Dynamic Traffic Assignment Systems Research Articles

Traffic Congestion Detection and Alternative Route Provision Using Machine Learning and IoT-Based Surveillance

The Automated Dynamic Traffic Assignment (ADTA) system introduces a novel approach to urban traffic management, merging the power of IoT with machine learning. This research assessed the system's performance in comparison to traditional traffic management strategies across various real-world scenarios. Findings consistently showcased the ADTA's superior efficiency: during peak traffic, it reduced vehicle wait times by half, and in scenarios with unexpected road closures, congestion detection was almost five times quicker, rerouting traffic with a remarkable 95% efficiency. The system's adaptability was further highlighted during weather challenges, ensuring safer vehicle speeds and substantially reducing weather-induced incidents. Large-scale public events, known disruptors of traffic flow, witnessed significantly reduced backlogs under the ADTA. Moreover, emergency situations benefitted from the system's rapid response, ensuring minimal delays for critical vehicles. This research underscores the potential of the ADTA system as a transformative solution for urban traffic woes, emphasizing its scalability and real-world applicability. With its integration of innovative technology and adaptive mechanisms, the ADTA offers a blueprint for the future of intelligent urban transport management.

Estimation and prediction of the OD matrix in uncongested urban road network based on traffic flows using deep learning

In this article, we propose a new method for OD (Origin–Destination)​ matrix prediction based on traffic data using deep learning. The input values of the developed model were determined based on data on the structure of the road network, origin and destination points of trips, as well as data on traffic intensity on road network sections recorded by video-sensing devices. The advantage of the method is that the complex process of data acquisition and processing is not required for the estimation and prediction of the matrix. Historical data and the iterative method of estimating a prior OD matrix were used only to generate training sequences for the neural network. The proposed method using deep learning neural networks with the long short-term memory (LSTM) or autoencoders layers (DLNa — deep learning networks with autoencoders) is characterized by relatively high accuracy and resistance to temporary missing data from several measurement points located in the urban road network. The case study was conducted for a network of a medium-sized city in Poland. The results show (average MAPE = 7.18% (LSTM), 6.80% (DLNa)) that the proposed method can have a practical implementation in real-time dynamic traffic assignment (DTA) systems for ITS applications. The proposed method of short-term forecasting the OD matrix does not require questionnaire research or detailed information on spatial development. Therefore, it is not as expensive and time-consuming as the methods based on these data.

Improving the accuracy and efficiency of online calibration for simulation-based Dynamic Traffic Assignment

Simulation-based Dynamic Traffic Assignment models have important applications in real-time traffic management and control. The efficacy of these systems rests on the ability to generate accurate estimates and predictions of traffic states, which necessitates online calibration. A widely used solution approach for online calibration is the Extended Kalman Filter (EKF), which – although appealing in its flexibility to incorporate any class of parameters and measurements – poses several challenges with regard to calibration accuracy and scalability, especially in congested situations for large-scale networks. This paper addresses these issues in turn so as to improve the accuracy and efficiency of EKF-based online calibration approaches for large and congested networks. First, the concept of state augmentation is revisited to handle violations of the Markovian assumption typically implicit in online applications of the EKF. Second, a method based on graph-coloring is proposed to operationalize the partitioned finite-difference approach that enhances scalability of the gradient computations.Several synthetic experiments and a real world case study demonstrate that application of the proposed approaches yields improvements in terms of both prediction accuracy and computational performance. The work has applications in real-world deployments of simulation-based dynamic traffic assignment systems.

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.

A large-scale, agent-based simulation of metropolitan freight movements with passenger and freight market interactions

Abstract This study summarizes the first stage in the implementation of an agent-based freight modeling system that has a global representation of agents and detailed modeling of a large-scale transportation network. The model is used to evaluate the transportation and energy impacts of goods movement across urban and national scales. The framework is implemented within POLARIS, a C++-based Planning and Operations Language for Agent-based Regional Integrated Simulation, which consists of an activity-based modeling (ABM) and dynamic traffic assignment (DTA) system that has robust features for passenger travel. This platform provides a tool to model interactions among consumers, producers, and the transportation system. The main objective of this initial implementation is to implement a freight model within POLARIS following an agent-based paradigm with behavioral and simulation methods. This paper presents the initial framework and illustrates the application of the model. Building upon earlier works, a parcel location assignment algorithm for business establishments in the population is documented, along with a method for estimating establishment production and consumption volumes. In addition to population generation, other features of the model include push-pull supply chains, multimodal path choice, choice of transportation logistics node, and dynamic traffic assignment. A module with e-commerce supply and demand was also developed to analyze the effects of e-commerce delivery on last-mile energy use and congestion.

