Loading [MathJax]/extensions/MathMenu.js
A Deep Neural Network-Based Communication Failure Prediction Scheme in 5G RAN | IEEE Journals & Magazine | IEEE Xplore

A Deep Neural Network-Based Communication Failure Prediction Scheme in 5G RAN


Abstract:

5G networks enable emerging latency and bandwidth critical applications like industrial IoT, AR/VR, or autonomous vehicles, in addition to supporting traditional voice an...Show More

Abstract:

5G networks enable emerging latency and bandwidth critical applications like industrial IoT, AR/VR, or autonomous vehicles, in addition to supporting traditional voice and data communications. In 5G infrastructure, Radio Access Networks (RANs) consist of radio base stations that communicate over wireless radio links. The communication, however, is prone to environmental changes like the weather and can suffer from radio link failure and interrupt ongoing services. The impact is severe in the above-mentioned applications. One way to mitigate such service interruption is to proactively predict failures and reconfigure the resource allocation accordingly. Existing works like the supervised ensemble learning-based model do not consider the spatial-temporal correlation between radio communication and weather changes. This paper proposes a communication link failure prediction scheme based on the LSTM-autoencoder that considers the spatial-temporal correlation between radio communication and weather forecast. We implement and evaluate the proposed scheme over a huge volume of real radio and weather data. The results confirm that the proposed scheme significantly outperforms the existing solutions.
Published in: IEEE Transactions on Network and Service Management ( Volume: 20, Issue: 2, June 2023)
Page(s): 1140 - 1152
Date of Publication: 15 December 2022

ISSN Information:


I. Introduction

Emerging networking applications like industry 4.0, intelligent transportation, smart health system, AR/VR, etc., demand high network bandwidth, high reliability, and low communication time [1]. Mobile and wireless devices from these applications usually communicate over radio links and form various types of networks like mesh, sensor, or cellular [2]. Specifically, fifth-generation (5G) cellular networks aim to support the above emerging applications with different service level objectives (SLOs). For example, Mobile Broadband (eMBB), ultra-Reliable Low Latency (uRLLC), and massive Machine Type Communication (mMTC) offer enhanced bandwidth (e.g., AR/VR), low latency (e.g., autonomous vehicles), and low-power massive machine-to-machine communication (e.g., industry 4.0), respectively. Unlike 4G networks with large and high-power cell towers to reflect signals over long distances, a 5G network consists of cells with a small coverage. Specifically, 5G uses millimeter-wave (mmWave) spectrums (between 24GHz and 100GHz) [3] that can travel over short distances; thus, 5G RAN needs to deploy a dense collection of base stations compared to 4G.

Contact IEEE to Subscribe

References

References is not available for this document.