基于时延耦合映象格子的相继拥堵模型

实际网络中由于拥塞、带宽、传输速度等因素,通常存在耦合时延。该文提出一种带时延耦合映象格子的相继拥堵模型,在此基础上研究交通路网上各个节点的非线性动力学特征,交通拥堵在路网上的形成机理与传播的复杂动力学行为,拥堵故障在网络中扩散的过程。模拟网络中随机发生拥堵和蓄意攻击所引发的两种相继拥堵策略,并推导出网络中故障承受能力的阈值范围。     

有效提高Internet传输性能的社团结构改善策略

提出一种增添能最有效减弱网络社团特性的边以提高Internet网络传输性能的策略,即减弱社团结构策略（简称WCS策略）,并基于光逻辑链路可以提供与实际物理链路相当的高性能,以实现WCS策略的Internet网络的拓扑重构。在伪随机网络、具有社团结构的无标度人工网络和实际Internet网络上分别进行了基于全局最短路径路由和局部路由的实验。实验结果表明,利用WCS策略在社团之间少量边的添加,就能实现网络负载能力和平均最短路径的大幅改善。     

Study on dynamic routing and spectrum assignment in bitrate flexible optical networks

The exponential growth of Internet traffic necessitates high-capacity optical networks and has also highlighted the importance of bandwidth-flexible and multi-granularity transport platforms. Improving both transport capacity and bandwidth flexibility is a significant challenge in optical networks. A bitrate flexible network architecture that is based on orthogonal frequency division multiplexing has been proposed as a promising solution for meeting this challenge. In the current study, we focus on the online routing and spectrum assignment problems in the aforementioned network architecture and introduce a general solution for dynamic bitrate flexible traffic in distributed environments. A novel spectrum representation method based on continuous spectrum segments is introduced into the networks. Segment-based routing and signaling mechanisms provide general solutions that support both the conventional slot-based networks and the ideal fully gridless networks. The routing algorithms and spectrum selection approaches are demonstrated and compared in a simulation. Performance estimation indicates that random spectrum segment assignment achieves the lowest capacity blocking rate in light traffic, whereas the adaptive routing plus minimum residual spectrum scheme obtains the lowest capacity blocking rate under heavy traffic.     

负载作用下相依网络择优恢复方法研究

优选节点实施恢复是控制相依网络级联失效的有效措施。针对以往恢复模型未考虑节点负载的情况,该文首先分析了包含依赖失效和过载失效的级联失效过程,构建了负载作用下相依网络恢复模型。然后,基于共同边界节点的结构和动力学属性,提出一种基于容量和连接边的择优恢复(PRCCL)方法。实验结果表明,在无标度相依网络中,PRCCL方法恢复效果明显好于基准方法,恢复时间更短,恢复后的网络具有更高的平均度和鲁棒性;在Power网和Internet网构成的相依网络中,PRCCL方法恢复效果同样优于基准方法;PRCCL方法的优势与恢复比例、负载控制参数成正比,与容忍系数成反比。实验结果验证了PRCCL方法的有效性,对于现实中相依网络恢复工作具有科学指导价值。     

A new architecture for transmission of MPEG-4 video on MPLS networks

Due to insufficient network bandwidth on the Internet, multimedia-oriented applications are still not popular. Traffic on the Internet often causes congestion in routers. Therefore, the Internet must overcome these challenges and bottlenecks to provide more multimedia-oriented applications. We study the transmission of MPEG-4-based video traffic in MPLS networks, and propose a better architecture, called actively reserved bandwidth architecture, for improving CR-LDP in MPLS networks. The architecture is designed to overcome the bottleneck of router in MPLS networks. This approach is beneficial to the transmission of MPEG-4-based video traffic.     

