Traffic dynamics on multilayer networks

Many real-world networks are demonstrated to either have layered network structures in themselves or interconnect with other networks, forming multilayer network structures. In this survey, we give a brief review of recent progress in traffic dynamics on multilayer networks. First, we introduce several typical multilayer network models. Then, we present some mainstream performance indicators, such as network capacity, average transmission time, etc. Moreover, we discuss some optimization strategies for improving the transmission performance. Finally, we provide some open issues that could be further explored in the future.     

Entropy-Based Reduction of Traffic Data

This letter proposes an entropy-based methodology to reduce large network traffic data sets obtained by measurements over real networks. The proposed off-line approach, based on the marginal utility concept, reveals interesting results when applied to real data captured over real networks: to show its applicability, results obtained with traffic traces from a popular network game, counter-strike, are presented     

基于覆盖网络的多路径流量均衡研究

现有网络发送数据都集中在一条最优路径上,使得网络流量不均衡,拥塞不可避免.传统的IP网络难以拓展,文章在应用层上对覆盖网络进行流量均衡,利用覆盖网络之间的互动性给出了覆盖网络的多路径流量均衡模型,在该模型上研究了输入流量和输出流量的分配算法,并通过仿真实验说明了可以有效地减小网络的端到端延迟.     

一种新型动态流量疏导策略

在WDM光网络中业务流量疏导能够有效地降低网络建设成本.为了疏导网络中的动态业务,提出动态业务流量的可重构疏导方案,并给出相应快速在线算法.此算法通过动态调整网络的虚拟拓扑结构,可使网络适应各种动态业务.计算机模拟结果表明,该算法能得到较优的疏导结果.     

业务疏导技术在WDM网络及OPS网络中的应用

在波分复用(WDM)光网络中,可使用业务疏导(Traffic Grooming)技术来提高网络性能,降低网络成本.详细阐述了WDM光网络中业务疏导的基本概念及主要目标,并对国内外研究现状进行了总结.最后介绍了OPS光交换网络中使用的业务疏导技术.     

Traffic engineering experience from operating cellular networks

Modeling of user traffic and the mobility impact of mobile users onto cellular networks is considered. The quality of service and traffic-handling capacity offered by the network play the most important roles. This article discusses the requirements on a traffic model and on performance design objectives which can be used as a basis for designing and engineering cellular networks. Requirements from actual network operation are discussed and are illustrated by measurement results     

On Hierarchical Traffic Grooming in WDM Networks

The traffic grooming problem is of high practical importance in emerging wide-area wavelength division multiplexing (WDM) optical networks, yet it is intractable for any but trivial network topologies. In this work, we present an effective and efficient hierarchical traffic grooming framework for WDM networks of general topology, with the objective of minimizing the total number of electronic ports. At the first level of hierarchy, we decompose the network into clusters and designate one node in each cluster as the hub for grooming traffic. At the second level, the hubs form another cluster for grooming intercluster traffic. We view each (first- or second-level) cluster as a virtual star, and we present an efficient near-optimal algorithm for determining the logical topology of lightpaths to carry the traffic within each cluster. Routing and wavelength assignment is then performed directly on the underlying physical topology. We demonstrate the effectiveness of our approach by applying it to two networks of realistic size, a 32-node, 53-link topology and a 47-node, 96-link network. Comparisons to lower bounds indicate that hierarchical grooming is efficient in its use of the network resources of interest, namely, electronic ports and wavelengths. In addition to scaling to large network sizes, our hierarchical approach also facilitates the control and management of multigranular networks.      

Traffic load metrics for multihomed mobile IP and global connectivity

Support for host mobility an essential and necessary feature for roaming users who connect to wireless networks via access points. Access points may have different capabilities, be connected to different networks and be installed by different providers. A mobile host will discover multiple access points in this environment. In such an environment, a mobile host should be able to use the best available connection to communicate with a correspondent host and perhaps use multiple connections for different hosts. In areas with wireless local area network access, pockets with limited or no coverage could exist. Such restricted connectivity could be compensated by neighbor hosts who form an ad hoc network and relay packets until they reach an access point. This paper describes and discusses a proposed solution towards enabling and supporting connectivity in wireless networks. In the proposed solution the network layer software will evaluate and decide which wireless network connections to use. A Running Variance Metric (RVM) and a Relative Network Load(RNL) are used to measure the traffic load of access points in wireless access networks. RVM and RNL can be efficiently used for both infrastructure networks and ad hoc networks. Multihomed Mobile IP (M-MIP) is an extension of Mobile IP that enables mobile hosts to use multiple care-of addresses simultaneously. The extension enhances network connectivity by enabling the mobile host, the home agent and correspondent hosts to evaluate and select the best connection. A proposed gateway architecture using M-MIP that integrates wired IP networks with ad hoc networks is described. The M-MIP and gateway architecture using the RVM and RNL metrics have been validated with simulation studies and results are presented.     

