Non-recurrent Congestion Research Articles

Traffic System Anomaly Detection using Spatiotemporal Pattern Networks

Traffic dynamics in the urban interstate system are critical in terms of highway safety and mobility. This paper proposes a systematic data mining technique to detect traffic system-level anomalies in a batch-processing fashion. Built on the concepts of symbolic dynamics, a spatiotemporal pattern network (STPN) architecture is developed to capture the system characteristics. This novel spatiotemporal graphical modeling approach is shown to be able to extract salient time series features and discover spatial and temporal patterns for a traffic system. An information-theoretic metric is used to quantify the causal relationships between sub-systems. By comparing the structural similarity of the information-theoretic metrics of the STPNs learnt from each day, a day with anomalous system characteristics can be identified. A case study is conducted on an urban interstate in Iowa, USA, with 11 roadside radar sensors collecting 20-second resolution speed and volume data. After applying the proposed methods on one-month data (Feb. 2017), several system-level anomalies are detected. The potential causes that include inclement weather condition and non-recurring congestion are also verified to demonstrate the efficacies of the proposed technique. Compared to the traditional predefined performance measures for the traffic systems, the proposed framework has advantages in capturing spatiotemporal features in a fast and scalable manner.

Identifying Critical Clusters of Traffic-Loading Events in Recurrent Congested Conditions on a Long-Span Road Bridge

This paper examines the nature of traffic loading in recurrent congested traffic conditions on a long-span suspension bridge. Traffic flow and percentage of trucks are extracted from image data and a cluster analysis performed to classify the data into four clusters. One cluster (MTHF, medium truck percentage and high flow) is identified that incorporates almost 50% of the hours of traffic data scattered throughout the day. Site-specific load assessment confirms that this MTHF cluster is the most critical for the bridge considered, the Forth Road Bridge in Scotland. For non-recurrent congestion, another cluster (HTLF, high percentage of trucks and low flow) is shown to govern but this finding is highly site-specific, depending on the relative frequency of the different types of congestion. A comparison of the maximum hourly/daily MTHF load effect of the cable force for five notional bridges shows that a 100% increase in the bridge span generates an increase of about 65% in the characteristic load effect.

Evaluating Active Traffic Management (ATM) Strategies under Non-Recurring Congestion: Simulation-Based with Benefit Cost Analysis Case Study

Dynamic hard shoulder running and ramp closure are two active traffic management (ATM) strategies that are used to alleviate highway traffic congestion. This study aims to evaluate the effects of these two strategies on congested freeways under non-recurring congestion. The study’s efforts can be considered in two parts. First, we performed a detailed microsimulation analysis to quantify the potential benefits of these two ATM strategies in terms of safety, traffic operation, and environmental impact. Second, we evaluated the implementation feasibility of these two strategies. The simulation results indicated that the implementation of the hard shoulder showed a 50%–57% reduction in delay, a 41%–44% reduction in fuel consumption and emissions, and a 15%–18% increase in bottleneck throughput. By contrast, the implementation of ramp closure showed a 20%–34% decrease in travel time, a 6%–9% increase in bottleneck throughput, and an 18%–32% reduction in fuel consumption and emissions. Eventually, both strategies were found to be economically feasible.

A Bayesian modeling framework for crash severity effects of active traffic management systems

Transportation agencies utilize Active traffic management (ATM) systems to dynamically manage recurrent and non-recurrent congestion based on real-time conditions. While these systems have been shown to have some safety benefits, their impact on injury severity outcomes is currently uncertain. This paper used full Bayesian mixed logit models to quantify the impact that ATM deployment had on crash severities. The estimation results revealed lower severities with ATM deployment. Marginal effects for ATM deployments that featured hard shoulder running (HSR) revealed lower likelihoods for severe and moderate injury crashes of 15.9 % and for minor injury crashes of 10.1 %. The likelihood of severe and moderate injury crashes and minor injury crashes reduced by 12.4 % and 8.33 % with ATM without HSR. The models were observed to be temporally transferable and had forecast error of 0.301 and 0.304 for the two models, revealing better performance with validation data. These results have implications for improving freeway crash risk at critical locations.

