基于SSA和LWLR组合的网络延迟预测

针对互联网网络端到端延迟因其非线性和非平稳性(时变)特性而导致其准确性预测的难题,提出了一种基于滑动窗口的奇异谱分析和局部加权线性回归的组合预测算法。并采用互联网所采集的RTT数据来验证提出的预测算法,实验结果表明,预测算法具有快速、精确的特点,是一种很适合实际工程应用的预测算法。     

控制端到端传输延迟抖动的改进TFRC算法

针对端到端实时通信业务对于网络传输的要求,提出基于速率控制的TCP友好性拥塞控制策略(TFRC)的一种改进算法——TFRC-CJUTD算法。该算法将单向传输延迟的抖动作为反馈信号来改进控制机制,降低业务传输过程中的单向传输延迟抖动,更好地适应实时业务。通过NS仿真验证,该算法取得较好的效果。     

基于EDF调度算法的端到端延迟保证方法

EDF(EarliestDeadlineFirst)是一种高效的调度算法。为了将其应用于提供端到端延迟保证,提出了一种新的算法JT-EDF(JitterTunableEDF),并证明了所有的端到端EDF调度算法都可以在相同的条件下保证相同的端到端延迟界。     

WiFi-TSN低时延转换架构

无线网络与TSN(Time Sensitive Networking)的融合是目前工业界的关注点之一。传统的基于应用层软件的网关存在CPU利用率高、处理延迟长、性能差等缺点。因此提出了一种WiFi-TSN低时延转换架构,来实现WiFi网络与TSN网络的集成。该架构采用Verilog语言实现,通过硬件来保证通信信道之间可预测的延迟,能够在极短的时间内完成协议转换和协议数据的转发。采用Vivado EDA工具来完成电路的设计,并进行足量的仿真测试来评估电路的端到端延迟性能。     

基于BPNN端到端时延预测的多路传输调度

针对移动异构网络环境网络参数动态变化、多路传输过程中数据包乱序引发的吞吐量下降等问题,提出一种基于BP神经网络(back propagation neural network,BPNN)端到端时延预测的多路传输调度方法,通过BP神经网络的构建、训练和学习,实现对端到端传输时延的更准确预测,以此为基础,对子流拥塞状况及网...     

基于深层声学特征的端到端语音分离

提出基于深层声学特征的端到端单声道语音分离算法,传统声学特征提取方法需要经过傅里叶变换、离散余弦变换等操作,会造成语音能量损失以及长时间延迟.为了改善这些问题,提出了以语音信号的原始波形作为深度神经网络的输入,通过网络模型来学习语音信号的更深层次的声学特征,实现端到端的语音分离.客观评价实验说明,本文提出的分离算法不仅有效地提升了语音分离的性能,也减少了语音分离算法的时间延迟.     

无线多媒体网络中端到端自适应QoS保证

无线网络中较高的信道误码率和不稳定的可用带宽等因素给多媒体传输服务质量(QoS)保证带来了新的挑战．该文提出了一种基于二级反馈的两层自适应QoS保证方法，即应用层QoS和传输层QoS，提出了将应用层的最小流速率λmax和最大帧错误率Emax两个QoS参数映射到传输层的最大端到端帧延迟Dmax的计算公式．在应用层提出了自适应节的系统资源的分配公式、自适应QoS调节算法A和算法B．在传输层提出了保证端到端帧延迟Dmax的包长计算公式，给出了自适应包长调节算法．     

基于抖动测试的AFDX端到端延迟紧性修正

AFDX引入虚拟链路(Virtual Link)实现物理带宽资源的逻辑分隔。由于数据帧的异步到达和多路复用输出造成虚拟链路的时延抖动现象,并最终导致流量端到端延迟分析的不确定性。本文提出了一种基于抖动测试值的网络演算紧缩方法。通过分布式测试,获得虚拟链路在网络中的实际传输抖动,并以此为基础,建立了流量传输精确化模型,通过流量模型的逐级修正,使端到端延迟计算结果逐级精确化。通过将抖动实际值与理论分析结果相结合,提供了网络演算悲观度及其扩散影响度量的直观对比,提高了延迟计算的紧性。     

