基于粒子群优化算法的数据中心网络流量调度策略

为解决当前数据中心网络存在链路负载不均衡及带宽资源浪费问题,提出了一种基于粒子群优化算法的流量调度策略.该策略结合软件定义网络控制器可获取全局网络拓扑信息的特性,依据当前链路带宽资源状况及网络流量的带宽需求建立目标函数.首先,根据流的源地址和目的地址找出最短路径集,通过定义粒子聚合度判断算法是否有陷入局部最优的趋势;然后,结合约束条件与目标函数,利用优化的粒子群算法从最短路径集中找出网络流量的最佳调度路径.实验结果表明,相比于其他算法,该算法有效地提高了网络平均吞吐量,获取了较低的丢包率,从而减轻了带宽资源的浪费,更好地实现了网络的负载均衡.     

基于离散粒子群算法的数据中心网络流量调度研究

数据中心网络利用多个并行路径为集群计算等网络服务提供高对分带宽.然而,现有的流量调度算法可能会引起链路负载不均衡,核心交换机冲突加剧,造成网络总体性能降低.本文将流调度问题转化成0-K背包问题求解,提出基于离散粒子群的流调度算法DPSOFS（Discrete Particle Swarm Optimization Flow Scheduling）.该算法根据Fat-Tree结构特点定义了粒子速度、位置和运算规则,以两次迭代冲突流个数差值作为目标函数,并限定路径搜索范围,减少随机搜索的盲目性.仿真实验验证了该算法对减少流冲突快速有效,能提高网络对分带宽.     

软件定义数据中心网络混合路由机制

针对数据中心网络流量大小分布不均匀、传输性能需求不相同的特征,提出了面向传统树型数据中心网络结构的软件定义混合路由机制SHR（software-defined hybrid routing）。SHR通过统计计算将数据流分为大流和小流,为满足其不同的传输性能需求,对大流采用自适应路由算法,对小流采用流量无视路由算法。SHR在OpenFlow机制的基础上,将部分控制权从控制器下放至交换机,以减轻网络的额外负载。在Fat-Tree网络拓扑结构上建立流量模型进行性能分析与仿真实验,结果表明,与传统的等价多路径转发ECMP算法相比,SHR能够提高网络吞吐量,降低数据流丢弃率和分组端到端时延,同时减轻网络的额外负载。     

一种基于OpenFlow的多路径传输机制

针对高连通度数据中心网络存在吞吐量低、网络负载均衡差等流量工程问题,该文提出一种基于OpenFlow的多路径传输(OpenFlow based Multipath Transmission, OFMT)机制。借助OpenFlow集中控制的优势,OFMT为每条流精确计算传输路径,将网络中的流量优化分配到端到端的多条路径上,并通过周期性轮询和动态调度实现良好的负载均衡,进而提高数据中心网络吞吐量。实验结果表明,在相同的网络流量负载下,OFMT与较典型数据中心传输协议相比,有效提高了网络的吞吐量,并降低了流完成时间。     

基于软件定义网络的服务器集群负载均衡技术研究

在当前的网络体系结构下,采用硬件系统实现服务器集群负载均衡存在着获取负载节点状态困难、流量导向方式复杂等制约因素,不利于提升服务器集群的伸缩性和服务性能。针对此问题,该文提出一种基于软件定义网络(SDN)的负载均衡机制(SDNLB)。该机制借助SDN具有的集中式控制和流量灵活调度优势,利用SNMP协议和OpenFlow协议对服务器的运行状态和全局网络负载信息进行实时监测,并通过权值计算的方式选择出权重最高的服务器作为流处理的目标服务器,在此基础上,采用最优转发路径算法进行流量调度,从而达到提高服务器集群的利用率与处理性能的目的。搭建了实验平台对SDNLB的性能进行仿真测试,实验结果表明:在相同的网络负载条件下,SDNLB与其他负载均衡算法相比,能够有效地降低服务器集群的负载,并能够显著提高网络吞吐量和带宽利用率,缩短流的完成时间和平均时延。     

基于流分类的数据中心网络负载均衡机制

为充分利用数据中心网络的多路径带宽,现有研究多采用基于链路感知的负载均衡算法,在动态获取全局链路拥塞信息后选取最优路径对流量进行转发.然而这些研究未考虑数据中心网络流量大小分布不均匀的特性,难以在选路成本和转发效率上取得平衡.为此,设计一种基于流分类的数据中心网络负载均衡机制(ULFC,Utilization-aware Load balancing based on Flow Classification),在实现拥塞感知的基础上进行流量特征分析,采用不同的策略为大、小流分配路径,实现网络流量特征与选路方法优势的最佳匹配.实验结果表明,相比于现有方案,ULFC的平均流处理效率提高了1.3倍至1.6倍,路由成本降低了50％以上.     