Day-to-Day Learning Framework for Online Origin–Destination Demand Estimation and Network State Prediction

Origin–destination (O–D) demand is a critical component in both online and offline dynamic traffic assignment (DTA) systems. Recent advances in real-time DTA applications in large networks call for robust and efficient methodologies for online O–D demand estimation and prediction. This study presents a day-to-day learning framework for a priori O–D demand, along with a predictive data-driven O–D correction approach for online consistency between predicted and observed (sensor) values. When deviations between simulation and real world are observed, a consistency-checking module initiates O–D demand correction for the given prediction horizon. Two predictive correction methods are suggested: 1) simple gradient method, and 2) Taylor approximation method. New O–D demand matrices, corrected for 24 simulation hours by the correction module, are used as the updated a priori demand for the next day simulation. The methodology is tested in a real-world network, Kansas City, MO, for a 3-day period. Actual tests in real-world networks of online DTA systems have been very limited in the literature and in actual practice. The test results are analyzed in time and space dimensions. The overall performance of observed links is assessed. To measure the impact of O–D correction and daily O–D updates, traffic prediction performance with the new modules is compared with the base case. Predictive O–D correction improves prediction performance in a long prediction window. Also, daily updated O–D demand provides better initial states for traffic prediction, enhancing prediction in short prediction windows. The two modules collectively improve traffic prediction performance of the real-time DTA system.

Incorporating trip chaining within online demand estimation

Time-dependent Origin–Destination (OD) demand flows are fundamental inputs for Dynamic Traffic Assignment (DTA) systems and real-time traffic management. This work introduces a novel state-space framework to estimate these demand flows in an online context. Specifically, we propose to explicitly include trip-chaining behavior within the state-space formulation, which is solved using the well-established Kalman Filtering technique. While existing works already consider structural information and recursive behavior within the online demand estimation problem, this information has been always considered at the OD level. In this study, we introduce this structural information by explicitly representing trip-chaining within the estimation framework. The advantage is twofold. First, all trips belonging to the same tour can be jointly calibrated. Second, given the estimation during a certain time interval, a prediction of the structural deviation over the whole day can be obtained without the need to run additional simulations. The effectiveness of the proposed methodology is demonstrated first on a toy network and then on a large real-world network. Results show that the model improves the prediction performance with respect to a conventional Kalman Filtering approach. We also show that, on the basis of the estimation of the morning commute, the model can be used to predict the evening commute without need of running additional simulations.

Dynamic Toll Pricing using Dynamic Traffic Assignment System with Online Calibration

The paper presents a toll pricing methodology using a dynamic traffic assignment (DTA) system. This methodology relies on the DTA system’s capability to understand and predict traffic conditions, thus enhanced online calibration methodologies are applied to the DTA system, featuring a heuristic technique to calibrate supply parameters online. Improved offline calibration techniques are developed to apply toll pricing in a real network consisting of managed lanes and general purpose lanes. The online calibration methodologies are tested using real data from this network, and the results find the DTA system able to estimate and predict traffic flow and speed with satisfactory accuracy under congestion. Toll pricing is formulated as an optimization problem to maximize toll revenue, subject to network conditions and tolling regulations. Travelers are assumed to make route choice based on offline calibrated discrete choice models. Toll optimization is applied in a closed-loop evaluation framework where a microscopic simulator is used to mimic the real network. Online calibration of the DTA system is enabled to ensure good optimization performance. Toll optimization is tested under multiple experimental scenarios, and the methodology is found able to increase toll revenue compared with the condition when online calibration is not available. It should be noted that the toll rates and revenues presented in this paper are obtained in a simulation environment based on the calibration and optimization algorithms, and as the work is ongoing these results are far from being a recommendation to operators of managed lanes.

Improving Scalability of Generic Online Calibration for Real-Time Dynamic Traffic Assignment Systems

Flexible calibration of dynamic traffic assignment (DTA) systems in real time has important applications in effective traffic management. However, the existing approaches are either limited to small networks or to a specific class of parameters. In this light, this study presents a framework to systematically reduce the dimension of the generic online calibration problem, making it more scalable. Specifically, a state–space formulation of the problem in the reduced dimension space is proposed. Following this the problem is solved using the constrained extended Kalman filter, which is made tractable because of the low dimensionality of the formulated problem. The effectiveness of the proposed approach is demonstrated using a real-world network leading to better state estimation by 13% and better state predictions by 11%—with a 50 fold dimensionality reduction. Insights into choosing the right degree of dimensionality reduction are also discussed. This work has the potential for a more widespread application of real-time DTA systems in practice.

