Network-wide Travel Time Research Articles

Flow prediction of mountain cities arterial road network for real-time regulation

This study aims to enhance the understanding of vehicle path selection behavior within arterial road networks by investigating the influencing factors and analyzing spatial and temporal traffic flow distributions. Using radio frequency identification (RFID) travel data, key factors such as travel duration, route familiarity, route length, expressway ratio, arterial road ratio, and ramp ratio were identified. We then proposed an origin–destination path acquisition method and developed a route-selection prediction model based on a multinomial logit model with sample weights. Additionally, the study linked the traffic control scheme with travel time using the Bureau of Public Roads function—a model that illustrates the relationship between network-wide travel time and traffic demand—and developed an arterial road network traffic forecasting model. Verification showed that the prediction accuracy of the improved multinomial logit model increased from 92.55 % to 97.87 %. Furthermore, reducing the green time ratio for multilane merging from 0.75 to 0.5 significantly decreased the likelihood of vehicles choosing this route and reduced the number of vehicles passing through the ramp. The flow prediction model achieved a 97.9 % accuracy, accurately reflecting actual volume changes and ensuring smooth operation of the main airport road. This provides a strong foundation for developing effective traffic control plans.

Equilibrium condition-based optimization models for network-wide travel time estimation using limited observed data

This paper presents a series of optimisation models to estimate network-wide travel times under equilibrium conditions. The proposed models estimate the upper and lower bounds (ULB) of the maximum total travel time (MTTT), path travel time (PTT), and link travel time (LTT). The uncertainty range of travel time is obtained by subtracting the upper bound of travel time from the corresponding lower bound. To minimise the uncertainty ranges of the estimated travel times, the relationship of PTTs is introduced as a generalised equilibrium condition. Numerical experiments show that adopting the equilibrium condition can minimise the uncertainty ranges of the travel time estimation. The proposed method can also more accurately estimate the travel times even when the observed data are limited in the entire network. These findings provide a basis for further research on the travel time observability problem of travel time estimation for the whole territory of the network.

A generative adversarial network-based framework for network-wide travel time reliability prediction

This paper introduces a generative model named the travel time reliability-generative adversarial network (TTR-GAN) model for predicting network-wide TTR using automatic vehicle identification data. The TTR-GAN model is capable of generating predicted travel time samples, enabling the assessment of network-wide TTR without the need to assume a specific travel time distribution. In the TTR-GAN model, a combination of graph convolutional networks and long short-term memory (LSTM) neural networks is employed within the GAN framework. When training the TTR-GAN model, special attention is given to adjusting the mean and standard deviation of the generated samples, aiming for a closer resemblance to real samples. Experiments conducted on a road network in China demonstrate the predictive capability of the proposed TTR-GAN model, surpassing several benchmark models such as the LSTM neural network, moving average model, and GAN model in terms of statistical, buffer time, and probability distribution measures. By incorporating the mean and standard deviation into the loss function, the TTR-GAN model achieves an 18.2% reduction in Jensen‒Shannon divergence between predicted and real samples. Furthermore, the model's performance in real-world applications is illustrated through a sensitivity test.

Spatial–Temporal Graph-Enabled Convolutional Neural Network–Based Approach for Traffic Networkwide Travel Time

Spatial–Temporal Graph-Enabled Convolutional Neural Network–Based Approach for Traffic Networkwide Travel Time

A stochastic framework using Bayesian optimization algorithm to assess the network-level societal impacts of connected and autonomous vehicles

