backbone network. Copyright © 2007 John Wiley & Sons, Ltd.     

IP骨干网流量的自动化预测

高效、可靠的网络流量预测是网络规划、扩容建设的基础。互联网流量目前缺乏完备的理论模型,行业内大多根据工程实践特点,设计简化可操作的预测模型以满足IP网络规划需求。首先根据中国电信自身IP骨干网流量预测工作的需求及特点,使用时间序列分析的多因子回归模型和函数自适应模型对IP骨干网流量进行分析和预测,基于大量现网实际数据的仿真运算,对比两种模型的特点、优劣和适用场景,提出了一种预测模型选择和参数优化的原则和方法。在此基础上,构建了可以满足百千量级时间序列要求的自动化流量预测系统,极大简化并提升了流量预测工作的效率。最后,展望了未来IP流量预测工作的延展方向和关注重点。     

Routing in ISL networks considering empirical IP traffic

Next-generation satellite networks are expected to provide a variety of applications with diverse performance requirements, which will call for the development of adaptive routing procedures supporting different levels of services. In this paper, we propose traffic class dependent (TCD) routing, which has the potential to differentiate between traffic classes using different optimization criteria in route calculation. The performance of TCD routing is evaluated for different traffic scenarios using an empirical traffic source model derived from the real backbone Internet traffic trace and compared with results obtained with equivalent Poisson traffic as a reference point. In addition, TCD routing is compared with a simple single service routing procedure, which does not make any distinction between traffic classes. Performance analysis, in terms of average packet delay, normalized data throughput, and normalized link load, reveals improved routing resulting from traffic class differentiation, regardless of the traffic scenario considered. The performance measures based of aggregate traffic flow show no significant difference between routing of empirical and equivalent Poisson traffic.     

Performance analysis of integrated-services load-adaptive/TDMA satellite networks

A load-adaptive/TDMA multiple-access communications system which serves to interconnect broad-band multimedia packet streams is considered. In particular, the use of a satellite backbone communications link whose channels are dynamically assigned to network stations is investigated. Each station supports packetized voice and data message streams. Incoming streams to a station are statistically multiplexed by the station across the backbone channels currently allocated to this station. To enhance the multiplexing process, a variable bit-rate packet-voice encoding scheme is also employed. Stations periodically issue requests for backbone channel allocations, based upon their estimated loading status. We introduce two distinct multiple-access algorithms for allocating the shared backbone channels to the stations. We develop analytical methods for the analysis and design of such integrated multiplexing/multiple-access networks. Performance measures include voice and data packet delays and packet blocking probabilities. Voice stream performance is also characterized by the average number of bits per sample used by the voice encoding scheme. The effects of the propagation delay across the backbone link are especially demonstrated. Also illustrated are the performance improvements attained due to the use of the load-adaptive/TDMA scheme. Under the example of the ’all-voice’ traffic loading, an LA/TDMA scheme exhibits no obvious performance improvement over a fix-assigned scheme. However, as the burstiness of the traffic loading increases in the example of the ’data-voice’ traffic loading, a significant amount of improvement (36 per cent bandwidth savings) is realized by a LA/TDMA scheme.     

OBT: Optical Burst Transport in Metro Area Networks

For the past few years, the evolution of electro-optical technology has driven change in optical networks in the access and backbone areas. Optical bypassing and traffic aggregation mitigate the scalability problem in backbone networks, and burst mode transmission can provide a cost-efficient solution for access networks. Using those technologies, a new solution can be found for metro area networks, which interconnect access and backbone networks. In this article, we introduce a new solution for metro area networks, called optical burst transport (OBT). OBT is designed to use the promising technologies of backbone and access networks so that it provides all benefits, such as dynamic bandwidth provisioning, scalability, and robustness for unbalanced traffic. The performance evaluation of OBT also is verified by means of a testbed implementation.     

