Traffic-responsive Ramp Metering Research Articles

Modeling and Validating Traffic Responsive Ramp Metering in the Highway Capacity Manual Context

This paper presents a methodology for modeling traffic responsive (or adaptive) ramp metering in the freeway facilities method based on the sixth edition of the Highway Capacity Manual (HCM6). Currently, the HCM only provides an option to meter on-ramps as user input using 15-min average flow rates with a focus on planning-level analyses. As a result, the possibilities for simulating and modeling ramp meters with any traffic responsive ramp metering algorithm in the HCM context are limited. Moreover, the freeway facilities methodology in the HCM plays a vital role in the analysis of travel time reliability, which is built on a set of operational scenarios. However, with the lack of traffic responsive ramp metering, analysts are burdened with the task of manually entering average effective ramp metering rates for each on-ramp within the set of reliability scenarios. This process can require a substantial amount of time, in addition to increasing the potential for inaccuracy and bias in freeway and performance measure estimations. As a result, this paper is designed to fill a significant research gap by providing a method for analyzing traffic responsive (or adaptive) ramp metering, an active traffic and demand management strategy, using the core freeway facilities methodology in the HCM. The direct application of the method focuses on the MaxView metering algorithm. However, the proposed framework can be used to model any traffic responsive ramp metering algorithm. The results are validated using real-world sites located on the I-540 westbound freeway corridor in North Carolina.

A Novel Ramp Metering Approach Based on Machine Learning and Historical Data

The random nature of traffic conditions on freeways can cause excessive congestion and irregularities in the traffic flow. Ramp metering is a proven effective method to maintain freeway efficiency under various traffic conditions. Creating a reliable and practical ramp metering algorithm that considers both critical traffic measures and historical data is still a challenging problem. In this study we use simple machine learning approaches to develop a novel real-time ramp metering algorithm. The proposed algorithm is computationally simple and has minimal data requirements, which makes it practical for real-world applications. We conduct a simulation study to evaluate and compare the proposed approach with an existing traffic-responsive ramp metering algorithm.

Analyzing Simulation-Based Active Traffic Management Impact on a Large-Scale Regional Network

A vast number of real-time corridor management strategies have been introduced because the dynamics of traffic patterns and increased congestion result in challenging problems on road systems. Although these strategies can offer positive impacts on regional traffic, their evaluation tools are often limited to the scope of one specific corridor. To fill this gap, this study integrates a mesoscopic dynamic traffic assignment simulation model with an existing traffic-responsive ramp metering strategy. This integrated model is suitable for network-wide analysis and large-scale simulation of integrated corridor management strategies. The integrated modeling platform is demonstrated as a practice-ready tool. We present a case study that explores the benefits of metering control under various traffic conditions in a real-world network in Maryland. Both local and network-wide impacts are illustrated in the case study. This is one of the first attempts to simultaneously analyze network-wide traffic impacts and capture minute-by-minute demand–supply interactions under managed corridor strategies. The results indicate that ramp metering is beneficial even under non-recurrent traffic conditions at multiple spatial resolutions.

Comparing INRIX speed data against concurrent loop detector stations over several months

Many real-time traffic-monitoring applications only require speed or travel time. In recent years INRIX Traffic has started collecting and selling real-time speed data collected from “a variety of sources.” The clients include direct to consumer and operating agencies alike. So far the INRIX speed data have received little independent evaluation in the literature, with only a few published studies. The current study exploits a unique juncture as the Ohio Department of Transportation transitioned from loop detectors to third party traffic data for real time management. The two traffic surveillance systems operated concurrently for about half a year in Columbus, Ohio, USA. This paper uses two months of the concurrent data to evaluate INRIX performance on 14 mi of I-71, including both recurrent and non-recurrent events.The work compared reported speeds from INRIX against the concurrent loop detector data, as detailed herein. Three issues became apparent: First, the reported INRIX speeds tend to lag the loop detector measurements by almost 6min. This latency appears to be within INRIX specifications, but from an operational standpoint it is important that time sensitive applications account for it, e.g., traffic responsive ramp metering. Second, although INRIX reports speed every minute, most of the time the reported speed is identical to the previous sample, suggesting that INRIX is effectively calculating the speeds over a longer period than it uses to report the speeds. This work observed an effective average sampling period of 3–5min, with many periods of repeated reported speed lasting in excess of 10min. Third, although INRIX reports two measures of confidence, these confidence measures do not appear to reflect the latency or the occurrence of repeated INRIX reported speeds.

