下一代异构网络中基于进化博弈论的业务负载均衡

阐述了进化博弈论(EGT)的基本理论和模型，并将其应用于异构(heterogeneous)通信网络的业务负载均衡问题中，给出了一种基于进化博弈理论的异构网络业务分配模型。应用复制动力学的动态学习能力，进化博弈模型中的用户方通过动态调整分配策略，可以获得进化稳定策略(ESS)下均衡的负载分配和改善的期望效用(utility，或适应度fitness)。计算机仿真结果从负载分配的稳定、均衡和改善的平均期望效用三个方面验证了进化博弈模型在异构网络负载均衡问题中的有效性。     

基于博弈的LTE负载均衡算法研究

针对LTE网络中小区之间负载不均衡的问题,提出了一种结合经济学中的博弈理论的解决方案.通过将博弈理论中的拍卖模型引入到LTE系统模型中,建立竞拍双方的效用函数,求出均衡解最大化其效用函数,从而合理地调整切换参数将热点小区的负载转移到目标小区.仿真结果证明了该算法的有效性,该方案可以合理有效地解决小区间负载不均衡问题、优化网络资源和提高资源利用率.     

基于全互连立方体的Ad Hoc网络自适应路由算法

路由算法是影响移动自组织网络（Mobile Ad Hoc Network）性能的关键问题,现有的自主式组网方式及路由存在扩展性差或节点负载不均衡问题。本文提出一种基于全互连立方体（FCCN,Fully Connected Cubic Network）虚拟拓扑的层次结构及自适应路由算法,能自适应于无线链路不稳定和网络拥塞的状况,提供良好的网络扩展和负载均衡,并与现有分层结构路由算法进行了比较,最后通过仿真验证了其具有良好的吞吐率和负载均衡能力。     

基于负载均衡的非合作博弈CoMP节点选择算法

在CoMP-JP中,通过对自身负载最小化和网络负载均衡性问题进行折中考虑,建立了基于非合作博弈的CoMP节点选择数学模型,将自身效益和网络效益作为优化目标,通过优化CoMP用户分类权值矢量来改变各小区负载,达到整体效益的最优化。仿真结果表明,所提算法具有较好的收敛性,而且能够在保证负载均衡性的同时降低小区资源占用率。     

基于负载均衡的非合作博弈CoMP节点选择算法北大核心

在CoMP-JP中,通过对自身负载最小化和网络负载均衡性问题进行折中考虑,建立了基于非合作博弈的CoMP节点选择数学模型,将自身效益和网络效益作为优化目标,通过优化CoMP用户分类权值矢量来改变各小区负载,达到整体效益的最优化。仿真结果表明,所提算法具有较好的收敛性,而且能够在保证负载均衡性的同时降低小区资源占用率。     

基于干扰协调的主动负载均衡

为了解决负载均衡后分流的有实时业务需求的用户因受到严重的小区间干扰和因传统被动式方法固有的接入延迟所导致的用户体验下降的问题,本文提出了一种基于干扰协调的主动负载均衡算法。为了协调干扰,通过部分频率重用为小区边缘用户分配正交的资源;为了在满足用户数据率需求和均衡网络负载的前提下使系统总资源开销最小,通过预测用户的大尺度信道信息进行主动负载均衡。仿真结果表明,与现有的负载均衡方法相比,所提出的算法不仅提高了资源利用率,还降低了用户掉线概率。      

P2P流媒体网络中基于博弈理论的带宽请求分配策略

基于对等网(P2P)技术的视频流媒体系统以其较低的服务器开销和良好的可扩展性被广泛应用。但由于在这类系统中普遍存在节点的资源及视频播放位置的异构性,使得节点负载不均衡的问题极易发生,进而严重影响到节点的视频播放质量。该文重点研究面向节点负载均衡的节点带宽请求分配策略,将服务请求节点竞争服务提供节点带宽的行为建模为一个非协作博弈,通过寻求该博弈问题的 Nash 均衡解的方法确定优化的带宽请求分配(GBRA)策略。通过和典型的带宽请求分配策略进行实验对比,数值结果表明该文提出的GBRA 策略能有效改善P2P流媒体网络节点负载不均的问题并降低节点获取所需视频数据的平均延迟。     

OpenMP源程序级同步段负载监测方法与均衡策略

在详细阐述以同步段为最小分析单位对OpenMP程序进行负载监测与均衡的重要性之后,本文提出了源程序级同步段负载监测方法与均衡策略.其中源程序级同步段负载监测方法以隐含同步的显性化为基础,具有实现简单和易于确定有效监测区域的优点.在获得负载分布信息之后,通过同步段性能评价、筛选、负载扫描与调整实现同步段的负载均衡,这是本文与现有OpenMP性能工具不同的地方.在负载均衡的过程中,根据加权剩余并行效率筛选出需要负载调整的同步段并对其负载进行扫描,最终确定出适合这些同步段的负载调度策略.实际测试结果表明本文提出的同步段负载监测方法与均衡策略是可行的.     

