{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T03:11:41Z","timestamp":1776309101883,"version":"3.50.1"},"reference-count":46,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T00:00:00Z","timestamp":1767139200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Humanities and Social Sciences Foundation of the Ministry of Education of China","award":["22YJCZH153"],"award-info":[{"award-number":["22YJCZH153"]}]},{"name":"the Postgraduate Research &amp; Practice Innovation Program of Jiangsu Province","award":["SJCX23_2050"],"award-info":[{"award-number":["SJCX23_2050"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Systems"],"abstract":"<jats:p>Adaptive traffic signal control is a critical component of intelligent transportation systems, and multi-agent deep reinforcement learning (MARL) has attracted increasing interest due to its scalability and control efficiency. However, existing methods have two major drawbacks: (i) they are largely driven by current and historical traffic states, without explicit forecasting of upcoming traffic conditions, and (ii) their coordination mechanisms are often weak, making it difficult to model complex spatial dependencies in large-scale road networks and thereby limiting the benefits of coordinated control. To address these issues, we propose TG-MADDPG, which integrates short-term traffic prediction with a graph attention network (GAT) for regional signal control. A WT-GWO-CNN-LSTM traffic forecasting module predicts near-future states and injects them into the MARL framework to support anticipatory decision-making. Meanwhile, the GAT dynamically encodes road-network topology and adaptively captures inter-intersection spatial correlations. In addition, we design a reward based on normalized pressure difference to guide cooperative optimization of signal timing. Experiments on the SUMO simulator across synthetic and real-world networks under both off-peak and peak demands show that TG-MADDPG consistently achieves lower average waiting times, shorter queue lengths, and higher cumulative rewards than IQL, MADDPG, and GMADDPG, demonstrating strong effectiveness and generalization.<\/jats:p>","DOI":"10.3390\/systems14010047","type":"journal-article","created":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T16:08:00Z","timestamp":1767197280000},"page":"47","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A Multi-Agent Regional Traffic Signal Control System Integrating Traffic Flow Prediction and Graph Attention Networks"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1543-5790","authenticated-orcid":false,"given":"Chao","family":"Sun","sequence":"first","affiliation":[{"name":"School of Automotive and Traffic Engineering, Jiangsu University, Zhenjiang 212013, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhao","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Automotive and Traffic Engineering, Jiangsu University, Zhenjiang 212013, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiacheng","family":"Li","sequence":"additional","affiliation":[{"name":"School of Automotive and Traffic Engineering, Jiangsu University, Zhenjiang 212013, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiyi","family":"Fang","sequence":"additional","affiliation":[{"name":"School of Automotive and Traffic Engineering, Jiangsu University, Zhenjiang 212013, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Automotive and Traffic Engineering, Jiangsu University, Zhenjiang 212013, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,12,31]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"105019","DOI":"10.1016\/j.engappai.2022.105019","article-title":"A Deep Reinforcement Learning-Based Cooperative Approach for Multi-Intersection Traffic Signal Control","volume":"114","author":"Haddad","year":"2022","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"439","DOI":"10.1080\/19427867.2022.2065592","article-title":"Investigating the Role of Green Transport, Environmental Taxes and Expenditures in Mitigating the Transport CO2 Emissions","volume":"15","author":"Hussain","year":"2023","journal-title":"Transp. Lett."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"623","DOI":"10.1109\/JAS.2019.1911471","article-title":"A Survey of Model Predictive Control Methods for Traffic Signal Control","volume":"6","author":"Ye","year":"2019","journal-title":"IEEE\/CAA J. Autom. Sin."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1016\/j.physa.2018.04.027","article-title":"Effect of Bypasses on Vehicular Traffic through a Series of Signals","volume":"506","author":"Nagatani","year":"2018","journal-title":"Phys. A Stat. Mech. Its Appl."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"256","DOI":"10.1016\/j.ins.2018.10.015","article-title":"A Two-Stage Model for Period-Dependent Traffic Signal Control in a Road Networked System with Stochastic Travel Demand","volume":"476","author":"Chiou","year":"2019","journal-title":"Inf. Sci."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1007\/s12555-011-0108-4","article-title":"Urban Arterial Traffic Two-Direction Green Wave Intelligent Coordination Control Technique and Its Application","volume":"9","author":"Kong","year":"2011","journal-title":"Int. J. Control Autom. Syst."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"539","DOI":"10.1080\/17477778.2023.2233464","article-title":"Design and Application of Real-Time Traffic Simulation Platform Based on UTC\/SCOOT and VISSIM","volume":"18","author":"Liu","year":"2023","journal-title":"J. Simul."