Fuel-Based Nash Bargaining Approach for Adaptive Signal Control in an N -Player Cooperative Game (in EN)
This paper presents a fuel-based game-theoretic approach for adaptive signal control. Our controller applies Nash bargaining (NB) in an n-player cooperative game to identify optimal phasing splits considering future traffic demands. The fuel-based NB controller utilizes an objective function that combines operational measures (delays and stops) with fuel consumption measures at intersections. The proposed controller was encoded in Python and then implemented and evaluated in a VISSIM microscopic traffic simulation model in an intersection with increasing volumes. The performance of the NB controller was compared to a traditional actuated control as the baseline. The results show that the NB controller was able to achieve superior environmental gains with a 17% saving in fuel consumption and a 17% reduction in CO emissions. In addition, the proposed controller was capable of maintaining acceptable operational conditions as it achieved a 20% reduction in delay, 8% reduction in the number of stops, and 8% reduction in queue lengths compared to the actuated controller. Compared to similar studies that applied NB for adaptive signal control, our fuel-based NB controller stands out as a promising approach to significantly improve fuel consumption at signalized intersections.
- Research Organization:
- Univ. of Tennessee, Knoxville, TN (United States)
- Sponsoring Organization:
- USDOE Office of Energy Efficiency and Renewable Energy (EERE)
- DOE Contract Number:
- EE0009208
- OSTI ID:
- 2580164
- Journal Information:
- Transportation Research Record: Journal of the Transportation Research Board, Journal Name: Transportation Research Record: Journal of the Transportation Research Board Journal Issue: 10 Vol. 2677; ISSN 0361-1981
- Publisher:
- SAGE
- Country of Publication:
- United States
- Language:
- EN
Similar Records
Integration of Decentralized Graph-Based Multi-Agent Reinforcement Learning with Digital Twin for Traffic Signal Optimization
Traffic Signal Optimization by Integrating Reinforcement Learning and Digital Twins