Cell Coverage Degradation Detection Using Deep Learning Techniques

Mulvey, D., Foh, C. H., Imran, M. A. and Tafazolli, R. (2018) Cell Coverage Degradation Detection Using Deep Learning Techniques. In: 2018 International Conference on Information and Communication Technology Convergence (ICTC), Jeju Island, Korea, 17-19 Oct 2018, pp. 446-447. ISBN 9781538650417 (doi: 10.1109/ICTC.2018.8539449)

[img]
Preview
Text
168096.pdf - Accepted Version

604kB

Abstract

We apply deep learning techniques to the sleeping cell problem, in order to achieve greater detection sensitivity than previously reported. We use a deep recurrent Neural Network (rNN) to process simulated RSRP reports in order to detect degradations of cell radio performance as well as complete outages. Using such a configuration we are able to achieve improved sensivity compared with a traditional Support Vector Machine (SVM) approach, while eliminating the need for a separate dimensionality reduction stage at the front end. We study multiple rNN configurations with up to three hidden layers and conclude that in this scenario we can achieve the target sensitivity with a single hidden layer, leading to highly efficient run time performance.

Item Type:Conference Proceedings
Status:Published
Refereed:Yes
Glasgow Author(s) Enlighten ID:Imran, Professor Muhammad
Authors: Mulvey, D., Foh, C. H., Imran, M. A., and Tafazolli, R.
College/School:College of Science and Engineering > School of Engineering > Systems Power and Energy
ISSN:2162-1233
ISBN:9781538650417
Published Online:19 November 2018
Copyright Holders:Copyright © 2018 IEEE
First Published:First published in
Publisher Policy:Reproduced in accordance with the publisher copyright policy
Related URLs:

University Staff: Request a correction | Enlighten Editors: Update this record