Affiliation:
1. School of Electronics Engineering, Vellore Institute of Technology, Vellore, India
Abstract
The emergence of 5G technology has presented new problems and opportunities in the field of software-defined networking (SDN). Recently, efficient traffic management and quality of service (QoS) assurance have deviated due to network threats. This study presents a new modified convolutional neural network (MCNN) method for 5G SDN infrastructures. The proposed approach incorporates neural routing algorithms to optimize the distribution of network resources and minimize latency in 5G SDN. MCNN's primary advantage rests in its sophisticated convolutional neural network architecture, which demonstrates exceptional proficiency in identifying patterns and detecting anomalies. The neural routing methods of MCNN enhance its real-time monitoring capabilities, allowing for quick analysis of network traffic and enabling prompt identification and response to emerging threats. The proposed approach attains an accuracy of 93.4%, where the MCNN techniques outperform the existing state-of-the-art techniques.