Repository logo
 

COMMUNICATION CHANNEL FAILURE PREDICTION IN 5G NETWORKS

dc.contributor.authorIslam, Mohammad Ariful
dc.contributor.copyright-releaseNot Applicableen_US
dc.contributor.degreeMaster of Computer Scienceen_US
dc.contributor.departmentFaculty of Computer Scienceen_US
dc.contributor.ethics-approvalNot Applicableen_US
dc.contributor.external-examinern/aen_US
dc.contributor.graduate-coordinatorDr. Michael McAllisteren_US
dc.contributor.manuscriptsNot Applicableen_US
dc.contributor.thesis-readerDr. Stan Matwinen_US
dc.contributor.thesis-readerDr. Qiang Yeen_US
dc.contributor.thesis-supervisorDr. Israat Haqueen_US
dc.date.accessioned2022-03-25T14:33:03Z
dc.date.available2022-03-25T14:33:03Z
dc.date.defence2022-02-28
dc.date.issued2022-03-25T14:33:03Z
dc.descriptionFifth-generation (5G) cellular networks aim to support the emerging applications with the ultra-fast mmWave radio frequency. However, the weather condition may impact heavily on the mmWave radio frequency. In this thesis, we proposed a deep learning-based time-series neural network solution where we are able to predict one-day-ahead link failure utilizing the weather forecast report and radio tower key performance indicator. We particularly used the combination of the LSTM network and the Autoencoder model.en_US
dc.description.abstract5G 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.en_US
dc.identifier.urihttp://hdl.handle.net/10222/81494
dc.language.isoen_USen_US
dc.subjectDeep Learningen_US
dc.subjectTime series processingen_US
dc.subjectNeural Networken_US
dc.titleCOMMUNICATION CHANNEL FAILURE PREDICTION IN 5G NETWORKSen_US

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
MohammadArifulIslam2022.pdf
Size:
1.93 MB
Format:
Adobe Portable Document Format
Description:
Main Thesis file

License bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description: