基于深度时空残差网络的路网短时交通流预测

针对城市路网短时交通流预测受到许多复杂因素的影响,提出一种基于深度时空残差网络的路网短时交通流预测模型DST-Res Net（deep spatio-temporal residual network）。针对时空数据的两个独特属性邻近性和周期性分别设计相应的残差网络分支,通过为两个分支中相同的道路分配不同的权重动态聚合两个分支网络的输出,调整时空属性对不同路段交通流预测的影响程度,将两个残差网络的聚合结果与外部因素进行融合。通过选择RMSE和R²为模型的评价指标进行实验验证,该DST-ResNet模型相较主流的LSTM模型具有更高的有效性和可行性。     

分布式网络流量预测模型的精度研究

网络流量模型是网络性能评价、网络协议设计、网络规划等的基础。本文设计基于分布式网络测试的时间与相关流量模型的方法,并采用该流量模型预测网络流量。文章提出网络流量预测精度的数学定义,网络测试实验表明,我们的流量模型具有更高的精度,并适用实际运行的网络环境。     

基于改进时空残差卷积神经网络的城市路网短时交通流预测

城市路网交通流预测受到历史交通流和相邻路口交通流的影响,具有复杂的时空关联性.针对传统时空残差模型缺乏对交通流数据进行相关性分析、捕获微小变化而容易忽略长期时间特征等问题,提出一种基于改进时空残差卷积神经网络(CNN)的城市路网短时交通流预测模型.该模型将原始交通流数据转化成交通栅格数据,利用皮尔逊相关系数(PCC)对...     

基于O-D矩阵估计的路网交通流量仿真模型

为了将交通出行需求对路网交通流量的影响进行动态的量化分析,提出了一个基于O-D矩阵估计的路网交通流量仿真模型。利用O-D矩阵估计的重力模型计算方法、复杂网络理论和路段阻抗模型,构建了路网模型;在人们出行总是选择路段阻抗最小路径的假定下,设计了出行需求的路网流量映射算法;基于离散事件仿真,在PC系统上实现了路网流量仿真系统。仿真结果表明：该仿真系统可以根据各交通子区域出行需求的变化,精确模拟路网流量和交通状态的动态演进。     

A fast network partition method for large-scale urban traffic networks

In order to control the large-scale urban traffic network through hierarchical or decentralized methods, it is necessary to exploit a network partition method, which should be both effective in extracting subnetworks and fast to compute. In this paper, a new approach to calculate the correlation degree, which determines the desire for interconnection between two adjacent intersections, is first proposed. It is used as a weight of a link in an urban traffic network, which considers both the physical characteristics and the dynamic traffic information of the link. Then, a fast network division approach by optimizing the modularity, which is a criterion to distinguish the quality of the partition results, is applied to identify the subnetworks for large-scale urban traffic networks. Finally, an application to a specified urban traffic network is investigated using the proposed algorithm. The results show that it is an effective and efficient method for partitioning urban traffic networks automatically in real world.     

基于非线性算法的网络业务流量预测

基于递归最小二乘支持向量机,提出了一种网络业务流量非线性预测算法。通过最小二乘支持量机首先将原始的网络流量数据映射到一个高维空间中,进而在这个高维空间中对流量数据进行预测,使得在低维空间中非线性预测转化为高维空间中的线性预测,提高了预测性能。仿真结果表明,预测误差能够维持在5%以内。     

大规模交通网络实时模拟系统

以元胞自动机模型为微观模型，以CS模型为指导构建二维的大规模交通网络，利用多线程机制实现了整个模拟系统的高速运行。具体的模拟实验显示：该模拟系统完全可以满足实时模拟的需要，对于包含400个十字路口的交通网络，模拟系统每更新一次所需要的时间小于1s。     

Short-term prediction of traffic flow using a binary neural network

This paper introduces a binary neural network-based prediction algorithm incorporating both spatial and temporal characteristics into the prediction process. The algorithm is used to predict short-term traffic flow by combining information from multiple traffic sensors (spatial lag) and time series prediction (temporal lag). It extends previously developed Advanced Uncertain Reasoning Architecture (AURA) k-nearest neighbour (k-NN) techniques. Our task was to produce a fast and accurate traffic flow predictor. The AURA k-NN predictor is comparable to other machine learning techniques with respect to recall accuracy but is able to train and predict rapidly. We incorporated consistency evaluations to determine whether the AURA k-NN has an ideal algorithmic configuration or an ideal data configuration or whether the settings needed to be varied for each data set. The results agree with previous research in that settings must be bespoke for each data set. This configuration process requires rapid and scalable learning to allow the predictor to be set-up for new data. The fast processing abilities of the AURA k-NN ensure this combinatorial optimisation will be computationally feasible for real-world applications. We intend to use the predictor to proactively manage traffic by predicting traffic volumes to anticipate traffic network problems.     

