Surrogate‐based toll optimization in a large‐scale heterogeneously congested network

Toll optimization in a large‐scale dynamic traffic network is typically characterized by an expensive‐to‐evaluate objective function. In this paper, we propose two toll‐level problems (TLPs) integrated with a large‐scale simulation‐based dynamic traffic assignment model of Melbourne, Australia. The first TLP aims to control the pricing zone (PZ) through a time‐varying joint distance and delay toll such that the network fundamental diagram (NFD) of the PZ does not enter the congested regime. The second TLP is built upon the first TLP by further considering the minimization of the heterogeneity of congestion distribution in the PZ. To solve the two TLPs, a computationally efficient surrogate‐based optimization method, that is, regressing kriging with expected improvement sampling, is applied to approximate the simulation input–output mapping, which can balance well between local exploitation and global exploration. Results show that the two optimal TLP solutions reduce the average travel time in the PZ (entire network) by 29.5% (1.4%) and 21.6% (2.5%), respectively. Reducing the heterogeneity of congestion distribution achieves higher network flows in the PZ and a lower average travel time or a larger total travel time saving in the entire network.     

Time‐Varying Lane‐Based Capacity Reversibility for Traffic Management

Abstract: This article presents a new bi‐level formulation for time‐varying lane‐based capacity reversibility problem for traffic management. The problem is formulated as a bi‐level program where the lower level is the cell‐transmission‐based user‐optimal dynamic traffic assignment (UODTA). Due to its Non‐deterministic Polynomial‐time hard (NP‐hard) complexity, the genetic algorithm (GA) with the simulation‐based UODTA is adopted to solve multiorigin multidestination problems. Four GA variations are proposed. GA1 is a simple GA. GA2, GA3, and GA4 with a jam‐density factor parameter (JDF) employ time‐dependent congestion measures in their decoding procedures. The four algorithms are empirically tested on a grid network and compared based on solution quality, convergence speed, and central processing unit (CPU) time. GA3 with JDF of 0.6 appears best on the three criteria. On the Sioux Falls network, GA3 with JDF of 0.7 performs best. The GA with the appropriate inclusion of problem‐specific knowledge and parameter calibration indeed provides excellent results when compared with the simple GA.     

Applying Projection‐Based Methods to the Asymmetric Traffic Assignment Problem

This article examines the application of a path‐based algorithm to the static and fixed demand asymmetric traffic assignment problem. The algorithm is of the simplicial decomposition type and it solves the equilibration or master problem step by means of five existing projection methods for variational inequality problems to evaluate their performance on real traffic networks. The projection methods evaluated are: (1) a cost approximation‐based method for minimizing the Fukushima's gap function, (2) the modified descent method of Zhu and Marcotte ( 1988 ), (3) the double projection method of Khobotov ( 1987 ) and three of its recently developed variants (Nadezhkina and Takahashi, 2006 ; Wang et al., 2010 ; and He et al., 2012); (4) the method of Solodov and Svaiter ( 1999 ); and (5) the method of Solodov and Tseng ( 1996 ). These projection methods do not require evaluation of the Jacobians of the path cost functions. The source for asymmetries are link costs with interactions, as in the case of priority ruled junctions. The path‐based algorithm has been computationally tested using the previous projection methods on three medium to large networks under different levels of congestion and the computational results are presented and discussed. Comparisons are also made with the basic projection algorithm for the fixed demand asymmetric traffic assignment problem. Despite the lack of monotonicity properties of the test problems, the only method that failed to converge under heavy congestion levels was the basic projection algorithm. The fastest convergence was obtained in all cases solving the master problem step using the method of He et al. (2012), which is a variant of Khobotov's method.     