Machine learning for multi-jurisdictional optimal traffic corridor control

Urban traffic corridors are often controlled by more than one agency. Typically in North America, a state of provincial transportation department controls freeways while another agency at the municipal or city level controls the nearby arterials. While the different segments of the corridor fall under different jurisdictions, traffic and users know no boundaries and expect seamless service. Common lack of coordination amongst those authorities due to lack of means for information exchange and/or possible bureaucratic ‘institutional grid-lock’ could hinder the full potential of technically-possible integrated control. Such institutional gridlock and related lack of timely coordination amongst the different agencies involved can have a direct impact on traffic gridlock. One potential solution to this problem is through integrated automatic control under intelligent transportation systems (ITS). Advancements in ITS and communication technology have the potential to considerably reduce delay and congestion through an array of network-wide traffic control and management strategies that can seamlessly cross-jurisdictional boundaries. Perhaps two of the most promising such control tools for freeway corridors are traffic-responsive ramp metering and/or dynamic traffic diversion possibly using variable message signs (VMS). Technically, the use of these control methods separately might limit their potential usefulness. Therefore, integrated corridor control using ramp metering and VMS diversion simultaneously might be synergetic and beneficial. Motivated by the above problem and potential solution approach, the aim of the research presented in this paper is to develop a self-learning adaptive integrated freeway-arterial corridor control for both recurring and non-recurring congestion. The paper introduces the use of reinforcement learning, an Artificial Intelligence method for machine learning, to provide optimal control using ramp metering and VMS routing in an integrated agent for a freeway-arterial corridor. Reinforcement learning is an approach whereby the control agent directly learns optimal strategies via feedback reward signals from its environment. A simple but powerful reinforcement learning method known as Q-learning is used. Results from an elaborate simulation study on a key corridor in Toronto are very encouraging and discussed in the paper.

Automated Adaptive Traffic Corridor Control Using Reinforcement Learning

Advancements in intelligent transportation systems and communication technology could considerably reduce delay and congestion through an array of networkwide traffic control and management strategies. The two most promising control tools for freeway corridors are traffic-responsive ramp metering and dynamic traffic diversion using variable message signs (VMSs). The use of these control methods independently could limit their usefulness. Therefore, integrated corridor control by using ramp metering and VMS diversion simultaneously could be beneficial. Administration of freeways and adjacent arterials often falls under different jurisdictional authorities. Lack of coordination among those authorities caused by lack of means for information exchange or “institutional gridlock” could hinder the full potential of technically possible integrated control. Fully automating corridor control could alleviate this problem. Research was conducted to develop a self-learning adaptive integrated freeway–arterial corridor control for both recurring and nonrecurring congestion. Reinforcement learning, an artificial intelligence method for machine learning, is used to provide a single, multiple, or integrated optimal control agent for a freeway or freeway–arterial corridor for both recurrent and nonrecurrent congestion. The microsimulation tool Paramics, which has been used to train and evaluate the agent in an offline mode within a simulated environment, is described. Results from various simulation case studies in the Toronto, Canada, area are encouraging and have demonstrated the effectiveness and superiority of the technique.

Automated Adaptive Traffic Corridor Control Using Reinforcement Learning: Approach and Case Studies

Advancements in intelligent transportation systems and communication technology could considerably reduce delay and congestion through an array of networkwide traffic control and management strategies. The two most promising control tools for freeway corridors are traffic-responsive ramp metering and dynamic traffic diversion using variable message signs (VMSs). The use of these control methods independently could limit their usefulness. Therefore, integrated corridor control by using ramp metering and VMS diversion simultaneously could be beneficial. Administration of freeways and adjacent arterials often falls under different jurisdictional authorities. Lack of coordination among those authorities caused by lack of means for information exchange or institutional gridlock could hinder the full potential of technically possible integrated control. Fully automating corridor control could alleviate this problem. Research was conducted to develop a self-learning adaptive integrated freeway-arterial corrido...