Reducing the Dimension of Online Calibration in Dynamic Traffic Assignment Systems

Effective real-time traffic management strategies often require dynamic traffic assignment systems that are calibrated online. But the computationally intensive nature of online calibration limits their application to smaller networks. This paper presents a dimensionality reduction of the online calibration problem that is based on principal components to overcome this limitation. To demonstrate this approach, the origin–destination flow estimation problem is formulated in relation to its principal components. The efficacy of the procedure was tested with real data on the Singapore Expressway network in an open-loop framework. A reduction in the problem dimension by a factor of 50 was observed with only a 2% loss in estimation accuracy. Further, the computational times were reduced by an order of 100. The procedure led to better predictions, as the principal components captured the structural spatial relationships. This work has the potential to make the online calibration problem more scalable.

Bilevel Generalized Least Squares Estimation of Dynamic Origin–Destination Matrix for Urban Network with Probe Vehicle Data

Methods of estimating dynamic origin–destination (O-D) matrices for urban networks from probe vehicle data are explored. A speed–density function is derived and fitted for different types of roads with the use of the maximum likelihood method. Both a Bayesian method that carefully incorporates prior information and an ordinary method are used to estimate link flows from probe vehicle speed. A dynamic traffic assignment–based bilevel generalized least squares (GLS) estimator considering the distance between the estimated and target O-D matrices as well as the distance between the calculated and observed link flows is formulated to estimate dynamic O-D matrices from estimated link flows. In the iterative solution procedure, the upper level is solved with the extended Bell algorithm, and the microscopic dynamic traffic assignment system VISSIM is applied to produce the assignment matrix in the lower level. A medium-sized signalized network in Tokyo is modeled in a case study in which Bayesian and ordinary methods are compared both in link flow estimation and O-D matrix estimation. Further, the bilevel GLS estimator and bilevel ordinary least squares estimator are implemented and then compared in O-D estimation. The results validate the proposed bilevel GLS estimator.

Calibration Methods for Simulation-Based Dynamic Traffic Assignment Systems

Dynamic Traffic Assignment (DTA) integrates complex transportation demand and network supply simulation models to estimate prevailing traffic conditions, predict future network performance and generate consistent, anticipatory route guidance. Prior to deployment, the DTA’s parameters and inputs must be calibrated to accurately reflect travel behaviour and traffic dynamics. This paper presents a unified framework for off-line and on-line DTA calibration. Off-line calibration simultaneously estimates demand and supply model parameters. On-line calibration jointly updates—in real-time—the off-line estimates in order to more accurately capture current conditions. The developed methods are flexible and can be applied to any simulation model and may utilize any available traffic surveillance information (including Automated Vehicle Identification systems, probe vehicles and other emerging data sources). The off-line and on-line components complement each other to efficiently combine historical and real-time information. The calibration approaches are demonstrated with DynaMIT (Dynamic network assignment for the Management of Information to Travelers), using time-varying count, speed and density data from conventional traffic sensors.

Off–line and on–line calibration of Dynamic Traffic Assignment Systems

Dynamic traffic assignment (DTA) systems integrate complex transportation demand and network supply simulation models to estimate current traffic conditions, predict future network performance and generate consistent, anticipatory route guidance. Before they are applied, DTA system parameters and inputs must be calibrated to accurately reflect travel behavior and traffic dynamics. This paper presents a systematic approach that unifies the off-line and on-line calibration of DTA systems through a common framework. Off-line calibration simultaneously estimates demand and supply model parameters. The on-line calibration jointly updates in real-time the demand and supply parameter values estimated during the off-line step to better reflect prevailing conditions. The methods are general and can utilize any available traffic surveillance information (including emerging data sources, such as Automated Vehicle Identification systems or probe vehicles). The two components complement each other so that the calibration of the DTA system parameters efficiently utilizes both historical as well as real-time information. The calibration approaches are demonstrated with DynaMIT (Dynamic network assignment for the Management of Information to Travelers), using time-varying count, speed and density data obtained from standard loop detectors.

Calibration of Dynamic Traffic Assignment Models with Point-to-Point Traffic Surveillance

Accurate calibration of demand and supply simulators within a dynamic traffic assignment system is critical for consistent travel information and efficient traffic management. Emerging traffic surveillance devices such as automatic vehicle identification (AVI) technology provide a rich source of disaggregated traffic data. A methodology for the joint calibration of demand and supply model parameters using travel time measurements obtained from these emerging traffic-sensing technologies is presented. The calibration problem has been formulated as a stochastic optimization framework. Two different algorithms are used for solving the calibration problem: a gradient approximation-based path search method and a random search metaheuristic. The methodology is first tested by using a small synthetic study network to illustrate its effectiveness and obtain insight into its operation. The methodology is further applied to a real traffic network in Lower Westchester County, New York, to demonstrate its scalability. The estimation results are tested by using a calibrated microscopic traffic simulator. The results are compared with the base case of calibration by the use of only the conventional point sensor data. The results indicate that use of AVI data significantly improves calibration accuracy.

