Calibration of traffic flow models using a memetic algorithm

A Memetic Algorithm (MA) for the calibration of microscopic traffic flow simulation models is proposed in this study. The proposed MA includes a combination of genetic and simulated annealing algorithms. The genetic algorithm performs the exploration of the search space and identifies a zone where a possible global solution could be located. After this zone has been found, the simulated annealing algorithm refines the search and locates an optimal set of parameters within that zone. The design and implementation of this methodology seeks to enable the generalized calibration of microscopic traffic flow models. Two different Corridor Simulation (CORSIM) vehicular traffic systems were calibrated for this study. All parameters after the calibration were within reasonable boundaries. The calibration methodology was developed independently of the characteristics of the traffic flow models. Hence, it is easily used for the calibration of any other model. The proposed methodology has the capability to calibrate all model parameters, considering multiple performance measures and time periods simultaneously. A comparison between the proposed MA and the Simultaneous Perturbation Stochastic Approximation (SPSA) algorithm was provided; results were similar between the two. However, the effort required to fine-tune the MA was considerably smaller when compared to the SPSA. The running time of the MA-based calibration was larger when it was compared to the SPSA running time. The MA still required some knowledge of the model in order to set adequate optimization parameters. The perturbation of the parameters during the mutation process must have been large enough to create a measurable change in the objective function, but not too large to avoid noisy measurements.     

Understanding the structure of hyper-congested traffic from empirical and experimental evidences

We study in this paper the structure of traffic under hypercongestion, which is a controversial issue between traditional two-phase traffic theory and Kerner’s three-phase theory. By analyzing video traffic data from a section of the Nanjing Airport Highway, it is found that traffic states inside hypercongestion are not homogeneous, which contradicts the existence of a “Homogeneous Congested Traffic” state claimed in two-phase traffic theory. Analysis of vehicle trajectories and velocities obtained from an experimental car-following study with a platoon of 25 vehicles also confirms the above findings. Furthermore, it is also found from the video traffic data that the structure of hypercongested traffic varies only slightly with location, which might be due to small jams inside hypercongested traffic merging into larger ones slowly and/or larger jams sometimes breaking into small ones. Finally, the implications of our observations on traffic modeling have been discussed.     

Globally energy-optimal speed planning for road vehicles on a given route

This paper provides a globally optimal solution to an important problem: given a real-world route, what is the most energy-efficient way to drive a vehicle from the origin to the destination within a certain period of time. Along the route, there may be multiple stop signs, traffic lights, turns and curved segments, roads with different grades and speed limits, and even leading vehicles with pre-known speed profiles. Most of such route information and features are actually constraints to the optimal vehicle speed control problem, but these constraints are described in two different domains. The most important concept in solving this problem is to convert the distance-domain route constraints to some time-domain state and input constraints that can be handled by optimization methods such as dynamic programming (DP). Multiple techniques including cost-to-go function interpolation and parallel computing are used to reduce the computation of DP and make the problem solvable within a reasonable amount of time on a personal computer.     

Predicting and planning airport acceptance rates in metroplex systems for improved traffic flow management decision support

Efficient planning of Airport Acceptance Rates (AARs) is key for the overall efficiency of Traffic Management Initiatives such as Ground Delay Programs (GDPs). Yet, precisely estimating future flow rates is a challenge for traffic managers during daily operations as capacity depends on a number of factors/decisions with very dynamic and uncertain profiles. This paper presents a data-driven framework for AAR prediction and planning towards improved traffic flow management decision support. A unique feature of this framework is to account for operational interdependency aspects that exist in metroplex systems and affect throughput performance. Gaussian Process regression is used to create an airport capacity prediction model capable of translating weather and metroplex configuration forecasts into probabilistic arrival capacity forecasts for strategic time horizons. To process the capacity forecasts and assist the design of traffic flow management strategies, an optimization model for capacity allocation is developed. The proposed models are found to outperform currently used methods in predicting throughput performance at the New York airports. Moreover, when used to prescribe optimal AARs in GDPs, an overall delay reduction of up to 9.7% is achieved. The results also reveal that incorporating robustness in the design of the traffic flow management plan can contribute to decrease delay costs while increasing predictability.     

Modeling the effect of electric vehicle adoption on pedestrian traffic safety: An agent-based approach

When operated at low speeds, electric and hybrid vehicles have created pedestrian safety concerns in congested areas of various city centers, because these vehicles have relatively silent engines compared to those of internal combustion engine vehicles, resulting in safety issues for pedestrians and cyclists due to the lack of engine noise to warn them of an oncoming electric or hybrid vehicle. However, the driver behavior characteristics have also been considered in many studies, and the high end-prices of electric vehicles indicate that electric vehicle drivers tend to have a higher prosperity index and are more likely to receive a better education, making them more alert while driving and more likely to obey traffic rules. In this paper, the positive and negative factors associated with electric vehicle adoption and the subsequent effects on pedestrian traffic safety are investigated using an agent-based modeling approach, in which a traffic micro-simulation of a real intersection is simulated in 3D using AnyLogic software. First, the interacting agents and dynamic parameters are defined in the agent-based model. Next, a 3D intersection environment is created to integrate the agent-based model into a visual simulation, where the simulation records the number of near-crashes occurring in certain pedestrian crossings throughout the virtual time duration of a year. A sensitivity analysis is also carried out with 9000 subsequent simulations performed in a supercomputer to account for the variation in dynamic parameters (ambient sound level, vehicle sound level, and ambient illumination). According to the analysis, electric vehicles have a 30% higher pedestrian traffic safety risk than internal combustion engine vehicles under high ambient sound levels. At low ambient sound levels, however, electric vehicles have only a 10% higher safety risk for pedestrians. Low levels of ambient illumination also increase the number of pedestrians involved in near-crashes for both electric vehicles and combustion engine vehicles.     