Reliable performance prediction for multigrid software on distributed memory systems

We propose a model for describing and predicting the parallel performance of a broad class of parallel numerical software on distributed memory architectures. The purpose of this model is to allow reliable predictions to be made for the performance of the software on large numbers of processors of a given parallel system, by only benchmarking the code on small numbers of processors. Having described the methods used, and emphasized the simplicity of their implementation, the approach is tested on a range of engineering software applications that are built upon the use of multigrid algorithms. Despite their simplicity, the models are demonstrated to provide both accurate and robust predictions across a range of different parallel architectures, partitioning strategies and multigrid codes. In particular, the effectiveness of the predictive methodology is shown for a practical engineering software implementation of an elastohydrodynamic lubrication solver.     

Parallel solution of a traffic flow simulation problem

Computational Fluid Dynamics (CFD) methods for solving traffic flow continuum models have been studied and efficiently implemented in traffic simulation codes in the past. This is the first time that such methods are studied from the point of view of parallel computing. We studied and implemented an implicit numerical method for solving the high-order flow conservation traffic model on parallel computers. Implicit methods allow much larger time-step than explicit methods, for the same accuracy. However, at each time-step a nonlinear system must be solved. We used the Newton method coupled with a linear iterative method (Orthomin). We accelerated the convergence of Orthomin with parallel incomplete LU factorization preconditionings. We ran simulation tests with real traffic data from an 12-mile freeway section (in Minnesota) on the nCUBE2 parallel computer. These tests gave the same accuracy as past tests, which were performed on one-processor computers, and the overall execution time was significantly reduced.     

基于网络全局流量异常特征的DDoS攻击检测

由于分布式拒绝服务（DDoS）攻击的隐蔽性和分布式特征，提出了一种基于全局网络的DDoS检测方法。与传统检测方法只对单条链路或者受害者网络进行检测的方式不同，该方法对营运商网络中的OD流进行检测。该方法首先求得网络的流量矩阵，利用多条链路中攻击流的相关特性，使用K L变换将流量矩阵分解为正常和异常流量空间，分析异常空间流量的相关特征，从而检测出攻击。仿真结果表明该方法对DDoS攻击的检测更准确、更快速，有利于DDoS攻击的早期检测与防御。     

ACO-BP神经网络在电梯交通流预测中的应用

电梯交通流预测为电梯配置与群控调度提供必要的乘客流数据信息.针对基于BP神经网络的电梯交通流预测模型在网络训练过程中表现出的对初值敏感、易陷入极小值等问题,提出利用全局寻优的蚁群优化(ACO)算法优化BP神经网络.同时,利用精英蚂蚁和排序策略对基本ACO算法进行改进.采集天津某办公大厦实际交通流数据进行实例分析,分别对基于传统的BP神经网络和蚁群优化的BP(ACO-BP)神经网络的电梯交通流预测模型进行仿真验证.结果表明:ACO-BP神经网络的预测效果远优于传统的BP神经网络,适用于电梯交通流预测系统.     

PARAMICS—Parallel microscopic simulation of road traffic

This paper describes work done on the original PARAMICS project, which was developed for the Edinburgh Parallel Computing Centre to examine parallel microscopic road traffic simulation. The simulator, constructed originally for a Thinking Machines Connection Machine (CM-200), uses a data-parallel approach to simulate approximately 200,000 vehicles on 20,000 miles of roadway. More recent work has focused on the use of a message-passing paradigm, with a 256-node CRAY T3D as the target machine. The message-passing version of PARAMICS, PARAMICS-MP, is inherently scalable and can model many smaller networks on a broad range of platforms.An earlier version of this paper was presented at Supercomputing '94.     