Evaluating the impact of emerging streaming media applications onTCP/IP performance

Emerging streaming media applications in the Internet primarily use UDP transport. The difficulty with supporting this type of traffic on the Internet is that they not only generate large volumes of traffic, but they are also not as responsive to network congestion as TCP-based applications. As a result, streaming media UDP traffic can cause two major problems in the Internet: congestion collapse and unfair allocations of bandwidth among competing traffic flows. A solution to these problems is available in many Internet environments. The Internet backbone, various ISPs, and DSL access networks rely on ATM as their layer 2 transport technology, and in such environments, ATM's available bit rate service can efficiently address these problems. ABR is able to avoid congestion collapse and provide fair bandwidth allocations by distributing the unutilized bandwidth fairly among competing flows. This article presents simulation results and empirical measurements that illustrate the congestion collapse and unfairness problems, and ATM ABR's effectiveness in addressing those problems     

Pinning a complex dynamical network to its equilibrium

It is now known that the complexity of network topology has a great impact on the stabilization of complex dynamical networks. In this work, we study the control of random networks and scale-free networks. Conditions are investigated for globally or locally stabilizing such networks. Our strategy is to apply local feedback control to a small fraction of network nodes. We propose the concept of virtual control for microscopic dynamics throughout the process with different pinning schemes for both random networks and scale-free networks. We explain the main reason why significantly less local controllers are required by specifically pinning the most highly connected nodes in a scale-free network than those required by the randomly pinning scheme, and why there is no significant difference between specifically and randomly pinning schemes for controlling random dynamical networks. We also study the synchronization phenomenon of controlled dynamical networks in the stabilization process, both analytically and numerically.     

Next-generation satellite networks: architectures andimplementations

A new generation of satellite networks is being developed to handle highly bursty Internet and multimedia traffic. In these networks, satellite links are used for interconnecting remote network segments as well as for providing direct network access to homes and businesses. In this environment, the satellite network must support not only circuit switched traffic, but also packet services with highly bursty traffic patterns. The traditional circuit switched approach based on the user or network signaling is inadequate to carry dynamically varying packet traffic efficiently, necessitating faster bandwidth allocation solutions. Standard interworking solutions and air interfaces are very important for interoperability leading to proliferation of satellite networks to potentially millions of home and business users. In this article we provide an overview of the standardization effort that has started at the TIA in the area of satellite ATM networks. Subsequently, a bandwidth-on-demand multiservice satellite network architecture implementation is described     

Architectures and performance of optical packet switching nodes for IP networks

As new bandwidth-hungry Internet protocol (IP) services are demanding more and more capacity, transport networks are evolving to provide a reconfigurable optical layer in order to allow fast dynamic allocation of wavelength-division-multiplexing (WDM) channels. To achieve this goal, optical packet-switched systems seem to be strong candidates as they allow a high degree of statistical resource sharing, which leads to an efficient bandwidth utilization. In this paper, we propose an architecture for optical packet-switched transport networks, together with an innovative switching node structure based on the concept of per-packet wavelength routing. The traffic performance of such node when loaded by a typical IP traffic is evaluated through computer simulation; packet loss probability and average delay performance are shown for various load conditions.     

Scalable Network-Layer Defense Against Internet Bandwidth-Flooding Attacks

In a bandwidth-flooding attack, compromised sources send high-volume traffic to the target with the purpose of causing congestion in its tail circuit and disrupting its legitimate communications. In this paper, we present Active Internet Traffic Filtering (AITF), a network-layer defense mechanism against such attacks. AITF enables a receiver to contact misbehaving sources and ask them to stop sending it traffic; each source that has been asked to stop is policed by its own Internet service provider (ISP), which ensures its compliance. An ISP that hosts misbehaving sources either supports AITF (and accepts to police its misbehaving clients), or risks losing all access to the complaining receiver—this is a strong incentive to cooperate, especially when the receiver is a popular public-access site. We show that AITF preserves a significant fraction of a receiver's bandwidth in the face of bandwidth flooding, and does so at a per-client cost that is already affordable for today's ISPs; this per-client cost is not expected to increase, as long as botnet-size growth does not outpace Moore's law. We also show that even the first two networks that deploy AITF can maintain their connectivity to each other in the face of bandwidth flooding. We conclude that the network-layer of the Internet can provide an effective, scalable, and incrementally deployable solution against bandwidth-flooding attacks.      