Wavelet‐Based Denoising for Traffic Volume Time Series Forecasting with Self‐Organizing Neural Networks

Abstract: In their goal to effectively manage the use of existing infrastructures, intelligent transportation systems require precise forecasting of near‐term traffic volumes to feed real‐time analytical models and traffic surveillance tools that alert of network links reaching their capacity. This article proposes a new methodological approach for short‐term predictions of time series of volume data at isolated cross sections. The originality in the computational modeling stems from the fit of threshold values used in the stationary wavelet‐based denoising process applied on the time series, and from the determination of patterns that characterize the evolution of its samples over a fixed prediction horizon. A self‐organizing fuzzy neural network is optimized in its configuration parameters for learning and recognition of these patterns. Four real‐world data sets from three interstate roads are considered for evaluating the performance of the proposed model. A quantitative comparison made with the results obtained by four other relevant prediction models shows a favorable outcome.     

Surrogate‐Based Optimization of Expensive‐to‐Evaluate Objective for Optimal Highway Toll Charges in Transportation Network

This article adopts a family of surrogate‐based optimization approaches to approximate the response surface for the transportation simulation input–output mapping and search for the optimal toll charges in a transportation network. The computational effort can thus be significantly reduced for the expensive‐to‐evaluate optimization problem. Meanwhile, the random noise that always occurs through simulations can be addressed by this family of approaches. Both one‐stage and two‐stage surrogate models are tested and compared. A suboptimal exploration strategy and a global exploration strategy are incorporated and validated. A simulation‐based dynamic traffic assignment model DynusT (Dynamic Urban Systems in Transportation) is utilized to evaluate the system performance in response to different link‐additive toll schemes implemented on a highway in a real road transportation network. With the objective of minimizing the network‐wide average travel time, the simulation results show that implementing the optimal toll predicted by the surrogate model can benefit society in multiple ways. The travelers gain from the 2.5% reduction (0.45 minutes) of the average travel time. The total reduction in the time cost during the extended peak hours would be around US$65,000 for all the 570,000 network users assuming a US$15 per hour value of time. Meanwhile, the government benefits from the 20% increase of toll revenue compared to the current situation. Thus, applying the optimized pricing scheme in real world can be an encouraging policy option to enhance the performance of the transportation system in the study region.     

Solving the first‐mile ridesharing problem using autonomous vehicles

Autonomous vehicles (AVs) are paving a way to reshape the operation and management of urban transportation systems by improving travel mobility. In this study, we propose to use AVs for solving the first‐mile (FM) problem that aims to transport passengers from their homes to metro stations. Passengers submit travel requests in advance and a fleet operator dispatches AVs and arranges ridesharing in a rolling horizon framework. The ridesharing is implemented by assigning one AV to serve several requests subject to the vehicle capacity, the maximum travel time, and the accessibility constraints. A mixed integer linear programming (MILP) model is formulated to determine the AV dispatch and ridesharing schemes for the minimum operational costs. Then, another MILP model with the objective of the maximum user satisfaction is formulated for the purpose of comparison. A cluster‐based solution method is designed to deal with the large‐scale FM problem. Extensive numerical experiments are conducted to demonstrate the application of the proposed method. Results show that ridesharing can reduce both required AV fleet size and vehicle traveled miles. The proposed solution method is able to solve the problem efficiently and fulfil the requirement of online computation.     

End‐to‐End Deep Learning Methodology for Real‐Time Traffic Network Management

This article presents a novel real‐time traffic network management system using an end‐to‐end deep learning (E2EDL) methodology. A computational learning model is trained, which allows the system to identify the time‐varying traffic congestion pattern in the network, and recommend integrated traffic management schemes to reduce this congestion. The proposed model structure captures the temporal and spatial congestion pattern correlations exhibited in the network, and associates these patterns with efficient traffic management schemes. The E2EDL traffic management system is trained using a laboratory‐generated data set consisting of pairings of prevailing traffic network conditions and efficient traffic management schemes designed to cope with these conditions. The system is applied for the US‐75 corridor in Dallas, Texas. Several experiments are conducted to examine the system performance under different traffic operational conditions. The results show that the E2EDL system achieves travel time savings comparable to those recorded for an optimization‐based traffic management system.     