Set of New Traffic-Responsive Ramp-Metering Algorithms and Microscopic Simulation Results

A novel switching traffic-responsive ramp-metering controller adapts to different traffic dynamics under different congestion conditions: free-flow or congested. The approach of multirate linear quadratic control with integral action is used to compensate for disturbances and to accommodate the difference between the model sampling time and the metering-rate update interval. In addition, a queue length regulator is designed to prevent the queue from exceeding the ramp storage capacity and yield improved performance over the current ad hoc queue override scheme. Subsequently, a queue length estimator is designed to provide feedback to the queue length regulator with the queue-detector speed data that are available in the field. A local ramp-metering control strategy is proposed to achieve the control goal of reducing the spatial and temporal span of the congestion, while satisfying the on-ramp storage capacity constraints, by using locally available information. Test results on a calibrated microscopic traffic simulator demonstrate the performance and effectiveness of the switching ramp-metering controller, the queue length estimator and regulator, and the overall control strategy. The total vehicle and passenger congestion delays are both reduced by 16%, and the total travel time is improved by 5.6%. As a comparison, simulation results of ALINEA are also presented.

Set of New Traffic-Responsive Ramp-Metering Algorithms and Microscopic Simulation Results

A novel switching traffic-responsive ramp-metering controller adapts to different traffic dynamics under different congestion conditions: free-flow or congested. The approach of multirate linear quadratic control with integral action is used to compensate for disturbances and to accommodate the difference between the model sampling time and the metering-rate update interval. In addition, a queue length regulator is designed to prevent the queue from exceeding the ramp storage capacity and yield improved performance over the current ad hoc queue override scheme. Subsequently, a queue length estimator is designed to provide feedback to the queue length regulator with the queue-detector speed data that are available in the field. A local ramp-metering control strategy is proposed to achieve the control goal of reducing the spatial and temporal span of the congestion, while satisfying the on-ramp storage capacity constraints, by using locally available information. Test results on a calibrated microscopic traffic simulator demonstrate the performance and effectiveness of the switching ramp-metering controller, the queue length estimator and regulator, and the overall control strategy. The total vehicle and passenger congestion delays are both reduced by 16%, and the total travel time is improved by 5.6%. As a comparison, simulation results of ALINEA are also presented.

Quantifying effects of ramp metering on freeway safety

This study presents a real-time crash prediction model and uses this model to investigate the effect of the local traffic-responsive ramp metering strategy on freeway safety. Safety benefits of ramp metering are quantified in terms of the reduced crash potential estimated by the real-time crash prediction model. Driver responses to ramp metering and the consequent traffic flow changes were observed using a microscopic traffic simulation model and crash potential was estimated for a 14.8 km section of I-880 in Hayward, California and a hypothetical isolated on-ramp network. The results showed that ramp metering reduced crash potential by 5–37% compared to the no-control case. It was found that safety benefits of local ramp metering strategy were only restricted to the freeway sections in the vicinity of the ramp, and were highly dependent on the existing traffic conditions and the spatial extent over which the evaluation was conducted. The results provide some insight into how a local ramp metering strategy can be modified to improve safety (by reducing total crash potential) on longer stretch of freeways over a wide range of traffic conditions.

A Low Cost Tool for Freeway Ramp Metering

Local, traffic-responsive ramp metering is a wellknown control measure aiming at ameliorating traffic conditions on interurban or metropolitan freeways and motorways. A particular control strategy (ALINEA), the only local ramp metering strategy to be based on rigorous application of classical regulator theory, is presented, along with a low cost implementation concept. Field application of ALINEA and evaluation of its performance in France and The Netherlands confirm its clear superiority as compared to other popular approaches.