Small-time scale network traffic prediction based on a local support vector machine regression model

In this paper we apply the nonlinear time series analysis method to small-time scale traffic measurement data. The prediction-based method is used to determine the embedding dimension of the traffic data. Based on the reconstructed phase space, the local support vector machine prediction method is used to predict the traffic measurement data, and the BIC-based neighbouring point selection method is used to choose the number of the nearest neighbouring points for the local support vector machine regression model. The experimental results show that the local support vector machine prediction method whose neighbouring points are optimized can effectively predict the small-time scale traffic measurement data and can reproduce the statistical features of real traffic measurements.

A Discrete-Time Traffic and Topology Adaptive Routing Algorithm for LEO Satellite Networks

“Minimizing path delay” is one of the challenges in low Earth orbit (LEO) satellite network routing algo-rithms. Many authors focus on propagation delays with the distance vector but ignore the status information and processing delays of inter-satellite links. For this purpose, a new discrete-time traffic and topology adap-tive routing (DT-TTAR) algorithm is proposed in this paper. This routing algorithm incorporates both inher-ent dynamics of network topology and variations of traffic load in inter-satellite links. The next hop decision is made by the adaptive link cost metric, depending on arrival rates, time slots and locations of source-destination pairs. Through comprehensive analysis, we derive computation formulas of the main per-formance indexes. Meanwhile, the performances are evaluated through a set of simulations, and compared with other static and adaptive routing mechanisms as a reference. The results show that the proposed DT-TTAR algorithm has better performance of end-to-end delay than other algorithms, especially in high traffic areas.

Novel Real-Time System for Traffic Flow Classification and Prediction

Traffic flow prediction has been applied into many wireless communication applications(e.g., smart city, Internet of Things). With the development of wireless communication technologies and artificial intelligence, how to design a system for real-time traffic flow prediction and receive high accuracy of prediction are urgent problems for both researchers and equipment suppliers. This paper presents a novel real-time system for traffic flow prediction. Different from the single algorithm for traffic flow prediction, our novel system firstly utilizes dynamic time wrapping to judge whether traffic flow data has regularity,realizing traffic flow data classification. After traffic flow data classification, we respectively make use of XGBoost and wavelet transform-echo state network to predict traffic flow data according to their regularity. Moreover, in order to realize real-time classification and prediction, we apply Spark/Hadoop computing platform to process large amounts of traffic data. Numerical results show that the proposed novel system has better performance and higher accuracy than other schemes.

Handover Traffic Model and Channel Occupancy Time in LEO Satellite Networks

This paper presents a method of determining handover traffic and mean channel occu-pancy time of a traffic model for the LEO(Low Earth Orbit)satellite networks.The mainideas are that the handover traffic is mainly due to the movement of the satellite and that thevelocity of the mobile terminals and earth rotation are ignored.The performance level can becalculated according to different handover queuing models.

Daily ETC Traffic Flow Time Series Prediction Based on k-NN and BP Neural Network

Daily Electronic Toll Collection(ETC)traffic flow prediction is one of the fundamental processes in ETC management.The precise prediction of traffic flow provides instructions for transportation hub management solution planning and ETC lane construction.At present,some of studies are proposed in forecasting traffic flow.However,most studies of model presentation are in the form of mathematical expressions,and it is difficult to describe the trend accurately.Therefore,an ETC traffic flow prediction model based on k nearest neighbor searching(k-NN)and Back Propagation(BP)neural network is proposed,which takes the effect of external factors like holiday,the free of highway and weather etc.into consideration.The traffic flow data of highway ETC lane somewhere is used for prediction.The prediction results indicate that the total average absolute relative error is 5.01%.The accuracy suggests its advantage in traffic flow prediction and on site application.

Proactive traffic responsive control based on state-space neural network and extended Kalman filter

The state-space neural network and extended Kalman filter model is used to directly predict the optimal timing plan that corresponds to futuristic traffic conditions in real time with the purposes of avoiding the lagging of the signal timing plans to traffic conditions. Utilizing the traffic conditions in current and former intervals, the network topology of the state-space neural network （SSNN）, which is derived from the geometry of urban arterial routes, is used to predict the optimal timing plan corresponding to the traffic conditions in the next time interval. In order to improve the effectiveness of the SSNN, the extended Kalman filter （EKF） is proposed to train the SSNN instead of conventional approaches. Raw traffic data of the Guangzhou Road, Nanjing and the optimal signal timing plan generated by a multi-objective optimization genetic algorithm are applied to test the performance of the proposed model. The results indicate that compared with the SSNN and the BP neural network, the proposed model can closely match the optimal timing plans in futuristic states with higher efficiency.