Development of a Data‐Driven Framework for Real‐Time Travel Time Prediction

Travel time prediction is one of the most important components in Intelligent Transportation Systems implementation. Various related techniques have been developed, but the efforts for improving the applicability of long‐term prediction in a real‐time manner have been lacking. Existing methods do not fully utilize the advantages of the state‐of‐the‐art cloud system and large amount of data due to computation issues. We propose a new prediction framework for real‐time travel time services in the cloud system. A distinctive feature is that the prediction is done with the entire data of a road section to stably and accurately produce the long‐term (at least 6‐hour prediction horizon) predicted value. Another distinctive feature is that the framework uses a hierarchical pattern matching called Multilevel k‐nearest neighbor (Mk‐NN) method which is compared with the conventional k‐NN method and Nearest Historical average method. The results show that the method can more accurately and robustly predict the long‐term travel time with shorter computation time.     

A Generic Approach to Estimate Freeway Traffic Time Using Vehicle ID‐Matching Technologies

New technologies have emerged to estimate the travel time on freeways by matching certain unique identifications of passing vehicles at different locations. These types of technologies share many similarities despite having different mechanisms. In this article, a generic method is presented to estimate freeway travel times using vehicle ID‐matching technologies. In particular, the new method addresses two long‐standing challenges: outlier screening and travel time estimation. Innovations include (1) using both statistical methods and traffic flow theory to screen outliers; and (2) accounting for mechanisms of various equipment measurement errors. The effectiveness of the proposed method is demonstrated using simulation and shown to be more accurate and responsive to travel time changes than methods based on the use of traditional inductive loops.     

Real‐Time Estimation of Pollution Emissions and Dispersion from Highway Traffic

Traffic‐related air pollution is a serious problem with significant health impacts in both urban and suburban environments. Despite an increased realization of the negative impacts of air pollution, assessing individuals' exposure to traffic‐related air pollution remains a challenge. Obtaining high‐resolution estimates are difficult due to the spatial and temporal variability of emissions, the dependence on local atmospheric conditions, and the lack of monitoring infrastructure. This presents a significant hurdle to identifying pollution concentration hot spots and understanding the emission sources responsible for these hot spots, which in turn makes it difficult to reduce the uncertainty of health risk estimates for communities and to develop policies that mitigate these risks. We present a novel air pollution estimation method that models the highway traffic state, highway traffic‐induced air pollution emissions, and pollution dispersion, and describe a prototype implementation for the San Francisco Bay Area. Our model is based on the availability of real‐time traffic estimates on highways, which we obtain using a traffic dynamics model and an estimation algorithm that augments real‐time data from both fixed sensors and probe vehicles. These traffic estimates combined with local weather conditions are used as inputs to an emission model that estimates pollutant levels for multiple gases and particulates in real‐time. Finally, a dispersion model is used to assess the spread of these pollutants away from the highway source. Maps generated using the output of the dispersion model allow users to easily analyze the evolution of individual pollutants over time, and provides transportation engineers and public health officials with valuable information that can be used to minimize health risks.     

Evaluation of Information Applications of a Self‐Organizing Distributed Traffic Information System for a Large‐Scale Real‐World Traffic Network

Abstract: This article presents an evaluation of the system performance of a proposed self‐organizing, distributed traffic information system based on vehicle‐to‐vehicle information‐sharing architecture. Using microsimulation, several information applications derived from this system are analyzed relative to the effectiveness and efficiency of the system to estimate traffic conditions along each individual path in the network, to identify possible incidents in the traffic network, and to provide rerouting strategies for vehicles to escape congested spots in the network. A subset of vehicles in the traffic network is equipped with specific intervehicle communication devices capable of autonomous traffic surveillance, peer‐to‐peer information sharing, and self‐data processing. A self‐organizing traffic information overlay on the existing vehicular roadway network assists their independent evaluation of route information, detection of traffic incidents, and dynamic rerouting in the network based both on historical information stored in an in‐vehicle database and on real‐time information disseminated through intervehicle communications. A path‐based microsimulation model is developed for these information applications and the proposed distributed traffic information system is tested in a large‐scale real‐world network. Based on simulation study results, potential benefits both for travelers with such equipment as well as for the traffic system as a whole are demonstrated.     

