Urban Eco-Network Traffic Control via MARL-Based Traffic Signals and Vehicle Speed Coordination
Source abstract
Abstract
This study proposes a Cooperative Traffic Controller System (CTS), an urban eco-network control system that leverages Multi-Agent Reinforcement Learning (MARL), to address urban road congestion and environmental pollution. The proposed system synergizes traffic signal timing optimization and speed guidance control, simultaneously enhancing network efficiency, reducing carbon emissions, and minimizing energy consumption. A Beta-enhanced Soft Actor-Critic (SAC) algorithm is applied to achieve the joint optimization of the traffic signal phasing and vehicle speed coordination. Experimental results show that in large-scale networks, the improved SAC reduces the average delay time per vehicle by approximately one minute, reduces CO2 emissions by more than double, and reduces fuel consumption by 56%. Comparative analyses of the algorithm versus the PPO and standard SAC demonstrate its superior performance in complex traffic scenarios—specifically in congestion mitigation and emissions reduction.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Vehicular Ad Hoc Networks (VANETs) · Traffic control and management · Traffic Prediction and Management Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Automation, Changzhou University, Changzhou 213159, China
School of Computer Science and Artificial Intelligence, Changzhou University, Changzhou 213159, China
References (34)
Show source-provided references
1. Traffic Flow as a Simple Fluid: Toward a Scaling Theory of Urban Congestion10.1177/03611981231179703 ↗
2. Self-organized criticality of traffic flow: Implications for congestion management technologies10.1016/j.trc.2023.104056 ↗
3. Aggravated air pollution and health burden due to traffic congestion in urban China10.5194/acp-23-2983-2023 ↗
4. Adverse Effect of Congestion on Economy, Health and Environment Under Mixed Traffic Scenario10.1007/s40890-021-00125-4 ↗
5. Estimating vehicle fuel consumption and emissions based on instantaneous speed and acceleration levels10.1061/(ASCE)0733-947X(2002)128:2(182) ↗
6. Personalized Driving Behaviors and Fuel Economy Over Realistic Commute Traffic: Modeling, Correlation, and Prediction10.1109/TVT.2022.3171165 ↗
7. Assessing driving behavior influence on fuel efficiency using machine-learning and drive-cycle simulations10.1016/j.trd.2023.104025 ↗
8. Combined influence of traffic conditions, driving behavior, and type of road on fuel consumption. Real driving data from Madrid Area
9. Pedram, A., Iskrov, A., and Chen, M. (2023, January 13). Deep Reinforcement Learning-Based Intelligent Traffic Signal Controls with Optimized CO2 Emissions. Proceedings of the 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Detroit, MI, USA.
10. Cooperative Traffic Control with Green Wave Coordination for Multiple Intersections Based on the Internet of Vehicles10.1109/TSMC.2016.2586500 ↗
11. Development and Evaluation of Non-Traditional Pedestrian Timing Treatments for Coordinated Signalized Intersections
12. Coordinated deep reinforcement learners for traffic light control
13. Wei, H., Zheng, G., Yao, H., and Li, Z. (2018, January 19–23). Intellilight: A reinforcement learning approach for intelligent traffic light control. Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, London, UK.10.1145/3219819.3220096 ↗
14. A Deep Reinforcement Learning Network for Traffic Light Cycle Control10.1109/TVT.2018.2890726 ↗
15. Multi-Agent Deep Reinforcement Learning for Large-Scale Traffic Signal Control10.1109/TITS.2019.2901791 ↗
16. Traffic signal control with reinforcement learning based on region-aware cooperative strategy10.1109/TITS.2021.3062072 ↗
17. Cooperative Deep Reinforcement Learning for Large-Scale Traffic Grid Signal Control10.1109/TCYB.2019.2904742 ↗
18. Mean field multi-agent reinforcement learning
19. Large-scale traffic signal control using a novel multiagent reinforcement learning10.1109/TCYB.2020.3015811 ↗
20. A mixed traffic speed harmonization model with connected autonomous vehicles10.1016/j.trc.2019.05.005 ↗
21. Safety evaluation of connected and automated vehicles in mixed traffic with conventional vehicles at intersections10.1080/15472450.2020.1834392 ↗
22. Lin, K., Jia, Z., Li, P., Shi, T., and Khamis, A. (2023, January 19–21). Cooperative Variable Speed Limit Control using Multi-agent Reinforcement Learning and Evolution Strategy for Improved Throughput in Mixed Traffic. Proceedings of the 2023 IEEE International Conference on Smart Mobility (SM), Thuwal, Saudi Arabia.10.1109/SM57895.2023.10112494 ↗
23. Integrated optimization of traffic signals and vehicle trajectories at isolated urban intersections10.1016/j.trb.2018.04.007 ↗
24. CoTV: Cooperative Control for Traffic Light Signals and Connected Autonomous Vehicles Using Deep Reinforcement Learning10.1109/TITS.2023.3276416 ↗
25. Busch, J.V.S., Voelckner, R., Sossalla, P., Vielhaus, C.L., Calandra, R., and Fitzek, F.H. (2023, January 15–17). Deep Reinforcement Learning for the Joint Control of Traffic Light Signaling and Vehicle Speed Advice. Proceedings of the 2023 International Conference on Machine Learning and Applications (ICMLA), Jacksonville, FL, USA.10.1109/ICMLA58977.2023.00033 ↗
26. Wei, H., Zheng, G., Gayah, V., and Li, Z. (2019). A Survey on Traffic Signal Control Methods. arXiv.
27. Adaptive traffic signal control with actor-critic methods in a real-world traffic network with different traffic disruption events10.1016/j.trc.2017.09.020 ↗
28. Wei, H., Chen, C., Zheng, G., Wu, K., Gayah, V., Xu, K., and Li, Z. (2019, January 4–8). PressLight: Learning Max Pressure Control to Coordinate Traffic Signals in Arterial Network. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Anchorage, AK, USA.10.1145/3292500.3330949 ↗
29. A survey and critique of multiagent deep reinforcement learning10.1007/s10458-019-09421-1 ↗
30. Papoudakis, G., Christianos, F., Schäfer, L., and Albrecht, S.V. (2019). Benchmarking multi-agent deep reinforcement learning algorithms in cooperative tasks. arXiv.
31. Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
32. Fuel consumption and emissions performance under real driving: Comparison between hybrid and conventional vehicles10.1016/j.scitotenv.2018.12.349 ↗
33. InTAS—The Ingolstadt Traffic Scenario for SUMO10.52825/scp.v1i.102 ↗
34. Toward A Thousand Lights: Decentralized Deep Reinforcement Learning for Large-Scale Traffic Signal Control