A Network Traffic Prediction Method Based on LSTM

As the network sizes continue to increase,network traffic grows exponentially.In this situation,how to accurately predict network traffic to serve customers better has become one of the issues that Internet service providers care most about.Current traditional network models cannot predict network traffic that behaves as a nonlinear system.In this paper,a long short-term memory(LSTM)neural network model is proposed to predict network traffic that behaves as a nonlinear system.According to characteristics of autocorrelation,an autocorrelation coefficient is added to the model to improve the accuracy of the prediction model.Several experiments were conducted using real-world data,showing the effectiveness of LSTM model and the improved accuracy with autocorrelation considered.The experimental results show that the proposed model is efficient and suitable for real-world network traffic prediction.

Traffic Forecasting and Planning of WiMAX under Multiple Priority Using Fuzzy Time Series Analysis

Network traffic prediction plays a fundamental role in characterizing the network performance and it is of significant interests in many network applications, such as admission control or network management. Therefore, The main idea behind this work, is the development of a WIMAX Traffic Forecasting System for predicting traffic time series based on the daily and monthly traffic data recorded (TRD) with association of feed forward multi-layer perceptron (FFMLP). The quality of forecasting WIMAX Traffic obtained by comparing different configurations of the FFMLP that consist of investigating different FFMLP model architectures and different Learning Algorithms. The decision of changing the FFMLP architecture is essentially based on prediction results to obtain the FFMLP model for flow traffic prediction model. The different configurations were tested using daily and monthly real traffic data recorded at each of the two base stations (A and B) that belongs to a Libyan WiMAX Network. We evaluate our approach with statistical measurement and a good statistic measure of FMLP indicates the performance of selected neural network configuration. The developed system indicates promising results in which it successfully network traffic prediction through daily and monthly traffic data recorded (TRD) association with artificial neural network.

Performance and robustness analysis of a fuzzy-immune flow controller in ATM networks with time-varying multiple time-delays

For the Asynchronous Transfer Mode （ATM） networks with time-varying multiple time-delays, a more realistic model for the available bit rate （ABR） traffic class with explicit rate feedback is introduced. A fuzzy-immune controller is designed, which can adjust the rates of ABR on-line, overcome the bad effect caused by the saturation nonlinearity and satisfy the weighted fairness. Also, the sufficient condition that guarantees the stability of the closed-loop system with a fuzzy-immune controller is presented in theory for the first time. The algorithm exhibits good performance, and most importantly, has a solid theoretical foundation and can be implemented in practice easily. Simulation results show that the control system is rapid, adaptive, robust, and meanwhile, the quality of service （QoS） is guaranteed.

面向车载时间敏感网络的流量调度策略及改进算法研究

本文面向汽车电子电气架构中的时间敏感网络(TSN)流量调度问题开展研究。针对实际应用需求,提出一种车载TSN网络拓扑建立方法。针对网络中多类型信息流调度问题,提出一种基于时间感知整形器(TAS)机制的流量调度策略并建立相应的数学模型,在降低网络总延时的同时,兼顾高优先级信息流的时间敏感性和低优先级信息流的数据完整性。为解决模型中信息流转发过程复杂导致求解效率不稳定和流量调度方案众多导致寻优困难的问题,提出一种改进的遗传算法(IGA),从设置自适应交叉概率公式、引入禁忌搜索变异、多种群联合3个方面进行了优化。实验结果表明,本文所提出的算法在端到端延时优化方面提升了43.47%,在生成方案稳定性方面提升了76.96%,该算法可得到低延时、高可靠的车载TSN流量调度方案。本文的研究成果为智能网联汽车领域的研究和车载网络通信算法的优化提供了思路。