基于深度视觉注意神经网络的端到端自动驾驶模型

针对现有端到端自动驾驶方法中存在的驾驶指令预测不准确、模型结构体量大和信息冗余多等问题,提出一种新的基于深度视觉注意神经网络的端到端自动驾驶模型。为了更有效地提取自动驾驶场景的特征,在端到端自动驾驶模型中引入视觉注意力机制,将卷积神经网络、视觉注意层和长短期记忆网络进行融合,提出一种深度视觉注意神经网络。该网络模型能够有效提取驾驶场景图像的空间特征和时间特征,并关注重要信息且减少信息冗余,实现用前向摄像机输入的序列图像来预测驾驶指令的端到端自动驾驶。利用模拟驾驶环境的数据进行训练和测试,该模型在乡村路、高速路、隧道和山路四个场景中对方向盘转向角预测的均方根误差分别为0.009 14、0.009 48、0.002 89和0.010 78,均低于对比用的英伟达公司提出的方法和基于深度级联神经网络的方法;并且与未使用视觉注意力机制的网络相比,该模型具有更少的网络层数。     

基于BP-DBN的认知网络端到端态势评估算法

文中提出了一种基于BP-深度信念网络（ BP-DBN）的端到端态势评估算法,实现网络端到端态势等级判定。基于提出的分布式态势评估架构,使用BP-DBN分别构建认知域网元评估值、局部态势评估值和端到端态势评估值三者间的映射关系,最后实现端到端态势等级定性评估。实验结果表明,基于少量标记训练样本,BP-DBN测试错误率低,能够保证评估准确性,同时提出的评估算法能够有效评估端到端网络态势等级。     

HMM delay prediction technique for VoIP

This paper proposes a new algorithm for predicting audio packet playout delay for voice conferencing applications that use silence suppression. The proposed algorithm uses a hidden Markov model (HMM) to predict the playout delay. Several existing algorithms are reviewed to show that the HMM technique is based on a combination of various desirable features of other algorithms. Voice over Internet protocol (VoIP) applications produce packets at a deterministic rate but various queuing delays are added to the packets by the network causing packet interarrival jitter. Playout delay prediction techniques schedule audio packets for playout and attempt to make a reasonable compromise between the number of lost packets, the one-way delay and the delay variation since these criteria cannot be optimized simultaneously. In particular, this paper will show that the proposed HMM technique makes a good compromise between the mean end-to-end delay, end-to-end delay standard deviation and average packet loss rate.     

基于仿真分析的端到端最小包时延测量方法

端到端最小包时延作为反映端到端路径拓扑特征的基本指标得到广泛应用，但目前缺少对最小时延测量方法的研究。以仿真为手段定量分析了在不同路径长度下最小时延的可测性，并建立了反映探测包数量与路径长度关系的线性方程。以此为基础，提出一种基于仿真分析的最小时延测量方法。在互联网的实际测量表明该方法能以较小的测量开销获得较准确的最小时延测量结果。     

Joint source coding and packet classification for real-time video transmission over differentiated services networks

Differentiated Services (DiffServ) is one of the leading architectures for providing quality of service in the Internet. We propose a scheme for real-time video transmission over a DiffServ network that jointly considers video source coding, packet classification, and error concealment within a framework of cost-distortion optimization. The selections of encoding parameters and packet classification are both used to manage end-to-end delay variations and packet losses within the network. We present two dual formulations of the proposed scheme: the minimum distortion problem, in which the objective is to minimize the end-to-end distortion subject to cost and delay constraints, and the minimum cost problem, which minimizes the total cost subject to end-to-end distortion and delay constraints. A solution to these problems using Lagrangian relaxation and dynamic programming is given. Simulation results demonstrate the advantage of jointly adapting the source coding and packet classification in DiffServ networks.     

