Non-recurrent Congestion Research Articles

Integrated ANN-Bayes-based travel time prediction modeling for signalized corridors with probe data acquisition paradigm

Travel time is a major information in support of Transportation System Management and Operations (TSMO). Accurate travel time information extracted from probe data sources, which have been evolved in recently years, has led to the considerable research into travel time prediction modeling on freeways. However, little research has been reported on dealing with predicting signalized arterial travel time. It is mainly because of the natures of interrupted traffic flows along a signalized corridor or dynamic urban network, wherein varying signal timing schemes, crossing traffic, and dynamic route choices make arterial travel time estimations much more challenging than freeways. This paper presents an innovative methodological framework that can be used to integrate the exponential smoothing technique, Artificial Neural Network (ANN) techniques and Bayes algorithms for predicting travel time along a signalized corridor. The data source obtained along the US-27 corridor in the State of Ohio, was used to test two types of the developed models, i.e., hourly instantaneous travel time prediction model and realized (or experienced) route travel time prediction model. The study results indicate that the developed models can effectively capture the travel time patterns by combining an exponential smoothing base profile and an ANN-Bayes-trained dynamic profile. In this way, more sensitive changes can be identified to a variation aroused by non-recurring congestion. The testing results with real-world travel time datasets indicates a good performance of the predicted travel time models. The most errors range from −0.608 to 0.485, which are much lower than the threshold standard deviation if 2.24 and close to 6% of mean travel time value of 9.08 min. Overall, the study results suggest that the proposed methods are capable of capturing traffic patterns even when an incident occurs by comparing with conventional methods.

Arterial Signal Offset Optimization Using Crowdsourced Speed Data

Signal offset for coordinated traffic signal control is traditionally optimized based on posted speed limit, free-flow speed, or average speed among intersections, without considering the variations of travel speed. Variation in travel speed caused by interference on arterials may lead to inaccurate offset estimation, reducing the efficiency of coordination control. Therefore, this study develops an arterial offset optimization method for traffic signal coordination control using real-time speed collected from high-resolution crowdsourced data. The objective of the proposed method is to minimize the average delay on the corridor. The optimization problem is formulated as integer programming, and a genetic algorithm (GA) is utilized to search for the best offset solution. The proposed method is evaluated on a major arterial (Speedway Boulevard) in Tucson, Arizona. In the numerical exercise, the effectiveness and performance of the proposed method are evaluated in various scenarios, including a scenario with non-recurring congestion. The results show that using high-resolution real-time speed data can reduce travel delay time in a coordinated direction by 32.5% and 17.6% when compared with methods using speed limit and free-flow speed, respectively, and the proposed method is more reliable and robust for handling traffic conditions with varying volume and speed.

Identification, cost evaluation, and prioritization of urban traffic congestions and their origin

The increasing urbanization in the last decades results in significant growth in urban traffic congestion around the world. This leads to enormous time people spent on roads and thus significant money waste and air pollution. Here, we present a novel methodology for identification, cost evaluation, and thus, prioritization of congestion origins, i.e., their bottlenecks. The presented work is based on network analysis of the entire road network from a global point of view. We identify and prioritize traffic bottlenecks based on big data of traffic speed retrieved in near-real-time. Our approach highlights the bottlenecks that have the most significant effect on the global urban traffic flow. We follow the evolution of every traffic congestion in the entire urban network and rank all the congestions, based on the cost they cause (in Vehicle Hours units). We show that the macro-stability that represents the seeming regularity of traffic load both in time and space, overshadows the existence of meso-dynamics, where the bottlenecks that create these congestions usually do not reappear on different days or hours. Thus, our method enables to identify in near-real-time both recurrent and nonrecurrent congestions and their sources.

Real-Time Incident-Responsive Signal Control Strategy under Partially Connected Vehicle Environment

The performance of the traffic system can drastically drop when nonrecurrent congestion caused by incidents occurs. Early detection and clearing of traffic incidents will enable the mitigation of the congestion and early restoration of normal traffic conditions. The research in this paper utilized the vehicle information from the recent technological advancement in transportation systems, connected vehicles (CV), and loop-detector information for nonconnected vehicles (NCVs) and developed a novel algorithm to (1) control traffic signals for normal traffic conditions in the absence of incidents, (2) detect traffic incidents using CV/NCV information, and (3) control traffic signals during the occurrence and dissipation of incidents. All the 3 strategies were integrated into one algorithm, which runs as per the real-time traffic conditions, in the presence or absence of incidents. Space-mean speeds of the vehicles on nonincident lanes and throughput maximization criteria were taken as the indicators for the activation of specific signal timings directed at the incident-affected approach. Diverse incident scenarios were tested on a four-legged isolated intersection using the VISSIM simulation tool. Incident detection results showed a higher detection rate and lower mean detection time at higher CV penetration and higher traffic volumes, and at the incident locations nearer to the stop-line. The proposed incident-responsive signal control strategy at 40% and higher CV penetration showed better performance over EPICS adaptive signal control solution, in reducing average travel time delay and the average number of stops per vehicle.