内河船舶机会性互联的复杂网络模型及其时变特性

针对内河船舶间出现时空邻近的机会性现象开展建模及实证研究。在社会网络分析方法的基础上,提出了1种考虑时序特征的网络分析方法,将大尺度时间跨度上的网络聚类转化为小尺度跨度上的网络聚类,进而分析内河船舶在有限水域内的动态行为;考察船舶间形成邻近关系网络的时变特征,利用复杂网络表示船舶社会网络随时间的演化特性,并借助复杂网络模型对内河水域内存在较多互相熟识船舶的现象给出统计解释。基于长江下游200 km河段1个月的AIS数据,按时隙划分得到网络模型的序列,由此表现船舶间发生单跳数据交换关系的互联形态。实证结果表明:①船舶联网瞬时的度分布可用高斯分布拟合,拟合度在96%以上;②随着时间尺度的增加船舶社会网络的小世界特性和无标度特征愈加明显,网络形态在空间维度上呈现簇团情形,局部密集的组团网络由大部分静止和少量运动船舶连接起来,网络密度随时间缓慢增加至0.1左右,相对平均路径长度稳定在0.2~0.3之间,平均赋权集聚系数呈现缓慢下降的趋势最后趋于0.4~0.5,离散度较快趋向于1,并实现整体上的连通;③度值较高的船舶节点,其平均速度在不同时隙的船舶社会网络中分时段呈现相关性;④相对于船舶密度的增加,船舶在1 d内的平均友邻时间以指数形式递增,而船舶的重复相遇近似服从负指数分布。上述结果表明,内河船舶航行中数据交换关系的建立或断开是由物理空间中船舶间邻近关系的时变性决定的;内河船舶的历史交互行为对未来交互行为具有记忆性并产生影响。

基于改进小波神经网络的实时系统任务流量预测方法

针对当前航空装备实时系统对非周期实时任务无法预知难以实现可靠调度的困难,开展对航空装备实时系统非周期任务流量预测方法的研究。以小波神经网络为基础结合航空装备实时系统的特性建立任务流量预测模型,并提出利用人工鱼群算法对小波预测模型关键参数进行优化,避免陷入局部最优解,最终构建一种人工鱼群算法改进的小波神经网络任务流量预测系统。利用提出的预测模型开展实时任务流量预测对比仿真实验,实验结果表明,建立的基于改进小波神经网络的实时系统任务流量预测系统对非周期实时任务具有较高的预测精度,预测效果优于原始小波神经网络模型及T-S模糊神经网络模型。

时间敏感网络中基于EDWF-MTTF的启发式调度算法

随着工业控制和信息网络的快速融合发展,基于以太网的时间敏感网络受到了广泛关注。时间敏感网络采用时间触发通信调度来保证数据传输的确定性。然而,现有调度算法难以快速计算大规模周期性流量的调度表。因此,设计了基于带权重的最早截止时间-最大传输时间优先的启发式调度算法,通过灵活适配流量排序权重以及回溯增强等方法,可以在较短时间内解决工业自动化场景中大规模流量的调度问题。实验结果表明,相比经典整数线性规划方法,带权重的最早截止时间-最大传输时间优先的启发式调度算法能更快地计算出大规模周期性流量调度表的较优解。

基于复杂网络的空中交通流量短期预测

为合理预测空中交通流量,结合复杂网络链路预测进行研究。首先,将时间序列转化为可视图得到拓扑特征量,然后结合基于局部信息、路径和随机游走的算法,比较在三亚不同扇区内的预测精度,发现RWR0.85算法预测精度最高。由于链路预测只能预测可能存在的连边,不能预测节点,因此引入D⁃S证据理论预测流量值,预测精度最高可达99.85%。结果表明,复杂网络链路预测结合D⁃S证据理论进行空中交通流量的预测是可行有效的,为进一步深入研究奠定了基础。

基于矢量量化IFTS的网络流量预测模型

针对传统网络流量预测模型存在的局限性,提出一种基于矢量量化直觉模糊时间序列的网络流量预测模型。利用模糊直觉推理有效地表述了网络流量数据中存在的高度模糊性以及不确定性,利用直觉模糊时间序列矢量距离作为评估标准,并且通过坐标平移与质心进行匹配,提升不同时间序列段的分类能力,从而有效地建立网络流量预测模型。通过实验分析可知,提出的预测模型能够提升预测精度并且减少计算复杂度,另外该算法有能力长期预测多个输出。

基于HPO-LSTM的公交周转时间预测

公交周转时间的准确预测是公交智能排班的基础和前提,是制定行车时刻表的关键。为提高公交周转时间的预测精度,提出了基于猎人猎物优化长短时记忆神经网络(HPO-LSTM)的公交周转时间预测模型,将长短时记忆神经网络(LSTM)中的超参数(隐含层节点数、迭代循环数以及初始学习率)映射为猎人猎物优化算法(HPO)种群的位置;以LSTM模型预测值与真实值产生的均方根误差E_(RMS)作为种群适应度函数,优化种群位置,实现LSTM神经网络超参数寻优;用最优超参数构建LSTM神经网络,进行公交周转时间预测。采用某市公交1号线数据对模型进行验证分析,结果表明:相比于BP、LSTM、FA-BP、HPO-BP模型,HPO-LSTM模型平均绝对百分比误差E_(MAP)分别降低10.44%、4.00%、3.61%、2.04%。