面向数据中心网络的分布式负载均衡网关架构

为满足数据中心网络在高并发量、低尾延时等性能上的需求,提出一种面向数据中心网络的分布式负载均衡网关架构。该新型网关架构主要包括资源池化汇聚算法、优先调度算法和动态负载均衡算法等3个核心算法模型。基于该架构,借助现场可编程门阵列(FPGA)实现智能网关的整体设计。通过第三方测试,基于分布式负载均衡网关架构的智能网关可针对数据包的关键信息实现灵活、可扩展的负载均衡,线速可达9.4 Gbps(不丢包),线速为10 Gbps的丢包率约5%,端口时延为2 μs。与通用的负载均衡方案(软件负载均衡与硬件负载均衡)相比,分布式负载均衡网关架构采用基于数据包优先调度的负载均衡策略和硬件存储资源智能“池化”的流量管理,保障了数据中心网络系统中百万级数据流的高效分发,提升高并发量、低时延应用的性能。在面向百万条并发情况下,网络链路响应尾延时小于60 ms。     

一种智慧协同网络多参数的多路径路由算法

多路径路由技术采用多条路径同时传输,作为优化资源配置和负载均衡的重要技术,在路由可靠性、QoS路由、传输效率等多方面比单路径传输具有优势.现有互联网网络资源配置和路由机制相对静态和僵化,导致多路径技术的发展存在发展的局限性.现有多路径技术考虑在路由层面不利于多路径路由选择和计算,难以保证传输性能,降低网络传输效率.智慧协同网络能够动态感知网络需求,灵活适配网络资源,更好的支持路由可扩展性.本文在智慧协同网络架构下提出了一种智慧协同网络多参数的多路径路由算法.该算法制定了智慧协同网络多参数的多路径路由协议,对网络性能参数CPU占用率、往返时延(RTT)、带宽进行加权计算得到路径权重值,根据权重值进行流量分配.采用图论理论对网络流量分配及模型进行了分析.并在Mini-Net平台上进行了开发和实验,结果表明,该算法能够优化网络配置,减小往返时延,提高网络吞吐量,从而提高网络性能,实现负载均衡.     

基于QoS付费业务的LTE下行跨层分组调度算法

准4G网络（LTE）即将商用会给人们带来更多的方便,以至于大量用户在日常生活中使用更多的QoS业务,这样系统会出现了拥塞和调度不够合理的情况,影响了高优先级业务的丢包率、时延和公平性。通过对LTE下行跨层分组调度各种算法的研究分析,从时延、丢包率、吞吐量和公平性等因素入手,在原有的比例公平性调度算法（PF）上进行改进,加入了补偿因子和付费权重值,使得改进型跨层调度算法,在吞吐量有一定提高的情况下,有效地降低了高优先级业务的丢包率和时延,并确保了高优先级业务的公平性。     

基于选择性迭代的KSP低轨卫星负载均衡路由方法

低轨卫星(Low Earth Orbit,LEO)系统具有传输时延低、路径损耗小和运行周期短的特点,但大规模卫星部署和地面业务非均匀性的特点,导致卫星网络局部拥塞和局部空闲,为优化卫星网络全局负载均衡和回避拥塞问题,文章提出一种基于选择性迭代的K最短路径算法(Selective Iteration of K Shortest Paths,SI-KSP)。与传统K最短路径方法相比,所提的SI-KSP负载均衡路由方法网络吞吐量增加且丢包率大幅下降;与CA-KSP方法相比,所提方法网络吞吐量相近但丢包率和平均时延均降低。该文所提方法能实现根据全局负载情况选择路径分布,有效避免链路拥塞,达到更优化的负载均衡效果。     

