一种空间分割信号源方向估计器的神经网络实现

本文在介绍了空间分割信号源方向估计方法后，提出了一种空间分割信号源方向估计器的神经网络实现方法。所提出的这种网络具有许多优良特性，即暂态混沌特性和平稳收敛特性，能有效地避免传统Ｈｏｐｆｉｅｌｄ神经网络极易陷入局部极值的缺陷。它通过短暂的倒分叉过程，能很快进入稳定收敛状态。稳定状态时网络的输出给出了空间信号源方向的最优估计。所给出的数值仿真实验都证明了本文方法的有效性。     

基于混沌神经网络的二维局部均值估计自适应滤波

为了提高自适应滤波的精度和收敛速度,提出了一种基于混沌神经网络的二维均值估计(LME)自适应滤波算法,在传统的二维LME自适应滤波方案中引入了混沌神经网络控制机制,用混沌神经网络自适应滤波器代替LME中的LMS自适应滤波算法,应用混沌神经网络估计局部期望输出进行滤波.仿真结果表明,该局部均值估计滤波器当输入信号为均值不为0且变化较大时,输出信号仍能较好地实现对输入信号的跟踪,获得了原始信号的主要特性,从均方误差曲面来看,算法具有较快的收敛速度和较高的滤波精度.     

一种基于改进暂态混沌神经网络的信道分配算法

该文针对暂态混沌神经网络(TCNN)求解信道分配问题(CAP),分析混沌神经网络模型及其混沌性态,依据其按自反馈连接权值的减小,由混沌态通过逆分岔而收敛到稳定状态的特性,提出了一种对暂态混沌神经网络进行分段退火的策略,即依据混沌神经网络运行过程中,对应Lyaponov指数的变化特性而确定分段点,使网络能有效地利用混沌态进行全局搜索和加快收敛;在7小区的信道分配中,网络收敛速度提升了30%左右,在25小区的Kunz基准测试程序的仿真中,收敛速度也提升了近15%;仿真结果表明其有效减少了网络运算的迭代步数,提高了网络的搜索效率;通过相应理论和仿真结果的分析,对网络的搜索性能、参数的选择与设置进行了进一步的讨论。     

基于大数据的电力通信通道智能路由推荐策略研究

面对规模庞大、结构复杂的电力通信网,针对通信调度如何根据业务需求准确、合理、高效地安排通信通道,提出了一种基于分布式图并行计算的大数据智能路由推荐方法。该方法根据电力通信网特点构建电力通信网络拓扑模型、建立优选路由指标模型,并采用基于分布式图并行计算框架实现并行路由推荐算法。实验证明,该方法具有快速迭代与收敛的特性,在大型复杂的电力通信网络路由推荐与规划中具有良好的应用前景。     

基于蚂蚁算法的分布式QoS路由选择算法

本文基于蚂蚁的自组织能力描述了一种新的分布动态路由选择方法,针对当前通信网中存在的服务质量问题提出了QoS保证的分布式路由选择算法（DQRA）。DRQA能以并行的方式解决网络中呼叫的时延和带宽分配问题,避免了NP－完全问题,算法简单,易于实现,能有效地解决大型网络的负载平衡问题,本文选择了OPNET仿真环境对网络进行实时仿真,通过和最小代价算法的比较,进一步表明了算法的有效性。     

基于混沌神经网络的移动通信信道分配方法研究

该文应用混沌神经网络求解信道分配问题,给出了信道分配的能量函数表达式和混沌神经网络模型,研究了判别混沌神经网络混沌特性的Lyapunov指数法,讨论了网络模型参数对网络混沌特性的影响,提出了基于混沌神经网络的信道分配算法.仿真结果表明,混沌神经网络具有复杂的瞬态混沌特性,它比Hopfield网络具有更强的搜索全局最优解的能力,和更快的收敛速度.     