A simple nonparametric car-following model driven by field data

Car-following models are always of great interest of traffic engineers and researchers. In the age of mass data, this paper proposes a nonparametric car-following model driven by field data. Different from most of the existing car-following models, neither driver’s behaviour parameters nor fundamental diagrams are assumed in the data-driven model. The model is proposed based on the simple k-nearest neighbour, which outputs the average of the most similar cases, i.e., the most likely driving behaviour under the current circumstance. The inputs and outputs are selected, and the determination of the only parameter k is introduced. Three simulation scenarios are conducted to test the model. The first scenario is to simulate platoons following real leaders, where traffic waves with constant speed and the detailed trajectories are observed to be consistent with the empirical data. Driver’s rubbernecking behaviour and driving errors are simulated in the second and third scenarios, respectively. The time–space diagrams of the simulated trajectories are presented and explicitly analysed. It is demonstrated that the model is able to well replicate periodic traffic oscillations from the precursor stage to the decay stage. Without making any assumption, the fundamental diagrams for the simulated scenario coincide with the empirical fundamental diagrams. These all validate that the model can well reproduce the traffic characteristics contained by the field data. The nonparametric car-following model exhibits traffic dynamics in a simple and parsimonious manner.     

Link-based day-to-day network traffic dynamics and equilibria

A general dynamical system model with link-based variables is formulated to characterize the processes of achieving equilibria from a non-equilibrium state in traffic networks. Several desirable properties of the dynamical system model are established, including the equivalence between its stationary state and user equilibrium, the invariance of its evolutionary trajectories, and the uniqueness and stability of its stationary points. Moreover, it is shown that not only a link-based version of two existing day-to-day traffic dynamics models but also two existing link-based dynamical system models of traffic flow are the special cases of the proposed model. The stabilities of stationary states of these special cases are also analyzed and discussed. In addition, an extension is made to the case with elastic demand. The study is helpful for better understanding the day-to-day adjustment mechanism of traffic flows in networks.     

Spatiotemporal intersection control in a connected and automated vehicle environment

Current research on traffic control has focused on the optimization of either traffic signals or vehicle trajectories. With the rapid development of connected and automated vehicle (CAV) technologies, vehicles equipped with dedicated short-range communications (DSRC) can communicate not only with other CAVs but also with infrastructure. Joint control of vehicle trajectories and traffic signals becomes feasible and may achieve greater benefits regarding system efficiency and environmental sustainability. Traffic control framework is expected to be extended from one dimension (either spatial or temporal) to two dimensions (spatiotemporal). This paper investigates a joint control framework for isolated intersections. The control framework is modeled as a two-stage optimization problem with signal optimization at the first stage and vehicle trajectory control at the second stage. The signal optimization is modeled as a dynamic programming (DP) problem with the objective to minimize vehicle delay. Optimal control theory is applied to the vehicle trajectory control problem with the objective to minimize fuel consumption and emissions. A simplified objective function is adopted to get analytical solutions to the optimal control problem so that the two-stage model is solved efficiently. Simulation results show that the proposed joint control framework is able to reduce both vehicle delay and emissions under a variety of demand levels compared to fixed-time and adaptive signal control when vehicle trajectories are not optimized. The reduced vehicle delay and CO₂ emissions can be as much as 24.0% and 13.8%, respectively for a simple two-phase intersection. Sensitivity analysis suggests that maximum acceleration and deceleration rates have a significant impact on the performance regarding both vehicle delay and emission reduction. Further extension to a full eight-phase intersection shows a similar pattern of delay and emission reduction by the joint control framework.     

Real-time traffic network state estimation and prediction with decision support capabilities: Application to integrated corridor management

This paper presents a real-time traffic network state estimation and prediction system with built-in decision support capabilities for traffic network management. The system provides traffic network managers with the capabilities to estimate the current network conditions, predict congestion dynamics, and generate efficient traffic management schemes for recurrent and non-recurrent congestion situations. The system adopts a closed-loop rolling horizon framework in which network state estimation and prediction modules are integrated with a traffic network manager module to generate efficient proactive traffic management schemes. The traffic network manger adopts a meta-heuristic search mechanism to construct the schemes by integrating a wide variety of control strategies. The system is applied in the context of Integrated Corridor Management (ICM), which is envisioned to provide a system approach for managing congested urban corridors. A simulation-based case study is presented for the US-75 corridor in Dallas, Texas. The results show the ability of the system to improve the overall network performance during hypothetical incident scenarios.     

Short-term traffic flow rate forecasting based on identifying similar traffic patterns

The ability to timely and accurately forecast the evolution of traffic is very important in traffic management and control applications. This paper proposes a non-parametric and data-driven methodology for short-term traffic forecasting based on identifying similar traffic patterns using an enhanced K-nearest neighbor (K-NN) algorithm. Weighted Euclidean distance, which gives more weight to recent measurements, is used as a similarity measure for K-NN. Moreover, winsorization of the neighbors is implemented to dampen the effects of dominant candidates, and rank exponent is used to aggregate the candidate values. Robustness of the proposed method is demonstrated by implementing it on large datasets collected from different regions and by comparing it with advanced time series models, such as SARIMA and adaptive Kalman Filter models proposed by others. It is demonstrated that the proposed method reduces the mean absolute percent error by more than 25%. In addition, the effectiveness of the proposed enhanced K-NN algorithm is evaluated for multiple forecast steps and also its performance is tested under data with missing values. This research provides strong evidence suggesting that the proposed non-parametric and data-driven approach for short-term traffic forecasting provides promising results. Given the simplicity, accuracy, and robustness of the proposed approach, it can be easily incorporated with real-time traffic control for proactive freeway traffic management.