Connected and autonomous vehicle technologies are expected to alter transportation systems by enhancements in mobility, safety, and emission reduction. While many studies have investigated the impacts of connected vehicle (CV) and autonomous vehicle (AV) technologies on traffic congestion and emission at the facility level, little is known about these impacts at large scales. Furthermore, different effective parameters associated with these impacts, such as the extra vehicle miles traveled (VMT) induced by AVs, technology cost of these vehicles, and possible reductions in the value of time of AV users, are highly uncertain. The uncertainty of these parameters and its role in assessing the societal impacts of CVs and AVs are not fully explored in the literature. Therefore, this study aims to develop a stochastic framework and an optimization algorithm to find the optimum market shares of CVs and AVs in a mixed traffic environment, consisting of human-driven vehicles without connectivity (HDVs), CVs, and AVs, minimizing the system cost. Emission, travel time, and technology costs are considered as components of the system cost. Thus, the framework combines a traffic simulation tool that considers a mixed fleet of HDVs, CVs, and AVs with heterogeneous drivers (for HDVs and CVs) distributed spatially over the network, along with an emission estimation model, to measure network-wide travel time and emission costs. Many parameters, such as extra VMT produced by AVs, value of time reduction for AV users, and automation cost, are subject to a considerable degree of stochasticity, which is considered by assuming probabilistic distributions for these parameters. A Bayesian Optimization algorithm with heteroskedastic non-stationary Gaussian process model is presented to estimate the optimum market shares of CVs and AVs considering these uncertainties. The stochastic framework and the optimization algorithm are successfully applied to a large-scale network of Chicago. The impacts of different parameters on the optimum CV and AV market shares and the system cost are explored, providing practical insights for policymakers.

Spatiotemporal Features—Extracted Travel Time Prediction Leveraging Deep-Learning-Enabled Graph Convolutional Neural Network Model

Travel time prediction is one of the most important parameters to forecast network-wide traffic conditions. Travelers can access traffic roadway networks and arrive in their destinations at the lowest costs guided by accurate travel time estimation on alternative routes. In this study, we propose a long short-term memory (LSTM)-based deep learning model, deep learning on spatiotemporal features with Convolution Neural Network (DLSF-CNN), to extract the spatial–temporal correlation of travel time on different routes to accurately predict route travel time. Specifically, this model utilizes network-wide travel time, considering its topological structure as inputs, and combines convolutional neural network and LSTM techniques to accurately predict travel time. In addition to their spatial dependence, both coarse-grained and fine-grained temporal dependences are fully considered among the road segments along a route as well. The shift problem is formulated in the coarse-grained granularity to predict the route travel time in the next time interval. The experimental tests were conducted using real route travel time obtained by taxi trajectories in Harbin. The test results show that the travel time prediction accuracy of DLSF-CNN is above 90%. Meanwhile, the proposed model outperformed the other machine learning models based on multiple evaluation criteria. The RMSE (Root Mean Squard Error) and R2 (R Squared) increased by 18.6% and 22.46%, respectively. The results indicate the proposed model performs reasonably well under prevailing traffic conditions.

A comprehensive welfare impact analysis for road expansion projects: A case study

This study provides the overall social welfare implications of key road-capacity expansion options considering free capacity, high occupancy vehicle – HOV, high occupancy toll – HOT, and toll lanes. The broad welfare impacts are estimated in terms of transport users, residents, the regional economy, and private-sector’s welfare. The study uses Dallas County and Tarrant County, Texas, as a case-study region. The study result shows that the HOT option outperforms all other options. It results in an overall increase in social welfare in net present value of $6.7 billion. Apart from that, estimation results do not clearly suggest a preferred option, but instead, depend on the criterion used. The best option in each criterion is: “Do nothing” for investment costs, “HOT” for regional economic impact, “All-tolled” for corridor travel time, “HOT” for network-wide travel time, “Free capacity” for users’ travel costs, “All-tolled” for energy and environmental costs, and “All-tolled” for revenue. The proposed social welfare analysis integrates these conflicting criteria by offering a unified index, and provides the best road-investment option for society.

The impacts of connected vehicle technology on network-wide traffic operation and fuel consumption under various incident scenarios

ABSTRACTIncidents are a major source of traffic congestion and can lead to long and unpredictable delays, deteriorating traffic operations and adverse environmental impacts. The emergence of connected vehicles and communication technologies has enabled travelers to use real-time traffic information. The ability to exchange traffic information among vehicles has tremendous potential impacts on network performance especially in the case of non-recurrent congestion. To this end, this paper utilizes a microscopic simulation model of traffic in El Paso, Texas to investigate the impacts of incidents on traffic operation and fuel consumption at different market penetration rates (MPR) of connected vehicles. Several scenarios are implemented and tested to determine the impacts of incidents on network performance in an urban area. The scenarios are defined by changing the duration of incidents and the number of lanes closed. This study also shows how communication technology affects network performance in response to congestion. The results of the study demonstrate the potential effectiveness of connected vehicle technology in improving network performance. For an incident with a duration of 900 s and MPR of 80%, total fuel consumption and total travel time decreased by approximately 20%; 26% was observed in network-wide travel time and fuel consumption at 100% MPR.