Multi-hour design of computer backbone networks

This paper addresses the problem of designing wide area computer backbone networks that span many time zones. The problem of designing wide area computer backbone networks is commonly referred to as the Capacity and Flow Assignment (CFA) problem. The CFA problem involves the routing of messages and the assignment of communication line capacities at minimum cost subject to performance constraints. In this paper, a version of the CFA problem is addressed in which the assignment of communication line capacities is based on multi-hour traffic requirements. Multi-hour traffic requirements are used since networks that span many time zones have changing traffic patterns that exhibit non-coincidence of traffic over the hours of the day. Thus, low cost network designs can be obtained by exploiting this non-coincidence. A heuristic procedure is presented that takes advantage of this non-coincidence to provide low cost solutions. This heuristic procedure is applied to a variety of test problems and the solutions obtained are compared with lower bound solutions computed using a branch- and-bound procedure.     

Dynamic weighted cell multiplexing method for real-time traffic inATM

A new cell multiplexing algorithm is proposed to satisfy the service requirements of real-time traffic in ATM networks. The proposed algorithm is capable of assigning higher weights to real-time traffic than to non-real-time traffic, thereby guaranteeing the quality of service of real-time traffic. Simulation results show that the proposed algorithm has better performance than other cell multiplexing algorithms in terms of the mean delay time and the maximum queue length     

Hybrid routing in ad hoc networks with a dynamic virtual backbone

Virtual backbone routing (VBR) is a scalable hybrid routing framework for ad hoc networks, which combines local proactive and global reactive routing components over a variable-sized zone hierarchy. The zone hierarchy is maintained through a novel distributed virtual backbone maintenance scheme, termed the distributed database coverage heuristic (DDCH), also presented in this paper. Borrowing from the design philosophy of the zone routing protocol, VBR limits the proactive link information exchange to the local routing zones only. Furthermore, the reactive component of VBR restricts the route queries to within the virtual backbone only, thus improving the overall routing efficiency. Our numerical results suggest that the cost of the hybrid VBR scheme can be a small fraction of that of either one of the purely proactive or purely reactive protocols, with or without route caching. Since the data routes do not necessarily pass through the virtual backbone nodes, traffic congestion is considerably reduced. Yet, the average length of the VBR routes tends to be close to optimal. Compared with the traditional one-hop hierarchical protocols, our results indicate that, for a network of moderate to large size, VBR with an optimal zone radius larger than one can significantly reduce the routing traffic. Furthermore, we demonstrate VBR's improved scalability through analysis and simulations.     

Internet traffic engineering

The main goal of Internet traffic engineering is to efficiently optimize the performance of operational networks in order to avoid the well-known shortcomings of the typical destination-based IP routing. Traffic engineering attempts to reduce or even avoid congestion hot spots and to improve resource utilization across the backbone IP network. During the last years traffic engineering has become an inevitable tool concerning performance optimization in large Internet backbones. The core objective of this paper is to give an overview of the architectures and mechanisms for traffic engineering.     

An approximate performance analysis of interconnected token-passingrings

An analysis of the performance, in terms of average message delay, is presented for a system of interconnected ring networks. The system is hierarchical, with local rings served by a high-speed backbone ring through gateway queues. In both the local and the backbone rings, the access technique employed is token passing. Service disciplines, with and without priority, have been studied. In the former, priority is given to inter-ring traffic over local traffic. The study makes use of certain results on average delay in systems where the customer initiating a busy period receives special service for the M/G/1 queue with nonpreemptive priority and for the G/G/1 queue. The analysis, which involved several approximations, was verified by simulation     

Measurement Based Resource Allocation for Interconnected WDM Rings

We present a measurement based resource allocation scheme for interconnected WDM rings in a metropolitan area network named DAVID (Data And Voice Integration over D-WDM). The network has a two level hierarchical structure, with a backbone of optical packet routers interconnected in a mesh, and metropolitan areas served by sets of optical rings connected to the backbone through devices called Hubs. The paper focuses on the operations of the media access protocol and on resource allocation schemes to be used in the metropolitan area network. A simple scheme for datagram (not-guaranteed) traffic is defined and its performance are examined mainly by simulation.     

