Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “traffic impact analysis”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 19 records

Regional-scale Spatio-Temporal Analysis of Impacts of Weather on Traffic Speed in Chicago using Probe Data

Understanding a regional-scale impact of the weather on the transportation system and how that impact varies geographically, is important from a sustainability standpoint. In this work, we have performed a city-scale analysis on the impact of weather on the traffic speed for the City of Chicago. We have found that there is a significant variation in the average hourly speed due to different weather patterns which also varies geographically. We have also observed that the rainfall has an evident impact on the average hourly speed on the freeways that are influenced by urbanized residential and commercial areas, and non-urbanized areas. Also, low visibility has shown a significant reduction in the average hourly traffic speed during the congested hours on the freeways that are influenced by non urbanized areas. We anticipate the contributions of this work in estimating emission and fuel economy at a regional scale which are important sustainability measures for transportation.

Kurte, Kuldeep↗

Socially-aware evaluation framework for transportation

Technological advancements are rapidly changing traffic management in cities. Navigation applications, in particular, have impacted cities in many ways by rerouting traffic. As different routing strategies distribute traffic differently, understanding these disparities across multiple city-relevant dimensions is extremely important for decision-makers. We develop a multi-themed framework called Socially- Aware Evaluation Framework for Transportation (SAEF), which assists in understanding how traffic routing and the resultant dynamics affect cities. The framework is presented for four Bay Area cities, for which we compare three routing strategies - user equilibrium travel time, system optimal travel time, and system optimal fuel. The results demonstrate that many neighborhood impacts, such as traffic load on residential streets and around minority schools, degraded with the system-optimal travel time and fuel routing in comparison to the user-equilibrium travel time routing. The findings also show that all routing strategies subject the city's disadvantaged neighborhoods to disproportionate traffic exposure. Our intent with this work is to provide an evaluation framework that enables reflection on the consequences of traffic routing and management strategies, allowing city planners to recognize the trade-offs and potential unintended consequences.

99 GENERAL AND MISCELLANEOUS↗

Utica Shale Energy and Environment Laboratory Final Scientific/Technical Report

The Ohio State University (OSU) was awarded a contract on October 1, 2014, from the Department of Energy National Energy Technology Laboratory (DOE-NETL) to develop the Utica Shale Energy and Environment Laboratory (USEEL) in the Utica-Point Pleasant shale play of the Appalachian Basin. It was designed to be an environmental and technology development lab that would enable the academic, industry, government, and non-governmental organization (NGO) research communities to better understand unconventional oil and gas (UOG) engineering practices and technology to increase production and safety, and decrease environmental effects. Political and economic consequences necessitated changes in project site location and design, from the Ohio State Eastern Agricultural Research Station (EARS) and the Muskingum Watershed Conservancy District (MWCD) in east-central Ohio to a site located at an Energy Corporation of America (ECA) Marcellus drill pad in Greene County, Pennsylvania. Although the overall project progressed little beyond planning and administration before termination on September 18, 2017, significant research and MS or PhD investigations were completed or continue today. An experimental study design for site specific and regional baseline assessments was developed utilizing ecoregions, United States Geological Survey (USGS) Hydraulic Unit Code watersheds, and GIS technology and databases. This can be utilized to build a defensible and scalable management and research framework for UOG investigations that can be extrapolated for predictive and comparative analyses. The most commonly mentioned perceived risks of shale energy development identified in a socioeconomic analysis included impacts to the environment and water resources, traffic and road deterioration, and crime. Economic benefits, such as the windfall wealth to residents, job opportunities, and the demand for hotels and restaurants emerged, as the main positive impact to the community. Preliminary results of an analysis of the location and mechanisms for extremely high pore pressures of the deep Utica-Point Pleasant formations of southwestern Pennsylvania and their possible relationship to high initial production rates indicate that the overpressure is caused by a combination disequilibrium compaction and fluid expansion. Drilling fluids research designed a proof-of-concept device to evaluate desalination and solvent separation in hydraulic fracturing flowback water that could facilitate water recycling and potentially mitigate deep-well injection. A groundwater study was devised to characterize the subsurface aquifers in terms of the geological framework and groundwater chemistry, including the chemistry of dissolved gases and salts. Brines and gases associated with hydrocarbon migration in groundwater (including noble gases and hydrocarbons) were to be specifically fingerprinted for use as tracers of fluid migration. Trace element analysis of fish otoliths, using laser ablation inductively coupled plasma mass spectrometry (LA-ICP-MS), is being utilized to assess surface water quality. This methodology will be used to reconstruct the exposure histories of fish from watersheds and discriminate between the signatures associated with hydraulic fracturing and coal mining activities.

