Explores AI-driven network slicing, improving communication in smart cities, indicating enhanced efficiency.
The fast growth of smart cities has prompted the proliferation of connected technology applications like smart traffic management system, surveillance cameras, self-driving cars, health care monitoring gadgets, smart energy meters, and environmental sensors. These applications constantly produce large amounts of information, hence needing a reliable, fast, and low latency communication network for efficient operation. Although the deployment of 5G communication networks has greatly enhanced the capabilities of the communication networks, the large number of connected applications with varying communication requirements is posing great challenges in resource management in smart cities. Static network slicing and resource management systems usually fail in handling these challenges as they cannot be adjusted to accommodate changes in traffic, leading to issues such as network congestion, communication delay, inefficiency in resource usage, and poor quality of service (QoS). In light of these issues, the proposed research is set to explore an AI-powered approach to solving smart cities' communication issues through the development of an Intelligent Network Slicing Framework based on Artificial Intelligence, Machine Learning, LSTM-based traffic prediction, Federated Learning, and Dynamic Resource Allocation. Services like health care monitoring, emergency alerts, and intelligent traffic control will be prioritized for reliability and continuous operation. Federated learning is introduced to improve data privacy through model training at various locations without passing any sensitive data. In terms of improvement in the proposed scheme, there would be a reduction in latency, packet loss, enhancement in throughput, optimized usage of resources, and an increase in QoS. The expected outcome in comparison to the conventional method of static network slicing shows that there will be a considerable improvement in the network. Therefore, the proposed framework is a potential solution for implementing a network in the smart cities of the future with 5G and upcoming 6G technologies.
No takes yet. Share an insight, caveat, or question.
Patekar et al. (2026) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: