T-s3ra: traffic-aware scheduling for secure slicing and resource allocation in sdn/nfv enabled 5g networks

TL;DR

This paper introduces T-S3RA, a traffic-aware scheduling method for secure network slicing and resource allocation in SDN/NFV-enabled 5G networks, utilizing deep learning to enhance security and performance under high traffic.

Contribution

The paper presents a novel traffic-aware scheduling framework, T-S3RA, integrating deep learning models for secure slicing and resource allocation in 5G networks, addressing DDoS threats and high traffic demands.

Findings

T-S3RA improves throughput and reduces latency.

Effective DDoS attack prediction using Renyi entropy.

Enhanced resource utilization across different 5G use cases.

Abstract

Network slicing and resource allocation play pivotal roles in software-defined network (SDN)/network function virtualization (NFV)-assisted 5G networks. In 5G communications, the traffic rate is high, necessitating high data rates and low latency. Deep learning is a potential solution for overcoming these constraints. Secure slicing avoids resource wastage; however, DDoS attackers can exploit the sliced network. Therefore, we focused on secure slicing with resource allocation under massive network traffic. Traffic-aware scheduling is proposed for secure slicing and resource allocation over SDN/NFV-enabled 5G networks. In this approach (T-S3RA), user devices are authenticated using Boolean logic with a password-based key derivation function. The traffic is scheduled in 5G access points, and secure network slicing and resource allocation are implemented using deep learning models such as SliceNet and HopFieldNet, respectively. To predict DDoS attackers, we computed the Renyi entropy for packet classification. Experiments were conducted using a network simulator with 250 nodes in the network topology. Performance was evaluated using metrics such as throughput, latency, packet transmission ratio, packet loss ratio, slice capacity, bandwidth consumption, and slice acceptance ratio. T-S3RA was implemented in three 5G use cases with different requirements including massive machine-type communication, ultrareliable low-latency communication, and enhanced mobile broadband.