03 NATURAL GAS↗

A Framework to Analyze the Requirements of a Multiport Megawatt-Level Charging Station for Heavy-Duty Electric Vehicles

Widespread adoption of heavy-duty (HD) electric vehicles (EVs) will soon necessitate the use of megawatt (MW)-scale charging stations to charge high-capacity HD EV battery packs. Such a station design needs to anticipate possible station traffic, average and peak power demand, and charging/wait time targets to improve throughput and maximize revenue-generating operations. High-power direct current charging is an attractive candidate for MW-scale charging stations at the time of this study, but there are no precedents for such a station design for HD vehicles. We present a modeling and data analysis framework to elucidate the dependencies of a MW-scale station operation on vehicle traffic data and station design parameters and how that impacts vehicle electrification. This framework integrates an agent-based charging station model with vehicle schedules obtained through real-world vehicle telemetry data analysis to explore the station design and operation space. A case study applies this framework to a Class 8 vehicle telemetry dataset and uses Monte Carlo simulations to explore various design considerations for MW-scale charging stations and EV battery technologies. The results show a direct correlation between optimal charging station placement and major traffic corridors such as cities with ports, e.g., Los Angeles and Oakland. Corresponding parametric sweeps reveal that while good quality of service can be achieved with a mix of 1.2-megawatt and 100-kilowatt chargers, the resultant fast charging time of 35–40 min will need higher charging power to reach parity with refueling times.

33 ADVANCED PROPULSION SYSTEMS↗

Evaluating Energy Efficiency Opportunities from Connected and Automated Vehicle Deployments Coupled with Shared Mobility in California