Developing a fuzzy-based decision-making procedure for traffic control in expressway congestion management

This paper presents part of a multi-stage fuzzy logic controller (MS-FLC) that is developed for traffic control in congestion management on expressways. The decision-making process of traffic control for expressway congestion management using the MS-FLC consists of three tasks: (1) evaluation of current traffic congestion; (2) prediction of traffic congestion tendency; and (3) recommendation of control strategies and control actions to alleviate the congestion. This paper presents the 3rd stage of the MS-FLC that develops a fuzzy-based decision-making procedure (FDMP) for management of recurring and non-recurring congestion. Using fuzzy rules, the FDMP evaluates the current and anticipated traffic data and incident information to recommend control strategies at the strategic level, and control actions at the operational level. Results from this research show that: (i) the FDMP offers a comprehensive procedure in deriving control strategies and actions; (ii) FDMP control actions are derived from a systematic decision-making logic where the design of control rules is consistently oriented toward achieving desirable control objectives; (iii) the FDMP targets a proper balance in congestion management between the mainline and the ramp using compromise rule design; (iv) the FDMP facilitates using various forms of available traffic and incident data on an extended expressway segment to derive at control actions, making the system-wide gains possible; and (v) the FDMP could be applied for management of both recurring and non-recurring congestion.

A framework for efficient dynamic routing under stochastically varying conditions

Despite measures to reduce congestion, occurrences of both recurrent and non-recurrent congestion cause large delays in road networks with important economic implications. Educated use of Intelligent Transportation Systems (ITS) can significantly reduce travel times. We focus on a dynamic stochastic shortest path problem: our objective is to minimize the expected travel time of a vehicle, assuming the vehicle may adapt the chosen route while driving. We introduce a new stochastic process that incorporates ITS information to model the uncertainties affecting congestion in road networks. A Markov-modulated background process tracks traffic events that affect the speed of travelers. The resulting continuous-time routing model allows for correlation between velocities on the arcs and incorporates both recurrent and non-recurrent congestion. Obtaining the optimal routing policy in the resulting semi-Markov decision process using dynamic programming is computationally intractable for realistic network sizes. To overcome this, we present the edsger⋆ algorithm, a Dijkstra-like shortest path algorithm that can be used dynamically with real-time response. We develop additional speed-up techniques that reduce the size of the network model. We quantify the performance of the algorithms by providing numerical examples that use road network detector data for The Netherlands.

Quantifying incident impacts and identifying influential features in urban traffic networks

Traffic incidents are a common occurrence in urban traffic networks, but predicting their impacts is challenging because of network complexity and the dynamic spatial and temporal dependencies inherent in traffic data. Nevertheless, the prediction of traffic incident impacts is crucial for global positioning systems to provide drivers with real-time route recommendations for bypassing congested roads. To this end, we formulated nonrecurrent congestion measures to quantify these impacts and developed a new method to identify the influential features that locally affect individual incidents. Because traffic incident impacts are determined by a complex entanglement of local features, a meaningful feature that can explain their impacts globally may not exist. Consequently, to identify all influential local features, we applied the local interpretable model-agnostic explanations (LIME) technique to the proposed nonrecurrent congestion measures. The proposed method was validated using real user trajectory data and incident data provided by the NAVER Corporation and the Korean National Police Agency, respectively.

Multiple Sensors Data Integration for Traffic Incident Detection Using the Quadrant Scan.

