An Adaptive Signal Control Model for Intersection Based on Deep Reinforcement Learning Considering Carbon Emissions
Abstract
:1. Introduction
- (1)
- Aiming at the limitation that existing models only consider fuel-powered vehicle scenarios, an adaptive signal control model suitable for mixed traffic flows of fuel-powered and electric vehicles is proposed, thereby more authentically reflecting the complexity of modern urban traffic.
- (2)
- The constructed model exhibits high algorithm adaptability, achieving excellent control performance under various common deep reinforcement learning frameworks, which overcomes the current models’ heavy dependence on specific algorithms.
- (3)
- A novel reward function integrating vehicle waiting times with CO2 emission control is designed, thereby achieving synchronous optimization of both traffic efficiency and environmental benefits and compensating for the shortcomings of existing models that only focus on single-metric optimization.
2. Methodology
2.1. D3QN
2.2. PPO
2.3. SAC
3. Modeling
3.1. State Space
3.2. Action Space
3.3. Reward
4. Results and Discussion
4.1. Basic Setup
- (a)
- Fixed time control (FTC): a static control strategy with pre-set signal timings.
- (b)
- Actuated traffic signal control (ATSC): a fully actuated control method based on real-time vehicle detection.
- (c)
- FECO-TSC: we use the simulation results of [2] for comparison named Fuel-ECO TSC (FECO-TSC). Because its simulation results cannot be directly compared with this study, we have converted the data.
- (d)
- D3QN: an adaptive traffic signal control model using Double Deep Q-Networks.
- (e)
- PPO: an adaptive model based on the Proximal Policy Optimization algorithm.
- (f)
- SAC: the Soft Actor-Critic algorithm proposed in this study.
4.2. Validation of the Reward Function
4.3. Comparison of Model Control Performance
5. Conclusions
Author Contributions
Funding
Data Availability Statement
Conflicts of Interest
References
- Höglund, P.G. Alternative intersection design—A possible way of reducing air pollutant emissions from road and street traffic? Sci. Total Environ. 1994, 146, 35–44. [Google Scholar] [CrossRef]
- Liu, L.Y.; Zhang, J.; Qian, K.; Min, F. Semi-supervised regression via embedding space mapping and pseudo-label smearing. Appl. Intell. 2024, 54, 9622–9640. [Google Scholar] [CrossRef]
- Liu, L.Y.; Zuo, H.M.; Min, F. BSRU: Boosting semi-supervised regressor through ramp-up unsupervised loss. Knowl. Inf. Syst. 2024, 66, 2769–2797. [Google Scholar] [CrossRef]
- He, S.F. Traffic flow prediction using an AttCLX hybrid model. World J. Inf. Technol. 2025, 3, 84–88. [Google Scholar]
- Chang, A.; Li, D.; Cao, G.F.; Liu, W.; Wang, L.; Zhou, N. Research on traffic object tracking and trajectory prediction technology based on deep learning. World J. Inf. Technol. 2024, 2, 40–47. [Google Scholar]
- Boukerche, A.; Zhong, D.H.; Sun, P. FECO: An Efficient Deep Reinforcement Learning-Based Fuel-Economic Traffic Signal Control Scheme. IEEE Trans. Sustain. Comput. 2022, 7, 144–156. [Google Scholar] [CrossRef]
- Liu, J.X.; Qin, S.; Su, M.; Luo, Y.; Zhang, S.; Wang, Y.; Yang, S. Traffic Signal Control Using Reinforcement Learning Based on the Teacher-Student Framework. Expert Syst. Appl. 2023, 228, 120458. [Google Scholar] [CrossRef]
- Bouktif, S.; Cheniki, A.; Ouin, A.; El-Sayed, H. Deep Reinforcement Learning for Traffic Signal Control with Consistent State and Reward Design Approach. Knowl.-Based Syst. 2023, 267, 110440. [Google Scholar] [CrossRef]
- Liang, X.Y.; Du, X.S.; Wang, G.L.; Han, Z. A deep reinforcement learning network for traffic light cycle control. IEEE Trans. Veh. Technol. 2019, 68, 1243–1253. [Google Scholar] [CrossRef]
- Lu, L.-P.; Cheng, K.; Chu, D.; Wu, C.; Qiu, Y. Adaptive Traffic Signal Control Based on Dueling Recurrent Double Q Network. China J. Highw. Transp. 2022, 35, 267–277. [Google Scholar]
