PGSLM:Edge-Enabled Probabilistic Graph Structure Learning Model for Traffic Forecasting in Internet of Vehicles

With the rapid development of the 5G communications,the edge intelligence enables Internet of Vehicles(IoV)to provide traffic forecasting to alleviate traffic congestion and improve quality of experience of users simultaneously.To enhance the forecasting performance,a novel edge-enabled probabilistic graph structure learning model(PGSLM)is proposed,which learns the graph structure and parameters by the edge sensing information and discrete probability distribution on the edges of the traffic road network.To obtain the spatio-temporal dependencies of traffic data,the learned dynamic graphs are combined with a predefined static graph to generate the graph convolution part of the recurrent graph convolution module.During the training process,a new graph training loss is introduced,which is composed of the K nearest neighbor(KNN)graph constructed by the traffic feature tensors and the graph structure.Detailed experimental results show that,compared with existing models,the proposed PGSLM improves the traffic prediction performance in terms of average absolute error and root mean square error in IoV.

Traffic Forecasting Model Based on Takagi-Sugeno Fuzzy Logical System

The local multiple regression fuzzy(LMRF)model based on Takagi-Sugeno fuzzy logical system and its application in traffic forecasting is proposed. Besides its prediction accuracy is testified and the model is proved much better than conventional forecasting methods. According to the regional traffic system, the model perfectly states the complex non-linear relation of the traffic and the local social economy. The model also efficiently deals with the system lack of enough data.

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.

CALTM:A Context-Aware Long-Term Time-Series Forecasting Model

Time series data plays a crucial role in intelligent transportation systems.Traffic flow forecasting represents a precise estimation of future traffic flow within a specific region and time interval.Existing approaches,including sequence periodic,regression,and deep learning models,have shown promising results in short-term series forecasting.However,forecasting scenarios specifically focused on holiday traffic flow present unique challenges,such as distinct traffic patterns during vacations and the increased demand for long-term forecastings.Consequently,the effectiveness of existing methods diminishes in such scenarios.Therefore,we propose a novel longterm forecasting model based on scene matching and embedding fusion representation to forecast long-term holiday traffic flow.Our model comprises three components:the similar scene matching module,responsible for extracting Similar Scene Features;the long-short term representation fusion module,which integrates scenario embeddings;and a simple fully connected layer at the head for making the final forecasting.Experimental results on real datasets demonstrate that our model outperforms other methods,particularly in medium and long-term forecasting scenarios.

Comparison of Several Traffic Forecasting Methods Based on Travel Time Index Data on Weekends

Traffic forecasting provides the estimation of future traffic state to help traffic control,travel guide,etc. This paper compared several widely used traffic forecasting methods,and analyzed each one's performance in detail to make conclusions,which could redound to researchers choosing an appropriate traffic forecasting method in their own works. Compared with conventional works,this paper creatively assessed the performance of traffic forecasting methods based on travel time index (TTI) data prediction,which made the accuracy of our comparison better.

Geospatial Data to Images: A Deep-Learning Framework for Traffic Forecasting

Traffic forecasting has been an active research field in recent decades, and with the development of deeplearning technologies, researchers are trying to utilize deep learning to achieve tremendous improvements in traffic forecasting, as it has been seen in other research areas, such as speech recognition and image classification. In this study, we summarize recent works in which deep-learning methods were applied for geospatial data-based traffic forecasting problems. Based on the insights from previous works, we further propose a deep-learning framework,which transforms geospatial data to images, and then utilizes the state-of-the-art deep-learning methodologies such as Convolutional Neural Network(CNN) and residual networks. To demonstrate the simplicity and effectiveness of our framework, we present a formulation of the New York taxi pick-up/drop-off forecasting problem, and show that our framework significantly outperforms traditional methods, including Historical Average(HA) and AutoRegressive Integrated Moving Average(ARIMA).

A Short-Term Traffic Flow Forecasting Method Based on a Three-Layer K-Nearest Neighbor Non-Parametric Regression Algorithm

Short-term traffic flow is one of the core technologies to realize traffic flow guidance. In this article, in view of the characteristics that the traffic flow changes repeatedly, a short-term traffic flow forecasting method based on a three-layer K-nearest neighbor non-parametric regression algorithm is proposed. Specifically, two screening layers based on shape similarity were introduced in K-nearest neighbor non-parametric regression method, and the forecasting results were output using the weighted averaging on the reciprocal values of the shape similarity distances and the most-similar-point distance adjustment method. According to the experimental results, the proposed algorithm has improved the predictive ability of the traditional K-nearest neighbor non-parametric regression method, and greatly enhanced the accuracy and real-time performance of short-term traffic flow forecasting.