城市复杂道路网络交通流的分解模型

针对城市道路交通流非线性、不确定性和模糊性特点,将城市道路与快速干道作为整体对待,提出了面向控制应用的城市交通网络宏观动态离散模型。将城市街区作为划分基点,把整个城市道路复杂交通网络分解为交叉口和单向环形道路两个子系统,分别建立了它们的宏观动态模型。通过对交叉口进行理想虚拟变形,将各个单向环形道路连接在一起,从而形成各种复杂网络。对西安市中心区域的实际交通流数据进行了仿真研究,结果表明该交通流模型基本实现了城市道路与快速干道的统一分析建模,较好地反映了城市路网的交通流信息,可以作为城市交通控制系统分析和设计的有力工具。     

分布式并行计算在交通网络仿真中的应用*

根据交通网络仿真的并行特征采用域分解方法设计交通并行仿真系统的框架,把交通网络分为几个子网,集群系统的每个节点机分别负责其中的一个子网,提出基于车辆数负载的网络分割算法来平衡各子网的负载量,并分析子网之间的通信机理.同时,在基于MPI 的并行计算平台上实现设计的并行仿真系统.通过实例表明,提出的并行算法能大大提高交通网络仿真的速度和效率.     

基于生成对抗网络的大规模路网交通流预测算法

对大规模路网交通流进行准确预测,能够应用于区域交通协同控制与管理,提高路网运行效率.针对如何高精度地拟合大规模路网交通流时空分布并对其进行准确预测,提出基于梯度惩罚的Wasserstein生成对抗网络(Wasserstein generative adversarial network with gradient penalty,WGAN-GP)的大规模路网交通流预测算法.根据大规模路网交通流数据特点,为了增加模型对时间相关性和远距离空间相关性特征的抽象能力,采用残差U型网络作为生成器来增加网络深度;采用多重判别器分别从时间和空间特征来对生成数据进行判别,从而提高判别器的判别能力.所提算法能够解决判别型深度学习模型仅能针对路网整体误差最小化,而忽略各交通流观测点预测误差最小化原则的问题,能够更好地满足现实交通场景需求.实验结果表明,所提算法能够有效地学习路网交通流数据内部多因素耦合特性,具有更高的预测精度.     

The evolution of a distributed processing network

Current trends in information systems technology increase the advantages of developing an increasingly complex distributed processing capacity. Distributed processing networks (DPNs) are expected to evolve gradually from centralized systems into more complex configurations. The introduction of major changes in organizational Structure, such as those precipitated by mergers or acquisitions, also require rapid changes to the DPN. This paper describes four distributed processing configurations. It then presents a case: the evolution of the DPN in a large corporate bank and holding company. This case illustrates configuration changes over the life cycle of the DPN of the bank and provides insight into the process of planning for DPN change. A tendency to return toward centralization is noted in this case; this may cause practitioners to rethink their own DPN growth plans.     

A time-optimal distributed sorting algorithm on a line network

We have achieved a strict lower time bound of n−1 for distributed sorting on a line network, where n is the number of processes. The lower time bound has traditionally been considered to be n because it is proved based on the number of disjoint comparison-exchange operations in parallel sorting on a linear array. Our result has overthrown the traditional common belief.     

.基于GIS的城市道路交通流信息发布系统应用研究*

根据基于GPRS/GPS/GSM浮动车交通流信息采集系统实时采集的交通流瞬时速度、路段速度、车辆定位等信息,借助面向对象技术、GIS技术、数据库技术设计、开发了基于GIS的城市交通流信息发布系统,系统采用数据库中的存储过程技术处理海量交通流信息与GIS信息等数据表的多表连接,实现了高效率信息查询,并融合GIS专题地图技术和数据库技术实现浮动车辆历史轨迹动态回放、交通流路段速度查询、可视化显示。开发的系统在天津市部分路段进行试验,系统能稳定、可靠地实现交通流信息发布,并能快速有效查询城市道路交通流信息及识别城市道路网络路况瓶颈,可以辅助交通管理者进行交通管理决策。     

Decorrelating wireless sensor network traffic to inhibit traffic analysis attacks

Typical packet traffic in a sensor network reveals pronounced patterns that allow an adversary analyzing packet traffic to deduce the location of a base station. Once discovered, the base station can be destroyed, rendering the entire sensor network inoperative, since a base station is a central point of data collection and hence failure. This paper investigates a suite of decorrelation countermeasures aimed at disguising the location of a base station against traffic analysis attacks. A set of basic countermeasures is described, including hop-by-hop reencryption of the packet to change its appearance, imposition of a uniform packet sending rate, and removal of correlation between a packet’s receipt time and its forwarding time. More sophisticated countermeasures are described that introduce randomness into the path taken by a packet. Packets may also fork into multiple fake paths to further confuse an adversary. A technique is introduced to create multiple random areas of high communication activity called hot spots to deceive an adversary as to the true location of the base station. The effectiveness of these countermeasures against traffic analysis attacks is demonstrated analytically and via simulation using three evaluation criteria: total entropy of the network, total overhead/energy consumed, and the ability to frustrate heuristic-based search techniques to locate a base station.