},{"key":"ref_8","unstructured":"Chen, R., Fang, F., and Sadeh, N. (2022). The Real Deal: A Review of Challenges and Opportunities in Moving Reinforcement Learning-Based Traffic Signal Control Systems Towards Reality. arXiv."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"108100","DOI":"10.1016\/j.engappai.2024.108100","article-title":"A Survey on Deep Reinforcement Learning Approaches for Traffic Signal Control","volume":"133","author":"Zhao","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Solaiappan, S., Kumar, B.R., Anbazhagan, N., Song, Y., Joshi, G.P., and Cho, W. (2023). Vehicular Traffic Flow Analysis and Minimize the Vehicle Queue Waiting Time Using Signal Distribution Control Algorithm. Sensors, 23.","DOI":"10.3390\/s23156819"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Zhao, R., Hu, H., Li, Y., Fan, Y., Gao, F., and Gao, Z. (2024). Sequence Decision Transformer for Adaptive Traffic Signal Control. Sensors, 24.","DOI":"10.3390\/s24196202"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"324","DOI":"10.1016\/j.comcom.2020.03.005","article-title":"Traffic Signal Control for Smart Cities Using Reinforcement Learning","volume":"154","author":"Joo","year":"2020","journal-title":"Comput. Commun."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1016\/j.aej.2024.07.046","article-title":"Reinforcement Learning Based Adaptive Control Method for Traffic Lights in Intelligent Transportation","volume":"106","author":"Huang","year":"2024","journal-title":"Alex. Eng. J."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1007\/s40747-024-01651-5","article-title":"Pri-DDQN: Learning Adaptive Traffic Signal Control Strategy through a Hybrid Agent","volume":"11","author":"Zheng","year":"2025","journal-title":"Complex Intell. Syst."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"103059","DOI":"10.1016\/j.trc.2021.103059","article-title":"Network-Wide Traffic Signal Control Optimization Using a Multi-Agent Deep Reinforcement Learning","volume":"125","author":"Li","year":"2021","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"110440","DOI":"10.1016\/j.engappai.2025.110440","article-title":"An Adaptive Traffic Signal Control Scheme with Proximal Policy Optimization Based on Deep Reinforcement Learning for a Single Intersection","volume":"149","author":"Wang","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1086","DOI":"10.1109\/TITS.2019.2901791","article-title":"Multi-Agent Deep Reinforcement Learning for Large-Scale Traffic Signal Control","volume":"21","author":"Chu","year":"2019","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"McCluskey, T.L., Kotsialos, A., M\u00fcller, J.P., Kl\u00fcgl, F., Rana, O., and Schumann, R. (2016). An Experimental Review of Reinforcement Learning Algorithms for Adaptive Traffic Signal Control. Autonomic Road Transport Support Systems, Springer International Publishing.","DOI":"10.1007\/978-3-319-25808-9"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"19750","DOI":"10.1109\/ACCESS.2020.2968937","article-title":"A Distributed Control Method for Urban Networks Using Multi-Agent Reinforcement Learning Based on Regional Mixed Strategy Nash-Equilibrium","volume":"8","author":"Qu","year":"2020","journal-title":"IEEE Access"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"2861","DOI":"10.1109\/TCE.2023.3272524","article-title":"KeyLight: Intelligent Traffic Signal Control Method Based on Improved Graph Neural Network","volume":"70","author":"Sun","year":"2024","journal-title":"IEEE Trans. Consum. Electron."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"104582","DOI":"10.1016\/j.trc.2024.104582","article-title":"A Large-Scale Traffic Signal Control Algorithm Based on Multi-Layer Graph Deep Reinforcement Learning","volume":"162","author":"Wang","year":"2024","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"880","DOI":"10.1177\/03611981241297979","article-title":"Multi-Agent Deep Reinforcement Learning with Graph Attention Network for Traffic Signal Control in Multiple-Intersection Urban Areas","volume":"2679","author":"Yang","year":"2025","journal-title":"Transp. Res. Rec."},{"key":"ref_23","unstructured":"Veli\u010dkovi\u0107, P., Cucurull, G., Casanova, A., Romero, A., Li\u00f2, P., and Bengio, Y. (2017). Graph Attention Networks. arXiv."},{"key":"ref_24","unstructured":"Kipf, T.N., and Welling, M. (2016). Semi-Supervised Classification with Graph Convolutional Networks. arXiv."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"21007","DOI":"10.1007\/s00521-023-08875-5","article-title":"AGRCNet: Communicate by Attentional Graph Relations in Multi-Agent Reinforcement Learning for Traffic Signal Control","volume":"35","author":"Ma","year":"2023","journal-title":"Neural Comput. Appl."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"6248","DOI":"10.1007\/s10489-022-03208-w","article-title":"Graph Cooperation Deep Reinforcement Learning for Ecological Urban Traffic Signal Control","volume":"53","author":"Yan","year":"2023","journal-title":"Appl. Intell."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"12183","DOI":"10.1109\/TITS.2025.3556931","article-title":"Communication Strategy on Macro-and-Micro Traffic State in Cooperative Deep Reinforcement Learning for Regional Traffic Signal Control","volume":"26","author":"Gu","year":"2025","journal-title":"IEEE Trans. Intell. Transport. Syst."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"361","DOI":"10.1016\/j.aej.2023.06.008","article-title":"Traffic Flow Prediction Model Based on Improved Variational Mode Decomposition and Error Correction","volume":"76","author":"Li","year":"2023","journal-title":"Alex. Eng. J."