Connected and Automated Vehicles (CAVs) can be considered to be a disruptive transportation technology, with the potential to significantly improve overall transportation system efficiency; however, CAVs may increase induce vehicle miles traveled (VMT) and bring on greater energy consumption. Further, shared mobility is another disruptive transportation event that is reshaping our travel patterns. The primary goal of this project was to extensively collect data from vehicles and associated infrastructure equipped with CAV technologies from both real-world experiments and simulation studies mainly deployed in California, and develop a comprehensive framework for evaluating energy efficiency opportunities from large-scale (e.g., statewide) introduction of CAVs and a wide deployment of shared mobility systems in a variety of scenarios. To quantify the combined impact of CAV and shared mobility on travel behavior, traffic performance, and energy efficiency, a unique mesoscopic simulation-based model was developed for mobility and energy efficiency evaluation considering these disruptive transportation technologies. As a complement to existing studies on nationwide evaluation of CAVs’ energy impacts, this project was focused on data collection efforts and CAV applications under congested traffic environments that are frequently experienced on a massive scale across the major metropolitan areas in California. Extensive real-world data collection supplemented with simulation studies were conducted to cover a variety of CAV and shared mobility scenarios, particularly on scenarios less-explored in the existing research. Another key component of this project was to consider the interaction between different CAV technologies and shared mobility models, and the compound effect on energy efficiency. A comprehensive modeling suite was developed to quantify the impact of new mobility technologies on travel behavior and traffic performance. The developed modeling framework includes an energy intensity module, mode choice module and activity generation module that are integrated into an agent-based BEAM simulation platform to perform impact analysis based on a variety of scenarios. In addition, the RouteE model has been upgraded to incorporate the impact of CAVs on traffic flow, VMT and energy intensity, using micro-simulation data collected from both freeways and urban arterials. A novel fundamental influencing factor (FIF) mode choice model was developed to link CAV and shared mobility components with travel behaviors, and adapted into the BEAM-centered model framework. A statewide energy inventory was constructed under various CAV technology deployment scenarios by incorporating datasets and models for predicting vehicle market share and vehicle usage, which are tightly associated with the penetration of shared mobility systems. Based applying this modeling suite to a calibrated network in Riverside California, it was found that cooperative automated driving in general will improve mobility, but automated vehicles, even when deployed in a shared autonomous fleet, will likely bring an increase of VMT (up to 36%) due to mode shifts and deadheading. Ride-hailing vehicles typically have better energy efficiency and a higher share of electric vehicles, which helps offset the negative impact from VMT increases when estimating the system-level energy consumption. In general, simulation results show a 6% increase in energy consumption for the scenarios with an increasing shift to ride-hailing modes. The statewide analysis based on the National Household Travel Survey (NHTS) sample data is consistent with the findings from the Riverside network and validate the developed clustering-prediction modeling methodology. The outcomes from this project will help close the knowledge gap on recognizing the potential performance and energy impacts of a broad deployment of CAV and shared mobility technologies across a wide range of roadway infrastructure with varying levels of congestion. Results from this project: 1) will support policymakers in steering CAV development and deployment towards an energy favorable direction; 2) reduce uncertainties in estimating energy saving opportunities from new mobility technologies and services; 3) increase the confidence of CAV technology investors both on the infrastructure side (i.e., transportation agencies) and on the vehicle side (i.e., OEMs); and 4) expedite the deployment of energy-efficient CAV and shared mobility applications.

33 ADVANCED PROPULSION SYSTEMS↗

Enhancing traffic safety analysis with digital twin technology: integrating vehicle dynamics and environmental factors into microscopic traffic simulation

Traffic safety is a critical concern in transportation engineering and urban planning. Traditional traffic safety analysis requires trained observers to collect data in the field, which is time-consuming, labor-intensive, and sometimes inaccurate. In recent years, microscopic traffic simulation, which simulates individual vehicles’ movements within a transportation network, have been utilized to study traffic safety. However, microscopic traffic simulation only focuses on traffic-related factors, such as traffic volume, traffic signals, and lane configurations, neglecting vehicle dynamics and environment-related factors like weather and lighting conditions, which can significantly impact traffic safety. In light of this, this paper explores the application of digital twin technology in traffic safety analysis, integrating vehicle simulators, which consider vehicle dynamics and environmental factors, and microscopic traffic simulators, which simulate the operations of traffic flow, for enhanced safety evaluations. Various scenarios, including different weather conditions and visibility levels, are simulated using a digital twin of a road segment in Tuscaloosa, Alabama. The simulations employ Surrogate Safety Measures (SSMs) like Time to Collision (TTC) and Deceleration Rate to Avoid a Crash (DRAC) to assess safety under varying conditions. The results demonstrate that traffic digital twin can identify potential safety issues that traditional microscopic simulation cannot, providing insights for improving traffic control strategies and transportation infrastructure to enhance traffic safety.

Civil engineering↗

Dynamic Wireless Power Transfer - Grid Impacts Analysis

This presentation discusses the current status of analysis of the electricity grid impacts of a dynamic wireless power transfer system deployed to the Atlanta region on select high traffic roadway segments.

