基于大流调度的软件定义数据中心网络负载均衡算法

传统负载均衡算法对数据中心网络中的大流进行调度时,会造成部分链路负载过重、网络整体负载不均衡等问题。将负载均衡问题转化为多商品流问题进行求解,结合软件定义网络集中控制的思想和数据中心网络的流量特征,提出一种基于大流调度的软件定义数据中心网络负载均衡算法。根据阈值将数据流划分为大流和小流,结合路径上大流分布度和可用负载度对大流进行重路由,以减小大流对网络负载均衡的影响。仿真实验表明,在流量大小分布不均衡的数据中心网络中,该算法与传统的等价多路径算法和基于全局最先匹配的动态流量调度算法相比,在平均对分带宽上获得了更大的提升,能够更好地实现数据中心网络的负载均衡。     

Bandwidth-aware energy efficient flow scheduling with SDN in data center networks

Nowadays the energy consumption has become one of the most urgent issues for Data center networks. For general network devices, the power is constant and independent from the actual transfer rate. Therefore the network devices are energy efficient when they are in full workload. The flow scheduling methods based on the exclusive routing can reduce the network energy consumption, as the exclusive routing paths can fully utilize all their links. However, these methods will no longer guarantee the energy efficiency of switches, as they handle flows in priority order by greedily choosing the path of available links instantaneously. In a previous work we proposed an extreme case of flow scheduling based on both link and switch utilization. Herein we consider general scenarios in data center networks and propose a novel energy efficient flow scheduling and routing algorithm in SDN. This method minimizes the overall energy for data center traffic in time dimension, and increases the utilization of switches and meet the flow requirements such as deadline. We did a series of simulation studies in the INET framework of OMNet++. The experiment results show that our algorithm can reduce the overall energy with respect to the traffic volume and reduce the flow completion time on average.     

A Computer Network with Fast Distributed Reconfiguration and Data Processing During Transfer

This paper considers a computer network with an extended functionality. The network is fully connected but only the currently necessary links are formed. The links are fast reconfigured, which allows for a repeated change of their structure subject to a solved problem. As shown below, such an approach significantly simplifies and accelerates the execution of massive operations with a simultaneous participation of many system devices. Using network resources only, it is possible to perform some types of distributed computing over data directly in the course of their transfer in the network. The examples of network usage and technical implementation of its basic components are given.     

数据中心网络中相关感知流量整合算法

随着大数据、云计算不断融入人们的日常生活,作为支撑其发展的基础设施--数据中心网络的能耗也在急剧增长。为了解决这个问题,学术界提出了能量感知路由（Energy-Aware Routing,EAR）。EAR的主要思想是通过将流量需求聚集在网络链路的子集,并睡眠未使用的网络设备以节省能量。但是在流量低谷时期频繁地切换网络设备模式可能会导致网络振荡甚至网络性能下降。因此提出了一种相关感知流量整合（Correlation-Aware Traffic Consolidation,CATC）算法。提出了基于软件定义网络（Software Defined Network,SDN）的CATC模型,即在流量整合时考虑了流之间的相关性,并结合链路速率来实现更高的节能。在流量约束和链路容量约束下将CATC模型转换为一个最优流量分配问题,并提出CATC算法来求解。仿真结果显示,与现有的节能算法相比,CATC算法在仅仅增加极少网络延迟的同时可以为数据中心网络节省大约45%的能量。     

基于XML的电信网络管理数据采集与处理

电信网络是非常复杂的大型异质网络。电信业务的发展要求对网络和服务进行综合的管理。因此,电信网络管理平台需要从大量不同的数据源(设备、软件等实体)获得数据,并进行处理、分析。语法和语义异构的数据采集是网络管理平台的基础和难题。论文提出了基于XML技术的统一接口方案,很好地解决了这个问题,使得网管系统平台可以处理任意的数据源,提高了平台的适应性和可扩展性。     