LEO multi-service routing algorithm based on multi-objective decision making

In low earth orbit(LEO) satellite networks,in view of the unbalanced link resource,it's difficult to meet differentiated quality of service(QoS) requirements and easily lead to reduce the efficiency of the whole network.A routing algorithm based on multi-objective decision making was proposed which defined LEO satellite network transmission service as the delay sensitive,sensitive bandwidth and reliability sensitive three categories.It used the eigenvector method to calculate service weights,and used the consistency ratio to determine whether it can be accepted.Based on the multi-objective decision making theory,it combined with the actual state of satellite network nodes and links and the specific requirements of the business,calculating the path that meets the QoS requirements of the service,so as to realize the LEO satellite network multi objective dynamic routing optimization.Established simulation platform based on the iridium network system simulated network delay,the uncertain characteristics like the residual bandwidth and packet error rate,route planning for the randomly generated three classes of business.The simulation results show that,the algorithm not only satisfies the QoS constrain while balancing the traffic load of the satellite link effectively,but also improves the performance on the throughput.     

基于模糊流感知的动态优先公平调度算法

为适应网络的动态性,提高调度公平性和资源效率,流感知优先公平调度机制需要动态的多业务区分转发。与链路负载状态相关的模糊流感知能够实现路径上的一致性业务区分,而基于模糊流感知的动态优先公平调度算法通过调整优先队列负载门限在流式流和弹性流之间实现转发优先权的动态交替,在链路轻载时实现不同流间的相对公平调度,在链路重载时则强调实时业务的绝对优先权以保证其时延要求。算法公平性分析和仿真计算显示提出算法的动态区分转发通过适度增加优先业务队长能够大幅度提高弹性流的接纳率,具有较高的链路平均吞吐量和资源效率。     

Greedy–knapsack algorithm for optimal downlink resource allocation in LTE networks

The long term evolution as a mobile broadband technology supports a wide domain of communication services with different requirements. Therefore, scheduling of all flows from various applications in overload states in which the requested amount of bandwidth exceeds the limited available spectrum resources is a challenging issue. Accordingly, in this paper, a greedy algorithm is presented to evaluate user candidates which are waiting for scheduling and select an optimal set of the users to maximize system performance, without exceeding available bandwidth capacity. The greedy–knapsack algorithm is defined as an optimal solution to the resource allocation problem, formulated based on the fractional knapsack problem. A compromise between throughput and QoS provisioning is obtained by proposing a class-based ranking function, which is a combination of throughput and QoS related parameters defined for each application. The simulation results show that the proposed method provides high performance in terms of throughput, loss and delay for different classes of QoS over the existing ones, especially under overload traffic.     

On Throughput Guarantee of Aloha-Like Multi-Hop Wireless Networks

Providing Quality of Service (QoS) is one of significant issues for multimedia traffic. One approach to achieve the requested QoS is to characterize the traffic flows and guarantee their committed throughput. In a typical multi-hop wireless ad hoc network, determining the feasibility for a given set of flow characteristics is challenging due to the multi-user interference problem. To that end, this paper presents the following contributions. First, we describe a simple Aloha-like Medium Access Control (MAC) protocol that enables each flow to maintain its requested bandwidth, and thus is suitable for multimedia traffic. Second, we propose a bandwidth feasibility algorithm based on the Variable Elimination (VE) technique. The bandwidth feasibility algorithm determines whether or not a given network can support a set of flows of certain bit rates. Simulations indicate that our solution can precisely control the bit rates over all hosts while providing the throughput guarantees.     

FEBA: A Bandwidth Allocation Algorithm for Service Differentiation in IEEE 802.16 Mesh Networks

In wireless mesh networks, the end-to-end throughput of traffic flows depends on the path length, i.e., the higher the number of hops, the lower becomes the throughput. In this paper, a fair end-to-end bandwidth allocation (FEBA) algorithm is introduced to solve this problem. FEBA is implemented at the medium access control (MAC) layer of single-radio, multiple channels IEEE 802.16 mesh nodes, operated in a distributed coordinated scheduling mode. FEBA negotiates bandwidth among neighbors to assign a fair share proportional to a specified weight to each end-to-end traffic flow. This way traffic flows are served in a differentiated manner, with higher priority traffic flows being allocated more bandwidth on the average than the lower priority traffic flows. In fact, a node requests/grants bandwidth from/to its neighbors in a round-robin fashion where the amount of service depends on both the load on its different links and the priority of currently active traffic flows. If multiple channels are available, they are all shared evenly in order to increase the network capacity due to frequency reuse. The performance of FEBA is evaluated by extensive simulations. It is shown that wireless resources are shared fairly among best-effort traffic flows, while multimedia streams are provided with a differentiated service that enables quality of service.     