Non-recurrent congestion disrupts normal traffic operations and lowers travel time (TT) reliability, which leads to many negative consequences such as difficulties in trip planning, missed appointments, loss in productivity, and driver frustration. Traffic incidents are one of the six causes of non-recurrent congestion. Early and accurate detection helps reduce incident duration, but it remains a challenge due to the limitation of current sensor technologies. In this paper, we employ a recurrence-based technique, the Quadrant Scan, to analyse time series traffic volume data for incident detection. The data is recorded by multiple sensors along a section of urban highway. The results show that the proposed method can detect incidents better by integrating data from the multiple sensors in each direction, compared to using them individually. It can also distinguish non-recurrent traffic congestion caused by incidents from recurrent congestion. The results show that the Quadrant Scan is a promising algorithm for real-time traffic incident detection with a short delay. It could also be extended to other non-recurrent congestion types.

A Data-Driven Method for Congestion Identification and Classification

Congestion detection is one of the key steps in reducing delays and associated costs in traffic management. With the increasing use of global positioning system (GPS)-based navigation, promising speed data are now available. This study used extensive historical probe data (year 2016) in Des Moines, Iowa. We used Bayesian change point detection to segment the speed signal and detect temporal congestion. The detected congestion events were then classified as recurrent congestion (RC) or nonrecurrent congestion (NRC). This paper thus presents a robust statistical, big-data-driven expert system and a big-data-mining methodology for identifying both recurrent and nonrecurrent congestion.

Extending the I-95 Rule-Based Incident Duration System With an Automated Knowledge Transferability Model

The rule-based incident duration prediction model (IDPM), covering Interstate highways I-95, I-495, and I-695, has been adopted by the Maryland Department of Transportation State Highway Administration in its daily responses to non-recurrent congestion. In light of its effectiveness and robustness in practice, expanding such a system to all other highways emerges as desirable but a challenging task, because of the need to integrate field operators’ expertise in generating prediction rules and the dependence on sufficient incident records for key parameter calibration. To circumvent such a data-demanding and time-consuming process for knowledge acquisition and refinement for extending the IDPM’s spatial coverage, this study has proposed a knowledge transferability analysis (KTA) method, featuring its automated process to assess, select, and transfer existing prediction rules to perform incident duration estimate for the new target highway. Evaluation of the proposed KTA with the incident records from Maryland I-70, using both transferred and customized local rules, reveals that it can achieve accuracy of 87% with the training dataset (i.e., 2016–2018) and 82% with the test dataset (i.e., 2019), comparable to the current system’s performance but demanding much fewer incident records for model calibration and significantly less effort for system expansion.

How incidents impact congestion on roadways: A queuing network approach

Motivated by the need for transportation infrastructure and incident management planning, we study traffic density under non-recurrent congestion. This paper provides an analytical solution approximating the stationary distribution of traffic density in roadways where deterioration of service occurs unpredictably. The proposed solution generalizes a queuing model discussed in the literature to long segments that are not space-homogeneous. We compare single and tandem queuing approaches to segments of different lengths and verify whether each model is appropriate. A single-queue approach works sufficiently well in segments with similar traffic behavior across space. In contrast, a tandem-queue approach more appropriately describes the density behavior for long segments with sections having distinct traffic characteristics. These models have a comparable fit to the ones generated using a lognormal distribution. However, they also have interpretable parameters, directly connecting the distribution of congestion to the dynamics of roadway behavior. The proposed models are general, adaptable, and tractable, thus being instrumental in infrastructure and incident management. • Traffic congestion model for highways that may experience unexpected slowdowns. • Intuitive analytical solution with a clear relation between incidents and congestion. • A discussion of situations where tandem queues work better than single queues. • The proposed models are similar to lognormal in fit but have explainable parameters.

A complex network analysis approach for estimation and detection of traffic incidents based on independent component analysis

Traffic incidents due to non-recurring congestion frequently occur in urban environments. In this study, we propose the estimation and detection of traffic incidents based on independent component analysis (ICA) and hybrid observer (HO)-generalized likelihood ratio (GLR) techniques. First, we develop the traffic time series to obtain insight into the traffic flow and to detect traffic incidents. Then, we use time series analysis to construct complex networks. Next, we propose the ICA technique to monitor traffic flow. Then, we introduce a piecewise switched linear model based observer to estimate the possible occurrence of traffic incidents. Finally, we propose a new incident detection method that combines HO and GLR techniques. The combined HO-GLR method can produce better incident detection, improve traffic safety, and enhance traffic management systems. We have validated the effectiveness of the proposed method using simulated traffic data generated from the Ayer Rajah Expressway in Singapore and a real-world dataset from the I-880 freeway of California. The performance metrics used to evaluate the performance of the proposed method includes detection rate, false alarm rate, classification rate, mean time to detection and the area under receiving operating characteristics curve. The experimental results show that the proposed method has obtained better performance in all of the criteria when compared with other well-known methods.

