6G Traffic Prediction with a Novel Parallel Convolutional Neural Networks Architecture and Matrix Format Method Integration

Abstract

In the evolving world of wireless communication, sixth generation (6G) networks represent a significant leap forward. Beyond its high-speed and reliable communication, 6G integrates Artificial Intelligence (AI), making networks intelligent entities. This elevates the infrastructure of smart cities and other ecosystems. A critical factor in 6G's success is real-time traffic analysis. As 6G aims to interconnect billions of devices, it faces unprecedented traffic patterns. Practical traffic analysis ensures optimal performance, resource distribution, and energy efficiency. It also supports the network in handling vital sectors like healthcare and transportation by anticipating congestion and prioritizing crucial data. However, traditional traffic analysis techniques designed for earlier generations cannot accommodate 6G's demands. With 6G's integration of diverse technologies, understanding traffic becomes more challenging. Recent advancements have incorporated deep learning architectures, notably Convolutional Neural Networks (CNNs), for traffic analysis. While these models show potential, adapting them to 6G's specifics remains challenging. This research presents a unique parallel CNN architecture for 6G traffic prediction. It converts network data into an image using the Matrix Format Method (MFM), making it suitable for CNN processing. This innovation addresses the limitations of traditional methods and meets 6G's requirements. Compared to other models, our parallel CNN architecture highlights enhanced performance, promising increased traffic prediction accuracy. It also paves the way for improved resource allocation, energy management, and quality of service in 6G environments.