On the possibility of short-term traffic prediction during disaster with machine learning approaches: An exploratory analysis

Since the cost and time required to finetune parameters in traditional short-term traffic prediction models such as traffic simulators are very high, the prediction models have been developed mainly for managing recurrent congestion, rather than non-recurrent congestion caused, for example, by disaster. Machine learning models are promising candidates for traffic prediction during non-recurrent congestion due to their ability to tune parameters without a-priori knowledge, while their applicability to non-recurrent conditions has rarely been explored. To fill in this gap, this study conducts an exploratory analysis on the applicability of various machine learning models during a transportation network disruption with particular focuses on their ability to predict traffic states and the interpretability of the results. The analysis is conducted by using data obtained during the massive transport network disruption which occurred in Hiroshima in July 2018 due to heavy rain and subsequent landslides. The models tested include random forest, support vector machine, XGBoost, shallow feed-forward neural network, and deep feed-forward neural network. The results indicate that random forest and XGBoost methods produced the best results in terms of prediction accuracy. On the other hand, deep neural network models produce better results in terms of the interpretability of the results, i.e., the results can be logically explained from the perspective of existing traffic flow theory. These findings indicate that the model which produces the best prediction accuracy is not always the best for practical use since it does not mimic the mechanisms of congestion occurrence.

Implications of Spatiotemporal Data Aggregation on Short-Term Traffic Prediction Using Machine Learning Algorithms

Short-term traffic prediction is a key component of Intelligent Transportation Systems. It uses historical data to construct models for reliably predicting traffic state at specific locations in road networks in the near future. Despite being a mature field, short-term traffic prediction still poses some open problems related to the choice of optimal data resolution, prediction of nonrecurring congestion, and the modelling of relevant spatiotemporal dependencies. As a step towards addressing these problems, this paper investigates the ability of Artificial Neural Networks, Random Forests, and Support Vector Regression algorithms to reliably model traffic flow at different data resolutions and respond to unexpected traffic incidents. We also explore different feature selection methods to identify and better understand the spatiotemporal attributes that most influence the reliability of these models. Experimental results indicate that data aggregation does not necessarily achieve good performance for multivariate spatiotemporal machine learning models. The models learned using high-resolution 30-second input data outperformed the corresponding baseline ARIMA models by 8%. Furthermore, feature selection based on Recursive Feature Elimination resulted in models that outperformed those based on linear correlation-based feature selection.

Deep Learning Approach for Predictive Analytics to Support Diversion during Freeway Incidents

Route diversion during incidents on freeways has been proven to be a useful tactic to mitigate non-recurrent congestion. However, the capacity constraints created by the signals on the alternative routes put limits on the diversion process since the typical time-of-day (TOD) signal control cannot handle the sudden increase in the traffic on the arterials because of diversion. Thus, there is a need for active transportation management strategies that support agencies in identifying the potential diversion routes for freeway incidents and the need for adjusting the traffic signal timing under different incident and traffic conditions. This paper investigates the use of a data analytic approach based on the long short-term memory (LSTM) deep neural network method to predict the alternative routes dynamically using incident attributes and traffic status on the freeway, and travel time on both the freeway and alternative routes during the incident. Additionally, a methodology is proposed for the development of special signal plans for the critical intersections on the alternative arterials based on the results from the LSTM neural network, combined with simulation modeling, and signal timing optimization. The methodology developed in the paper can be easily implemented by the transportation agencies, as it is based on data that are generally available to the agencies. The results from this paper indicate that the developed methodology can be used as part of a decision support system (DSS) to manage the traffic proactively during the incidents on the freeways.

A deep fusion model based on restricted Boltzmann machines for traffic accident duration prediction

Traffic accidents causing nonrecurrent congestion can decrease the capacity of highways and increase car emissions. Some models in previous studies have been built based on artificial intelligence or statistical theory because estimating the duration of an accident can aid traffic operation and management. However, only characteristics of traffic accidents were considered in most models; the spatial–temporal correlations of traffic flow were always ignored. In this study, a deep fusion model, which can simultaneously handle categorical and continuous variables, is proposed. The model considers not only the characteristics of traffic accidents but also the spatial–temporal correlations in traffic flow. In this model, a stacked restricted Boltzmann machine (RBM) is used to handle the categorical variables, a stacked Gaussian-Bernoulli RBM is used to handle the continuous variables, and a joint layer is used to fuse the extracted features. With extracted I-80 data, the performance of the proposed model was evaluated and compared to some benchmark models. Furthermore, the target variable (duration) was divided into ten groups, and then the evaluation criteria of the models of each group were calculated. The results show that the novel model outperforms some previous models and that the fusion of different types of variables can improve prediction accuracy. In conclusion, the proposed model can fully mine nonlinear and complex patterns in traffic accident data and traffic flow data. The fusion of features is important to predict traffic accident durations.