33 ADVANCED PROPULSION SYSTEMS↗

Developing an Energy-Conscious Traffic Signal Control System for Optimized Fuel Consumption in Connected Vehicle Environments

The project titled “Developing an Energy-Conscious Traffic Signal Control System for Optimized Fuel Consumption in Connected Vehicle Environments” addresses energy-related challenges associated with adaptive traffic control systems by integrating connected vehicles (CV) and connected infrastructure (CI). The system developed in this project, a CV-based adaptive traffic control system, aims to improve fuel consumption in mixed traffic environments by capitalizing on emerging CV and CI communication technologies, as well as leveraging recent advances in Artificial Intelligence (AI), optimization, and edge computing. The system was tested at the MLK Smart Corridor, an urban testbed managed by the University of Tennessee at Chattanooga (UTC) and the City of Chattanooga. The system was validated through extensive simulations, both Software-in-the-Loop (SILS) and Hardware-in-the-Loop (HILS), and was further implemented and tested in real-world conditions at several intersections along the corridor. The Fuel Consumption Performance Index (FC-PI) and the Ecological Performance Index (Eco-PI) were developed as the key components for evaluating the system’s impact on fuel consumption and emissions. These metrics provided a comprehensive means of understanding the impact of traffic signal control optimization in mixed traffic environments. The report presents an in-depth analysis of the Eco-PI, FC-PI, adaptive traffic control system integration, and the testing and field implementation of the system. The results demonstrate significant reductions in fuel consumption and emissions, showcasing the system’s capability to contribute to more sustainable urban traffic management. The report also documents the challenges encountered and recommendations for scaling and further improving the system.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Extending cost–benefit analysis for the sustainability impact of inter-urban Intelligent Transport Systems

The paper reports research involving three cost–benefit analyses performed on different ITS schemes (Active Traffic Management, Intelligent Speed Adaptation and the Automated Highway System) on one of the UK's busiest highways — the M42. The environmental scope of the assets involved is widened to take into account the possibility of new technology linked by ICT and located within multiple spatial regions. The areas focused on in the study were data centre energy emissions, the embedded emissions of the road-side infrastructure, vehicle tailpipe emissions, additional hardware required by the vehicles (if applicable) and safety, and all aspects of sustainability. Dual discounting is applied which aims to provide a separate discount rate for environmental elements. For ATM, despite the energy costs of the data centre, the initial implementation costs and mitigation costs of its embedded emissions, a high cost–benefit ratio of 5.89 is achieved, although the scheme becomes less effective later on its lifecycle due to rising costs of energy. ISA and AHS generate a negative result, mainly due to the cost of getting the vehicle on the road. In order to negate these costs, the pricing of the vehicle should be scaled depending upon the technology that is outfitted. Retrofitting on vehicles without the technology should be paid for by the driver. ATM will offset greenhouse gas emissions by 99 kt of CO{sub 2} equivalency over a 25 year lifespan. This reduction has taken into account the expected improvement in vehicle technology. AHS is anticipated to save 280 kt of CO{sub 2} equivalency over 15 years of operational usage. However, this offset is largely dependent on assumptions such as the level of market penetration. - Highlights: • Three cost–benefit analyses are applied to inter-urban intelligent transport. • For ATM, a high cost–benefit ratio of 5.89 is achieved. • ATM offsets greenhouse gas emissions by 99 kt of CO{sub 2} equivalency over 25 years. • ISA and AHS generate a negative result due to vehicle implementation costs. • AHS is anticipated to save 280 kt of CO{sub 2} equivalency over 15 years.

54 ENVIRONMENTAL SCIENCES↗

Evacuee Compliance Behavior Analysis using High Resolution Demographic Information