Real-Time Predictive Control Strategy Optimization

Urban traffic congestion has led to an increasing emphasis on management measures for more efficient utilization of existing infrastructure. In this context, this paper proposes a novel framework that integrates real-time optimization of control strategies (tolls, ramp metering rates, etc.) with the generation of traffic guidance information using predicted network states for dynamic traffic assignment systems. The efficacy of the framework is demonstrated through a fixed demand dynamic toll optimization problem, which is formulated as a non-linear program to minimize predicted network travel times. A scalable efficient genetic algorithm that exploits parallel computing is applied to solve this problem. Experiments using a closed-loop approach are conducted on a large-scale road network in Singapore to investigate the performance of the proposed methodology. The results indicate significant improvements in network-wide travel time of up to 9% with real-time computational performance.

Mode shift impacts of optimal time-dependent congestion pricing in large networks: A simulation-based case study in the greater toronto area

This paper presents a case study on commuter’s departure time, route and mode choice responses to optimized tolling in the Toronto, Ontario, Canada. The study integrates a toll optimization component into an integrated framework of econometric departure time choice, dynamic traffic assignment model, and random utility maximization (RUM) based mode choice model. An iterative optimization algorithm is used to generate optimal tolling structure which explicitly considers heterogeneous user preferences through econometric departure time choice modelling component. The mode choice component is exogenously retrofitted in an integrated econometric departure time choice modelling component and dynamic operational traffic assignment model to capture individual mode choice behaviour in response to variable congestion pricing. The integrated model results show that individuals are more likely to switch driving routes and departure times than commuting modes when making tradeoffs between schedule delay cost, travel time cost, and toll cost. It is found that the optimal toll scenario improves the network-wide travel time. The modelling framework presented in this study can test a wide range of policy scenarios including the time-variable tolling of congested highways, and high occupancy toll lanes. While the integrated framework presented here is tested at a large scale on the Greater Toronto Area (GTA), we believe the approach can be applied to large-scale networks globally where the objective is seeking the best network-wide spatial and temporal traffic distribution.

Integrated variable speed limit and ramp metering control study on flow interaction between mainline and ramps

During peak periods, bottlenecks are often triggered by excessive demand from both on-ramp and mainline input flows. To relieve bottleneck severity and improve traffic safety, ramp metering and variable speed limit are implemented to control the on-ramp and mainline input flows, and sometimes they are integrated. This article presents a proactive integrated control, with goals to save network-wide travel time and increase traffic flow. A METANET-based macroscopic traffic model was adopted as a prediction model. Micro-simulation tests were performed to evaluate and compare the control approaches among integrated and isolated control scenarios. By decoupling the traffic prediction and simulation models, the control error sources were analyzed. The evaluation revealed that both isolated and integrated controls benefit the traffic network to different extents under varying demand scenarios. Under proactive integrated control, ramp metering is activated solely during slight congestion; or it is activated during high-congestion periods to assist variable speed limit and thus integration maximizes the infrastructure utility.

Multiline holding based control for lines merging to a shared transit corridor

ABSTRACTIn transit corridors, multiple lines share a sequence of consecutive stops to provide higher joint frequency in higher demand areas. A key challenge is to coordinate the transition from single line to joint operation. A holding control strategy aimed at minimizing passenger travel times is introduced for lines merging into a shared corridor, accounting for the coordination of vehicle arrivals from the merging lines as well as the regularity of each line. The criterion is tested using an artificial network and a real-world network to analyze the impact of demand distribution and compare cooperative versus single line control. We illustrate how the real-time strategy yields overall passenger gains, depending on the composition of different user groups. Results are assessed based on operation and passenger performance indicators and show that coordination is achieved. When combined with joint control in the common part, the proposed approach achieves consistent network-wide travel time benefits.