基于服务分类和性能监测的负载均衡研究

负载均衡在集群系统中的作用日益重要,而现有算法的效率不高、部署复杂的原因限制了其更进一步发展。通过分析不同类型的服务请求对服务器造成不同负载,结合监测服务器的CPU和内存利用的即时性能,在克服了现有负载均衡算法的一些缺陷基础上提出了一种简单稳定的基于服务分类和性能监测算法,并通过Web压力测试实验比较了该算法在实际应用中的均衡性能。结果验证了其在服务器集群系统有大的访问请求量时有突出性能,能够使集群系统达到良好的负载均衡。     

一种基于移动代理的P2P系统主动负载均衡算法

负载均衡是P2P系统的研究热点,针对现有负载均衡算法的不足,提出了一种基于移动代理的主动负载均衡算法.该算法使用移动代理收集负载信息、生成负载迁移决策,降低了系统的通信开销,而且避免了单点失效问题和"颠簸"现象.通过引入对用户请求的评估和迁移,预见性的处理负载问题,提高了系统的服务质量.     

Semantic context dissemination and service matchmaking in future network management

The ever‐increasing size, complexity and heterogeneity of telecommunications networks necessitate the introduction of autonomic elements that assist providers in managing and configuring the network's resources. To tackle this increased complexity, it is expected that many specialized autonomic elements will take part in the management process. It becomes necessary for them to collaborate and communicate in order to achieve high‐level, human‐specified, management goals. Therefore, the need for a scalable mechanism to facilitate the interactions between autonomic elements has arisen. This article presents a communications bus, augmented with semantics through the use of ontologies and semantic reasoning, which governs the communication and collaboration between autonomic elements. It supports filtering of context based on meaning. Additionally, it facilitates matchmaking of autonomic element goals with management services using semantic definitions of their inputs, outputs, preconditions and effects. Furthermore, the delay introduced by semantic reasoning was evaluated through an implemented prototype and was shown to be limited to only a few milliseconds. Copyright © 2011 John Wiley & Sons, Ltd.     

Markov game for autonomic joint radio resource management in a multi-operator scenario

This article addresses the autonomy of joint radio resource management (JRRM) between heterogeneous radio access technologies (RATs) owned by multiple operators.By modeling the inter-operator competition as a general-sum Markov game, correlated-Q learning (CE-Q) is introduced to generate the operators' pricing and admission policies at the correlated equilibrium autonomically.The heterogeneity in terms of coverage, service suitability, and cell capacity amongst different RATs are considered in the input state space, which is generalized using multi-layer feed-forward neural networks for less memory requirement.Simulation results indicate that the proposed algorithm can produce rational JRRM polices for each network under different load conditions through the autonomic learning process.Such policies guide the traffic toward an optimized distribution and improved resource utilization, which results in the highest network profits and lowest blocking probability compared to other self-learning algorithms.     

A Distributed and Adaptive Location Management Scheme for Hierarchical Mobility Management

1IntroductionThe IETF Mobile IPstandards[1~2]were proposedtosolve the general problemof host mobility in the inter-net.However,whenthe number of Mobile Node(MN)grows rapidly and the MNare far away fromhome andwith micro mobility,this basic mechanism will …     

一种高效的基于可复制资源的分布式负载均衡策略

为了克服传统负载均衡策略的缺陷,本文提出了一种高效的基于可复制资源的分布式负载均衡策略.在传统负载均衡策略基础上,本文提出了将节点的资源负载分为内部、外部和转发负载,并且分别进行处理的策略;同时给出了该策略的模型.此外,本文提出了负载的方向性概念,并将它应用于负载均衡策略中.最后,分析及仿真结果证明,该策略能够有效的均衡负载,减小内部通信量,同时能够有效的抑制系统负载抖动.     