基于物理拓扑的P2P网络模型

对等网络的拓扑失配会引起不必要的网络流量,不仅加重了物理网络的负担,而且加大了节点间资源搜索的平均时延。提出一种基于物理拓扑信息的P2P网络模型CSL。CSL模型是以自治系统之间的物理连接构成Center层,以节点的网络地址构成Super层,由普通节点形成Leaf层的三层模型,并采用相应的算法维护网络的运行。通过实验表明,CSL模型在资源搜索时可以明显降低系统的平均时延。针对拓扑失配问题提出的CSL模型可以很好的工作,特别是节点规模较大时在减轻网络负担和降低资源搜索的平均时延方面表现更好。     

MPLS流量工程仿真

在通信网络中,负载不均衡或部分网络失效常常会引起网络拥塞问题,导致业务的服务质量下降.相对于传统的动态路由协议解决此类问题所具有的局限性,MPLS流量工程是解决问题的一种有效途径.在计算机网络仿真平台上,设计了动态路由协议和MPLS流量工程仿真实例,通过运行仿真,获取了它们的网络性能及业务服务质量数据.通过对仿真结果进行比较和分析,可以看出,MPLS流量工程通过更为灵活的方式在多条链路上实现负载分担,可以改进网络资源利用率,当链路或节点失效时,能够提供快速的恢复机制.     

基于多语义元路径的异质网节点分类方法*

异质网是包含多种类型的对象和复杂链接关系的大规模异构信息网络.针对科研异质网,文中提出基于元路径信息的节点分类方法.利用异质网中具有不同语义信息的元路径,建立节点之间的关联特征矩阵,并通过加入跳转路径扩展异质网,解决信息稀疏问题.在DBLP数据集上的实验表明,文中方法可以有效利用较少的分类标签,解决复杂网络中的节点分类,在标注数据比例规模较小时,加入跳转路径,优化决策树分类性能.     

基于节点连通性排序的虚拟网络映射算法

对当今云环境下的数据中心来说,以虚拟资源租赁的运营方式具有极大的灵活性,尤其是以虚拟网络为粒度的资源租赁能够为用户提供更好的个性化需求支持。虚拟网络映射问题是指依据用户资源需求,合理分配底层主机和网络资源。现有的虚拟网络映射算法大多是针对随机拓扑设计的通用算法,未针对数据中心拓扑结构进行优化,映射效率有很大提升空间。针对数据中心的结构特点,提出了一种基于节点连通性排序的虚拟网络映射算法BS-VNE算法。首先,设计了一种最大生成算法来对虚拟节点重要程度进行求解和排序。该算法不仅基于虚拟节点的带宽和连通度,还基于虚拟节点在整个虚拟网络中的连通性来进行节点连通性的计算,以获得更加合理的排序结果。然后,根据虚拟节点连通性排序结果利用离散粒子群优化算法求解虚拟网络的映射解。在求解过程中,引入了针对数据中心结构的物理网络拓扑启发式规则,并将其组合到粒子搜索过程中,以提高映射算法的收敛速度。仿真实验结果表明,与现有算法相比,本文提出的算法可以提高物理网络的收益/成本比和资源利用率。     

Increasing multicast transmission rate with localized multipath in software-defined networks

Network layer multicast is a highly efficient oneto- many transmission mode. Data rates supported by different group members may differ if these members are located in different network environments. Currently there are roughly two types of methods solving the problem, one is limiting the data rate so that every group member can sustain transmissions, and the other is building multiple trees to increase the provision of network bandwidth. The former is inefficient in bandwidth usage, and the latter adds too many states in the network, which is a serious problem in Software-Defined Networks. In this paper, we propose to build localized extra path(s) for each bottleneck link in the tree. By providing extra bandwidth to reinforce the bottleneck links, the overall data rate is increased. As extra paths are only built in small areas around the bottleneck links, the number of states added in the network is restrained to be as small as possible. Experiments on Mininet verify the effectiveness of our solution.     

