The increased need of various services with different QoS (Quality of Service) requirements motivated the deployment of 5G wireless communication networks. While the one logical network approach was good in theory, today has given rise to a new technology called Network Slicing where multiple independent Logical Networks were provided on shared infrastructure that caters specifically for service specific requirements. However, a 5G network is far more dynamic and large scale so the concept of network slicing and resource allocation becomes significantly harder. This work has been made from our exploration to explore the deep learning approach based on CNN for better network slicing in 5G networks. The CNN algorithm is to search the spatial pattern in data, so we are able to provision resource allocation and QoS parameter for each slice automatically at network level. Network slicing framework allows great flexibility in responding to the highly dynamic network conditions and services demands, an advantage that is best leveraged with deep learning. CNN models discover spatial patterns in network data with high accuracy, which can be significantly beneficial to optimize resource usage and prediction for different network slices. This way, it enhances the QoS provisioning more than conventional workings eventually resulting in good network performance with higher resource utilization. This paper also discusses the trade-off between model complexity of CNNs and their corresponding improvement in logistic performance at practical deployment scenario when they are running on 5G networks, computational requirements (with natural scalability guarantees or not). By and large, deep learning is able to significantly improve the efficiency of 5G networks so they are more accommodating as well as adaptable to cater for various services & applications being placed at the very top of the 5G ecosystem.
Authors: Reenu Mohandas, K. Srujan Raju, Arempula Sreenivasa Rao, K. Kumara Swamy, Mohit Tiwari
DOI: https://doi.org/10.2139/ssrn.5076185
Publish Year: 2025