Gossip-Based Load Balance Strategy in Big Data Systems with Hierarchical Processors

In big data systems, data are assigned to different processors by the system manager, which has a large amount of work to perform, such as achieving load balances and allocating data to the system processors in a centralized way. To alleviate its load, we claim that load balancing can be conducted in a decentralized way, and thus, the system manager need not be in charge of this task anymore. Two decentralized approaches are proposed for load balancing schemes, namely, a utilization scheme based on a load balance algorithm (UBLB) and a number of layers scheme based on a load balance algorithm (NLBLB). In the UBLB scheme, considering the hierarchy of the processor’s processing abilities, a gossip-based algorithm is proposed to achieve load balance using the jobs’ utilizations as load balance indicators in addition to the number of jobs. The reason for this action is that the processor’s process abilities are different from one another. Thus, the utilization indicator is more reasonable. In the NLBLB scheme, the processors are classified into different layers according to their processing abilities. In each layer, a sub-load balance is conducted, which means that the UBLB is achieved in a sub-region. The efficiencies of the two proposed schemes are validated by simulation, which proves their positive effect.     

一种基于软件定义网络的自治服务质量管理机制(英文)

With the increase of network complexity,the flexibility of network control and management becomes a nontrivial problem.Both Software Defined Network(SDN) and Autonomic Network technologies are sophisticated technologies for the network control and management.These two technologies could be combined together to construct a software defined self-managing solution for the future network.An autonomic QoS management mechanism in Software Defined Network(AQSDN) is proposed in this paper.In AQSDN,the various QoS features can be configured autonomically in an OpenFlow switch through extending the OpenFlow and OF-Config protocols.Based on AQSDN,a novel packet context-aware QoS model(PCaQoS) is also introduced for improving the network QoS.PCaQoS takes packet context into account when packet is marked and managed into forwarding queues.The implementation of a video application's prototype which evaluates the self-configuration feature of the AQSDN and the enhancement ability of the PCaQoS is presented in order to validate this design.     

一种改进的网格作业管理实现方法

面向服务的网格中，实现作业管理的应用程序一般采用多线程机制。这种方法相对于可以划分为相互独立子任务的网格作业而言，灵活性欠缺，而且会造成中心服务器负载过重、资源浪费、导致系统效率降低。针对这个问题，提出了一种“主任务分发-子任务签单”的机制实现作业管理，该机制能够较好地解决面向服务的网格中，具有此类特点的作业的管理方法存在的问题。     

电信网络话务流量自动控制技术的研究

电信网络话务流量自动控制是实现网络自动化管理的内容之一。在分析话务理论的基础上 ,提出了基于本地网网络管理与集中监控系统平台的话务流量自动控制技术 ,并详细介绍了系统的模型和软件流程 ,通过具体的工程应用说明该系统有一定的可行性和实用性。     

无人机装备自主式保障系统研究

目前我军无人机装备采用事后维修、定期维修、预防性维修等维修保障方式,存在故障诊断及修复能力差、维修资源繁多、保障费用急剧增长等问题。充分考虑我军无人机装备技术特点及现行维修保障体制,文中创新性地提出了构建适合我军无人机装备的自主式保障系统;并对系统组成、故障模式影响及危害性分析、测试性设计技术、机载故障快速诊断及自修复技术、预测与健康管理技术、分布式信息融合技术等关键技术进行重点研究。该系统为我军新型信息化装备提供了新的维修保障模式,并可提高我军无人机装备的一体化、精确化保障水平。     

Trust management-based and energy efficient hierarchical routing protocol in wireless sensor networks

The single planar routing protocol has a slow convergence rate in the large-scale Wireless Sensor Network (WSN). Although the hierarchical routing protocol can effectively cope with large-scale application scenarios, how to elect a secure cluster head and balance the network load becomes an enormous challenge. In this paper, a Trust Management-based and ​Low Energy Adaptive Clustering Hierarchy protocol (LEACH-TM) is proposed. In LEACH-TM, by using the number of dynamic decision cluster head nodes, residual energy and density of neighbor nodes, the size of the cluster can be better constrained to improve energy efficiency, and avoid excessive energy consumption of a node. Simultaneously, the trust management scheme is introduced into LEACH-TM to defend against internal attacks. The simulation results show that, compared with LEACH-SWDN protocol and LEACH protocol, LEACH-TM outperforms in prolonging the network lifetime and balancing the energy consumption, and can effectively mitigate the influence of malicious nodes on cluster head selection, which can greatly guarantee the security of the overall network.