Combining Machine Learning and Fuzzy Rule-Based System in Automating Signal Timing Experts’ Decisions during Non-Recurrent Congestion

Events such as surges in demand or lane blockages can create queue spillbacks even during off-peak periods, resulting in delays and spillbacks to upstream intersections. To address this issue, some transportation agencies have started implementing processes to change signal timings in real time based on traffic signal engineers’ observations of incident and traffic conditions at the intersections upstream and downstream of the congested locations. Decisions to change the signal timing are governed by many factors, such as queue length, conditions of the main and side streets, potential of traffic spilling back to upstream intersections, the importance of upstream cross streets, and the potential of the queue backing up to a freeway ramp. This paper investigates and assesses automating the process of updating the signal timing plans during non-recurrent conditions by capturing the history of the responses of the traffic signal engineers to non-recurrent conditions and utilizing this experience to train a machine learning model. A combination of recursive partitioning and regression decision tree (RPART) and fuzzy rule-based system (FRBS) is utilized in this study to deal with the vagueness and uncertainty of human decisions. Comparing the decisions made based on the resulting fuzzy rules from applying the methodology with previously recorded expert decisions for a project case study indicates accurate recommendations for shifts in the green phases of traffic signals. The simulation results indicate that changing the green times based on the output of the fuzzy rules decreased delays caused by lane blockages or demand surge.

Estimating the Probability That a Vehicle Reaches a Near-Term Goal State Using Multiple Lane Changes

This paper proposes a model to estimate the probability of a vehicle reaching a near-term goal state using one or multiple lane changes based on parameters corresponding to traffic conditions and driving behavior. The proposed model not only has broad application in path planning and autonomous vehicle navigation, it can also be incorporated in advance warning systems to reduce traffic delay during recurrent and non-recurrent congestion. The model is first formulated for a two-lane road segment through systemic reduction of the number of parameters and transforming the problem into an abstract statistical form, for which the probability can be calculated numerically. It is then extended to cases with a higher number of lanes using the law of total probability. VISSIM simulations are used to validate the predictions of the model and study the effect of different parameters on the probability. For most cases, simulation results are within 4% of model predictions, and the effect of different parameters such as driving behavior and traffic density on the probability match our expectation. The model can be implemented with near real-time performance, with computation time increasing linearly with the number of lanes.

Crash Classification by Congestion Type for Highways

Effective management of highway networks requires a thorough understanding of the conditions under which vehicular crashes occur. Such an understanding can and should inform related operational and resource allocation decisions. This paper presents an easily implementable methodology that can classify all reported crashes in terms of the operational conditions under which each crash occurred. The classification methodology uses link-based speed data. Unlike previous secondary collision identification schemes, it neither requires an a priori identification of the precipitating incident nor definition of the precipitating incident’s impact area. To accomplish this objective, the methodology makes use of a novel scheme for distinguishing between recurrent and non-recurrent congestion. A 500-crash case study was performed using a 274 km section of the I-40 in North Carolina. Twelve percent of the case study crashes were classified as occurring in non-recurrent congestion. Thirty-seven percent of the crashes in non-recurrent congestion classified were identified within unreported primary incidents or crashes influence area. The remainder was classified as primary crashes occurring in either uncongested conditions (84%) or recurrent congestion (4%). The methodology can be implemented in any advanced traffic management system for which crash time and link location are available along with corresponding archived link speed data are available.

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.