A new structure-preserving method of sampling for predicting self-similar traffic

The paper presents a structure-preserving method of sampling self-similar traffic with an application to network monitoring and resource provisioning. Based on the observation of the self-similarity of Internet traffic, we propose a new sampling technique (so-called the maximum-based sampling). We show that the resulting data suits perfectly for predicting the bandwidth required by upcoming traffic so that the resource provisioning can be done efficiently and intelligently especially for the context of IP over WDM networks. Hence, we prove mathematically that the proposed technique preserves the self-similarity of the traffic. Besides, experimental results using real Internet traffic show that unlike other sampling techniques (systematic sampling and stratified random sampling), the maximum-based sampling capture faithfully the traffic self-similarity. In order to assess the effect of the sampling technique impact on the performance of the traffic prediction,we undertake a series of prediction experiments using sampled traffic with the proposed technique and the other sampling techniques. A neurofuzzy model (α _SNF), the AutoRegressive Integrated Moving Average model (ARIMA) and the Linear Minimum Mean Square Error (LMMSE) are considered in this study for bandwidth prediction. Our experiments results show that the maximum-based sampled traffic—used for the identification of the prediction model—is the most suitable for predicting the traffic for different time scales.     

Constrained light-tree design for WDM mesh networks with multicast traffic grooming

Multicast applications such as IPTV, video conferencing, telemedicine and online multiplayer gaming are expected to be major drivers of Internet traffic growth. The disparity between the bandwidth offered by a wavelength and the bandwidth requirement of a multicast connection can be tackled by grooming multiple low bandwidth multicast connections into a high bandwidth wavelength channel or light-tree. Light-trees are known to be especially suited for networks that carry ample multicast traffic. In this paper, we propose new algorithms to address the problem of multicast traffic grooming. In particular, an Integer Linear Programming (ILP) formulation is proposed for optimal assignments of hop constrained light-trees for multicast connections so that network throughput can be maximized. Hop constrained light-trees improve the scalability of the approach by reducing the search space of the ILP formulation. Since solving the ILP problem is very time consuming for realistically large networks, we are motivated to propose a heuristic algorithm with a polynomial complexity, called Dividable Light-Tree Grooming (DLTG) algorithm. This algorithm is based on grooming traffic to constrained light-trees and also divides a light-tree to smaller constrained light-trees on which traffic is groomed for better resource utilization. Simulations show that the proposed DLTG heuristic performs better than other algorithms. It achieves network throughputs which are very close to the ILP formulation results, but with far lower running times.     

Performance analysis of bandwidth allocation strategy with state-dependent Bernoulli access and preemptive priority in wideband integrated networks

In this paper, we study a bandwidth allocation strategy with state-dependent Bernoulli access (SDBA) and preemptive priority (PP) to serve wideband (WB) and narrowband (NB) traffics in wideband integrated networks. In this strategy, total bandwidth is divided into three regions, bandwidth for WB traffic, bandwidth for NB traffic and shared bandwidth. Under this environment, the minimum usable bandwidths for queueable NB traffic are controlled adaptively according to the system states. And the bandwidths used by the NB traffic are probabilistically preempted by a blockable WB traffic, when the number of NB messages waiting in the buffer is varying. The strategy is analyzed using the Neuts' matrix analytic approach. It shows better performance than other schemes which do not use SDBA and PP. In addition, the strategy with multiple buffer thresholds controls bandwidth allocation more dynamically and shows more performance build-up than the strategy with single buffer threshold.     

复杂网络与可扩展路由

互联网规模扩大,相应路由表大小呈指数增加,形成下一代互联网可扩展路由“瓶颈”。基于复杂网络和可扩展路由的相关理论与主要策略,文章对相关研究成果。如小世界效应所表现出来的特性、小世界和无标度网络模型,网格、层次及隐藏度量等3种可扩展路由网络模型,随机游走、贪婪、最大度、优先、本地介数、距离与度及相似性与度混合等多种路由策略等进行了分析与归纳。这些研究结果和方法为因互联网规模不断扩大所带来的路由系统可扩展性问题提供解决方案     