Graph‐Based Modeling of Information Flow Evolution and Propagation under V2V Communications‐Based Advanced Traveler Information Systems

A vehicle equipped with a vehicle‐to‐vehicle (V2V) communications capability can continuously update its knowledge on traffic conditions using its own experience and anonymously obtained travel experience data from other such equipped vehicles without any central coordination. In such a V2V communications‐based advanced traveler information system (ATIS), the dynamics of traffic flow and intervehicle communication lead to the time‐dependent vehicle knowledge on the traffic network conditions. In this context, this study proposes a graph‐based multilayer network framework to model the V2V‐based ATIS as a complex system which is composed of three coupled network layers: a physical traffic flow network, and virtual intervehicle communication and information flow networks. To determine the occurrence of V2V communication, the intervehicle communication layer is first constructed using the time‐dependent locations of vehicles in the traffic flow layer and intervehicle communication‐related constraints. Then an information flow network is constructed based on events in the traffic and intervehicle communication networks. The graph structure of this information flow network enables the efficient tracking of the time‐dependent vehicle knowledge of the traffic network conditions using a simple graph‐based reverse search algorithm and the storage of the information flow network as a single graph database. Further, the proposed framework provides a retrospective modeling capability to articulate explicitly how information flow evolves and propagates. These capabilities are critical to develop strategies for the rapid flow of useful information and traffic routing to enhance network performance. It also serves as a basic building block for the design of V2V‐based route guidance strategies to manage traffic conditions in congested networks. Synthetic experiments are used to compare the graph‐based approach to a simulation‐based approach, and illustrate both memory usage and computational time efficiencies.     

A Mixed User‐Equilibrium and System‐Optimal Traffic Flow for Connected Vehicles Stated as a Complementarity Problem

Connected vehicles (CVs), be they autonomous vehicles or a fleet of cargo carriers or Uber, are a matter of when they become a reality and not if. It is not unreasonable to think that CV technology may have a far‐reaching impact, even to the genesis of a completely new traffic pattern. To this end, the literature has yet to address the routing behavior of the CVs, namely traffic assignment problem (TAP) (perhaps it is assumed, they ought to follow the traditional shortest possible paths, known as user equilibrium [UE]). It is possible that real‐time data could be derived from the vehicles’ communications that in turn could be used to achieve a better traffic circulation. In this article, we propose a mathematical formulation to ensure the CVs are seeking the system optimal (SO) principles, while the remainder continue to pursue the old‐fashioned UE pattern. The model is formulated as a nonlinear complementarity problem (NCP). This article contributes to the literature in three distinct ways: (i) mathematical formulation for the CVs’ routing, stated as a mixed UE‐SO traffic pattern, is proposed; (ii) a variety of realistic features are explicitly considered in the solution to the TAP including road capacity, elastic demand, multiclass and asymmetric travel time; and (iii) formal proof of the existence and uniqueness of the solutions are also presented. The proposed methodology is applied to the networks of Sioux‐Falls and Melbourne.     