Short-term traffic forecasting based on principal component analysis and a generalized regression neural network for satellite networks

With the rapid growth of satellite traffic, the ability to forecast traffic loads becomes vital for improving data transmission efficiency and resource management in satellite networks. To precisely forecast the short-term traffic loads in satellite networks, a forecasting algorithm based on principal component analysis and a generalized regression neural network （PCA-GRNN） is proposed. The PCA-GRNN algorithm exploits the hidden regularity of satellite networks and fully considers both the temporal and spatial correlations of satellite traffic. Specifically, it selects optimal time series of spatio-temporally correlated historical traffic from satellites as forecasting inputs and applies principal component analysis to reduce the input dimensions while preserving the main features of the data. Then, a generalized regression neural network is utilized to perform the final short-term load forecasting based on the obtained principal components. The PCA-GRNN algorithm is evaluated based on real-world traffic traces, and the results show that the PCA-GRNN method achieves a higher forecasting accuracy, has a shorter training time and is more robust than other state-of-the-art algorithms, even for incomplete traffic datasets. Therefore, the PCA- GRNN algorithm can be regarded as a preferred solution for use in real-time traffic forecasting for realistic satellite networks.

Research on traffic flow forecasting model based on cusp catastrophe theory

This paper intends to describe the relationship between traffic parameters by using cusp catastrophe theory and to deduce highway capacity and corresponding speed forecasting value through suitable transformation of catastrophe model. The five properties of a catastrophe system are outlined briefly, and then the data collected on freeways of Zhujiang River Delta, Guangdong province, China are examined to ascertain whether they exhibit qualitative properties and attributes of the catastrophe model. The forecasting value of speed and capacity for freeway segments are given based on the catastrophe model. Furthermore, speed-flow curve on freeway is drawn by plotting out congested and uncongested traffic flow and the capacity value for the same freeway segment is also obtained from speed-flow curve to test the feasibility of the application of cusp catastrophe theory in traffic flow analysis. The calculating results of catastrophe model coincide with those of traditional traffic flow models regressed from field observed data, which indicates that the deficiency of traditional analysis of relationship between speed, flow and occupancy in two-dimension can be compensated by analysis of the relationship among speed, flow and occupancy based on catastrophe model in three-dimension. Finally, the prospects and problems of its application in traffic flow research in China are discussed.

Traffic Assignment Forecast Model Research in ITS

As an important role in the development of ITS, traffic assignment forecast is always the research focus. Based on the analysis of classic traffic assignment forecast models, an improved traffic assignment forecast model, multi-ways probability and capacity constraint (MPCC) is presented. Using the new traffic as- signment forecast model to forecast the traffic volume will improve the rationality and veracity of traffic as- signment forecast.

Traffic simulation and forecasting system in Beijing

Transport system is a time-varying, huge and complex system. In order to have the traffic management department make pre-appropriate traffic management measures to adjust the traffic management control program, and release travel information to travelers, to provide optimal path options to ensure that the transport system operates efficiently and safely, we have to monitor the changing of the state of road traffic and to accurately evaluate the state of the traffic, then to predict the future state of traffic. This paper represents the construction of the road traffic flow simulation including the logical structure and the physical structure, and introduces the system functions of forecasting system in Beijing.

Flow Direction Level Traffic Flow Prediction Based on a GCN-LSTM Combined Model

Traffic flow prediction plays an important role in intelligent transportation systems and is of great significance in the applications of traffic control and urban planning.Due to the complexity of road traffic flow data,traffic flow prediction has been one of the challenging tasks to fully exploit the spatiotemporal characteristics of roads to improve prediction accuracy.In this study,a combined flow direction level traffic flow prediction graph convolutional network(GCN)and long short-term memory(LSTM)model based on spatiotemporal characteristics is proposed.First,a GCN model is employed to capture the topological structure of the data graph and extract the spatial features of road networks.Additionally,due to the capability to handle long-term dependencies,the longterm memory is used to predict the time series of traffic flow and extract the time features.The proposed model is evaluated using real-world data,which are obtained from the intersection of Liuquan Road and Zhongrun Avenue in the Zibo High-Tech Zone of China.The results show that the developed combined GCNLSTM flow direction level traffic flow prediction model can perform better than the single models of the LSTM model and GCN model,and the combined ARIMA-LSTM model in traffic flow has a strong spatiotemporal correlation.

