Stochastic user equilibrium with equilibrated choice sets: Part I – Model formulations under alternative distributions and restrictions

The aim of this paper is to remove the known limitations of Deterministic and Stochastic User Equilibrium (DUE and SUE), namely that only routes with the minimum cost are used in DUE, and that all permitted routes are used in SUE regardless of their costs. We achieve this by combining the advantages of the two principles, namely the definition of unused routes in DUE and of mis-perception in SUE, such that the resulting choice sets of used routes are equilibrated. Two model families are formulated to address this issue: the first is a general version of SUE permitting bounded and discrete error distributions; the second is a Restricted SUE model with an additional constraint that must be satisfied for unused paths. The overall advantage of these model families consists in their ability to combine the unused routes with the use of random utility models for used routes, without the need to pre-specify the choice set. We present model specifications within these families, show illustrative examples, evaluate their relative merits, and identify key directions for further research.     

Estimating historical hourly traffic volumes via machine learning and vehicle probe data: A Maryland case study

This paper focuses on the problem of estimating historical traffic volumes between sparsely-located traffic sensors, which transportation agencies need to accurately compute statewide performance measures. To this end, the paper examines applications of vehicle probe data, automatic traffic recorder counts, and neural network models to estimate hourly volumes in the Maryland highway network, and proposes a novel approach that combines neural networks with an existing profiling method. On average, the proposed approach yields 24% more accurate estimates than volume profiles, which are currently used by transportation agencies across the US to compute statewide performance measures. The paper also quantifies the value of using vehicle probe data in estimating hourly traffic volumes, which provides important managerial insights to transportation agencies interested in acquiring this type of data. For example, results show that volumes can be estimated with a mean absolute percent error of about 21% at locations where average number of observed probes is between 30 and 47 vehicles/h, which provides a useful guideline for assessing the value of probe vehicle data from different vendors.     

Dynamic charging-while-driving systems for freight delivery services with electric vehicles: Traffic and energy modelling

This paper presents a research on traffic modelling developed for assessing traffic and energy performance of electric systems installed along roads for dynamic charging-while-driving (CWD) of fully electric vehicles (FEVs).The logic adopted by the developed traffic model is derived from a particular simulation scenario of electric charging: a freight distribution service operated using medium-sized vans. In this case, the CWD service is used to recover the state of charge of the FEV batteries to shortly start with further activities after arrival at the depot.The CWD system is assumed to be implemented in a multilane ring road with several intermediate on-ramp entrances, where the slowest lane is reserved for the dynamic charging of authorized electric vehicles. A specific traffic model is developed and implemented based on a mesoscopic approach, where energy requirements and charging opportunities affect driving and traffic behaviours. Overtaking manoeuvres as well as new entries in the CWD lane of vehicles that need to charge are modelled according to a cooperative driving system, which manages adequate time gaps between consecutive vehicles. Finally, a speed control strategy is simulated at a defined node to create an empty time-space slot in the CWD lane, by delaying the arriving vehicles. This simulated control, implemented to allow maintenance operations for CWD that may require clearing a charging zone for a short time slot, could also be applied to facilitate on-ramp merging manoeuvres.     

Adaptive traffic signal control with actor-critic methods in a real-world traffic network with different traffic disruption events