Estimating the Traffic Distribution Matrix of a Packet-Switched Network Using Aggregate Traffic Measurements

Methods are developed to estimate the source–destination traffic distribution matrix of a packet network using only aggregate link and source/sink traffic measurements. The methods are useful for network planning and monitoring of large packet networks, where it is impractical to gather measurement data on every end-to-end traffic flow. The first method assumes that the distribution matrix is time-invariant. This method is of theoretical interest but provides the foundation for developing a method for the realistic case of a time-varying matrix. The second method assumes that the matrix is time-varying. It uses linear programming (LP) to find a distribution matrix that optimally fits the measurement data. A practical problem with the first two methods is that the computational requirements increase as the square of the number of network nodes. The third method is a fast exact decomposition procedure for the time-invariant case that scales with the network size. The maximum number of unknowns that needs to be solved simultaneously is equal to the number of network nodes. The final method is a fast decomposition procedure for the time-varying case. This procedure scales with the network size. It uses LP to find an approximate distribution matrix that optimally fits the measurement data. The methods are applied to simulated example networks to illustrate the accuracy and speed.     

Traffic grooming in an optical WDM mesh network

In wavelength-division multiplexing (WDM) optical networks, the bandwidth request of a traffic stream can be much lower than the capacity of a lightpath. Efficiently grooming low-speed connections onto high-capacity lightpaths will improve the network throughput and reduce the network cost. In WDM/SONET ring networks, it has been shown in the optical network literature that by carefully grooming the low-speed connection and using wavelength-division multiplexer (OADM) to perform the optical bypass at intermediate nodes, electronic ADMs can be saved and network cost will be reduced. In this study, we investigate the traffic-grooming problem in a WDM-based optical mesh topology network. Our objective is to improve the network throughput. We study the node architecture for a WDM mesh network with traffic-grooming capability. A mathematical formulation of the traffic-grooming problem is presented in this study and several fast heuristics are also proposed and evaluated     

基于神经网络的网络流量预测算法研究

网络流量预测有助于网络服务质量的提升和网络资源的合理分配,对优化网络管理与运营、保障用户体验质量至关重要。因特网业务的急剧增加和基础网络的快速发展导致网络流量变得更加复杂多样,传统网络流量预测模型难以保证较高的预测精度,而神经网络作为人工智能的重要分支,在预测复杂网络流量时具有显著优势。简述反向传播神经网络、径向基神经网络和长短期记忆神经网络的模型原理,通过分析这些神经网络预测不同时间尺度的网络流量结果,可总结其预测性能与优缺点,为基于神经网络的故障预测和故障定位的学术研究和实际应用提供技术支撑。     

Traffic models for slotted optical packet switched networks

Optical packet switching (OPS) has emerged as a promising architecture for the future all-optical network scenario. In order to have a successful deployment of OPS networks, several networking issues must be resolved, e.g., how to resolve contentions and how to provide Quality-of-Service (QoS) differentiation. Such networking studies often rely on teletraffic analysis in order to quantify the performance of the OPS network. In this paper, we introduce new and review existing traffic models for slotted buffer-less OPS networks. In particular, we present a novel asymmetric traffic model, suitable for studying the effects of non-uniform traffic. Optical packet switches with and without wavelength conversion are studied. Numerical evaluations and a comparison study of the presented traffic models are reported. The main contributions of this paper are to advance the field of establishing a theoretical framework for slotted OPS networks and to act as a tutorial for teletraffic engineering in such networks. http://www.item.ntnu.no/~haraldov.     

Adjacent-Cell Interference in Direct-Sequence CDMA Forward Traffic Channels

Each transmission from a base station in a mobile cellular direct-sequence CDMA network is a source of interference for the receivers in the mobile handsets that are operating in adjacent cells. This interference can limit the capacity of the forward traffic channels. The effect of adjacent-cell interference on the performance of the handset receivers is evaluated for a mobile cellular CDMA network that employs quadriphase-shift-key spreading, convolutional coding, and soft-decision decoding. It is demonstrated that acceptable performance may not be possible for a fully loaded cellular network. Of particular interest in this paper are cellular networks in which the base stations are mobile and must be interconnected by wireless communication links. Such networks are important for military applications and certain civilian emergency communications services.     