基于混沌蚁群的神经网络速度辨识器研究

针对BP神经网络收敛速度慢和易陷入局部极小值的缺点,提出了混沌蚁群优化神经网络的实现方法。该方法在基本蚁群算法的基础上引入混沌因子,并利用混沌的遍历性和随机性,将带有混沌特征的初始化变量线性映射到变量取值区间,从而得到神经网络权值的全局最优值。利用该算法可对直接转矩控制系统进行转速辨识。     

Hopfield神经网络在B-ISDN路由选择中的应用

宽带综合业务数字网（Ｂ－ＩＳＤＮ）采用异步转移模式（ＡＴＭ）作为其传输技术,引入了虎通道（ＶＰ）和虚通路（ＶＣ）概念。本文针对Ｂ－ＩＳＤＮ中的ＶＰ路由问题,提出了一种基于Ｈｏｐｆｉｅｌｄ神经网络的ＶＰ路由选择算法,给出了神经网络能量函数的表示方法及神经元的状态方程。计算机模拟结果表明,本算法能根据网络的物理结构和业务需求情况,快速、有效地实现ＶＰ路由选择,提高网络的生存性。     

Hopfield神经网络在B—ISDN路由选择中的应用

宽带综合业务数字网（Ｂ－ＩＳＤＮ）采用异步转移模式（ＡＴＭ）作为其传输技术,引入了虎通道（ＶＰ）和虚通路（ＶＣ）概念。本文针对Ｂ－ＩＳＤＮ中的ＶＰ路由问题,提出了一种基于Ｈｏｐｆｉｅｌｄ神经网络的ＶＰ路由选择算法,给出了神经网络能量函数的表示方法及神经元的状态方程。计算机模拟结果表明,本算法能根据网络的物理结构和业务需求情况,快速、有效地实现ＶＰ路由选择,提高网络的生存性。     

基于人工神经网络的分簇多播路由算法

为了能够快速有效地求解多播路由模型,融合分簇算法和多播树算法思想,利用神经网络作为计算工具,提出了一种基于分簇思想的多播路由算法:用自组织神经网络来分簇,用Hopfield神经网络来构造一个由簇首节点组成的多播树.该算法不但简单易行,而且具有收敛速度快、效率高、控制开销小的特点.最后,通过仿真从实践上支持了本算法的可行性.     

A novel robust routing algorithm for multi-granularity connection requests in wavelength division multiplexing mesh networks

In this paper, we propose a novel robust routing algorithm based on Valiant load-balancing under the model of polyhedral uncertainty (i.e., hose uncertainty model) for WDM (wavelength division multiplexing) mesh networks. Valiant load-balanced robust routing algorithm constructs the stable virtual topology on which any traffic patterns under the hose uncertainty model can be efficiently routed. Considering there are multi-granularity connection requests in WDM mesh networks, we propose the method called hose-model separation to solve the problem for the proposed algorithm. Our goal is to minimize total network cost when constructing the stable virtual topology that assures robust routing for the hose model in WDM mesh networks. A mathematical formulation (integer linear programming, ILP) about Valiant load-balanced robust routing algorithm is presented. Two fast heuristic approaches are also proposed and evaluated. We compare the network throughput of the virtual topology constructed by the proposed algorithm with that of the traditional traffic grooming algorithm under the same total network cost by computer simulation.     

Entire network load‐aware cooperative routing algorithm for video streaming over mobile ad hoc networks

In this paper, we present an entire network load‐aware cooperative routing algorithm based on IEEE 802.11 multi‐rate for video streaming over mobile ad hoc networks. The proposed routing algorithm is designed to minimize the consumed time slots while guaranteeing the required time slots at all the pairs of adjacent nodes over the route and the contention neighbors of these nodes to support the route. Furthermore, the proposed routing algorithm can distribute the network loads well over the entire network. This technology is essential because video streaming applications require stringent quality of service and even larger network resources compared with traditional data services, and these demands may dramatically increase the entire network load and/or cause network congestion. Finally, experimental results are provided to show a performance of the proposed routing algorithm. Copyright © 2011 John Wiley & Sons, Ltd.     

