An approach for failure recognition in IP‐based industrial control networks and systems

Industrial control networks (ICNs) and systems support robust communications of devices in process control or manufacturing environments. ICN proprietary protocols are being migrated to Ethernet/IP networks in order to merge various different types of networks into a single common network. ICNs are deployed in mission‐critical operations, which require a maximum level of network stability. Network stability is often described using several categories of network performance quality‐of‐service metrics, such as throughput, delay, and loss measurements. The question arises as to whether these network performance metrics are sufficient to run valuable diagnostics of ICN components and their communications. Any abnormal decision with respect to typical IP traffic behavior does not necessarily coincide with ICN fault cases. A precise and specific diagnostic technique for ICNs is required to remove the uncertainty in detecting problems. However, existing Ethernet/IP diagnosis tools have not been able to fully handle fault symptoms and mainly focus on network diagnostics rather than process or device diagnostics. This paper demonstrates that the absence of advanced fault diagnosis techniques leads to the development of new methodologies that are suitazble for ICN. We describe unique traffic characteristics and categorize the faults of ICN. We also propose a fault diagnosis, prediction, and adaptive decision methodologies, and verify them with real‐world ICN data from the steel‐making company POSCO. Our experience in developing the fault diagnosis system provides a firm guideline to understand the fault management mechanisms in large ICNs. Copyright © 2012 John Wiley & Sons, Ltd.     

一种基于小波变换和FIR神经网络的广域网网络流量预测模型

该文提出了一种基于小波变换和FIR神经网络的广域网网络流量预测模型,首先采用小波分解把网络流量数据分解成小波系数和尺度系数,即高频系数和低频系数,将这些不同频率成分的系数单支重构为高频流量分量和低频流量分量,利用FIR神经网络对这些分量分别进行预测,将合成之后的结果作为原始网络流量的预测。实验结果表明:采用该模型对实际的广域网网络流量数据进行预测,不仅可以得到较快的收敛效果,而且预测性能比现有的小波神经网络和FIR神经网络要好得多。     

基于神经网络的网络流量预测算法研究

网络流量预测有助于网络服务质量的提升和网络资源的合理分配,对优化网络管理与运营、保障用户体验质量至关重要.因特网业务的急剧增加和基础网络的快速发展导致网络流量变得更加复杂多样,传统网络流量预测模型难以保证较高的预测精度,而神经网络作为人工智能的重要分支,在预测复杂网络流量时具有显著优势.简述反向传播神经网络、径向基神经...     

Network traffic prediction based on INGARCH model

In this paper, we introduce the integer-valued generalized autoregressive conditional heteroscedasticity (INGARCH) as a network traffic prediction model. As the INGARCH is known as a non-linear analytical model that could capture the characteristics of network traffic such as Poisson packet arrival and long-range dependence property, INGARCH seems to be an adequate model for network traffic prediction. Based on the investigation for the traffic arrival process in various network topologies including IoT and VANET, we could confirm that assuming the Poisson process as packet arrival works for some networks and environments of networks. The prediction model is generated by estimating parameters of the INGARCH process and predicting the Poisson parameters of future-steps ahead process using the conditional maximum likelihood estimation method and prediction procedure, respectively. Its performance is compared with those of three different models; autoregressive integrated moving average, GARCH, and long short-term memory recurrent neural network. Anonymized passive traffic traces provided by the Center for Applied Internet Data Analysis are used in the experiment. Numerical results show that the proposed model predicts better than the three models in terms of measurements used in prediction models. Based on the study, we can conclude the followings: INGARCH can capture the characteristics of network traffic better than other statistic models, it is more tractable than neural networks (NNs) overcoming the black-box nature of NNs, and the performances of some statistical models are comparable or even superior to those of NNs, especially when the data is insufficient to apply deep NNs.