The purpose of this study is to examine whether evacuee compliance behavior with route assignments from different resolutions of demographic data would impact the evacuation performance. Most existing evacuation strategies assume that travelers will follow evacuation instructions, while in reality a certain percent of evacuees do not comply with prescribed instructions. In this paper, a comparison study of evacuation assignment based on Traffic Analysis Zones (TAZ) and high resolution LandScan USA Population Cells (LPC) were conducted for the detailed road network representing Alexandria, Virginia. A revised platform for evacuation modeling built on high resolution demographic data and activity-based microscopic traffic simulation is proposed. The results indicate that evacuee compliance behavior affects evacuation efficiency with traditional TAZ assignment, but it does not significantly compromise the efficiency with high resolution LPC assignment. The TAZ assignment also underestimates the real travel time during evacuation, especially for high compliance simulations. This suggests that conventional evacuation studies based on TAZ assignment might not be effective at providing efficient guidance to evacuees. From the high resolution data perspective, traveler compliance behavior is an important factor but it does not impact the system performance significantly. The highlight of evacuee compliance behavior analysis should be emphasized on individual evacuee level route/shelter assignments, rather than the whole system performance.

Lu, Wei↗

Impact of Mixed Traffic on the Energy Savings of a Truck Platoon

A two-truck platoon based on a prototype cooperative adaptive cruise control (CACC) system was tested on a closed test track in a variety of realistic traffic and transient operating scenarios - conditions that truck platoons are likely to face on real highways. The fuel consumption for both trucks in the platoon was measured using the SAE J1321 gravimetric procedure as well as calibrated J1939 instantaneous fuel rate, serving as proxies to evaluate the impact of aerodynamic drag reduction under constant-speed conditions. These measurements demonstrate the effects of: the presence of a multiple-passenger-vehicle pattern ahead of and adjacent to the platoon, cut-in and cut-out manoeuvres by other vehicles, transient traffic, the use of mismatched platooned vehicles (van trailer mixed with flatbed trailer), and the platoon following another truck with adaptive cruise control (ACC). These scenarios are intended to address the possibility of “background aerodynamic platooning” impacting realized savings on public roads. Using calibrated J1939 fuel rate analysis, fuel savings for curved track sections versus straight track sections were also evaluated for these scenarios, highlighting differences in the implementation of the CACC control strategies compared to a stock ACC implementation. The use of different trailer types and the presence of passenger-vehicle traffic patterns showed a measurable impact on platoon performance in some conditions, but the basic fuel savings trends were retained.

adaptive cruise control↗

Impact of Mixed Traffic on the Energy Savings of a Truck Platoon: Preprint

A two-truck platoon based on a prototype cooperative adaptive cruise control (CACC) system was tested on a closed test track in a variety of realistic traffic and transient operating scenarios - conditions that truck platoons are likely to face on real highways. The fuel consumption for both trucks in the platoon was measured using the SAE J1321 gravimetric procedure as well as calibrated J1939 instantaneous fuel rate, serving as proxies to evaluate the impact of aerodynamic drag reduction under constant-speed conditions. These measurements demonstrate the effects of: the presence of a multiple-passenger-vehicle pattern ahead of and adjacent to the platoon, cut-in and cut-out manoeuvres by other vehicles, transient traffic, the use of mismatched platooned vehicles (van trailer mixed with flatbed trailer), and the platoon following another truck with adaptive cruise control (ACC). These scenarios are intended to address the possibility of “background aerodynamic platooning” impacting realized savings on public roads. Using calibrated J1939 fuel rate analysis, fuel savings for curved track sections versus straight track sections were also evaluated for these scenarios, highlighting differences in the implementation of the CACC control strategies compared to a stock ACC implementation. The use of different trailer types and the presence of passenger-vehicle traffic patterns showed a measurable impact on platoon performance in some conditions, but the basic fuel savings trends were retained.

adaptive cruise control↗

U.S. Virgin Islands Transportation Petroleum Reduction Plan

This NREL technical report determines a way for USVI to meet its petroleum reduction goal in the transportation sector. It does so first by estimating current petroleum use and key statistics and characteristics of USVI transportation. It then breaks the goal down into subordinate goals and estimates the petroleum impacts of these goals with a wedge analysis. These goals focus on reducing vehiclemiles, improving fuel economy, improving traffic flow, using electric vehicles, using biodiesel and renewable diesel, and using 10% ethanol in gasoline. The final section of the report suggests specific projects to achieve the goals, and ranks the projects according to cost, petroleum reduction, time frame, and popularity.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Streamlining Transportation Corridor Planning Processess: Freight and Traffic Information