利用流量特征的GIDS报文分类优化算法

 本文结合流量的动态特征和入侵检测系统规则库的静态特征生成高性能报文分类树,提出了一个新的面向骨干网高速入侵检测的报文分类算法FlowCopySearch(FCS).改进在于:①从流量的新角度提出了最优分类树定义并引入分类域熵衡量每个分类域对于流量的分类能力;②将传统分类算法中每个报文都必须频繁执行的内存拷贝操作简化为每个流只执行一次内存拷贝操作,克服了报文分类算法的瓶颈.实验结果表明FCS更适用于骨干网大流量trace的报文分类,较之两种经典分类算法,分类速度提高了10.1%~45.1%,同时存储消耗降低了11.1%~36.6%.     

MPLS and traffic engineering in IP networks

Rapid growth and increasing requirements for service quality, reliability, and efficiency have made traffic engineering an essential consideration in the design and operation of large public Internet backbone networks. Internet traffic engineering addresses the issue of performance optimization of operational networks. A paramount objective of Internet traffic engineering is to facilitate the transport of IP traffic through a given network in the most efficient, reliable, and expeditious manner possible. Historically, traffic engineering in the Internet has been hampered by the limited functional capabilities of conventional IP technologies. Recent developments in multiprotocol label switching (MPLS) and differentiated services have opened up new possibilities to address some of the limitations of the conventional technologies. This article discusses the applications of MPLS to traffic engineering in IP networks     

Exploiting IP‐layer traffic prediction analytics to allocate spectrum resources using swarm intelligence

Elastic optical networks emerge as a reliable backbone platform covering the next‐generation connectivity requirements. It consists of advanced enabling components that provide the ability for extensive configuration leading to performance improvement in many areas of interest. Higher layer analytics like data from IP traffic prediction can assist in the process of allocating resources at the optical layer. This way, light connections are established more efficiently while targeting specific performance goals. For that purpose, an algorithm is designed and evaluated that exploits traffic prediction of data transfers between nodes of an optical metro or backbone network. Next, it utilizes adaptive functionality based on particle swarm optimization to find paths with available spectrum resources. These resources can facilitate more efficiently the future traffic demand, since traffic prediction data are considered when finding the related paths. The innovative resource allocation method is evaluated using small and very large real topologies. It scales (in execution time and resource usage) according to node increase, executes in feasible time frames, and reduces transponder utilization resulting to increased energy efficiency.     

A Hybrid Centralized Routing Protocol for 802.11s WMNs

Wireless mesh networks (WMNs) are being widely accepted as a critical wireless access solution for various applications. Due to minimal mobility in mesh nodes, a backbone topology can be effectively maintained in WMN using a proactive routing protocol. In IEEE 802.11s standard, a tree-based routing (TBR) protocol is adopted as a viable proactive routing protocol for a WMN with user traffic flowing to/from a wired network through a root (i.e., a mesh portal). However, the performance of the TBR protocol degrades rapidly as the user traffic becomes dominated by intra-mesh traffic. The reason is that the routing path through the root even for intra-mesh traffic unnecessarily overloads the root. Furthermore, the TBR performance becomes more severe when the network size of WMN is large, which could lead to the huge amount of intra-mesh traffic towards the root. To overcome these problems, we propose a new routing mechanism, root driven routing (RDR) protocol, for the root to quickly determine the best-metric route for any source-destination pair of intra-mesh traffic. For inter-mesh traffic, the original TBR protocol is employed. Thus, the hybrid centralized routing protocol that combines TBR and RDR and is adaptive to all traffic scenarios. Our simulation results reveal that the proposed RDR protocol outperforms the TBR protocol with much lower average end-to-end delay and much higher packet delivery ratio for intra-mesh traffic. The simulation results also provide some insight into the right tradeoff between the TBR protocol and the RDR protocol to achieve the best performance of the hybrid centralized routing protocol for WMNs.     

TDMA时隙分配对业务时延性能的影响分析

 在TDMA通信系统中,时隙分配是影响业务时延性能的重要因素,包括时隙数量分配(带宽分配)、时隙分配周期(TDMA帧长)和时隙位置分配三方面.本文针对可变速率和固定速率两类业务,基于随机服务系统理论和交通流理论建立了业务时延模型,得到了平均时延的解析式,分析了时隙数量、时隙位置和TDMA帧长度对业务时延影响的规律和特点.结果表明时隙位置分配越均匀,越能改善业务的平均时延和时延抖动性能;而在传统的时隙连续分配方式下,增加时隙数量分配对时延性能提高非常有限.在DVB-RCS卫星系统等具有较长帧设计的TDMA系统中,采用时隙均匀分配方式能够有效提高业务时延性能.计算机仿真验证了建模分析的正确性.     

