Edge Intelligence and TinyML for Sustainable Smart Cities: A Review of Emerging Architectures
Abstract
Smart cities rely on real-time data processing and intelligent decision-making to enhance urban living and sustainability. Edge Intelligence and TinyML have emerged as key enablers for deploying machine learning models on resource-constrained devices at the network edge. This paper reviews recent advancements in edge AI architectures and TinyML frameworks for smart city applications such as traffic management, energy optimization, and environmental monitoring. It examines challenges related to computational limitations, energy efficiency, and model deployment. The study also highlights the role of 5G and next-generation communication technologies in supporting edge intelligence. Future research directions include decentralized AI ecosystems and green computing strategies.
References
Whig, P., & Elngar, A. (2025). AI innovations for transforming food production. IGI Global.
Whig, P., & Elngar, A. (2025). Modernizing the food industry: AI-powered infrastructure, security, and supply chain innovation. IGI Global.
Whig, P., Sharma, P., Elngar, A. A., & Silva, N. (2025). Quantum learning: Bridging artificial intelligence, quantum computing, and data science in education. CRC Press.
Rather, R., Vats, H., Sharma, S., & Whig, P. (2025). AI and ML applications in data-informed leadership: Transforming higher education. In Advances in data science driven technologies (Vol. 5, pp. 36–53). Bentham Science.
Whig, P., Silva, N., Elngar, A. A., Aneja, N., & Sharma, P. (2025). Sustainable development through machine learning, AI and IoT: Proceedings of ICSD 2025 (Part I). Springer.
Whig, P., Silva, N., Elngar, A. A., Aneja, N., & Sharma, P. (2025). Sustainable development through machine learning, AI and IoT: Proceedings of ICSD 2025 (Part II). Springer.
Whig, P., et al. (2025). Shield-Pay: Secure healthcare encryption and integrated ledger for data and payments authentication yield (Patent application). Government of India.
Singh, B., Anand, A., Prabhat, S., & Ranjan, P. (2025). Threat Onboarding and Response (TOR): Automating Cybersecurity in Enterprise Networks.
Anand, A., Singh, B., & Prabhat, S. (2022). Real-Time Network Monitoring and Incident Response with AI-Driven Automation Data Center and WAN Transformation. Available at SSRN 5577033.
Anand, A., Singh, B., Khemka, S., Banerjee, B., Bhatia, V. S., & Ranjan, P. (2025, October). Malware Classification using Diluted Convolutional Neural Network with Fast Gradient Sign Method. In 2025 2nd International Conference on Software, Systems and Information Technology (SSITCON) (pp. 1-5). IEEE.
Singh, B., Bhatia, V., Anand, A., Edamadaka, G., & Sudhakar, M. (2025, June). Intent-based Software Defined Networking for Flexible Network Management in Heterogeneous Environments. In 4th Conference on SGCNSP-2025.
Szeliski, R. (2010). Computer vision: Algorithms and applications. Springer.
Kaur, K., & Sood, S. K. (2017). Machine learning-based anomaly detection in IoT systems. Journal of Network and Computer Applications, 89, 1–15.
Al-Fuqaha, A., Guizani, M., Mohammadi, M., & Aledhari, M. (2015). Internet of Things: A survey on enabling technologies. IEEE Communications Surveys & Tutorials, 17(4), 2347–2376.