The traffic investigation is one of the most important parts of an Environmental Impact Statement of projects involving the construction of new roadway facilities and/or the improvement of existing ones. The focus of the traffic analysis is on the determination of anticipated traffic flow characteristics of the proposed project, by the application of analytical methods that can be grouped under the umbrella of capacity analysis methodologies. In general, the main traffic parameter used in EISs to describe the quality of traffic flow is the Level of Service (LOS). The current state of the practice in terms of the traffic investigations for EISs has two main shortcomings. The first one is related to the information that is necessary to conduct the traffic analysis, and specifically to the lack of integration among the different transportation models and the sources of information that, in general, reside in GIS databases. A discussion of the benefits of integrating CRS&SI technologies and the transportation models used in the EIS traffic investigation is included. The second shortcoming is in the presentation of the results, both in terms of the appearance and formatting, as well as content. The presentation of traffic results (current and proposed) is discussed. This chapter also addresses the need of additional data, in terms of content and coverage. Regarding the former, other traffic parameters (e.g., delays) that are more meaningful to non-transportation experts than LOS, as well as additional information (e.g., freight flows) that can impact traffic conditions and safety are discussed. Spatial information technologies can decrease the negative effects of, and even eliminate, these shortcomings by making the relevant information that is input to the models more complete and readily available, and by providing the means to communicate the results in a more clear and efficient manner. The benefits that the application and use of CRS&SI technologies can provide to improve and expedite the traffic investigation part of the EIS process are presented.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

Soil response model verification: A multi-year study of foot traffic impact

The purpose of this research is to build upon the baseline study of soil compaction response to trampling previously conducted. Although trampling studies have been conducted in the past, the analysis of military training, in part, provides a different perspective and approach. The baseline data showed bulk densities remained relatively constant for a time and then began to increase at an increasing rate for several hundred passes and finally leveled and remained at or below 1.30 gm/cm{sup 3} through the remainder of the experiment. A mathematical model was created based on empirical data from the trampling experiment using a gamma cumulative distribution function. Subsequent similar experiments were conducted over the following 2 years to verify the baseline model soil response. The follow-on data were modeled using the same gamma distribution function with good results. The model replicated the soil response for the subsequent years well with the exception of the initial threshold which was dramatically reduced for both years. The experiments and the resulting model give quantifiable continuous inference on the effects of trampling, as opposed to the existing qualitative assessments. This model performed well and can be used as a foundation for future studies of land management when trampling occurs.

54 ENVIRONMENTAL SCIENCES↗

Proteomic Investigation of the Time Course Responses of RAW 264.7 Macrophages to Infection with Salmonella enterica

Macrophages plan important roles in controlling Salmonella-mediated systemic infection. To investigate the responses of macrophages to Salmonella infection, we infected RAW 264.7 macrophages with Salmonella enterica serovar Typhimurium (STM) and then performed a comparative liquid chromatography-tandem mass spectrometry [LC-MS(/MS)]-based proteomics analysis of the infected macrophages. A total of 1006 macrophage and 115 STM proteins were indentified from this study. Most of STM proteins were found at late stage of the time course of infection, consistent with the fact that STM proliferates inside RAW 264.7 macrophages. Majority of the identified macrophage proteins were house keeping-related, including cytoplasmic superoxide dismutase 1 (SOD1), whose peptide abundances were relatively constant during the time course of infection. Compared to those in no infection control, the peptide abundances of 244 macrophage proteins (or 24% of total indentified macrophage proteins) changed considerably after STM infection. The functions of these STM infection-affected macrophage proteins were diverse and ranged from production of antibacterial nitric oxide (i.e., inducible nitric oxide synthase or iNOS) or production of prostaglandin H2 (i.e., prostaglandin-endoperoxide synthase 2, also know as cyclooxygenase-2 or COX-2) to regulation of intracellular traffic (e.g., sorting nexin or SNX 5, 6 and 9), demonstrating a global impact of STM infection on macrophage proteome. Western-blot analysis not only confirmed the LC-MS(/MS) results of SOD1, COX-2 and iNOS, but also revealed that the protein abundances of mitochondrial SOD2 increased after STM infection, indicating an infection-induced oxidative stress in mitochondria.

