IRO Journals
IRO Journal on Sustainable Wireless Systems

AI-Powered Digital Twin Framework for Real-Time Smart City Infrastructure Optimization

Open Access
Published: 02 July, 2026
Pages: 142-159
  • Gayathri C. , Gayathri C.
    Assistant Professor, Department of Computer Science and Engineering (AI & ML), Mangayarkarasi College of Engineering, Madurai, India
    Assistant Professor, Department of Computer Science and Engineering (AI & ML), Mangayarkarasi College of Engineering, Madurai, India
  • Dhanushri A. , Dhanushri A.
    Department of Electronics and Communication Engineering, Mangayarkarasi College of Engineering, Madurai, India
    Department of Electronics and Communication Engineering, Mangayarkarasi College of Engineering, Madurai, India
  • Vijayalakshmi T B. Vijayalakshmi T B.
    Department of Electronics and Communication Engineering, Mangayarkarasi College of Engineering, Madurai, India
    Department of Electronics and Communication Engineering, Mangayarkarasi College of Engineering, Madurai, India
view PDF
view PDF

How to Cite

C., Gayathri, Dhanushri A., and Vijayalakshmi T B. 2026. “AI-Powered Digital Twin Framework for Real-Time Smart City Infrastructure Optimization”. IRO Journal on Sustainable Wireless Systems 8 (3): 142-59. https://doi.org/10.36548/jsws.2026.3.002.
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Keywords

Digital Twin
Smart Cities
Internet of Things
Physics-Informed Neural Networks
Reinforcement Learning
Multi-Agent Systems

Abstract

A smart city requires efficient management and coordination of connected urban infrastructures, which could effectively cope with the rising requirements on energy, water, transport, and buildings. The traditional methods of infrastructure management do not allow making proper predictions due to independent functioning in different spheres. This paper proposes UrbanMirror – a novel smart city framework that integrates Digital Twin technique, Physics-Informed Neural Networks (PINNs), and Swarm Optimization Reinforcement Learning (SwarmOpt-RL) engine in order to provide real-time infrastructure monitoring, prediction, and optimizationMulti-agent SwarmOpt-RL approach is applied for coordination of decision-making process within the domains of energy, water, mobility, and buildings, whereas the role of the coordinator (Meta-Agent) in cross-domain optimization and resource allocation is fulfilled by the Meta-Agent. The proposed framework was tested using a large-scale smart city simulation setting including up to 50,000 infrastructure nodes interconnected. Experimental results show significant improvement of operational efficiency, resource consumption, sustainability, and infrastructure resilience, having achieved the overall predictive accuracy of 95.5%. Scalability analysis proves the applicability of the developed.

References

  1. Tao, F., H. Zhang, A. Liu, and A. Y. C. Nee. "Digital Twin in Industry: State-of-the-Art in IEEE Transactions on Industrial Informatics 2019, vol. 15, no. 4.: 2405-2415.
  2. Bektas, Mutlu. "Energy Outlook." Artificial Intelligence: Technical and Societal Advancements 2024, 316.
  3. Zanella, Andrea, Nicola Bui, Angelo Castellani, Lorenzo Vangelista, and Michele Zorzi. "Internet of Things for Smart Cities." IEEE Internet of Things journal 2014, vol 1, no. 1: 22-32.
  4. Deng, Tianhu, Keren Zhang, and Zuo-Jun Max Shen. "A Systematic Review of a Digital Twin City: A New Pattern of Urban Governance Toward Smart Cities." Journal of management science and engineering 2021, vol 6, no. 2: 125-134.
  5. Deren, Li, Yu Wenbo, and Shao Zhenfeng. "Smart City Based on Digital Twins." Computational Urban Science 2021, vol 1, no. 1: 4.
  6. Chen, Chacha, Hua Wei, Nan Xu, Guanjie Zheng, Ming Yang, Yuanhao Xiong, Kai Xu, and Zhenhui Li. "Toward A Thousand Lights: Decentralized Deep Reinforcement Learning for Large-Scale Traffic Signal Control." In Proceedings of the AAAI conference on artificial intelligence 2020, vol. 34, no. 04: 3414-3421.
  7. Haydari, Ammar, and Yasin Yılmaz. "Deep Reinforcement Learning for Intelligent Transportation Systems: A Survey." IEEE Transactions on Intelligent Transportation Systems 2020, vol 23, no. 1: 11-32.
  8. Cao, Zhiwei, Xin Zhou, Han Hu, Zhi Wang, and Yonggang Wen. "Toward A Systematic Survey for Carbon Neutral Data Centers." IEEE Communications Surveys & Tutorials 2022, vol 24, no. 2: 895-936.
  9. Fachrudin, Suaedi, and Rismawati Rismawati. "Assessment of Anthropogenic Impacts on River Water Quality in Palopo City Indonesia Using Physicochemical Parameters and Pollution Indices." Discover Environment 2026, vol 4, no. 1: 214.
  10. Fragkias, Michail, Burak Güneralp, Karen C. Seto, and Julie Goodness. "A Synthesis of Global Urbanization Projections." Urbanization, biodiversity and ecosystem services: Challenges and opportunities: A global assessment (2013): 409-435.