数据驱动的新能源公交车能耗预测

鉴于现有电动车能耗预测多基于实验室条件,存在结果过于理想化或预测准确度不足的问题。本文基于北京市51路公交车的实车运行数据,分析能耗影响因素,通过时钟循环编码优化时间信息、使用箱线图设置阈值以构造行驶工况、建立基于熵权法的驾驶行为评价体系对驾驶行为与工况状态进行辅助分析,最后,对聚类后的4类典型工况片段分别建立引入注意力机制的LSTM能耗预测模型,并将其与传统LSTM及LGBM等多种预测模型进行对比分析,验证结果表明引入注意力机制的LSTM预测模型性能显著高于其他模型。

基于时空图网络的空中交通流量预测研究

准确的空中交通流量预测对航空运输管理和飞行安全保障有至关重要的意义。然而,空中流量存在复杂时间波动模式,并且不同机场之间存在依赖关系,给空中交通流量的精确预测带来了巨大的挑战。提出基于时空图网络的空中交通流量预测方法,捕获空中流量的时间变化模式和不同机场之间的依赖关系,从而实现精准的空中交通流预测。在空间特征学习模块,通过对机场之间关系进行建模,采用常微分方程提取机场之间的依赖关系。在时间特征学习模块中,引入了高效的重构器表征空中交通流的长程时间相关性。在Airline On-Time Performance Data数据集,该方法在未来6 h、9 h、12 h预测实验的加权平均绝对百分比误差分别为35.51%、36.54%、35.55%,性能明显优于已有预测方法。

基于缺失数据的交通速度预测算法

交通速度预测是智能交通系统的基础,可以缓解交通拥堵,节约公共资源,提高人们的生活质量。在真实情况下,采集到的交通速度数据通常存在缺失,而现有研究成果大多数只考虑了数据相对完整的场景。文章主要针对缺失场景下的交通速度数据进行研究,捕捉其中的时空相关性,并对未来交通速度进行预测。为了充分利用到交通数据的时空特征,提出了一种新的基于深度学习的交通速度预测模型。首先,提出了“还原-预测”算法,先使用自监督学习方法让模型还原缺失数据,再对交通速度进行预测;其次,引入了对比学习的方法,使得速度时间序列的特征表示更鲁棒;最后,模拟了不同数据缺失率的场景,通过实验验证了所提方法在各种缺失率下的预测准确率都优于现有方法,并设计了实验对对比学习方法和不同的还原算法进行分析,证明了所提方法的有效性。

结合自相关注意力动态卷积的交通预测网络

交通流量预测作为智能交通系统(ITS)的重要任务之一,受到极大关注,其常被建模为时空序列预测问题,准确把握交通数据的时间-空间相关性成为了解决此问题的关键,现有的工作往往采用循环神经网络以捕获时间依赖性,采用图卷积网络以捕获空间依赖性,两者尚未有机的结合且捕获时空依赖的能力有限,导致预测精度不佳.本文提出了用于交通预测的基于自相关注意力和动态卷积的时空网络(AADCSN),设计采用类Transformer架构,结合自相关注意力与动态学习图卷积有效捕获交通数据的时间特征与空间特征,并引入数据蒸馏技术和多种嵌入表示有效提升预测性能.论文选用4个真实数据集和9个先进的基线方法进行比较,实验结果表明,本文提出的模型在几乎所有对比指标上都优于基线模型.

基于双路先验自适应图神经常微分方程的交通流预测

准确的交通流量预测是智能交通系统不可或缺的组成部分。近年来,图神经网络在交通流预测任务中取得了较好的预测结果。然而,图神经网络的信息传递是不连续的潜在状态传播,且随着网络层数的增加存在过平滑的问题,这限制了模型捕获远距离节点的空间依赖关系的能力。同时,在表示道路网络的空间关系时,现有方法大多仅使用先验知识构建的预定义图或仅使用路网状况构建的自适应图,忽略了两类图结合的方式。针对上述问题,提出了一种基于双路先验自适应图神经常微分方程的交通流预测模型。利用时间卷积网络捕获序列的时间相关性,使用先验自适应图融合模块表示道路网络的空间关系,并通过基于张量乘法的神经常微分方程以连续的方式传播复杂的时空特征。最后,在美国加利福尼亚州4个公开的高速公路流量数据集上进行对比实验,结果表明所提模型的预测效果优于现有的10种对比方法。

基于图自编码器和GRU网络的分层交通流预测模型

准确的交通流预测信息不仅可以为交通管理人员提供交通决策的坚实基础,还可以减少交通拥堵情况。在交通流预测任务中,获得有效的交通流的时空特性是保证预测效果的前提。现有的方法大多是用未来时刻的数据进行监督学习,提取的特征具有局限性。针对现有预测模型无法充分挖掘交通流的时空特性的问题,提出了基于改进的图自编码器和门控循环单元的分层交通预测模型。首先使用图注意力自编码器以无监督的方式深度挖掘交通流的空间特性,然后使用门控循环单元进行时间特征提取。分层结构采用分开训练的方式进行时空依赖关系的学习,旨在获取路网天然存在的空间拓扑特征,使其可以兼容不同时间步下的交通流预测任务。大量实验证明,所提出的GAE-GRU模型在不同数据集下的交通预测任务中取得了优异的表现,MAE,RMSE和MAPE指标均优于基线模型。

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。