Simulation-based Evaluation of Using Variable Speed Limit in Traffic Incidents

Abstract Variable Speed Limit (VSL) systems are used to improve the traffic conditions on road by adjusting the speed limits according to current traffic situations. The variable speed limit system usually comprises of stationary detectors to estimate the traffic condition and dynamic variable message signs at predefined locations for the application of new speed limits. In connected environment, the system can recognize bottlenecks due to the incident and, further, it is possible to use direct control of the connected vehicles to adjust vehicle speeds towards the new traffic situation. In this study, we propose a variable speed limit framework based on connected vehicles environment to improve the management of non-recurrent congestion. The proposed framework is evaluated in terms of traffic efficiency, safety, and environmental impact using microscopic traffic simulation. Furthermore, economic evaluation of these strategies is performed to determine the financial feasibility of their implementation. The results indicate that the VSL system manage to improve traffic efficiency, safety and environmental impact during the incidents. However, it is found that the results depend on incident location and incident severity (number of lanes blocked, and the incident duration).

Determinants of the congestion caused by a traffic accident in urban road networks

Non-recurrent congestion is frustrating to travelers as it often causes unexpected delay, which would result in missing important meetings or appointments. Major causes of non-recurrent congestion include adverse weather conditions, natural hazards, and traffic accidents. Although there has been a proliferation of studies that investigate how adverse weather conditions and natural hazards impact road congestion in urban road networks, studies that look into determinants of the congestion caused by a traffic accident are scarce. This research fills in this gap in the literature. When a traffic accident occurs on an urban link, the congestion would propagate to and affect adjacent links. We develop a modified version of the Dijkstra's algorithm to identify the set of links in the neighborhood of the accident. We first measure the level of congestion caused by the traffic accident as the reduction in traveling speed on those links. As the impact of congestion varies both in space and in time, we then estimate a generalized linear mixed-effects model with spatiotemporal panel data to identify its determinants. Finally, we conduct a case study using real data in Beijing. We find that: (1) the level of congestion is mostly associated with the types of the traffic accidents, the types of vehicles involved, and the occurrence time; (2) for the three types of traffic accidents, namely, scrape among vehicles, collisions with fixed objects, and rear-end collisions, the level of congestion associated with the first two types are comparable, while that associated with the third type is 8.43% more intense; (3) for the types of vehicles involved, the level of congestion involving buses/trucks is 6.03% more intense than those involving only cars; (4) for the occurrence time, the level of congestion associated with morning peaks and afternoon peaks are 5.87% and 6.57% more intense than that associated with off-peak hours, respectively.

Traffic density on corridors subject to incidents: models for long-term congestion management

The purpose of this research is to provide a faster and more efficient method to determine traffic density behavior for long-term congestion management using minimal statistical information. Applications include road work, road improvements, and route choice. To this end, this paper adapts and generalizes two analytical models (for non-peak and peak hours) for the probability mass function of traffic density for a major highway. It then validates the model against real data. The studied corridor has a total of 36 sensors, 18 in each direction, and the traffic experiences randomly occurring service deterioration due to accidents and inclement weather such as snow and thunderstorms. We base the models on queuing theory, and we compare the fundamental diagram with the data. This paper supports the validity of the models for each traffic condition under certain assumptions on the distributional properties of the associated random parameters. It discusses why these assumptions are needed and how they are determined. Furthermore, once the models are validated, different scenarios are presented to demonstrate traffic congestion behavior under various deterioration levels, as well as the estimation of traffic breakdown. These models, which account for non-recurrent congestion, can improve decision making without the need for extensive datasets or time-consuming simulations.

Recurrent Congestion Impact based on Spatiotemporally Historic Congested Information — Case Study: Separating Collision-Induced Congestion

Transportation jurisdictions should monitor mobility and reliability of roadway systems in order to adequately invest capacity expansion and deployment of ITS technologies to alleviate congestion effectively and efficiently. In recent years, several link-based bottleneck identification schemes have estimated bottleneck impact factors on freeways based on the characteristics of congestion. However, those have used congestion data with no attention to distinguishing recurrent level of at the same “bottleneck” location. Most existing studies that distinguish between recurrent and non-recurrent congestion have focused on separating non-recurrent congestion from recurrent congestion only for intensity of congestion using parameters for the speed distribution in a time of day in a segment or point. As such, this study introduced a data-driven procedure for quantifying spatiotemporal “recurrent” congestion impact. In addition, this study used spatiotemporally historic congestion information and generated stochastic spatiotemporal congestion distributions in terms of congestion types. Using the relationship between the distributions of recurrent and non-recurrent congestion occurring at bottlenecks, the bottleneck impacts were estimated by capturing spatial and temporal impact of recurrent bottleneck from that of non-recurrent congestion occurring at recurrent bottleneck. The proposed approach represents a significant improvement in the understanding and monitoring of mobility on freeways. This can be directly applied to evaluate and rank bottlenecks.