- Li, C.H.; Ma, X.T.; Xia, L.; Zhao, Q.; Yang, J. Fairness Control of Traffic Light via Deep Reinforcement Learning. In Proceedings of the 2020 IEEE 16th International Conference on Automation Science and Engineering, Hong Kong, China, 20–21 August 2020. [Google Scholar]
- Mao, F.; Li, Z.H.; Li, L. A Comparison of Deep Reinforcement Learning Models for Isolated Traffic Signal Control. IEEE Intell. Transp. Syst. Mag. 2023, 15, 160–180. [Google Scholar] [CrossRef]
- Jiang, H.Y.; Li, Z.Y.; Li, Z.S.; Bai, L.; Mao, H.; Ketter, W.; Zhao, R. A General Scenario-Agnostic Reinforcement Learning for Traffic Signal Control. IEEE Trans. Intell. Transp. Syst. 2024, 25, 11330–11344. [Google Scholar] [CrossRef]
- Tan, C.P.; Cao, Y.M.; Ban, X.G.; Tang, K. Connected Vehicle Data-Driven Fixed-Time Traffic Signal Control Considering Cyclic Time-Dependent Vehicle Arrivals Based on Cumulative Flow Diagram. IEEE Trans. Intell. Transp. Syst. 2024, 25, 8881–8897. [Google Scholar] [CrossRef]
- Vlachogiannis, D.M.; Wei, H.; Moura, S.; Macfarlane, J. HumanLight: Incentivizing Ridesharing via Human-centric Deep Reinforcement Learning in Traffic Signal Control. Transp. Res. Part C Emerg. Technol. 2024, 162, 104593. [Google Scholar] [CrossRef]
- Gu, H.K.; Wang, S.B.; Ma, X.G.; Jia, D.; Mao, G.; Lim, E.G.; Wong, C.P.R. Large-Scale Traffic Signal Control Using Constrained Network Partition and Adaptive Deep Reinforcement Learning. IEEE Trans. Intell. Transp. Syst. 2024, 25, 7619–7632. [Google Scholar] [CrossRef]
- Tan, C.P.; Yang, K.D. Privacy-preserving Adaptive Traffic Signal Control in A Connected Vehicle Environment. Transp. Res. Part C: Emerg. Technol. 2024, 158, 104453. [Google Scholar] [CrossRef]
- Wiseman, Y. Autonomous Vehicles. In Research Anthology on Cross-Disciplinary Designs and Applications of Automation; Information Resources Management Association: Alexandria, VA, USA, 2022; Volume 2, pp. 878–889. [Google Scholar]
Traffic Flow Direction | Lane | Vehicle Flow/h |
---|---|---|
East–West–Straight | Middle | 702 |
Right | 300 | |
East–West–Right | Right | 306 |
East–West–Left | Left | 372 |
North–South–Straight | Middle | 586 |
Right | 206 | |
North–South–Right | Right | 204 |
North–South–Left | Left | 294 |
Hyperparameters | Value |
---|---|
Learning rate | 3 × 10−4 |
Discount factor | 0.99 |
Clip ratio | 0.2 |
Batch size | 128 |
Mini batch size | 16 |
K_epochs | 20 |
C1 | 0.5 |
C2 | 0.01 |
Epsilon | |
Buffer | 100,000 |
Tau | 0.005 |
Models | FTC | ATSC | FECO | PPO | D3QN | SAC |
---|---|---|---|---|---|---|
Average CO2 emissions/g | 189.16 | 176.49 | 169.46 | 170.71 | 164.34 | 162.46 |
Optimization rate/% | −7.19 | \ | 3.98 | 3.27 | 6.88 | 7.95 |
Average waiting time/s | 31.76 | 26.71 | 24.16 | 24.27 | 21.24 | 22.09 |
Optimization rate/% | −18.91 | \ | 9.55 | 9.14 | 20.48 | 17.30 |
Average queue length/m | 23.4 | 17.6 | 12.4 | 13.5 | 9.7 | 9.8 |
Optimization rate/% | −32.95 | \ | 29.55 | 23.30 | 44.89 | 44.32 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Duan, L.; Zhao, H. An Adaptive Signal Control Model for Intersection Based on Deep Reinforcement Learning Considering Carbon Emissions. Electronics 2025, 14, 1664. https://doi.org/10.3390/electronics14081664
Duan L, Zhao H. An Adaptive Signal Control Model for Intersection Based on Deep Reinforcement Learning Considering Carbon Emissions. Electronics. 2025; 14(8):1664. https://doi.org/10.3390/electronics14081664
Chicago/Turabian StyleDuan, Lin, and Hongxing Zhao. 2025. "An Adaptive Signal Control Model for Intersection Based on Deep Reinforcement Learning Considering Carbon Emissions" Electronics 14, no. 8: 1664. https://doi.org/10.3390/electronics14081664
APA StyleDuan, L., & Zhao, H. (2025). An Adaptive Signal Control Model for Intersection Based on Deep Reinforcement Learning Considering Carbon Emissions. Electronics, 14(8), 1664. https://doi.org/10.3390/electronics14081664