Citation :

B. Raveendra Naick, K. Delhi Babu, "A Context-Aware Deep Swarm and Federated Meta-Reinforcement Learning Signal Controller for Sustainable Urban Mobility Optimization," International Journal of Engineering Trends and Technology (IJETT), vol. 74, no. 5, pp. 524-539, 2026. Crossref, https://doi.org/10.14445/22315381/IJETT-V74I5P133

Abstract

Urban road systems are experiencing an increasing rate of congestion due to the rapid population growth, increased vehicle ownership, and uneven mobility demand across the metropolitan corridors. Although the traffic agencies have deployed the sensor networks and surveillance infrastructure, a significant portion of signal controllers still follow the rigid or semi-adaptive timing plans-this struggles to handle the fluctuating traffic patterns, multimodal flow pressure, and energy-related constraints. Current smart mobility research has explored deep learning, spatiotemporal forecasting, transfer learning, and optimization-driven control. However, it does not completely combine the contextual, environmental, and real-world uncertainties into a unified traffic management framework. The conventional traffic signal optimization methods mainly have focused on the minimization of congestion and the reduction of delay, but they remain limited in sustainability. They depend heavily on the large labeled datasets, but the real traffic environments frequently involve missing or noisy data. The majority of data-driven controllers also function at the isolated intersections rather than the coordinating corridor-level decisions. Further, recent models have lacked resilience during disturbances such as sudden traffic surges, road incidents, and cyber-threat-driven disruptions. These limitations have restricted the capability of the traffic authorities to convert the real-time prediction into a stable, reliable, and sustainable mobility planning. The study has introduced a hybrid adaptive control framework that tends to combine the Context-Aware Multi-Objective Deep Swarm Learning (CM-DSL) and Threat-Adaptive Federated Meta-Reinforcement Learning (TA-FMRL). The CM-DSL module learns the multimodal traffic dependencies, environmental indicators, queue dynamics, and the sustainability metrics through a multi-objective swarm search. It guides the advancement towards the globally beneficial phase selections. The TA-FMRL layer then distributes the learning across intersections, and it has provided fast policy transfer, privacy preservation, and resilience against incomplete data and security threats. The system relies entirely on the real-time vehicle counts, optical flow patterns, contextual state inputs, and the cloud synchronization layer for a collaborative decision update. The experimental tests in a dense urban network have confirmed a great improvement in mobility and sustainability. The average waiting time has reduced to 64.0 s on METR-LA and 68.5 s on PEMS-BAY, while the average queue length is reduced to 120 m and 128 m, respectively. The Intersection throughput increases to 1390 vehicles/h and 1360 vehicles/h, which confirms a faster clearance of the traffic inflow. The travel time index has declined to 1.60 and 1.65, which shows a smoother vehicle movement. The fuel consumption and emission output have decreased to 33.5 L/35.0 L and 388 kg/400 kg, respectively. This confirms that the proposed method has supported sustainable and energy-efficient driving conditions for the intelligent transportation systems.

Keywords

Urban Mobility Optimization, Deep Swarm Learning, Federated Meta-Reinforcement Learning, Sustainable Traffic Control, Intelligent Transportation Systems.