Detecting and interpreting non‐recurrent congestion from traffic and social media data

A non-recurring incident often negatively affects traffic, which is represented as non-recurrent congestion. However, travellers can usually perceive congestion without knowing the underlying reasons. Accordingly, this paper proposes a data-driven framework for non-recurrent congestion detection and interpretation analysis. First, a statistical algorithm named generalized extreme studentized deviate is introduced to detect non-recurrent congestion by comparing the current traffic speed with the speed threshold learned from historical data. The case study in Beijing shows that the proposed generalized extreme studentized deviate outperforms other prevailing algorithms in terms of detection rate, false alarm rate, and mean detection time. Second, data mining and natural language processing technologies are implemented on data collected from Sina Weibo, a Chinese microblog site akin to Twitter, to classify non-recurring incidents that may be associated with non-recurrent congestion, including traffic accident, road construction, concert, special sport (marathon), and commercial activity. Results show that overall classification accuracy reaches 95%. Finally, the association relationship between the detected non-recurrent congestions and incidents is established via spatiotemporal information matching. This information matching provides a bidirectional verification. On the one hand, nearly 58% of non-recurrent congestion can be explained by incident-related (IR) microblogs. On the other hand, an average of 62% of IR microblogs can be traced by nearby non-recurrent congestions. This paper suggests that social media can be used as a secondary source and integrated with traffic data to enhance the understanding of non-recurrent congestion.

Unmanned aerial vehicle path planning for traffic estimation and detection of non-recurrent congestion

ABSTRACT Unmanned aerial vehicles (UAVs) provide a novel means of extracting road and traffic information from video data. In particular, by analyzing objects in a video frame, UAVs can detect traffic characteristics and road incidents. Leveraging the mobility and detection capabilities of UAVs, we investigate a navigation algorithm that seeks to maximize information on the road/traffic state under non-recurrent congestion. We propose an active exploration framework that (1) assimilates UAV observations with speed-density sensor data, (2) quantifies uncertainty on the road/traffic state, and (3) adaptively navigates the UAV to minimize this uncertainty. The navigation algorithm uses the A-optimal information measure (mean uncertainty), and it depends on covariance matrices generated by a dual state ensemble Kalman filter (EnKF). Our results indicate that targeted UAV observations aid in the detection of incidents under congested conditions where speed-density data are not informative.

Statistical Distance-Based Travel-Time Reliability Measurement for Freeway Bottleneck Identification and Ranking

Freeway bottleneck identification is an essential component in the process of deploying mitigation strategies to reduce congestion at freeway bottlenecks. Most previous studies on bottleneck identification focus on recurrent bottlenecks, and limited work has been conducted to identify the locations of non-recurrent bottlenecks. Therefore, in this study, we propose a new travel time reliability (TTR) measurement and develop a freeway bottleneck identification method based on this measurement, which can identify with high probability not only recurrent bottlenecks but also the locations of non-recurrent bottlenecks. The TTR measurement is developed based on statistical distance between travel time distributions. Three statistical distance measurements, Jensen–Shannon divergence, Wasserstein distance, and Hellinger distance, are applied in the TTR measurement. The bottleneck identification method is evaluated in a case study on I-15 freeway corridor in Salt Lake City, Utah. The three statistical distance measurements show good consistency in ranking locations by the impacts of recurrent and non-recurrent congestion, especially for extreme cases with very high or low variation between travel time distributions. The recurrent bottlenecks identified in this study show their clustering characteristics, which is similar to the generating and dismissing process of recurrent congestion. The locations with high probability of non-recurrent bottlenecks scatter both spatially and temporally, which agrees with the random characteristic of non-recurrent congestion.

Solving in real-time the dynamic and stochastic shortest path problem for electric vehicles by a prognostic decision making strategy

