COMMUNICATION CHANNEL FAILURE PREDICTION IN 5G NETWORKS
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 the 5G infrastructure, Radio Access Networks (RANs)
consist of radio base stations that communicate over wireless radio links. This communication, however, is prone to environmental changes, such as the weather. These
links can suffer from radio link failure and subsequently interrupt ongoing services,
severely impacting the above-mentioned applications. One way to mitigate such service interruption is to proactively predict failures and reconfigure the resource allocation accordingly. In this work, we propose a communication
link failure prediction model based on the LSTM autoencoder, i.e., considering both
the spatio-temporal correlation of radio communication as well as weather changes.
The results confirm that the proposed scheme performs better than the state-of-the-art solution.