References

[1] Tatiane Borchers, Dirk Wittowsky, and Ricardo Augusto Souza Fernandes, “A Comprehensive Survey and Future Directions on Optimising Sustainable Urban Mobility,” IEEE Access, vol. 12, pp. 63023-63048, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[2] Mubashir Islam, “Analysis of AI-Enabled Adaptive Traffic Control Systems for Urban Mobility Optimization Through Intelligent Road Network Management,” Review of Applied Science and Technology, vol. 4, no. 02, pp. 207-232, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[3] Foroogh Behnia, Beth-Anne Schuelke-Leech, and Mitra Mirhassani, “Optimizing Sustainable Urban Mobility: A Comprehensive Review of Electric Bus Scheduling Strategies and Future Directions,” Sustainable Cities and Society, vol. 108, pp. 1-15, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[4] Hayri Ulvi, Mehmet Akif Yerlikaya, and Kürşat Yildiz, “Urban Traffic Mobility Optimization Model: A Novel Mathematical Approach for Predictive Urban Traffic Analysis,” Applied Sciences, vol. 14, no. 13, pp. 1-22, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[5] Ayad Ghany Ismaeel et al., “Traffic Pattern Classification in Smart Cities Using Deep Recurrent Neural Network,” Sustainability, vol. 15, no. 19, pp. 1-17, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[6] N. Yuvaret et al., “An Investigation of Garbage Disposal Electric Vehicles (GDEVs) Integrated with Deep Neural Networking (DNN) and Intelligent Transportation System (ITS) in Smart City Management System (SCMS),” Wireless Personal Communications, vol. 123, no. 2, pp. 1733-1752, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[7] Jing Jiang et al., “Smart Transportation Systems Using Learning Method for Urban Mobility and Management in Modern Cities,” Sustainable Cities and Society, vol. 108, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[8] Muhammad Usman Tariq, “Smart Transportation Systems: Paving the Way for Sustainable Urban Mobility,” Contemporary Solutions for Sustainable Transportation Practices, IGI Global Scientific Publishing, pp. 254-283, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[9] Hajar Fatorachian, and Hadi Kazemi, “Sustainable Optimization Strategies for On-Demand Transportation Systems: Enhancing Efficiency and Reducing Energy Use,” Sustainable Environment, vol. 11, no. 1, pp.  1-19, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[10] Samuel Jesupelumi Owoade et al., “Optimizing Urban Mobility with Multi-Modal Transportation Solutions: A Digital Approach to Sustainable Infrastructure,” Engineering Science & Technology Journal, vol. 5, no. 11, pp. 3193-3208, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[11] Andrea Grotto et al., “Formalizing Sustainable Urban Mobility Management: An Innovative Approach with Digital Twin and Integrated Modeling,” Logistics, vol. 8, no. 4, Pp. 1-24, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[12] D.D. Herrera-Acevedo, and D. Sierra-Porta, “Network Structure and Urban Mobility Sustainability: A Topological Analysis of Cities from the Urban Mobility Readiness Index,” Sustainable Cities and Society, vol. 119, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[13] F. Rahman, and Charpe Prasanjeet Prabhakar, “Enhancing Smart Urban Mobility through AI-Based Traffic Flow Modeling and Optimization Techniques,” Bridge: Journal of Multidisciplinary Explorations, vol. 1, no. 1, pp. 31-42, 2025.
[Google Scholar] [Publisher Link]

