Spatial-Temporal Traffic Flow Control on Motorways Using Distributed Multi-Agent Reinforcement Learning

This paper presents the systematic evaluation of Variable Speed Limit (VSL) system implemented on I-270 in St. Louis County. The system varies the speed limit in real time during periods of recurring and non-recurring congestion to prevent traffic from breaking down. The system was evaluated objectively and subjectively, and this paper describes the objective evaluation of the system. The objective evaluation was performed by comparing the traffic flow parameters during static speed limit (pre-VSL) with variable speed limit (post-VSL) by using five measures of performance: 1) speed, 2) volume, 3) occupancy, 4) travel time, and 5) congestion measures. Identification of congested segments and the time periods for the analyses were the initial steps for evaluating the system. Traffic data were provided by MoDOT collected using Remote Traffic Microwave Sensors. Average speed, volume and time occupancy profiles indicated that the VSL system change in traffic conditions including congestion. Preventing the highway from reaching its capacity and avoiding the traffic breakdown is one of the main objectives of VSL system initiation. It can be achieved by upstream drivers reducing speed, metering the upstream traffic and preventing traffic from breaking down. Congestion measures evaluation indicates change in Travel Time, Percentage of Congested Travel and reduction in duration, extent and intensity of congestion. The VSL system benefits were determined, which indicated that the system benefits will pay for the initial capital cost of the system over the years. This study can be used by Departments of Transportation for evaluation of active management systems.

Variable speed limit (VSL) systems are important active traffic management tools that are being deployed across the U.S. and indeed around the world for relieving congestion and improving safety. Oregon’s first variable advisory speed limit signs were activated along Oregon Highway 217 in the summer of 2014. The variable advisory speed system is responsive to both congestion and weather conditions. This seven-mile corridor stretches around Western Portland and has suffered from high crash rates and peak period congestion in the past. VSL systems are often deployed to address safety, mobility and sustainability related performance. This research seeks to determine whether the newly implemented variable advisory speed limit system has had measurable impacts on traffic safety and what the scale of the impact has been. The research utilizes a before-after crash analysis with three years of data prior to implementation and around 16 months after. Statistical analysis using an Empirical Bayes (EB) approach will aim to separate the direct impacts of the variable advisory speed limit signs from the long term trends on the highway. In addition, the analysis corrects for the changes in traffic volumes over the study period. Three data sources will be utilized including Washington County 911 call data, Oregon incident reports, and official Oregon Department of Transportation crash data reports. The analysis results are compared between data sources to determine the reliability of 911 call data as a proxy for crash statistics. The conclusions should be able to provide an indication of whether variable advisory speed limits can provide increased safety along high crash corridors.

Variable Speed Limit (VSL) control contributes to potential crash risk reduction by suggesting a suitable dynamic speed limit to achieve more stable and uniform traffic flow. In recent studies, researchers adopted macroscopic traffic flow models and perform prediction-based optimal VSL control. The response of drivers to the advised VSL is one of the most critical parameters in VSL-controlled speed dynamics modeling, which significantly affects the accuracy of traffic state prediction as well as the control reliability and performance. Nevertheless, the variations of driver responses were not explicitly modeled. Thus, in this research, the authors proposed a dynamic driver response model to formulate how the drivers respond to the advised VSL during various traffic conditions. The model was established and calibrated using field data to quantitatively analyze the dynamics of drivers’ desired speed regarding the advised VSL and current traffic state variables. A proactive VSL control algorithm incorporating the established driver response model was designed and implemented in field-data-based simulation study. The design proactive control algorithm modifies VSL in real-time according to the traffic state prediction results, aiming to reduce potential crash risks over the experiment site. By taking into account the real-time driver response variations, the VSL-controlled traffic state dynamics was more accurately predicted. The experimental results illustrated that the proposed control algorithm effectively reduces the crash probabilities in the traffic network.

Author(s): Gao, Hang; Cheng, Shenyang; Zhang, Michael | Abstract: The model based variable speed limit (VSL) control has been proven effective to resolve capacity-drop and time delay at a single recurrent bottleneck in previous studies. This project applies VSL controls to the traffic corridors with multi-segment and multi-bottleneck with the objective of reducing fuel consumption and greenhouse gas emissions. Based on a comprehensive review of existing methods, we develop and compare two fuel consumption centered VSL control (FC-VSL) strategies: flow-based control versus density-based control. These control strategies are implemented in SUMO, a microscopic traffic simulation package, on a 10-mile long freeway section. Results show that the density-based control reduces fuel consumption and gas emissions significantly at the cost of slight increase of travel time. The flow-based control, in contrast, reduces congestion and emissions in the downstream segments but transfers the congestion to the segments upstream of the controlled segments, resulting in an overall performance that is worse than the density-based FC-VSL, and no better than imposing static speed limits.