Cross‐comparison of convergence algorithms to solve trip‐based dynamic traffic assignment problems

Solving a dynamic traffic assignment problem in a transportation network is a computational challenge. This study first reviews the different algorithms in the literature used to numerically calculate the user equilibrium (UE) related to dynamic network loading. Most of them are based on iterative methods to solve a fixed‐point problem. Two elements must be computed: the path set and the optimal path flow distribution between all origin–destination pairs. In a generic framework, these two steps are referred to as the outer and the inner loops, respectively. The goal of this study is to assess the computational performance of the inner loop methods that calculate the path flow distribution for different network settings (mainly network size and demand levels). Several improvements are also proposed to speed up convergence: four new swapping algorithms and two new methods for the step size initialization used in each descent iteration. All these extensions significantly reduce the number of iterations to obtain a good convergence rate and drastically speed up the overall simulations. The results show that the performance of different components of the solution algorithm is sensitive to the network size and saturation. Finally, the best algorithms and settings are identified for all network sizes with particular attention being given to the largest scale.     

A Dantzig‐Wolfe Decomposition‐Based Heuristic for Off‐line Capacity Calibration of Dynamic Traffic Assignment

Abstract: One of the critical elements in considering any real‐time traffic management strategy requires assessing network traffic dynamics. Traffic is inherently dynamic, since it features congestion patterns that evolve over time and queues that form and dissipate over a planning horizon. Dynamic traffic assignment (DTA) is therefore gaining wider acceptance among agencies and practitioners as a more realistic representation of traffic phenomena than static traffic assignment. Though it is imperative to calibrate the DTA model such that it can accurately reproduce field observations and avoid erroneous flow predictions when evaluating traffic management strategies, DTA calibration is an onerous task due to the large number of variables that can be modified and the intensive computational resources required. To compliment other research on behavioral and trip table issues, this work focuses on DTA capacity calibration and presents an efficient Dantzig‐Wolfe decomposition‐based heuristic that decomposes the problem into a restricted master problem and a series of pricing problems. The restricted master problem is a capacity manipulation problem, which can be solved by a linear programming solver. The pricing problem is the user optimal DTA which can be optimally solved by an existing combinatorial algorithm. In addition, the proposed set of dual variable approximation techniques is one of a very limited number of approaches that can be used to estimate network‐wide dual information in facilitating algorithmic designs while maintaining scalability. Two networks of various sizes are empirically tested to demonstrate the efficiency and efficacy of the proposed heuristic. Based on the results, the proposed heuristic can calibrate the network capacity and match the counts within a 1% optimality gap.     

Reliability‐Based Transit Assignment for Congested Stochastic Transit Networks

Abstract: This article proposes a nonlinear complementarity problem (NCP) formulation for the risk‐aversive stochastic transit assignment problem in which in‐vehicle travel time, waiting time, capacity, and the effect of congestion are considered as stochastic variables simultaneously and both their means and variances are incorporated into the formulation. A new congestion model is developed and captured in the proposed NCP formulation to account for different effects of on‐board passengers and passengers waiting at stops. A reliability‐based user equilibrium condition is also defined based on the proposed generalized concept of travel time budget referred to as effective travel cost, and is captured in the formulation. A column generation based algorithm is proposed to solve the NCP formulation. A survey was conducted to validate that the degree of risk aversion of transit passengers affects their route choices. Numerical studies were performed to demonstrate the problem and the effectiveness of the proposed algorithm. The results obtained show that underestimating the congestion effect and ignoring the risk aversion behavior can overestimate the patronage of transit service, which have profound implications on the profit of the operators involved and the development of transit network design models.     

Seismic response of semi‐active friction‐damped reinforced concrete structures with self‐variable stiffness

The influence of structural self‐variable stiffness and semi‐active friction dampers on the behavior of reinforced concrete (RC) buildings during strong earthquakes is discussed. A fully braced six‐story beamless RC frame is analyzed. The effect of concrete braces (with only constructive reinforcement) as a self‐variable mechanism is studied. It is shown that up to a certain limit the frame itself controls its behavior by adapting its dynamic characteristics in the real time of the earthquake. This self‐adaptation is achieved by autonomous disengagement of the braces under tension and their further nonlinear action under compression. The system has several levels of seismic adaptation, and it selects one of them for enhanced response to the given earthquake. However, when the limit is reached, further self‐adaptation of the frame becomes impossible. The occurrence of an earthquake of higher magnitude can then lead to disengagement of the concrete braces under compression, intensifying structural damage and even causing collapse. The use of semi‐active controlled friction dampers is proposed as a means of preventing the collapse of braces under compression, thereby enabling structures to withstand earthquakes. The forces in the friction dampers are regulated according to an optimal control algorithm. Modulation of the friction level in real time during the earthquake yields additional improvement of structural seismic behavior and obviates the need for retrofitting. Copyright © 2007 John Wiley & Sons, Ltd.     