[14] Enver Cenan İnce, “Mapping the Path to Sustainable Urban Mobility: A Bibliometric Analysis of Global Trends and Innovations in Transportation Research,” Sustainability, vol. 17, no. 4, pp. 1-31, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[15] Ming Xiao et al., “Sustainable and Robust Route Planning Scheme for Smart City Public Transport Based on Multi-Objective Optimization: Digital Twin Model,” Sustainable Energy Technologies and Assessments, vol. 65, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[16] Vladimir Stadnichuk et al., “Optimisation of Mobility Hub Locations for a Sustainable Mobility System,” Transportation Research Interdisciplinary Perspectives, vol. 26, pp. 1-14, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[17] Marinko Maslaric et al., “Sustainable Urban Mobility Planning in the Port Areas: A Case Study,” Sustainability, vol. 16, no. 2, pp. 1-28, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[18] Stavros Xanthopoulos et al., “Optimization of the Location and Capacity of Shared Multimodal Mobility Hubs to Maximize Travel Utility in Urban Areas,” Transportation Research Part A: Policy and Practice, vol. 179, pp.1- 24, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[19] Yuan Yuan et al., “Learning the Complexity of Urban Mobility with Deep Generative Network,” PNAS Nexus, vol. 4, no. 5, p. pp. 1-14, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[20] Yun Wang, Faiz Currim, and Sudha Ram, “Deep Learning of Spatiotemporal Patterns for Urban Mobility Prediction Using Big Data,” Information Systems Research, vol. 33, no. 2, pp. 579-598, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[21] Ankur Chaudhary, et al., “Enhancing Urban Mobility: Machine Learning-Powered Fusion Approach for Intelligent Traffic Congestion Control in Smart Cities,” International Journal of System Assurance Engineering and Management, pp. 1-8, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[22] Gen Chen, and Jia wan Zhang, “Intelligent Transportation Systems: Machine Learning Approaches for Urban Mobility in Smart Cities,” Sustainable Cities and Society, vol. 107, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[23] Pengjun W et al., “Deep Learning Solutions for Smart City Challenges in Urban Development,” Scientific Reports, vol. 14, no. 1, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[24] M. Sreelekha, and Midhunchakkaravarthy, “Intelligent Transportation System for Sustainable and Efficient Urban Mobility: Machine Learning Approach for Traffic Flow Prediction,” International Conference on Multi-Strategy Learning Environment, Singapore, pp. 399-412, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[25] Dina Bousdar Ahmed, and Estefania Munoz Diaz, “Survey of Machine Learning Methods Applied to Urban Mobility,” IEEE Access, vol. 10, pp. 30349-30366, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[26] Sangeetha S.K.B et al., “A Multi-Modal Geospatial–Temporal LSTM Based Deep Learning Framework for Predictive Modeling of Urban Mobility Patterns,” Scientific Reports, vol. 14, no. 1, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[27] Gerard Caravaca Ibañez et al., “MobilitApp: A Deep Learning-Based Tool for Transport Mode Detection to Support Sustainable Urban Mobility,” IEEE Access, vol. 13, pp. 68439-68461, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[28] Shiyuan Zhang, et al., “Deep Transfer Learning for City-Scale Cellular Traffic Generation through Urban Knowledge Graph,” Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp. 4842-4851, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[29] Xingyu Tao et al., “Towards Green Innovation in Smart Cities: Leveraging Traffic Flow Prediction with Machine Learning Algorithms for Sustainable Transportation Systems,” Sustainability, vol. 16, no. 1, pp. 1-22, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[30] Srishti Dikshit, et al., “The Use of Artificial Intelligence to Optimize the Routing of Vehicles and Reduce Traffic Congestion in Urban Areas,” EAI Endorsed Transactions on Energy Web, vol. 10, pp. 1-13, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[31] Mohammad R. Khosravi et al., “Crowd Emotion Prediction for Human-Vehicle Interaction through Modified Transfer Learning and Fuzzy Logic Ranking,” IEEE Transactions on Intelligent Transportation Systems, vol. 24, no. 12, pp. 15752-15761, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[32] Muhammad Saleem et al., “Smart Cities: Fusion-Based Intelligent Traffic Congestion Control System for Vehicular Networks Using Machine Learning Techniques,” Egyptian Informatics Journal, vol. 23, no. 3, pp. 417-426, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[33] Shaofei Wu, “Spatiotemporal Dynamic Forecasting and Analysis of Regional Traffic Flow in Urban Road Networks Using Deep Learning Convolutional Neural Network,” IEEE Transactions on Intelligent Transportation Systems, vol. 23, no. 2, pp. 1607-1615, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[34] Wahida Mansouri et al., “Deep Convolutional Neural Network-Based Enhanced Crowd Density Monitoring for Intelligent Urban Planning on Smart Cities,” Scientific Reports, vol. 15, no. 1, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[35] Ali Louati, “Machine Learning Framework for Sustainable Traffic Management and Safety in AlKharj City,” Sustainable Futures, vol. 9, pp.  1-27, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[36] HuuAnnn, METR-LA Dataset, Kaggle, 2023. [Online]. Available: https://www.kaggle.com/datasets/annnnguyen/metr-la-dataset   

[37] Sunil Sun, PEMS-BAY Dataset, Kaggle, 2022. [Online]. Available: https://www.kaggle.com/datasets/scchuy/pemsbay