59 BASIC BIOLOGICAL SCIENCES↗

Investigating the Impact of Temporal and Directional Traffic Distribution on Crash Frequencies

Safety Performance Functions (SPFs) are mathematical models that establish relationships between the frequency of various crash types and site-specific characteristics, serving as essential tools for traffic safety analysis and roadway design. Traditional SPFs, however, often overlook the temporal fluctuations in traffic flow (such as peak-hour surges) and directional imbalances between opposing traffic streams. These traffic patterns can exacerbate congestion, disrupt driver behavior, and create unexpected conflict points, potentially leading to increased crash frequencies and more severe accidents. In light of this gap, this study aims to explore the potential of incorporating K-factors (representing peak-hour traffic proportions) and D-factors (reflecting the imbalance of directional traffic) into the development of SPFs to assess whether these factors can effectively represent the impact of temporal and spatial traffic distribution on roadway safety. Using crash data from Pennsylvania urban-suburban collector roadways, it is found that the D-factor plays a significant role in predicting the frequency of total crashes, fatal + injury crashes, and angle crashes, with positive coefficient signs indicating that higher directional imbalances correspond to increased crash risks. Similarly, the K-factor emerges as a critical predictor for fatal + injury crashes and rear-end crashes, with negative coefficients suggesting that a more pronounced traffic peak is associated with a reduction in expected crash frequencies. These results highlight the importance of accounting for uneven traffic distribution in both time and direction when developing SPFs, offering deeper insights into crash patterns and supporting more effective safety interventions and roadway designs.

Xu, Guanhao [ORNL] (ORCID:0000000214326357)↗

Integration of Decentralized Graph-Based Multi-Agent Reinforcement Learning with Digital Twin for Traffic Signal Optimization

Machine learning (ML) methods, particularly Reinforcement Learning (RL), have gained widespread attention for optimizing traffic signal control in intelligent transportation systems. However, existing ML approaches often exhibit limitations in scalability and adaptability, particularly within large traffic networks. This paper introduces an innovative solution by integrating decentralized graph-based multi-agent reinforcement learning (DGMARL) with a Digital Twin to enhance traffic signal optimization, targeting the reduction of traffic congestion and network-wide fuel consumption associated with vehicle stops and stop delays. In this approach, DGMARL agents are employed to learn traffic state patterns and make informed decisions regarding traffic signal control. The integration with a Digital Twin module further facilitates this process by simulating and replicating the real-time asymmetric traffic behaviors of a complex traffic network. The evaluation of this proposed methodology utilized PTV-Vissim, a traffic simulation software, which also serves as the simulation engine for the Digital Twin. The study focused on the Martin Luther King (MLK) Smart Corridor in Chattanooga, Tennessee, USA, by considering symmetric and asymmetric road layouts and traffic conditions. Comparative analysis against an actuated signal control baseline approach revealed significant improvements. Experiment results demonstrate a remarkable 55.38% reduction in Eco_PI, a developed performance measure capturing the cumulative impact of stops and penalized stop delays on fuel consumption, over a 24 h scenario. In a PM-peak-hour scenario, the average reduction in Eco_PI reached 38.94%, indicating the substantial improvement achieved in optimizing traffic flow and reducing fuel consumption during high-demand periods. These findings underscore the effectiveness of the integrated DGMARL and Digital Twin approach in optimizing traffic signals, contributing to a more sustainable and efficient traffic management system.

42 ENGINEERING↗