Cross-Vendor and Cross-State Analysis of GPS Probe Data Latency

Crowd sourced GPS probe data have become a major source of real-time traffic information applications. In addition to traditional traveler advisory systems such as dynamic message signs (DMS) and 511 systems, probe data are being used for automatic incident detection, integrated corridor management (ICM), end of queue warning systems, and mobility-related smartphone applications. Several private sector vendors offer minute by minute network-wide travel time and speed probe data. The quality of such data in terms of deviation of the reported travel time and speeds from ground-truth has been extensively studied in recent years, and as a result concerns over the accuracy of probe data have mostly faded away. However, the latency of probe data—defined as the lag between the time at which disturbance in traffic speed is reported in the outsourced data feed, and the time at which the traffic is perturbed—has become a subject of interest. The extent of latency of probe data for real-time applications is critical, so it is important to have a good understanding of the amount of latency and its influencing factors. This paper uses high-quality independent Bluetooth/Wi-Fi re-identification data collected on multiple freeway segments in three different states, to measure the latency of the vehicle probe data provided by three major vendors. The statistical distribution of the latency and its sensitivity to speed slowdown and recovery periods are discussed.

Simulation-based pricing optimization for improving network-wide travel time reliability

ABSTRACTTravel time variability in a network is an important measure of the transportation system performance and a major factor influencing the decision-making of system management such as congestion pricing. The congestion-pricing problem with reliability maximization as the goal of a transportation network is characterized by expensive-to-evaluate objective functions without closed forms. In this paper, an effective simulation-based optimization (SBO) method is utilized to solve the problem. The network reliability is measured by a weighted average link travel time coefficient of variation (CV) with link traffic flows as the weights. We employ DynusT to evaluate the system reliability as the objective function corresponding to different toll charges for a new toll road in Maryland. The results show that the two optimal toll charge strategies improve the network-wide reliability, reducing the weighted travel time CV by 9.60% and 1.16%, respectively, when compared to the baseline toll.

Network-wide on-line travel time estimation with inconsistent data from multiple sensor systems under network uncertainty

ABSTRACTThis paper proposes a new modeling approach for network-wide on-line travel time estimation with inconsistent data from multiple sensor systems. It makes full use of both the available data from multiple sensor systems (on-line data) and historical data (off-line data). The first- and second-order statistical properties of the on-line data are investigated together with the data inconsistency issue to estimate network-wide travel times. The proposed model is formulated as a generalized least squares problem with non-linear constraints. A solution algorithm based on the penalty function method is adopted to solve the proposed model, whose application is illustrated by numerical examples using a local road network in Hong Kong.

Impact of connected vehicle guidance information on network-wide average travel time

With the emergence of connected vehicle technologies, the potential positive impact of connected vehicle guidance on mobility has become a research hotspot by data exchange among vehicles, infrastructure, and mobile devices. This study is focused on micro-modeling and quantitatively evaluating the impact of connected vehicle guidance on network-wide travel time by introducing various affecting factors. To evaluate the benefits of connected vehicle guidance, a simulation architecture based on one engine is proposed representing the connected vehicle–enabled virtual world, and connected vehicle route guidance scenario is established through the development of communication agent and intelligent transportation systems agents using connected vehicle application programming interface considering the communication properties, such as path loss and transmission power. The impact of connected vehicle guidance on network-wide travel time is analyzed by comparing with non-connected vehicle guidance in response to different market penetration rate, following rate, and congestion level. The simulation results explore that average network-wide travel time in connected vehicle guidance shows a significant reduction versus that in non–connected vehicle guidance. Average network-wide travel time in connected vehicle guidance have an increase of 42.23% comparing to that in non-connected vehicle guidance, and average travel time variability (represented by the coefficient of variance) increases as the travel time increases. Other vital findings include that higher penetration rate and following rate generate bigger savings of average network-wide travel time. The savings of average network-wide travel time increase from 17% to 38% according to different congestion levels, and savings of average travel time in more serious congestion have a more obvious improvement for the same penetration rate or following rate.

