Developing an Energy-Conscious Traffic Signal Control System for Optimized Fuel Consumption in Connected Vehicle Environments
- Univ. of Tennessee, Chattanooga, TN (United States)
- Univ. of Pittsburgh, PA (United States)
- Georgia Institute of Technology, Atlanta, GA (United States)
- Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
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.
- Research Organization:
- Univ. of Tennessee, Chattanooga, TN (United States)
- Sponsoring Organization:
- USDOE Office of Energy Efficiency and Renewable Energy (EERE), Office of Sustainable Transportation. Vehicle Technologies Office (VTO)
- DOE Contract Number:
- EE0009208
- OSTI ID:
- 2497339
- Report Number(s):
- UTC--EE0009208
- Country of Publication:
- United States
- Language:
- English
Similar Records
Pedestrian-Involved Traffic Signal Optimization Using Decentralized Graph-based Multi-Agent Reinforcement Learning
Traffic Signal Optimization by Integrating Reinforcement Learning and Digital Twins
Integration of Decentralized Graph-Based Multi-Agent Reinforcement Learning with Digital Twin for Traffic Signal Optimization
Conference
·
Mon Jan 08 23:00:00 EST 2024
·
OSTI ID:2439977
Traffic Signal Optimization by Integrating Reinforcement Learning and Digital Twins
Conference
·
Mon Aug 28 00:00:00 EDT 2023
· 2023 IEEE Smart World Congress (SWC)
·
OSTI ID:2439938
Integration of Decentralized Graph-Based Multi-Agent Reinforcement Learning with Digital Twin for Traffic Signal Optimization
Other
·
Sun Apr 07 00:00:00 EDT 2024
·
OSTI ID:2439940