     

Methodologies for characterizing traffic in wide area networks: Analysis and benchmarking

Since computer networks play an important role in distributed computing environments, an application's performance depends heavily on the quality of service provided by the communication networks. To ensure a high performance, the characteristics of wide area networks, WANs, must be well understood. This paper presents methodologies to characterize WAN traffic based on real measurements from Bellcore's backbone network that connects remote sites using dedicated T1 links. This paper also suggests some workload models that can be used for wide area network sizing and performance evaluation studies. It is found that the inter-site traffic pattern depends on the time of the day and the day of the week. Furthermore, the traffic between two sites is found to be reasonably symmetric, except for those sites designated as back-up sites. The coefficient of variation is used as a measure for the traffic burstiness and it is found to be 1·5 degree during working hours. The methods presented here are easy to use and cost-effective.     

Research on fuzzy neural network algorithms for nonlinear network traffic predicting

Neural networks provide massive parallelism,robust-ness ,and approxi mate reasoning,which are i mportantfor dealing with uncertain,inexact ,and ambiguous data,withill-defined problems and sparse data sets[1].It hasbeen proved that a neural network system …     

Metro WDM networks: performance comparison of slotted ring and AWG star networks

Both wavelength-division-multiplexing (WDM) networks with a ring architecture and WDM networks with a star architecture have been extensively studied as solutions to the ever increasing amount of traffic in the metropolitan area. Studies typically focus on either the ring or the star and significant advances have been made in the protocol design and performance optimization for the WDM ring and the WDM star, respectively. However, very little is known about the relative performance comparisons of ring and star networks. In this paper, we conduct a comprehensive comparison of a state-of-the-art WDM ring network with a state-of-the-art WDM star network. In particular, we compare time-slotted WDM ring networks (both single-fiber and dual-fiber) with tunable-transmitter and fixed-receiver (TT-FR) nodes and an arrayed-waveguide grating-based single-hop star network with tunable-transmitter and tunable-receiver (TT-TR) nodes. We evaluate mean aggregate throughput, relative packet loss, and mean delay by means of simulation for Bernoulli and self-similar traffic models for unicast traffic with uniform and hot-spot traffic matrices, as well as for multicast traffic. Our results quantify the fundamental performance characteristics of ring networks versus star networks and vice versa, as well as their respective performance limiting bottlenecks and, thus, provide guidance for directing future research efforts.     

基于神经网络模型的网络流量预测综述

网络流量预测技术可以帮助运营商准确预估网络的使用情况,合理分配并高效利用网络资源,以满足日益增长且多样化的用户需求。大量研究表明,神经网络的预测性能高于其他经典预测方法,在网络流量预测中的应用潜力巨大。总结网络流量预测的一些关键因素和预测误差评判方法,重点介绍近年提出的可用于预测的神经网络模型原理、相关预测方法及其属性比较,旨在为包括流量在内的各种网络参数预测技术的学术研究与实际应用提供可借鉴的方法和手段。     

Tracking Traffic Peaks in Mobile Networks Using Statistics of Performance Metrics

In recent years, there has been an increasing awareness to tracking traffic peaks reflecting the presence of mass events or permanent traffic hotspots. This trend is driven by dominant themes for wireless evolution towards 5G networks such as the problematic of hotspot offloading solutions, the emergence of heterogeneous networks with small cells’ deployment and the development of green networks’ concept. Actually, tracking traffic peaks with a high accuracy is of great interest to know how the congested zones can be offloaded, where small cells should be deployed and how they could be managed for sleep mode concept or even controlled according to traffic mobility if they are moving. In this paper, we propose a method for tracking peaks of traffic using performance metrics extracted from the operation and maintenance database of the network. These metrics are the timing advance, the angle of arrival, the neighboring cell level, the cell load and two mean throughputs: arithmetic (AMT) and harmonic (HMT). The combined use of these performance metrics, projected over a coverage map, yields a promising traffic localization precision even with considering imperfections of coverage prediction and mobile equipment capabilities in handling measurements. The proposed solution can be easily implemented in the network at an appreciable low cost.     