Evaluating Performance of a Proactive Optimal Variable Speed Limit Control Using Different Objective Functions

A deep reinforcement learning-based intelligent intervention framework for real-time proactive road safety management

Dynamic areas strategy design for variable speed limiting at fixed freeway bottlenecks

Safety and congestion are ever present and increasingly severe transportation problems in urban areas throughout the nation and world. These phenomena can have wide-ranging consequences relating to safety, the economy, and the environment. Adverse weather conditions represent another significant challenge to safety and mobility on highways. Oregon is not immune from either of these global issues. Oregon Route (OR) 217, to the southwest of the downtown Portland, is one of the worst freeways for congestion in the state and is also subject to the Pacific Northwest's frequently inclement and unpredictable climate. High crash rates, severe recurrent bottlenecks and highly unreliable travel times continuously plague the corridor, making it a major headache for the thousands of commuters using it every day. In an effort to more effectively combat both congestion and adverse weather, transportation officials all over the world have been turning to increasingly technological strategies like Active Traffic Management (ATM). This can come in many forms, but among the most common are variable speed limit (VSL) systems which use real-time data to compute and display appropriate reduced speeds during congestion and/or adverse weather. After numerous studies and deliberations, Oregon Department of Transportation (ODOT) selected Oregon Route (OR) 217 as one of the first locations in the state to be implemented with an advisory VSL system, and that system began operation in the summer of 2014. This thesis seeks to evaluate the effectiveness of this VSL system through the first eight months of its operation through an in-depth and wide-ranging "before and after" analysis. Analysis of traffic flow and safety data for OR 217 from before the VSL system was implemented made clear some of the most prevalent issues which convinced ODOT to pursue VSL. Using those issues as a basis, a framework of seven specific evaluation questions relating to both performance and safety, as well as both congestion and adverse weather, was established to guide the "before and after" comparisons. Hypotheses, and measures of effectiveness for each question were developed, and data were obtained from a diverse array of sources including freeway detectors, ODOT's incident database, and the National Oceanic and Atmospheric Administration (NOAA). The results of the various "before and after" comparisons performed as a part of this thesis indicate that conditions have changed on OR 217 in a number of ways since the VSL system was activated. Many, but not all, of the findings were consistent with the

Exploring the impact of a coordinated variable speed limit control on congestion distribution in freeway

This study employs a Vissim–Matlab component object model (COM)-based microsimulation model to evaluate the effectiveness of variable speed limit (VSL) strategies during traffic incidents. This study examines two VSL strategies on a 2.7 km section of Thailand’s Motorway No. 7: VSL1 with 1 km spacing and VSL2 with 2 km spacing. Simulation results show that under peak volume conditions, the VSL1 strategy outperforms both the existing scenario and VSL2 in terms of traffic performance and safety. This advantage holds for single-lane closures for both short and long periods. However, for two-lane closures with prolonged incident-clearance times, the VSL system should be temporarily deactivated to prevent increased congestion. Sensitivity analysis results indicate that under mild to moderate traffic volumes, VSL1 and VSL2 perform similarly in both traffic performance and safety across single- and double-lane closures and both closure durations. Both strategies outperform the existing scenario in nearly all cases. The VSL implementation yielded up to an 18% increase in average speed and an 88% reduction in rear-end conflicts. The magnitude of these improvements increased as traffic demand decreased. However, under congested conditions with two-lane closures, the VSL system should remain inactive regardless of the expected incident-clearance time.

The variable speed limit (VSL) is a control instrument of emerging intelligent transportation systems used to help manage motorway traffic. The VSL has the potential to improve traffic safety and reduce both traffic congestion and emissions through better harmonisation of traffic flow. The VSL results in a reduction of speed variations among vehicles travelling along controlled sections. In this paper, a modified logic-tree-based algorithm is proposed to improve the mobility benefits of VSL controllers. The modified algorithm is assessed using a case study in Auckland, New Zealand. Analysis of the case study is based on a critical bottleneck section of the Auckland motorway using the Aimsun micro-simulator. The proposed algorithm is compared with a known algorithm proposed in the literature and used in practice. The simulation results of the case study show that the proposed logic-tree-based VSL control algorithm outperforms the existing method. Compared with a no-control scenario, it results in respective improvements of 6%, 11%, 3%, 9% and 3% in the capacity of the bottleneck section, the total travel time and emissions of carbon dioxide, carbon monoxide and nitrogen oxides.

Ahstract- Different types of variable speed limit (VSL) controllers have been proposed to improve the traffic mobility at highway bottlenecks. However, the benefit of VSL is sometimes deteriorated by the capacity drop phenomenon introduced by the disordered lane changes at the vicinity of the bottleneck. Our recent results show that by combining the VSL controller with lane change control, the capacity drop can be significantly relieved or avoided at the bottleneck. In this paper, we propose feedback linearization and model predictive control schemes for VSL-actuated highway traffic, where a lane change controller is assumed to be active upstream of the bottleneck. Via simulation studies, we compare the performance and robustness of the proposed controllers with respect to perturbations on traffic demand, model parameters and measurement noise. Results show that both controllers are able to improve the total time spent under different levels of perturbation and noise. Furthermore, feedback linearization VSL can provide better performance than model predictive VSL with negligible computational effort and similar robustness.

Congestion has become highly recognized as a worldwide traffic problem, as traffic demand has grown steadily over the past few decades. Variable speed limits (VSLs) are an intelligent transportation system (ITS) measure that limits mainline flow to mitigate bottleneck congestion. Currently, VSLs have become proactive based on short-term prediction. Proactive VSLs succeed in simulation evaluations, but few have been deployed in the field and their real-world effectiveness has not been proven. Various factors may lead to this limitation, such as the absence of reliable field application software, accuracy of prediction models, and high computation time for proactive control. To address this research gap, this study reports a preliminary VSL test and details its implementation results on Whitemud Drive, Edmonton, Canada. First, based on field traffic measurements before VSL control, recurrent bottleneck locations are identified. Second, the proactive control algorithm is briefly introduced. Then, a s...

Robust variable speed limit control with respect to uncertainties

A reliability-based weather-responsive variable speed limit system to improve the safety of rural highways