A micro-simulation study on proactive coordinated ramp metering for relieving freeway congestion

To relieve freeway congestion during peak periods, ramp metering (RM) is often implemented to control the input flow from onramps on freeways. Many studies focus on proactive coordinated RM controls; however, successful implementation of proactive RM control still requires a more accurate prediction model and a less complex control algorithm. To this end, this study tests a proactive RM approach in micro-simulation, with goals to improve network-wide travel time and traffic flow. A METANET-based dynamic traffic model was adopted as a prediction model within a predictive control framework. The evaluation revealed a 6.50% amelioration in total travel time on the mainline and a 2.52% reduction of total time spent in the network. The applied algorithm was compared with the HERO algorithm and implemented in various peak demand scenarios. This analysis could lead to efficient and effective field applications of proactive coordinated RM control to improve freeway operation.

Arterial Travel Time Validation and Augmentation with Two Independent Data Sources

Travel time data are a key input to applications of intelligent transportation systems. Advancement in vehicle tracking and reidentification technologies and proliferation of location-aware and connected devices have made networkwide travel time data available to transportation management agencies. The trend started with data collection on freeways and has been quickly extended to arterials. Although the freeway travel time data have been validated extensively in recent years, the quality of arterial travel time data is not well known. This paper presents a comprehensive validation scheme for arterial travel time data based on GPS probe and Bluetooth data as two independent sources. Since travel time on arterials is subject to a higher degree of variation than that on freeways, mainly because of the presence of signals, a new validation methodology based on the coefficient of variation is introduced. Moreover, a context-dependent travel time fusion framework is developed to improve the reliability of travel time information by fusing data from multiple sources. All 2012 data from a busy arterial corridor in Maryland are used to demonstrate the proposed comparison and augmentation model.

Optimal Ramp Metering Control for Weaving Segments Considering Dynamic Weaving Capacity Estimation

On freeway corridors, traffic flow is limited by active bottlenecks. Weaving maneuvers (i.e., intensive lane changes) are a major cause of bottlenecks during high-demand periods. To relieve bottleneck severity, ramp metering (RM) is implemented as an active traffic control method. Ample research has been devoted to developing RM control algorithms and to exploring weaving impacts; however, RM control that is considerate of dynamic weaving impact and its evaluation has received little attention in the published literature. This paper aims to bridge that gap by proposing a proactive control algorithm that uses as inputs dynamic weaving capacity (as opposed to traditional fixed capacity values) for RM control at weaving segments. The control goals are to reduce networkwide travel time and improve traffic flow. Capacity and capacity drop were estimated through fundamental diagrams (FDs). Then, capacity drop sensitivities to on-ramp and mainline demand were analyzed within a field-data-based microsimulation model. The findings were applied to dynamically estimate weaving capacity within a macroscopic traffic flow model. The proposed traffic flow model conducted estimation in a model predictive control (MPC) framework. The RM rates were optimized by sequential quadratic programming (SQP). The proposed RM algorithm was evaluated in macrosimulation and compared with a no-control scenario as well as with a control scenario that used static (as opposed to dynamic) weaving capacity. This analysis contributes to efficient and effective field applications and freeway operational improvements.

Incorporating spatial equity into interurban road network design

Methods for the road network design problem, typically, are based on optimization of the network efficiency measures (e.g. network-wide travel time) under a predefined budget. In these approaches, equity issues are not taken into account and, consequently, most of the road improvements are planned next to large cities. Thus, disparities between large and small cities increase, which does not conform to sustainable development objectives. In this paper, to overcome concerns associated with traditional methods, equity is incorporated into the interurban road network design problem. To this end, accessibility concepts are employed. However, unlike previous studies, instead of maximizing the total accessibility, a new definition is proposed for inaccessibility, and total inaccessibility is minimized throughout the network. Using this new definition not only is more compatible with the equity issue, but also helps to eliminate the nonlinearity of the problem. Average travel time to neighboring opportunities is utilized to propose this definition for inaccessibility, which captures the reality more effectively. With the aim of this definition, equity is incorporated into the road network design problem implicitly. This is another improvement over previous methods, where a new term in the objective function or a new constraint is added to include the equity. The proposed model is formulated as a mixed integer linear programming (MILP) problem, where the objective is to minimize the aggregate inaccessibility over all the population centers in the network. To illustrate the application of the model, the Northwest region of the United States is used as the case study. The respective exact solution of the example is found using a commercial solver (CPLEX). This new solution is also compared with the solutions from the traditional methods.