Exploiting IP‐layer traffic prediction analytics to allocate spectrum resources using swarm intelligence

Elastic optical networks emerge as a reliable backbone platform covering the next‐generation connectivity requirements. It consists of advanced enabling components that provide the ability for extensive configuration leading to performance improvement in many areas of interest. Higher layer analytics like data from IP traffic prediction can assist in the process of allocating resources at the optical layer. This way, light connections are established more efficiently while targeting specific performance goals. For that purpose, an algorithm is designed and evaluated that exploits traffic prediction of data transfers between nodes of an optical metro or backbone network. Next, it utilizes adaptive functionality based on particle swarm optimization to find paths with available spectrum resources. These resources can facilitate more efficiently the future traffic demand, since traffic prediction data are considered when finding the related paths. The innovative resource allocation method is evaluated using small and very large real topologies. It scales (in execution time and resource usage) according to node increase, executes in feasible time frames, and reduces transponder utilization resulting to increased energy efficiency.     

Real-time VBR video traffic prediction for dynamic bandwidth allocation

In this paper, we systematically investigate the long-term, online, real-time variable-bit-rate (VBR) video traffic prediction, which is the key and complicated component for advanced predictive dynamic bandwidth control and allocation framework for the future networks and Internet multimedia services. We focus on neural network-based approach for traffic prediction and demonstrate that the prediction performance and robustness of neural network predictors can be significantly improved through multiresolution learning. We show that neural network traffic predictor trained through the multiresolution learning (called multiresolution learning NN traffic predictor) can successfully predict various real-world VBR video traffic up to hundreds of frames in advance, which then lays a solid foundation for predictive dynamic bandwidth control and allocation mechanism. Also, dynamic bandwidth control/allocation based on long-term traffic prediction is discussed in detail.     

Evaluation of neural network architectures for MPEG-4 video traffic prediction

Multimedia applications and particularly MPEG-coded video streams are becoming major traffic components in high speed networks. Traffic prediction is important in enhancing the reliable operation over these networks. However, MPEG video traffic exhibits periodic correlation structure and a complex bit rate distribution, making prediction difficult. Neural networks can effectively be used to overcome such problem. In the literature, the problem has been mostly evaluated using standard feed-forward neural networks. However, a significant improvement can be expected using different types of neural networks. In this paper, six separate neural network predictors (including feed-forward) that can predict the basic frame types of MPEG-4: I, P, and B are developed and evaluated using long entertainment and broadcast video sequences. The performance is also compared to the widely used linear predictor. Comparison with results published in a recent work is also presented.     

Effective Energy Adaptive and Consumption in Wireless Sensor Network Using Distributed Source Coding and Sampling Techniques

Multimedia is the process of handling multiple medium of messages over network with high rate data services in wireless cellular area networks. Communication is the process of exchanging information form one service to another. In wireless networks are significantly growth of affecting network performance and energy consumption. The major problem is end to end delay in each node and meets the quality of services. The followings are considered for implementing wireless sensor network such as reduces the network delay, propagation delay and energy consumption. The senor node can sense the encoding value and reduce the network traffic delay using mitigation method. This paper propose a unique approach to provide simple routing services with reduced traffic delay, end to end delay network performance and to achieve better performance using Distributed Source Coding and Effective Energy Consumption methods. In this paper we use optimal early detection algorithm for improving network performance and energy consumption problem. An iterative Shannon fano and Tuker method is used for finding optimal solution of each node values. Network Simulator-3 is used for simulating network environments and setup the experiments. Our proposed method shows high data rate, good performance and low energy consumptions. The results compare with existing methodologies and performance is good.

