UPCommons. Portal del coneixement obert de la UPC
Publicación
Artículo científico (JournalArticle)
Realistic urban traffic generator using decentralized federated learning for the SUMO simulator
Realistic urban traffic simulation is essential for sustainable urban planning and the development of intelligent transportation systems. However, generating high-fidelity, time-varying traffic profiles that accurately reflect real-world conditions, especially in large-scale scenarios, remains a major challenge. Existing methods often suffer from limitations in accuracy, scalability, or raise privacy concerns due to centralized data processing. This work introduces DesRUTGe (Decentralized Realistic Urban Traffic Generator), a novel framework that integrates Deep Reinforcement Learning (DRL) agents with the SUMO simulator to generate realistic 24-hour traffic patterns. A key innovation of DesRUTGe is its use of Decentralized Federated Learning (DFL), wherein each traffic detector and its corresponding urban zone function as an independent learning node. These nodes train local DRL models using minimal historical data and collaboratively refine their performance by exchanging model parameters with selected peers (e.g., geographically adjacent zones), without requiring a central coordinator. Evaluated using real-world data from the city of Barcelona, DesRUTGe outperforms standard SUMO-based tools such as RouteSampler, as well as other centralized learning approaches, by delivering more accurate traffic pattern generation., This work was supported in part by the MICIU/AEI/10.13039/501100011033 (COMPROMISE Project) under Grant PID2020-113795RB-C33; in part by the MCIU/AEI/10.13039/501100011033 (DISCOVERY Project) under Grant PID2023-148716OB-C31; in part by the TRUFFLES: Trusted Framework for Federated Learning Systems, within the Strategic Cybersecurity Projects (INCIBE, Spain); in part by the Recovery, Transformation and Resilience Plan (European Union, Next Generation); in part by the Galician Regional Government under Project ED431B 2024/41 (GPC); in part by the Project Anonymization Technology for AI-Based Analytics of Mobility Data (MOBILYTICS) funded by MCIN/AEI/10.13039/501100011033 under Grant TED2021-129782B-I00; in part by the European Union NextGenerationEU/ PRTR; in part by the Project MultiMO: Datos MultiSectoriales para la Movilidad Obligada (European Union, NextGenerationEU) under Grant TSI-100123-2024-60; in part by the Generalitat de Catalunya under AGAUR Grant 2021 SGR 01413; and in part by the Predoctoral Scholarship for the Training of Research Personnel Associated with the Generación de Conocimiento Project under Grant PRE2021-099830.