The adoption of Electric Vehicles (EVs) has substantially increased during the last decade, creating the need for customized EV-oriented routing strategies capable of using the enormous amount of historical, and real-time, traffic data that is collected through Intelligent Transport Systems (ITSs). Existing EV routing algorithms, however, concentrate mostly on the usage historical data to compute offline optimal paths, whereas the use of real-time traffic information to compute en-route path updates is still an almost unexplored topic; mainly due to its inherent computational challenges. This research effort proposes a Prognostic Decision Making (PDM) strategy to solve in real-time the Electric Vehicle Dynamic Stochastic Shortest Path Problem (EV-DSSPP); aiming at the simultaneous utilization of historical and real-time traffic data. Factors such as recurring and non-recurring traffic congestion, elevation, velocity and EV’s parameters are incorporated into the decision-making process. The proposed strategy has two hierarchical functional layers. The lower layer consists of a fast-computing routing algorithm that, by construction, guarantees a real-time execution. The higher layer organizes the periodic en-route execution of the first layer to compute en-route path updates during a trip. This strategy can hence serve as an expert router that works jointly with an ITS to assist EV drivers on route. The proposal is validated through a simulation study based on real-world traffic data collected in Santiago, Chile. The results show that periodic en-route path updates can generate a reduction in both travel time and energy consumption, which evidences the benefits of incorporating real-time traffic information into the EV-routing problems.

Secondary Crash Identification using Crowdsourced Waze User Reports

Secondary crashes are crashes that occur as a result of the nonrecurrent congestion originating from primary crashes, and always have a greater impact on safety and traffic than a single crash. A better understanding of secondary crashes would benefit traffic incident management, and this requires accurate identification of secondary crashes. This study explores using crowdsourced Waze user reports to identify secondary crashes. A network-based clustering algorithm is proposed to extract the primary crash cluster, including all user reports originating from the primary crash, and any crash that occurred within the cluster would be a secondary crash. This method works as a filter to select accurate primary–secondary relationships, thus precisely identifying secondary crashes. A case study is performed with crashes occurring from June to December 2019 on a 30-mi stretch of I-40 in Knoxville, TN. A static threshold method (crash duration and 10 mi) was used to preselect the potential primary–secondary crash pairs, and 75 out of 708 crashes were identified as potential secondary crashes. Based on the preselected primary–secondary crash pairs, 17 secondary crashes were obtained with the proposed method and the results were compared with one of the commonly used methods, the speed contour plot method. Though the proposed method captured fewer secondary crashes, it did identify several secondary crashes that could not be observed with the speed contour plot method. The results showed the applicability of the method and the potential of crowdsourced Waze user reports in secondary crash identification.

Online Estimation and Prediction of Large-Scale Network Traffic From Sparse Probe Vehicle Data

Network traffic prediction based on probe vehicle data is important for traffic management and route recommendation and has been intensively studied. Previous traffic prediction methods mainly focused on recurring traffic congestion. Predicting non-recurring traffic congestion, caused by events and accidents, is significantly more important; however, it has not been intensively studied. To predict non-recurring traffic congestion using probe data, we need to estimate the current traffic conditions based on <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">sparse</i> observations for <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">large</i> traffic networks to track traffic changes <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">online</i> . Conventional traffic forecasting methods have not been able to solve all of these problems. To address these problems, we propose a data assimilation method using a state space neural network (SSNN) with an incorporated topology of road networks. The SSNN model can easily model network traffic and can easily estimate its states and parameters by data assimilation using Bayesian filtering. In this study, we adopted a decoupled extended Kalman filter (DEKF) based data assimilation, which is scalable and applicable to large-scale network traffic, to estimate the states and parameters online. We evaluate the proposed method using an open dataset that includes a road network comprising over 30000 road segments. The results show that our method achieves higher prediction accuracy for predicting unknown traffic congestion and is more robust against data sparsity than conventional state estimation methods.

STIMF: a smart traffic incident management framework

Non-recurrent congestion, which is mainly due to traffic incidents, may seriously impact the performance and operation of a traffic system. Reacting quickly and in a uniform and structured way is vital. In particular, choosing the appropriate response strategy with only a short delay may mitigate the impact of incidents, improve traffic efficiency, and increase safety in the transportation system. This paper proposes STIMF: a smart traffic incident management framework to reduce the burden on traffic incident operators by assisting them in selecting the most appropriate response strategy when an incident occurs. STIMF includes two software systems: (a) a simulation environment used to evaluate traffic incident management strategies and (b) a fuzzy-logic inference system that allows the traffic operator to get prompt recommendations on the best response strategies based on the current context and conditions. Moreover, the STIMF framework also describes the process of preparing and building the simulation environment. To evaluate the proposed framework, we tested it on a section of the Muscat expressway in Oman.

High-order Markov model for prediction of secondary crash likelihood considering incident duration

Traffic incidents can create major non-recurring congestion and have the potential to be fatal. Traffic Engineers and researchers have worked vigorously to reduce and prevent traffic crashes and ma...