民航客运量预测方法研究综述

为了提升民航运行效率、准确预测客运量,促进其可持续发展,采用分类学方法将民航客运量预测方法划分为传统统计学、机器学习、组合模型3大类。详述各类方法的改进原理、效果和应用,通过数据处理、权重调整、参数优化和结构改进提高准确性,并总结组合模型相对单一模型的优势。实证研究结果表明,组合预测模型相较于单一模型具有更高的准确性,并指出结合人工智能和大数据技术的发展趋势,构建优秀的组合预测模型将是提高准确性的潜在研究方向。

考虑负荷时空均衡和弹性响应的电动汽车快充电价定价策略

为了引导电动汽车有序充电,提出了一种考虑负荷时空均衡和弹性响应的电动汽车快充电价定价策略。引入交通流理论描述交通路网,建立电动汽车快充负荷时空分布模型;考虑配电网调度和电动汽车快充负荷的弹性需求,构建源-荷互动下的快充电价定价架构,并基于潮流追踪法从时空双维度推导快充电价的计算方法;在此基础上,计及电动汽车负荷弹性响应特性,以提升配电网的负荷均衡性为目标,建立快充电价定价策略,并通过迭代算法求解该定价策略。算例仿真结果表明,所提定价策略能够有效引导电动汽车进行有序快充,激励电动汽车用户与配电网友好互动,提升负荷的时空分布均衡性。

基于时间敏感网络的列车通信网络实时流量调度优化

随着轨道交通智能化的发展,列车控制与监测产生的高带宽实时数据对列车通信网络提出了更高的要求。时间敏感网络可作为兼具高传输速率、高确定性和高兼容性的下一代列车通信网络解决方案。然而,实现时间敏感网络确定性通信机制的流量门控调度设计难以拓展到实际场景规模。因此,针对车载网络流量特性,提出一种基于改进增量式调度策略和改进灰狼优化算法的列车通信网络流量门控调度生成方法。首先,基于列车通信网络流量和拓扑结构建立门控调度系统模型。然后,为提高调度生成效率,提出了基于增量式调度的单帧简易调度(Single Frame Simple Scheduling,SFSS)策略,弥补了门控调度模型在计算速度方面的不足。其次,为提高灰狼优化算法的寻优性能,引入了粒子群优化算法、Logistic混沌映射策略和反正切函数,提出了改进灰狼优化(Improved Grey Wolf Optimization,IGWO)算法,改善了实时周期性流量的实时性能和带宽占用。最后,利用SFSS策略和IGWO算法对列车通信网络门控调度系统模型进行测试和求解,通过实验验证所提出调度生成方法的可行性和有效性。实验结果表明,与其他方法相比,提出的门控调度生成方法在计算精度和计算速度方面具有更大的优势,流量调度的平均端到端时延降低为57μs。研究成果能够满足列车通信网络流量调度的需求,可有效地实现时间敏感网络确定性通信在列车中的应用和改善。

时空图神经网络在交通流预测研究中的构建与应用综述

交通流量预测是城市交通管理和规划中的关键问题,而传统预测方法在面对数据稀疏性、非线性关系和复杂动态性等挑战时表现不佳。图神经网络是一种基于非欧结构数据的深度学习方法,近年来在各种复杂网络建模和预测任务中得到广泛应用。为了应用于交通流量预测领域,提出了时空图神经网络,其能够捕捉空间和时间相关性,相较之前的预测模型有显著进步。对近年来使用时空图神经网络进行交通流量预测的模型进行分析,概述和比较了多种邻接阵的构造方式,然后从空间相关性和时间相关性的角度列举了构建交通流预测模型的常用组件,并对不同的时空融合方式进行了分类和对比;在应用方面,根据时间尺度的不同将时空图神经网络模型分为长期预测、短期预测与兼顾长短期的预测三类,分析了各自的目标与要求,并列举比较了近年来较为突出的新模型。最后,讨论了现有研究的局限性,对相关模型的未来研究做出展望。