基于混合粒子群算法的虚拟数据中心能耗优化

针对当前数据中心节能整合研究中仅考虑服务器能耗的现状,提出一种同时考虑服务器和网络设备能耗的方法。该方法通过感知数据中心的网络拓扑,使运行的服务器和网络设备最少,以此最小化能耗。对问题进行新的形式化建模,并设计一种混合的粒子群优化算法HPSO-NA来实现虚拟机整合。实验结果表明,该方法能有效降低整体能耗。     

An intelligent optimization-based traffic information acquirement approach to software-defined networking

Internet of things (IoT) is a global information infrastructure that supports access to thousands of monitoring devices and user terminals. A large amount of monitoring data generated by IoT is integrated to cloud computing through the network to improve the quality of life of citizens. Fine-grained and accurate traffic information is important for IoT network management. Software-defined networking (SDN) is a centralized control plane as a logical control center, making network management more flexible and efficient. Then, we collect fine-grained traffic information in SDN-based IoT networks to improve network management. To acquire the traffic information with low overhead and high accuracy, first, we collect the statistics of coarse-grained traffic of flows and fine-grained traffic of links, and then we utilize the intelligent optimization methods to estimate the network traffic. To improve the granularity and accuracy of the acquired traffic information, we construct an optimization function with constraints to decrease the estimation errors. As the optimization function of traffic information is a non-deterministic polynomial-hard problem, we present a heuristic algorithm to obtain the optimal solution of the fine-grained measurement. Finally, we conduct some simulations to verify the proposed measurement scheme. Simulation results show that our approach can improve the granularity and accuracy of traffic information with intelligent optimization methods.     

Sign prediction in sparse social networks using clustering and collaborative filtering

Today, social networks have created a wide variety of relationships between users. Friendships on Facebook and trust in the Epinions network are examples of these relationships. Most social media research has often focused on positive interpersonal relationships, such as friendships. However, in many real-world applications, there are also networks of negative relationships whose communication between users is either distrustful or hostile in nature. Such networks are called signed networks. In this work, sign prediction is made based on existing links between nodes. However, in real signed networks, links between nodes are usually sparse and sometimes absent. Therefore, existing methods are not appropriate to address the challenges of accurate sign prediction. To address the sparsity problem, this work aims to propose a method to predict the sign of positive and negative links based on clustering and collaborative filtering methods. Network clustering is done in such a way that the number of negative links between the clusters and the number of positive links within the clusters are as large as possible. As a result, the clusters are as close as possible to social balance. The main contribution of this work is using clustering and collaborative filtering methods, as well as proposing a new similarity criterion, to overcome the data sparseness problem and predict the unknown sign of links. Evaluations on the Epinions network have shown that the prediction accuracy of the proposed method has improved by 8% compared to previous studies.

     

基于简单网络断层扫描的失效链路定位研究

失效链路是无线传感器网络中一种典型的网络故障现象,严重影响了无线传感器网络的运行与服务质量,必须加以发现并修复。主要研究了基于简单网络断层扫描方法定位失效链路的技术。引入二元分离模型描述链路状态,在已知链路状态先验分布条件下,失效链路定位问题描述为最大后验估计问题。通过将失效链路定位问题映射为加权最小集合覆盖问题,提出了一种基于启发策略的失效链路定位算法。仿真实验结果表明,该算法具有可行性和有效性。     

SDN数据中心网络基于流分类的负载均衡方案

随着数据中心内的数据流量不断增加,导致网络中部分链路负载过重。传统的ECMP机制由于没有考虑链路状态以及流量特征,因此不再适用数据中心网络。同时ECMP可能会将多条大流映射到同一条路径上,造成大流映射冲突,导致链路瓶颈问题。基于SDN（Software Defined Network）架构提出一种面向Fat-Tree拓扑的动态流量负载均衡机制（Load Balancing based on Flow Classification,LBFC）,同时考虑了链路状态信息与流量特征进行负载均衡。LBFC机制动态调整流分类阈值来判定大流和小流,采用不同的方式为大流和小流选择转发路径,以满足大流和小流不同的传输性能需求。仿真结果表明LBFC机制能够根据网络链路状态以及流量特征动态地判定大流和小流并实现负载均衡,与ECMP、GFF和DLB算法相比,LBFC机制提高了网络吞吐量以及链路利用率,降低了传输时延。     