Service overlay networks: SLAs, QoS, and bandwidth provisioning

We advocate the notion of service overlay network (SON) as an effective means to address some of the issues, in particular, end-to-end quality of service (QoS), plaguing the current Internet, and to facilitate the creation and deployment of value-added Internet services such as VoIP, Video-on-Demand, and other emerging QoS-sensitive services. The SON purchases bandwidth with certain QoS guarantees from the individual network domains via bilateral service level agreement (SLA) to build a logical end-to-end service delivery infrastructure on top of the existing data transport networks. Via a service contract, users directly pay the SON for using the value-added services provided by the SON. In this paper, we study the bandwidth provisioning problem for a SON which buys bandwidth from the underlying network domains to provide end-to-end value-added QoS sensitive services such as VoIP and Video-on-Demand. A key problem in the SON deployment is the problem of bandwidth provisioning, which is critical to cost recovery in deploying and operating the value-added services over the SON. The paper is devoted to the study of this problem. We formulate the bandwidth provisioning problem mathematically, taking various factors such as SLA, service QoS, traffic demand distributions, and bandwidth costs. Analytical models and approximate solutions are developed for both static and dynamic bandwidth provisioning. Numerical studies are also performed to illustrate the properties of the proposed solutions and demonstrate the effect of traffic demand distributions and bandwidth costs on SON bandwidth provisioning.     

Real-time VBR video traffic prediction for dynamic bandwidth allocation

In this paper, we systematically investigate the long-term, online, real-time variable-bit-rate (VBR) video traffic prediction, which is the key and complicated component for advanced predictive dynamic bandwidth control and allocation framework for the future networks and Internet multimedia services. We focus on neural network-based approach for traffic prediction and demonstrate that the prediction performance and robustness of neural network predictors can be significantly improved through multiresolution learning. We show that neural network traffic predictor trained through the multiresolution learning (called multiresolution learning NN traffic predictor) can successfully predict various real-world VBR video traffic up to hundreds of frames in advance, which then lays a solid foundation for predictive dynamic bandwidth control and allocation mechanism. Also, dynamic bandwidth control/allocation based on long-term traffic prediction is discussed in detail.     

Overlay networks of in situ instruments for probabilistic guarantees on message delays in wide-area networks

Messages transported over wide-area networks are subject to various delays at the hosts and intermediate nodes. In addition to bandwidth limits, the delays have an apparent "random" component due to the complicated dynamics of the network traffic. We consider that the messages sent over the network are subjected to three types of delays: 1) propagation delays along the links; 2) delays due to bandwidth of the links; 3) "other delays" at the hosts and intermediate nodes which are randomly distributed according to unknown distributions. We propose an overlay network of in situ instruments on such a network to collect delay measurements, compute paths and route messages. We propose regression methods to compute a path whose message delay is close to the optimal expected delay with a high probability, based entirely on measurements. The delay distributions are arbitrary and this guarantee is the best kind possible for this network. We then present a simple multiple path method for achieving low end-to-end delays. This overlay network is implemented over the Internet using user-level daemons that realize paths among themselves without explicit support from the underlying network routers. Internet measurements show that this method achieves significantly higher aggregated bandwidths compared with the default paths.     

Multiple link failure recovery in survivable optical networks

Survivability is of critical importance in high-speed optical communication networks. A typical approach to the design of survivable networks is through a protection scheme that pre-determines and reserves backup bandwidth considering single/double link failure scenarios. In this article, a greedy algorithm is presented to reserve backup bandwidth considering multiple (F > 2) link (SRLG) failure scenarios. A bandwidth-saving joint selection scheme of working and protection paths is presented for protection against random multiple-link failures under dynamic traffic. Simulation shows that the algorithm can achieve maximum sharing of backup bandwidth for protection against random multiple-link failure with significant amount of bandwidth saving.     

Per-Stream QoS and Admission Control in Ethernet Passive Optical Networks (EPONs)

Ethernet passive optical networks (EPONs) are designed to deliver services for numerous applications such as voice over Internet protocol, standard and high-definition video, video conferencing (interactive video), and data traffic. Various dynamic bandwidth allocation and intra-optical network unit (ONU) scheduling algorithms have been proposed to enable EPONs to deliver differentiated services for traffic with different quality of service (QoS) requirements. However, none of these protocols and schedulers can guarantee bandwidth for each class of service nor can they protect the QoS level required by admitted real-time traffic streams. In this paper, we propose the first framework for per-stream QoS protection in EPONs using a two-stage admission control (AC) system. The first stage enables the ONU to perform flow admission locally according to the bandwidth availability, and the second stage allows for global AC at the optical line terminal. Appropriate bandwidth allocation algorithms are presented as well. An event-driven simulation model is implemented to study the effectiveness of the proposed schemes in providing and protecting QoS.