基于深度报文检测和深度流检测的骨干网流量特征分析

Based on the massive data collected with a passive network monitoring equipment placed in China's backbone, we present a deep insight into the network backbone traffic and evaluate various ways for improving traffic classifying efficiency in this paper. In particular, the study has scrutinized the network traffic in terms of protocol types and signatures, flow length, and port distribution, from which meaningful and interesting insights on the current Internet of China from the perspective of both the packet and flow levels are derived. We show that the classification efficiency can be greatly improved by using the information of preferred ports of the network applications. Quantitatively, we find two traffic duration thresholds, with which 40% of TCP flows and 70% of UDP flows can be excluded from classification processing while the impact on classification accuracy is trivial, i.e., the classification accuracy can still reach a high level by saving 85% of the resources.     

一种轻量型YOLOv5交通标志识别方法

针对为提高交通标志识别精度使得神经网络层数过深从而导致实时性不佳的问题,提出了一种轻量型YOLOv5交通标志识别方法。首先采用遗传学习算法和K-means聚类确定适合交通标志识别的锚框,然后引入Stem模块和ShufflenetV2的基础单元网络来替换YOLOv5的主干网络。相比于YOLOv5模型,在中国交通标志检测数据集上,轻量型YOLOv5模型在保持识别精度为95.9%的同时,参数量减少了95.4%,实际内存空间减少了93.9%,在GPU和CPU上运行的速度分别提升了79.7%和75%,极大地提高了交通标志识别的实时性,更适合无人驾驶环境感知系统的部署。     

A Hybrid RF and Vision Aware Fusion Scheme for Multi-Sensor Wireless Capsule Endoscopic Localization

A huge torrent of data traffic is generated from various heterogeneous applications and services at the Internet backbone. In general, at the backbone, all such applications and services are allocated spectral resources under a shared spectrum environment within elastic optical networks (EONs). In such a fully shared environment, connection requests (CRs) belonging to different traffic profiles compete for spectral resources. Hence, it is very challenging for network operators to resolve resource conflict that occur at the time of provisioning resources to such CRs. The heterogeneous traffic profile (HTP) considered in this work includes permanent lightpath demands (PLDs) and scheduled lightpath demands (SLDs). We propose various distance adaptive routing and spectrum assignment (DA-RSA) heuristics to resolve resource conflict among these two traffic profiles in EONs under a full sharing environment. Conventionally, preemption was the only technique to resolve such resource conflict among HTPs. Since preemption involves the overhead of selecting CRs to be preempted and then deallocating the resources given to those CRs, excessive preemption adversely affects the performance of the network. Therefore, in this work, we utilized bandwidth splitting as a solution to resolve resource conflict among HTPs under such a shared environment in EONs. Moreover, an integrated solution consisting of splitting and preemption is also proposed. We refer to this new integration as flow-based preemption. Our simulation results demonstrate that bandwidth splitting-based heuristics yield significant improvement in terms of the amount of bandwidth accepted in the network, link and node utilization ratio, number of transponders utilized and the amount of bandwidth dropped due to preemption. Moreover, the flow-based preemption approach is proved to be superior in performance amongst all proposed strategies.

     

The IEEE 802.17 media access protocol for high-speed metropolitan-area resilient packet rings

The resilient packet ring (RPR) IEEE 802.17 standards is under development as a new high-speed technology for metropolitan backbone networks. A key performance objective of PRP is to simultaneously achieve high utilization, spatial reuse, and fairness, an objective not achieved by current technologies such as SONET and Gigabit Ethernet or legacy ring technologies, such as FDDI. The core technical challenge for RPR is the design of a fairness algorithm that dynamically throttles traffic to achieve these properties. The difficulty is in the distributed nature of the problem, that upstream ring nodes must inject traffic at a rate according to congestion and fairness criteria downstream. This article provides an overview of the RPR protocol with a focus on medium access and fairness.