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"97072","DOI":"10.1109\/ACCESS.2023.3312711","article-title":"Short-Term Traffic Flow Prediction Based on VMD and IDBO-LSTM","volume":"11","author":"Zhao","year":"2023","journal-title":"IEEE Access"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"17142","DOI":"10.1038\/s41598-025-98496-w","article-title":"A Combined Model for Short-Term Traffic Flow Prediction Based on Variational Modal Decomposition and Deep Learning","volume":"15","author":"Ren","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"14356","DOI":"10.1109\/JSEN.2022.3181451","article-title":"Short-Term Traffic Flow Prediction via Improved Mode Decomposition and Self-Attention Mechanism Based Deep Learning Approach","volume":"22","author":"Li","year":"2022","journal-title":"IEEE Sens. J."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1016\/j.neunet.2021.05.035","article-title":"IGAGCN: Information Geometry and Attention-Based Spatiotemporal Graph Convolutional Networks for Traffic Flow Prediction","volume":"143","author":"An","year":"2021","journal-title":"Neural Netw."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Zhang, J., Sha, J., Zhang, C., and Zhang, Y. (2025). A CNN-LSTM-GRU Hybrid Model for Spatiotemporal Highway Traffic Flow Prediction. Systems, 13.","DOI":"10.3390\/systems13090765"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"114496","DOI":"10.1109\/ACCESS.2019.2935504","article-title":"Deep Temporal Convolutional Networks for Short-Term Traffic Flow Forecasting","volume":"7","author":"Zhao","year":"2019","journal-title":"IEEE Access"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Han, G., Zheng, Q., Liao, L., Tang, P., Li, Z., and Zhu, Y. (2022). Deep Reinforcement Learning for Intersection Signal Control Considering Pedestrian Behavior. Electronics, 11.","DOI":"10.3390\/electronics11213519"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"160","DOI":"10.1109\/MITS.2022.3144797","article-title":"A Comparison of Deep Reinforcement Learning Models for Isolated Traffic Signal Control","volume":"15","author":"Mao","year":"2023","journal-title":"IEEE Intell. Transport. Syst. Mag."},{"key":"ref_37","first-page":"4079","article-title":"AttendLight: Universal Attention-Based Reinforcement Learning Model for Traffic Signal Control","volume":"33","author":"Oroojlooy","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"21946","DOI":"10.1109\/JIOT.2024.3377600","article-title":"Digital-Twin-Based Deep Reinforcement Learning Approach for Adaptive Traffic Signal Control","volume":"11","author":"Kamal","year":"2024","journal-title":"IEEE Internet Things J."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"143997","DOI":"10.1016\/j.foodchem.2025.143997","article-title":"Quantitative analysis and visualization of chemical compositions during shrimp flesh deterioration using hyperspectral imaging: A comparative study of machine learning and deep learning models","volume":"481","author":"Xi","year":"2025","journal-title":"Food Chemistry"},{"key":"ref_40","first-page":"458","article-title":"Chaotic Grey Wolf Optimization Algorithm for Constrained Optimization Problems","volume":"5","author":"Kohli","year":"2018","journal-title":"J. Comput. Des. Eng."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1007\/s10462-024-10721-6","article-title":"A Review of Convolutional Neural Networks in Computer Vision","volume":"57","author":"Zhao","year":"2024","journal-title":"Artif. Intell. Rev."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"111258","DOI":"10.1016\/j.foodcont.2025.111258","article-title":"Physicochemical properties and gel quality monitoring of surimi during thermal processing using hyperspectral imaging combined with deep learning","volume":"175","author":"Xia","year":"2025","journal-title":"Food Control"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"2575","DOI":"10.1109\/ITSC.2018.8569938","article-title":"Microscopic Traffic Simulation Using SUMO","volume":"Volume 11","author":"Lopez","year":"2018","journal-title":"Proceedings of the 2018 21st International Conference on Intelligent Transportation Systems (ITSC)"},{"key":"ref_44","unstructured":"Whiteson, S. (2017, January 6\u201311). Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning. Proceedings of the 34th International Conference on Machine Learning (ICML 2017), Sydney, Australia."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"113269","DOI":"10.1016\/j.asoc.2025.113269","article-title":"Macroscopic GA-Based Multi-Objective Traffic Light Optimization Prioritizing Tramways","volume":"178","author":"Bilotta","year":"2025","journal-title":"Appl. Soft Comput."},{"key":"ref_46","unstructured":"Kwesiga, D.K., Vishnoi, S.C., Guin, A., and Hunter, M. (2024). Integrating Transit Signal Priority into Multi-Agent Reinforcement Learning Based Traffic Signal Control. arXiv."}],"container-title":["Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2079-8954\/14\/1\/47\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T05:23:10Z","timestamp":1767676990000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2079-8954\/14\/1\/47"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,31]]},"references-count":46,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["systems14010047"],"URL":"https:\/\/doi.org\/10.3390\/systems14010047","relation":{},"ISSN":["2079-8954"],"issn-type":[{"value":"2079-8954","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,31]]}}}