Traffic engineering in next-generation optical Networks

In this article traffic-engineering issues regarding network survivability, traffic grooming, impairment-aware routing, virtual-topology engineering, and coordination among multiple layers of network architecture will be reviewed for next-generation optical networks based on Wavelength-Division Multiplexing (WDM). Due to the recent progress and development of WDM technology, increasing traffic demands can be readily accommodated in the next-generation optical networks. In spite of the huge amount of capacity (e.g., OC-192) provided by a WDM channel, enhanced network services and network performance improvement can only be achieved with efficient traffic-engineering mechanisms. The fault-tolerant function is essential in order to provide seamless services to users by protecting their traffic against failures in the optical network because many connections can be carried on a fiber. Because the capacity of a WDM channel is very large, its bandwidth may not be efficiently utilized by a single connection. Hence, low-rate user connections need to be efficiently aggregated through the traffic-grooming scheme. An intelligent routing algorithm is especially necessary in the optical network where signal impairments due to device imperfections might degrade the signal quality. In addition, the virtual network connectivity (topology) should be flexibly maintained such that dynamic changes to the traffic demands can be easily absorbed, which can be implemented by the virtualtopology engineering method in a WDM network. As the dominant usage of Internet Protocol (IP) of the Internet is expected to reside directly above the WDM layer in the future network, the coordinated trafficengineering scheme should be deliberately designed for the multi-layer network by judiciously choosing where to put many overlapping functions in the different network layers.     

Traffic engineering in a multipoint-to-point network

The need to guarantee quality-of-service (QoS) to multimedia applications leads to a tight integration between the routing and forwarding functions in the Internet. multiprotocol label switching tries to provide a global solution for this integration. In this context, multipoint-to-point (m2p) networks appear as a key architecture since they provide a cheaper way to connect edge nodes than point-to-point connections. M2p networks have been mainly studied for their load balancing ability. In this paper, we go a step further: we propose and evaluate a traffic management scheme that provides deterministic QoS guarantees for multimedia sources in an m2p network. We first derive an accurate upper bound on the end-to-end delay in an m2p architecture based on the concept of additivity. Broadly speaking, an m2p network is additive if the maximum end-to-end delay is equal to the sum of local maximum delays. We then introduce two admission control algorithms for additive networks: a centralized algorithm and a distributed algorithm and discuss their complexity and their scalability     

Traffic analysis of large TST networks

The traffic performance of time-space-time (TST) switching networks built from large time-switching stages used in digital switching systems is discussed. These switching networks exhibit steep load-service characteristics and present new numerical problems for traffic performance evaluation. The precise numerical calculation of switch blocking and the amount of search effort needed to find a network path are addressed. Computational efficiency and robustness are emphasized. The approach is based on a familiar model that uses state-dependent transitions in formulating the balance equations. A comparative study with traditional methods illustrates the numerical gains to be made for switching networks of arbitrary size     

组合神经网络的网络流量预测研究

提出一种组合神经网络的网络流量预测模型.首先采用SMOF网络对网络流量数据进行聚类,然后采用Elman网络对聚类后的流量数据进行训练并预测,同时采用遗传算法对Elman网络的网络结构进行优化,提高网络流量预测精度.仿真结果表明,组合神经网络加快了网络流量预测速度,提高了网络流量预测精度,克服了单一预测模型不足,为网络流量预测提供了新的思路,具有很好的应用前景.     

The Efficiency of Engineering Traffic Across Network Boundaries

With the arrival of wideband packet and circuit-oriented data services, it becomes a challenge to provide efficiently the desired quality of service for speech, packet data, and real-time data on a network. As these diverse networks will coexist, architectural studies on integrated heterogeneous networks suggest that a common radio resource manager be used to coordinate radio resource allocation between diverse network types. Initial studies show that supernets, which engineer traffic across wireless networks, are more efficient than operating separate cellular/wireless networks. Increased sharing occurs in supernets because a larger number of services compete for a larger pool of resources. If sharing can be shown to be efficient in general, then supernets should likewise be more efficient. This study decomposes the two-dimensional Markov chain to prove when sharing is beneficial and when it is not.     

Traffic processing algorithms for the SIGnet metropolitan areanetwork

Traffic processing algorithms are introduced for SIGnet (slotted interconnected-grid network), which is intended for local and metropolitan area backbone communication networks using multichannel optical transmission media. The design is motivated by the development of inexpensive multichannel capabilities based on dense wavelength division multiplexing (WDM) and future coherent optical systems. In SIGnet, the virtual topology is piecewise regular and permits bandwidth allocation and network evolution which is much more easily accomplished than in previous designs. SIGnet employs deflection routing to accommodate nonisochronous traffic. However, a multilink grid topology provides a closer match to the actual physical topology in many networks. This work includes an introduction to the network design and presents results obtained concerning the traffic processing algorithms which have been investigated