Simulation and analysis of non-recurrent traffic congestion triggered by crashes in road networks using a grid-based approach

The non-recurrent traffic congestion triggered by crashes is one of the most important factors that undermine the traffic efficiency of urban road networks. In this article, an improved cellular automaton model was proposed to simulate the non-recurrent congestion triggered by crashes in grid networks with signalized intersections. Four rules were adopted to represent vehicle movements on road sections and intersections. The network speed is adopted to capture the propagation and dissipation of the non-recurrent congestion. The effect of main influencing factors of crashes on the road network was evaluated through the simulation. Simulation results showed the incident duration and areas affected by the distance between the crash point and the upstream intersection, the number of closed lanes, and the crash duration. In addition, the stop-start wave was observed in the simulation. The realistic findings from the simulations validated the model to have the potential for practical applications in the analysis of the non-recurrent congestion triggered by crashes.

Risk analysis of traffic congestion due to problem in heavy vehicles: a concept

One of the most common problems on roads is traffic congestion caused by problems with heavy vehicles (e.g. trucks, trailers). The consequences of this problem often harm the wider community, both in material and non-material forms such as fuel waste and loss of time. Several previous studies have tried to look for factors that cause traffic congestion, but it has not been able to provide a complete understanding of the root causes and who are the stakeholders who must have an important role in solving this problem. This study aims to develop a research framework to get more better understanding about congestion caused by problems with heavy vehicles, which can be categorized as a type of non-recurrent congestion (NRC) that is dynamic and unpredictable. Risk management prioritizes a proactive approach before an event occurs, so the impact of risk can be minimized. Probability and Impact Matrix techniques are used to determine risk priority. Furthermore, to find the root causes of traffic congestion problems, the Fault Tree Analysis (FTA) method and Social Network Analysis (SNA) are considered to be quite potential to be used to describe complex patterns of relationships among stakeholders. The results of this study are expected to provide more complete information to understand the problem of congestion due to the problem of heavy vehicles, so that a more comprehensive solution can be formulated.

A data‐driven approach to determining freeway incident impact areas with fuzzy and graph theory‐based clustering

AbstractDetermining spatiotemporal impact areas of incidents plays a significant role in incident impact analysis. Although existing empirical methods have proven to be promising, they suffer from the drawbacks that limit their wide applications in automated freeway safety management. This study presents a data‐driven approach to automatically determining the spatiotemporal impact areas of freeway incidents. The spatiotemporal contour plots were first constructed using three representative traffic measures. Next, a nonrecurrent congestion area identification method based on fuzzy clustering was developed. To distinguish possible multiple independent blocks in the nonrecurrent congestion area, a clustering algorithm based on graph theory was adopted. The incident impact areas were then determined by conducting a postprocessing strategy. The incident records and the associated traffic flow data, collected on I‐5 freeway segments in San Diego Region, CA, were used to evaluate the proposed approach. Experimental results show the proposed approach can automatically and properly determine incident impact areas while accounting for the uncertainty resulting from traffic variations.

Deep Learning System for Vehicular Re-Routing and Congestion Avoidance

Delays in transportation due to congestion generated by public and private transportation are common in many urban areas of the world. To make transportation systems more efficient, intelligent transportation systems (ITS) are currently being developed. One of the objectives of ITS is to detect congested areas and redirect vehicles away from them. However, most existing approaches only react once the traffic jam has occurred and, therefore, the delay has already spread to more areas of the traffic network. We propose a vehicle redirection system to avoid congestion that uses a model based on deep learning to predict the future state of the traffic network. The model uses the information obtained from the previous step to determine the zones with possible congestion, and redirects the vehicles that are about to cross them. Alternative routes are generated using the entropy-balanced k Shortest Path algorithm (EBkSP). The proposal uses information obtained in real time by a set of probe cars to detect non-recurrent congestion. The results obtained from simulations in various scenarios have shown that the proposal is capable of reducing the average travel time (ATT) by up to 19%, benefiting a maximum of 38% of the vehicles.