Soft QoS provisioning using the token bank fair queuing scheduling algorithm

Future-generation wireless packet networks will support multimedia applications with diverse QoS requirements. Much of the research on scheduling algorithms has been focused on hard QoS provisioning of integrated services. Although these algorithms give hard delay bounds, their stringent requirements sacrifice the potential statistical multiplexing performance and flexibility of the packet-switched network. Furthermore, the complexities of the algorithms often make them impractical for wireless networks. There is a need to develop a packet scheduling scheme for wireless packet-switched networks that provides soft QoS guarantees for heterogeneous traffic, and is also simple to implement and manage. This article proposes token bank fair queuing (TBFQ), a soft scheduling algorithm that possesses these qualities. This algorithm is work-conserving and has a complexity of O(1). We focus on packet scheduling on a reservation-based TDMA/TDD wireless channel to service integrated real-time traffic. The TBFQ scheduling mechanism integrates the policing and servicing functions, and keeps track of the usage of each connection. We address the impact of TBFQ on mean packet delay, violation probability, and bandwidth utilization. We also demonstrate that due to its soft provisioning capabilities, the TBFQ performs rather well even when traffic conditions deviate from the established contracts.     

Resource allocation algorithm for LTE networks using fuzzy based adaptive priority and effective bandwidth estimation

In this paper, we propose a scheme to allocate resource blocks for the Long Term Evolution (LTE) downlink based on the estimation of the effective bandwidths of traffic flows, where users’ priorities are adaptively computed using fuzzy logic. The effective bandwidth of each user traffic flow that is estimated through the parameters of the adaptive β-Multifractal Wavelet Mode modeling, is used to attain their quality of service (QoS) parameters. The proposed allocation scheme aims to guarantee the QoS parameters of users respecting the constraints of modulation and code schemes (modulation and coding scheme) of the LTE downlink transmission. The proposed algorithm considers the average channel quality and the adaptive estimation of effective bandwidth to decide about the scheduling of available radio resources. The efficiency of the proposed scheme is verified through simulations and compared to other algorithms in the literature in terms of parameters such as: system throughput, required data rate not provided, fairness index, data loss rate and network delay.     

一种基于带宽接入控制的AODV改进路由协议

无线自组网中的路由协议AODV没有提供流控和拥塞避免机制,当网络负载较重时,多媒体业务或产生较大的延时,或分组被大量丢弃,使网络性能下降.在AODV协议的基础上,提出一种基于带宽接入控制的改进协议BAC-AODV,对节点和路径的可用带宽进行估算,修改路由建立机制,使路径满足业务流对带宽的需求,保证网络的QoS质量.分析和仿真结果表明,改进后的协议相比原有AODV,能更有效地控制业务流量,提高吞吐量,降低延时.     

A Packet Scheduling Approach to QoS Support in Multihop Wireless Networks

Providing packet-level quality of service (QoS) is critical to support both rate-sensitive and delay-sensitive applications in bandwidth-constrained, shared-channel, multihop wireless networks. Packet scheduling has been a very popular paradigm to ensure minimum throughput and bounded delay access for packet flows. This work describes a packet scheduling approach to QoS provisioning in multihop wireless networks. Besides minimum throughput and delay bounds for each flow, our scheduling disciplines seek to achieve fair and maximum allocation of the shared wireless channel bandwidth. However, these two criteria can potentially be in conflict in a generic-topology multihop wireless network where a single logical channel is shared among multiple contending flows and spatial reuse of the channel bandwidth is possible. In this paper, we propose a new scheduling model that addresses this conflict. The main results of this paper are the following: (a) a two-tier service model that provides a minimum fair allocation of the channel bandwidth for each packet flow and additionally maximizes spatial reuse of bandwidth, (b) an ideal centralized packet scheduling algorithm that realizes the above service model, and (c) a practical distributed backoff-based channel contention mechanism that approximates the ideal service within the framework of the CSMA/CA protocol.