     

改进的变权组合业务量预测应用方法

对预测误差平方和最小为原则的固定权重最优组合预测模型进行改进,提出了一种应用于移动通信网业务量预测的变权组合预测方法。通过4种预测方法对某地业务量进行预测并比较其精确度,结果表明改进的变权组合预测方法取得了较高的预测精确度。     

小波神经网络在短时交通流量预测中的应用

随着交通基础设施建设和智能运输系统的发展,交通规划和交通诱导成为交通领域的研究热点,对交通规划和交通诱导而言,准确的交通流量预测是其实现的前提和关键。短时交通流量预测是一个时间序列预测问题,文中应用小波神经网络对短时交通流量进行了预测。首先,对神经网络、小波分析等相关理论进行了简要介绍。在此基础上,采用5-7-1小波神经网络结构,以Morlet小波基函数作为隐含层节点的传递函数,将车流量数据输入该模型中,以训练小波神经网络,并用训练好的神经网络来预测短时交通流量。从预测结果来看,小波神经网络的预测结果较为准确,网络预测值接近期望值,效果较好。     

基于混沌预测的宽带DVB-RCS卫星接入信道动态分配方案研究

该文概述了基于卫星数字视频广播-反向信道系统(DVB-RCS)标准的宽带卫星通信网的特点,并重点研究了多址接入信道的动态分配策略,在利用混沌理论对网络中的自相似业务流量进行预测的基础上,提出了一种新型混合按需分配多址接入方案。该文还利用OPNET软件建立了仿真系统,用于比较不同方案的性能。仿真结果表明,在高信道负载以及网络中业务流具有较高自相似程度的条件下,该文所提出方案具有更优越的性能。     

VoIP traffic in wireless mesh networks: a MOS‐based routing scheme

Support of Voice over Internet Protocol (VoIP) services in wireless mesh networks requires implementation of efficient policies to support low‐delay data delivery. Multipath routing is typically supported in wireless mesh networks at the network level to provide high fault tolerance and load balancing because links in the proximity of the wireless mesh gateways can be very stressed and overloaded, thus causing scarce performance. As a consequence of using multipath solutions, lower delay and higher throughput can be supported also when a given path is broken because of mobility or bad channel conditions, and alternative routes are available. This can be a relevant improvement especially when assuming that real‐time traffic, such as VoIP, travels into the network. In this paper, we address the problem of Quality of Service (QoS) support in wireless mesh networks and propose a multipath routing strategy that exploits the Mean Opinion Score (MOS) metric to select the most suitable paths for supporting VoIP applications and performing adaptive load balancing among the available paths to equalize network traffic. Performance results assess the effectiveness of the proposed approach when compared with other existing methodologies. Copyright © 2015 John Wiley & Sons, Ltd.     

Reminder on queueing theory for ATM networks

Queueing theory is a very useful means for performance prediction during the system design phase, for resource dimensioning and for planning of networks according to load andquality of service figures. In this paper, an overview is given about traffic models for ATM traffic sources, generic ATM traffic control models and performance evaluation methods.     

Cooperative load-balancing strategy based on N-hops routing algorithm of ad hoc network in heterogeneous overlapping networks

A major challenge of the heterogeneous wireless networks is how to jointly utilize the resources of different radio access technologies in an efficient manner. In this paper, system performance, such as the block probability and throughput, was investigated in communication hot spots overlapped by heterogeneous networks: cellular, WLAN, and WiMax networks. Two cooperative load-balancing strategies based on hops-limited routing algorithm of ad hoc network are proposed in order to raise the resource utilization of the whole overlapping heterogeneous networks. They both firstly make a decision whether to admit a new call or not based on common radio resource management strategies, and in overloaded condition, select certain traffic to transfer into targeted BS/AP according to minimum price strategy or minimum load BS/AP and nearest traffic strategy, which take into account these factors such as load index, number of hops, traffic prediction, cost, etc. An analytical model is used to compute the call block probability and throughput performance for two different traffic models. Simulation results show that the proposed load-balancing strategies can distribute traffics to the whole heterogeneous wireless networks, decrease the call block probability, improve system throughputs efficiently, and obviously outperform HM-MACA and HS-TC load-balancing strategies.