无线传感器节点针对捕获节点攻击可靠性研究

无线传感器网络中的节点通常运算和存储能力有限,由于网络本身的特点,数据容易遭到攻击,因此,保密成为一个重要的因素;为解决这一问题,许多文献提出公钥密码系统,但这种方法存在的一个普遍问题是源节点到目的节点密钥的建立;当源节点到目的节点建立新密钥时,它们必须频繁的交换信息实现可靠链接;由于无线连接的不可靠性和电池耗尽等因素无线传感器网络路由机制也要不断改变;传感器节点增加时安全问题尤为严重;提出了一种新的基于机密共享方案数据分配方法应对网络攻击,并通过实验证明这种方法的有效;最后,考虑到安全性,和已有的无线传感器网络安全体系结构TinySec方法进行对比。     

Network infrastructure design with a multilevel algorithm

This paper presents a novel algorithm to deal with the network design problem, which optimizes the network levels considering their interdependency. The idea is to design a low cost and optimized network providing the number and the geographic location of devices as well as the links among them for each network level, while taking into account the existing dependency among them. In addition, a new database composed of real and georeferenced data is created and make available for the research community. This database contains three datasets that represent distinct projects related to geographic regions of the city of Curitiba (Brazil). The experimental results show that the proposed algorithm provides a significant cost reduction in the network design. The savings of this proposal go from 1% to 40% (depending on the network size, number of levels and demand nodes), making it attractive for companies that spend a considerable amount of resources in network projects and deployment.     

K-means聚类算法优化方法的研究

针对K-means算法全局搜索能力的不足,提出基于改进PSO的优化K-means聚类算法(IPSO-KM),该算法克服了K-means聚类算法对初始聚类中心选择敏感问题,能够获得全局最优的聚类划分.同时,提出一种基于信息增益比例的属性加权的实体之间距离计算方法,使用属性加权距离计算方法进行聚类划分时,无论是球形数据还是椭球形数据都能够获得较好的聚类划分结果.仿真实验采用KDD-cup 99的测试数据,实验结果表明本文提出的算法不但能检测到多种已知的网络入侵行为,而且能够检测到许多未知的网络入侵行为,同时保持较高的网络入侵的检测率和较低入侵的误报率.     

基于SDN的数据中心动态优先级多路径调度算法

随着云计算技术和分布式业务的发展,数据中心内部“东西向”大象流量激增,这部分大象流在调度不当的情况下容易发生碰撞,造成链路拥塞。本文提出一种基于软件定义网络（SDN）的动态优先级多路径调度算法（DPMS）。该算法根据数据中心流量的特点制定大象流和老鼠流调度模型,充分利用各网络节点间的冗余链路,提高资源利用率;并结合组表优化SDN架构中控制器和交换机的通信模式,降低了数据包处理时延。实验结果表明,相比ECMP和Hedera这2种调度策略,DPMS提高了网络吞吐量和链路利用率,减少了平均流完成时间,网络的整体性能有所提高。     

基于WEB服务的移动网管决策支持系统

目前国内的移动通讯业务不断扩张,用户量迅猛增加。移动运营商在面对巨大市场的同时,也面临着巨大的挑战。一是其网络设备的数量和种类急剧增多,网络拓扑结构更加复杂,网络负载也不断加重;二是海外运营商急于分割国内市场,竞争愈发激烈。因此,如何充分利用有限的资源提供优质的服务,成为摆在运营商面前的一个艰巨的任务。该文分析了采用数据仓库、数据挖掘、WEB服务等先进技术开发的“移动网管决策支持系统”,该系统可帮助决策层从各个角度、各个层次分析网管数据,以及隐藏在数据之间的深层次知识,有利于管理者制定出正确的决策。目前该系统在四川移动网管中心运行良好。