An ensemble machine learning‐based modeling framework for analysis of traffic crash frequency

This study is, to our knowledge, the first in the literature to introduce a modeling framework for analyzing traffic crash frequency based on a series of ensemble machine learning (EML) methods. The main objectives of this study are fourfold: (a) to design a systematic EML‐based framework for crash frequency analysis, (b) to comprehensively compare the performance in analyzing crash frequency by different optimized EML models, (c) to identify significant contributors to crash frequency, and (d) to propose the approach to construct schemes to reduce traffic crashes. To achieve the research goal, the Highway Safety Information System database that includes records of over 1.5 million crashes is employed for model estimation and validation. We first optimize the EML models for crash analysis via the k‐fold cross‐training, including the two averaging methods of random forest and extremely randomized trees, and the two boosting methods of adaptive boosting and gradient tree boosting. Then, we assess the behavior of the optimized models, and conduct a sensitivity test to validate the stability of model performance. Furthermore, we evaluate the relative importance of features to crash frequency by using the Gini diversity index. The results indicate that the two averaging EML models can achieve desirable performance in crash frequency analysis, which outperform the two boosting EML models, in terms of predictive accuracy, generalization ability, and stability. From the results, we explore new insights into the significance of contributors to crash occurrence. Finally, we present the approach of safety improvements for transport facilities.     

Simulation‐based dynamic traffic assignment: Meta‐heuristic solution methods with parallel computing

The aim of this study is to solve the large‐scale dynamic traffic assignment (DTA) model using a simulation‐based framework, which is computationally a challenging problem. Many studies have been performed on developing an efficient algorithm to solve DTA. Most of the existing algorithms are based on path‐swapping descent direction methods. From the computational standpoint, the main drawback of these methods is that they cannot be parallelized. This is because the existing algorithms need to know the results of the last iteration to determine the next best path flow for the next iteration. Thus, their performance depends on the single initial or intermediate solution, which means they exploit a solution that satisfies the equilibrium conditions more than explore the solution space for the optimal solution. More specifically, the goal of this study is to overcome the drawbacks of serial algorithms by using meta‐heuristic algorithms known to be parallelizable and that have never been applied to the simulation‐based DTA problem. This study proposes two new solution methods: a new extension of the simulated annealing and an adapted genetic algorithm. With parallel simulation, the algorithm runs more simulations in comparison with existing methods, but the algorithm explores the solution space better and therefore obtains better solutions in terms of closeness to the optimal solution and computation time compared to classical methods.     

Random Process Model for Urban Traffic Flow Using a Wavelet‐Bayesian Hierarchical Technique

Abstract: The existing well‐known short‐term traffic forecasting algorithms require large traffic flow data sets, including information on current traffic scenarios to predict the future traffic conditions. This article proposes a random process traffic volume model that enables estimation and prediction of traffic volume at sites where such large and continuous data sets of traffic condition related information are unavailable. The proposed model is based on a combination of wavelet analysis (WA) and Bayesian hierarchical methodology (BHM). The average daily “trend” of urban traffic flow observations can be reliably modeled using discrete WA. The remaining fluctuating parts of the traffic volume observations are modeled using BHM. This BHM modeling considers that the variance of the urban traffic flow observations from an intersection vary with the time‐of‐the‐day. A case study has been performed at two busy junctions at the city‐centre of Dublin to validate the effectiveness of the strategy.