The transportation demand is rapidly growing in metropolises, resulting in chronic traffic congestions in dense downtown areas. Adaptive traffic signal control as the principle part of intelligent transportation systems has a primary role to effectively reduce traffic congestion by making a real-time adaptation in response to the changing traffic network dynamics. Reinforcement learning (RL) is an effective approach in machine learning that has been applied for designing adaptive traffic signal controllers. One of the most efficient and robust type of RL algorithms are continuous state actor-critic algorithms that have the advantage of fast learning and the ability to generalize to new and unseen traffic conditions. These algorithms are utilized in this paper to design adaptive traffic signal controllers called actor-critic adaptive traffic signal controllers (A-CATs controllers).The contribution of the present work rests on the integration of three threads: (a) showing performance comparisons of both discrete and continuous A-CATs controllers in a traffic network with recurring congestion (24-h traffic demand) in the upper downtown core of Tehran city, (b) analyzing the effects of different traffic disruptions including opportunistic pedestrians crossing, parking lane, non-recurring congestion, and different levels of sensor noise on the performance of A-CATS controllers, and (c) comparing the performance of different function approximators (tile coding and radial basis function) on the learning of A-CATs controllers. To this end, first an agent-based traffic simulation of the study area is carried out. Then six different scenarios are conducted to find the best A-CATs controller that is robust enough against different traffic disruptions. We observe that the A-CATs controller based on radial basis function networks (RBF (5)) outperforms others. This controller is benchmarked against controllers of discrete state Q-learning, Bayesian Q-learning, fixed time and actuated controllers; and the results reveal that it consistently outperforms them.     

Commuters’ acceptance of and behavior reactions to license plate restriction policy: A case study of Tianjin,China

License plate restriction (LPR) policies are currently being implemented in major Chinese cities with the aim of mitigating traffic congestions. Meanwhile, much controversy regarding the effectiveness of the LPR policies is arising. To better understand the impact of the LPR policies, this paper studies commuters’ acceptance of and behavior reactions to the policies after their implementation. A theoretical model was proposed as the first step, followed by a questionnaire survey that was conducted in Tianjin, China, where an LPR policy has been in place since March 2014. Car owners frequently commuting within the restricted area were sampled as respondents, and a multi-variable regression method was employed to analyze the collected survey data. The results indicate that it is necessary to promote public’s acceptance of the LPR policy, because lower acceptance will lead to more negative reactions towards the policy, which may weaken its effectiveness. Main factors affecting the level of acceptance of the policy are also found, which may serve as a reference for transportation authorities seeking to increase commuters’ acceptance of the policy. These findings are beneficial to designing and implementing LPR policies.     

A new probability statistical model for traffic noise prediction on free flow roads and control flow roads

A new traffic noise prediction approach based on a probability distribution model of vehicle noise emissions and achieved by Monte Carlo simulation is proposed in this paper. The probability distributions of the noise emissions of three types of vehicles are obtained using an experimental method. On this basis, a new probability statistical model for traffic noise prediction on free flow roads and control flow roads is established. The accuracy of the probability statistical model is verified by means of a comparison with the measured data, which has shown that the calculated results of L_eq, L₁₀, L₅₀, L₉₀, and the probability distribution of noise level occurrence agree well with the measurements. The results demonstrate that the new method can avoid the complicated process of traffic flow simulation but still maintain high accuracy for the traffic noise prediction.     

Calibration of nonlinear car-following laws for traffic oscillation prediction

Frequency-domain analysis has been successfully used to (i) predict the amplification of traffic oscillations along a platoon of vehicles with nonlinear car-following laws and (ii) measure traffic oscillation properties (e.g., periodicity, magnitude) from field data. This paper proposes a new method to calibrate nonlinear car-following laws based on real-world vehicle trajectories, such that oscillation prediction (based on the calibrated car-following laws) and measurement from the same data can be compared and validated. This calibration method, for the first time, takes into account not only the driver’s car-following behavior but also the vehicle trajectory’s time-domain (e.g., location, speed) and frequency-domain properties (e.g., peak oscillation amplitude). We use Newell’s car-following model (1961) as an example and calibrate its parameters based on a penalty-based maximum likelihood estimation procedure. A series of experiments using Next Generation Simulation (NGSIM) data are conducted to illustrate the applicability and performance of the proposed approach. Results show that the calibrated car-following models are able to simultaneously reproduce observed driver behavior, time-domain trajectories, and oscillation propagation along the platoon with reasonable accuracy.     