一种双参数拓扑推测方法

针对采用单一性能参数推测网络拓扑结构算法的问题, 如有效性与网络负载有关以及测量节点性能参数时大多需要节点间时钟的同步等, 在现有的测量方法基础上, 提出了一种不需要节点间时钟同步可以测量端到端时延抖动和丢包相关性的紧接分组对序列测量方法, 同时设计了一种综合端到端时延抖动和丢包相关性的双参数拓扑推测算法, 该算法能够适应不同的网络负载环境。最后通过NS-2仿真实验验证了该算法的有效性和准确性。     

基于Internet的实时机器人系统时延预测研究及算法

针对基于Internet实时机器人系统,提出了多尺度的时延预测算法,该算法是在线和实时的。基于网络结构分析了网络时延的主要组成及其时延特性。不同于传统的网络往返时延的预测,该算法预测的是能真实反映端对端数据包传递的单程时延,而且还提出了预测单向时延所需的时钟同步算法。理论分析和多点之间的网络实验验证了该算法的高效性。     

Multi-manifold model of the Internet delay space

The network coordinate systems (NCSes) can assist the network applications to improve their performance by choosing preferred severs or constructing optimal overlay networks. However, the current NCSes cannot predict the end-to-end delay accurately, because they have neglected the inherent characters of the Internet delay space. By analyzing typical datasets, the Internet delay space was found to have obvious multi-manifold property. Thus, a multi-manifold model of the Internet delay space and a Principal Component Analysis (PCA) based Multi-manifold Partition algorithm of the Internet Delay Space (MPIDS-PCA) were proposed. Beginning with choosing landmarks randomly, MPIDS-PCA partitions the whole dataset into several sub datasets with low dimensionality by iterations. After the partition, the whole delay dataset and sub datasets are embedded into a hierarchical coordinate system Vivaldi-M. The experimental results show that MPIDS-PCA can gurantee the low dimensionality of sub datasets and Vivaldi-M can achieve better prediction accuracy.     

Neural network prediction model for a real-time data transmission

Both the real-time transmission and the amount of valid transmitted data are important factors in real-time multimedia transmission through the Internet. They are mainly affected by the channel bandwidth, delay time, and packet loss. In this paper, we propose a predictive rate control system for data transmission, which is designed to improve the number of valid transmitted packets for the transmission of real-time multimedia over the Internet. The one-step-ahead round-trip delay time and packet loss are predicted using a prediction algorithm and then these predicted values are used to determine the transmission rate. A real-time multimedia transmission system was implemented using a TCP-friendly algorithm, in order to obtain the measurement data needed for the proposed system. Neural network modeling was performed using the collected data, which consisted of the round-trip time (RTT) delay and packet loss rate (PLR). In addition, the performance of the neural network prediction model was verified through a validation process. The transmission rate was determined from the values of RTT delay and PLR, and a data transmission test for an actual system was performed using this transmission rate. The experiment results show that the algorithm proposed in this study increases the number of valid packets compared with the TCP-friendly algorithm.     

Cross-Layer Error Control for Multimedia Streaming in Wireless/Wireline Packet Networks

In this paper, we propose a cross-layer error control framework for robust and low delay multimedia streaming in tandem-connected IEEE 802.11 wireless LANs and the Internet. For this network configuration, we model the end-to-end delay and packet loss rate as a function of the automatic repeat request (ARQ) and forward error correction (FEC) error control mechanisms that are employed at the application and wireless link layers. The analytical model is used as the basis of a delay-constrained error control algorithm that adapts the protection level at the application and link layers so that the end-to-end packet loss rate is minimized. With extensive simulations, we validate the efficiency of the proposed cross-layer error control methodology for delay-sensitive pre-compressed video streaming.      

联合车速–队列感知的路边单元分组调度随机优化

路边单元(RSU)是车联网中为其无线覆盖范围内过往车辆提供信息服务的基础设施,路边单元间的分组传输可通过移动车辆"存储–载带–转发"的方式进行,其传输过程中分组的端到端时延由源RSU缓存中的排队时延与车辆载带过程的传播时延两部分组成.为使RSU间分组传输过程中平均端到端时延最小化,本文提出一种联合车速–队列感知的路边单元分组调度随机优化方法,该方法根据源RSU缓存队列长度和经过源RSU覆盖范围的车辆速度状态作分组调度决策.通过马尔科夫决策(MDP)框架对分组传输过程中的平均排队时延和平均传播时延进行分析,建立一个非线性平均端到端时延最小化问题并求解.仿真结果表明,所提出的RSU分组调度随机优化方法可以显著降低RSU间分组传输过程中的平均端到端时延,并提高系统中分组传输的吞吐量.