Edge Intelligence in Softwarized 6G: Deep Learning-enabled Network Traffic Predictions

TL;DR

This paper proposes an edge-native deep learning framework using LSTM models to accurately predict network traffic in 6G environments, enabling better data flow management at the network edge.

Contribution

It introduces a novel edge-native prognosis framework employing LSTM-based deep learning for real-time network traffic prediction in 6G edge environments.

Findings

Accurately predicts statistical characteristics of network traffic.

Verifies model performance with real-time data and ground truth.

Demonstrates effectiveness in dynamic cloud-native environments.

Abstract

The 6G vision is envisaged to enable agile network expansion and rapid deployment of new on-demand microservices (e.g., visibility services for data traffic management, mobile edge computing services) closer to the network's edge IoT devices. However, providing one of the critical features of network visibility services, i.e., data flow prediction in the network, is challenging at the edge devices within a dynamic cloud-native environment as the traffic flow characteristics are random and sporadic. To provide the AI-native services for the 6G vision, we propose a novel edge-native framework to provide an intelligent prognosis technique for data traffic management in this paper. The prognosis model uses long short-term memory (LSTM)-based encoder-decoder deep learning, which we train on real time-series multivariate data records collected from the edge $\mu$-boxes of a selected testbed network. Our result accurately predicts the statistical characteristics of data traffic and verifies the trained model against the ground truth observations. Moreover, we validate our novel framework with two performance metrics for each feature of the multivariate data.