多光纤波分复用网的一种新的备用路由算法

基于经典的LLR算法,研究了波分复用光网络的路由问题,提出了一种用于多光纤网的新算法—LLHR,该算法综合考虑了链路负载和路由跳数两个因素。文章深入研究了网络光纤数、备用路由数和网络负载对算法性能的影响。计算机仿真结果表明,与LLR算法相比,该算法能有效降低网络的阻塞率,提高网络的性能。     

基于并行BP神经网络的路由查找算法

结合Bloom-filter算法和并行反向传播神经网络,提出了一种新的基于并行神经网络的路由查找算法(BFBP)。该算法满足路由查找的需求,只需学习路由条目的网络ID,且易于扩展到IPv6地址查询。研究结果表明,相比于己有的神经网络路由查找方法,该算法需要学习的条目数平均减少了520倍,提高了学习效率,为神经网络应用于路由查找创造了有利条件。     

Joint load balanced stable routing and communication segment assignment in mobile cognitive radio ad‐hoc networks

The fundamental issues in mobile cognitive radio ad‐hoc networks are the selection of the optimal stable paths between nodes and proper assignment of the frequency channels/time slots (communication segments) to the links. In this paper, a joint load balanced stable routing and communication segment assignment algorithm is proposed that considers jointly the mobility prediction, mitigating the co‐channel interference and energy consumption. The novelty of the proposed algorithm lies in the increasing of the path stability, which benefits from the maximum link lifetime parameter and introduced weighting function to keep routes away from the PU's region. This avoids the negative impacts on the PUs' operations and decreases the conflict of the cognitive nodes. In the proposed algorithm, the concept of load balancing is considered that yields in the balancing energy consumption in the network, improving the network performance and distributing traffic loads on all available channels. The effectiveness of the proposed algorithm is verified by evaluating the aggregate interference energy, average end‐to‐end delay, goodput, and the energy usage per packet under 6 scenarios. The results show that the performance of the proposed algorithm is significantly better than the recently proposed joint stable routing and channel assignment protocol.     

An adaptive load-aware routing algorithm for multi-interface wireless mesh networks

In wireless mesh networks, the number of gateway nodes are limited, when the nodes access to the internet by fixed gateway node, different requirements of nodes lead to the dataflow shows heterogeneity. Many new routing metrics and algorithms existing in traditional wired networks and the Ad Hoc network, can not be directly applied to wireless mesh networks, so how to design a routing metric and algorithm which can dynamically adapt to current networks topology and dataflow changes, avoid bottleneck node, and select the most stable and least congestion link to establish a route is very important. In this paper, we presented a new dynamic adaptive channel load-aware metric (LAM) to solve the link load imbalance caused by inter-flow and inner-flow interference, designed a self-adaptive dynamic load balancing on-demand routing algorithm through extending and improving AODV routing method with the LAM, to achieve flow balance, reduce the high packet loss ratio and latency because congestion and Packet retransmission, and can increase Network Throughput.     

Virtual channel load-balanced routing algorithm for Torus networks

In order to improve the network performance furthermore,a routing algorithm for 2D-Torus is investigated from the standpoint of load balance for virtual channels.The 2D-Torus network is divided into two virtual networks and each physical channel is split into three virtual channels.A novel virtual channel allocation policy and a routing algorithm are proposed,in which traffic load is distributed to those three virtual channels in a more load-balanced manner by introducing a random parameter.Simulations of the proposed algorithm are developed with a SystemC-based test bench.The results show that compared with the negative first for Torus networks(NF-T) algorithm,the proposed algorithm can achieve better performance in terms of network latency and throughput under different traffic patterns.It also shows that a routing algorithm with load balance for virtual channels can significantly improve the network performance furthermore.     

OBS中基于优先级与负载均衡的偏射路由算法

为了解决偏射算法在偏射控制七的问题,提出了一种基于优先级与负载均衡的偏射路由算法.当冲突发生时,分割优先级低的突发数据包;将冲突部分的突发包偏射到空闲的链路上,并在空闲的链路中选择若干条"当前最大剩余跳数小于源-目的节点的最大跳数"的路由作为候选路由;最后,在这些候选路由中选择一条可以使网络中各链路使用波长数的统计方差...     

Blocking evaluation for networks with residual capacity adaptiverouting

An algorithm is proposed for obtaining conservative estimates for the end-to-end blocking probability of networks operating with residual capacity adaptive routing. Two important requirements are that it should be fast enough for use within an iterative network design procedure and have an accuracy sufficient for that purpose. The algorithm is based on the assumption that the stationary behavior of residual capacity adaptive routing can be adequately modeled by a nonadaptive routing with suitably chosen parameters. An algorithm is proposed for the stationary version that is stable and fast but overestimates the blocking. A number of modifications of the model to improve its accuracy are examined. It is concluded that the model can be used for network design if a conservative solution is acceptable