Nonlinear Kalman Filtering Algorithms for On-Line Calibration of Dynamic Traffic Assignment Models

An online calibration approach that jointly estimates demand and supply parameters of dynamic traffic assignment (DTA) systems is presented and empirically validated through an extensive application. The problem can be formulated as a nonlinear state-space model. Because of its nonlinear nature, the resulting model cannot be solved by the Kalman filter, and therefore, nonlinear extensions need to be considered. The following three extensions to the Kalman filtering algorithm are presented: 1) the extended Kalman filter (EKF); 2) the limiting EKF (LimEKF); and 3) the unscented Kalman filter. The solution algorithms are applied to the on-line calibration of the state-of-the-art DynaMIT DTA model, and their use is demonstrated in a freeway network in Southampton, U.K. The LimEKF shows accuracy that is comparable to that of the <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">best</i> algorithm but with vastly superior computational performance. The robustness of the approach to varying weather conditions is demonstrated, and practical aspects are discussed.

A structural state space model for real-time traffic origin–destination demand estimation and prediction in a day-to-day learning framework

Dynamic origin–destination (OD) estimation and prediction is an essential support function for real-time dynamic traffic assignment model systems for ITS applications. This paper presents a structural state space model to systematically incorporate regular demand pattern information, structural deviations and random fluctuations. By considering demand deviations from the a priori estimate of the regular pattern as a time-varying process with smooth trend, a polynomial trend filter is developed to capture possible structural deviations in real-time demand. Based on a Kalman filtering framework, an optimal adaptive procedure is further proposed to capture day-to-day demand evolution, and update the a priori regular demand pattern estimate using new real-time estimates and observations obtained every day. These models can be naturally integrated into a real-time dynamic traffic assignment system and provide an effective and efficient approach to utilize the real-time traffic data continuously in operational settings. A case study based on the Irvine test bed network is conducted to illustrate the proposed methodology.

A COMPARISON OF MACHINE LEARNING MODELS FOR SPEED ESTIMATION

Speed-density relationships are a classic way of modeling stationary traffic relationships. Besides offering valuable insight in traffic stream flows, such relationships are widely used in simulation-based Dynamic Traffic Assignment (DTA) systems. In this paper, alternative approaches for modeling traffic dynamics, appropriate for traffic simulation, are proposed. Their basic premise is the wide availability of sensor data. The approaches are based on machine learning methods such as locally weighted regression and support vector regression. Neural networks are also considered, as they are a well-established approach, successful in many applications. While such models may not provide as much insight into traffic flow theory, they allow for easy incorporation of additional information to speed estimation, and hence, may be more appropriate for use in DTA models, especially simulation based. In particular, in this paper, it is demonstrated (using data from a network in Irvine, CA) that the use of such machine learning methods can improve the accuracy of speed estimation.

Estimation of Traffic Dynamics Models with Machine-Learning Methods

Speed–density relationships are a classic way of modeling stationary traffic relationships. Besides offering valuable insight into traffic stream flows, such relationships are widely used in dynamic traffic assignment (DTA) systems. In this research, an alternative paradigm for traffic dynamics models, appropriate for traffic simulation models and based on machine-learning approaches such as k-means clustering, k-nearest-neighborhood classification, and locally weighted regression is proposed. Although these models may not provide as much insight into traffic flow theory as speed–density relationships do, they allow for easy incorporation of additional information to speed estimation and hence may be more appropriate for use in DTA models, especially simulation-based models. This paper (with data from a network in Irvine, California) demonstrates that such machine-learning methods can considerably improve the accuracy of speed estimation.

Estimation of Traffic Dynamics Models with Machine-Learning Methods

Speed-density relationships are a classic way of modeling stationary traffic relationships. Besides offering valuable insight into traffic stream flows, such relationships are widely used in dynamic traffic assignment (DTA) systems. In this research, an alternative paradigm for traffic dynamics models, appropriate for traffic simulation models and based on machine-learning approaches such as k-means clustering, k-nearest-neighborhood classification, and locally weighted regression is proposed. Although these models may not provide as much insight into traffic flow theory as speed-density relationships do, they allow for easy incorporation of additional information to speed estimation and hence may be more appropriate for use in DTA models, especially simulation-based models. This paper (with data from a network in Irvine, California) demonstrates that such machine-learning methods can considerably improve the accuracy of speed estimation.

Online deployment of dynamic traffic assignment: architecture and run-time management

Key issues for the online deployment of dynamic traffic assignment systems are addressed, including model calibration, computational efficiency and system robustness to input data. A case study of the recent deployment of the DynaMIT route guidance system in Los Angeles is provided as an illustration of critical practical aspects in the deployment process. A preliminary evaluation of the system indicates online feasibility from a computational perspective and validates the system&apos;s ability to replicate off-line data. Online accuracy tests are promising. Ongoing research approaches to enhance system operation and performance are suggested.