Traffic evacuation simulation based on multi-level driving decision model

Traffic evacuation is a critical task in disaster management. Planning its evacuation in advance requires taking many factors into consideration such as the destination shelter locations and numbers, the number of vehicles to clear, the traffic congestions as well as traffic road configurations. A traffic evacuation simulation tool can provide the emergency managers with the flexibility of exploring various scenarios for identifying more accurate model to plan their evacuation. This paper presents a traffic evacuation simulation system based on integrated multi-level driving-decision models which generate agents’ behavior in a unified framework. In this framework, each agent undergoes a Strategic, Cognitive, Tactical and Operational (SCTO) decision process, in order to make a driving decision. An agent’s actions are determined by a combination, on each process level, of various existing behavior models widely used in different driving simulation models. A wide spectrum of variability in each agent’s decision and driving behaviors, such as in pre-evacuation activities, in choice of route, and in the following or overtaking the car ahead, are represented in the SCTO decision process models to simulate various scenarios. We present the formal model for the agent and the multi-level decision models. A prototype simulation system that reflects the multi-level driving-decision process modeling is developed and implemented. Our SCTO framework is validated by comparing with MATSim tool, and the experimental results of evacuation simulation models are compared with the existing evacuation plan for densely populated Beijing, China in terms of various performance metrics. Our simulation system shows promising results to support emergency managers in designing and evaluating more realistic traffic evacuation plans with multi-level agent’s decision models that reflect different levels of individual variability of handling stress situations. The flexible combination of existing behavior and decision models can help generating the best evacuation plan to manage each crisis with unique characteristics, rather than resorting to a fixed evacuation plan.     

Using connected vehicle technology to improve the efficiency of intersections

Information from connected vehicles, such as the position and speed of individual vehicles, can be used to optimize traffic operations at an intersection. This paper proposes such an algorithm for two one-way-streets assuming that only a certain percentage of cars are equipped with this technology. The algorithm enumerates different sequences of cars discharging from the intersection to minimize the objective function. Benefits of platooning (multiple cars consecutively discharging from a queue) and signal flexibility (adaptability to demand) are also considered. The goal is to gain insights about the value (in terms of delay savings) of using connected vehicle technology for intersection control.Simulations are conducted for different total demand values and demand ratios to understand the effects of changing the minimum green time at the signal and the penetration rate of connected cars. Using autonomous vehicle control systems, the signal could rapidly change the direction of priority without relying on the reaction of drivers. However, without this technology a minimum green time is necessary. The results of the simulations show that a minimum green time increases the delay only for the low and balanced demand scenarios. Therefore, the value of using cars with autonomous vehicle control can only be seen at intersections with this kind of demand patterns, and could result in up to 7% decrease in delay. On the other hand, using information from connected vehicles to better adapt the traffic signal has proven to be indeed very valuable. Increases in the penetration rate from 0% up to 60% can significantly reduce the average delay (in low demand scenarios a decrease in delay of up to 60% can be observed). That being said, after a penetration rate of 60%, while the delays continue to decrease, the rate of reduction decreases and the marginal value of information from communication technologies diminishes. Overall, it is observed that connected vehicle technology could significantly improve the operation of traffic at signalized intersections, at least under the proposed algorithm.     

Integrated feedback ramp metering and mainstream traffic flow control on motorways using variable speed limits

Ramp metering (RM) is the most direct and efficient tool for the motorway traffic flow management. However, because of the usually short length of the on-ramps, RM is typically deactivated to avoid interference of the created ramp queue with adjacent street traffic. By the integration of local RM with mainstream traffic flow control (MTFC) enabled via variable speed limits (VSL), control operation upstream of active bottlenecks could be continued even if the on-ramp is full or if the RM lower bound has been reached. Such integration is proposed via the extension of an existing local cascade feedback controller for MTFC-VSL by use of a split-range-like scheme that allows different control periods for RM and MTFC-VSL. The new integrated controller remains simple yet efficient and suitable for field implementation. The controller is evaluated in simulation for a real motorway infrastructure (a ring-road) fed with real (measured) demands and compared to stand-alone RM or MTFC-VSL, both with feedback and optimal control results. The controller’s performance is shown to meet the specifications and to approach the optimal control results for the investigated scenario.