A SON Solution for Sleeping Cell Detection Using Low-Dimensional Embedding of MDT Measurements

Zoha, A., Saeed, A., Imran, A., Imran, M. A. and Abu-Dayya, A. (2015) A SON Solution for Sleeping Cell Detection Using Low-Dimensional Embedding of MDT Measurements. In: 2014 IEEE 25th Annual International Symposium on Personal, Indoor, and Mobile Radio Communication (PIMRC), Washington, DC, USA, 02-05 Sep 2014, pp. 1626-1630. ISBN 9781479949120 (doi:10.1109/PIMRC.2014.7136428)

Zoha, A., Saeed, A., Imran, A., Imran, M. A. and Abu-Dayya, A. (2015) A SON Solution for Sleeping Cell Detection Using Low-Dimensional Embedding of MDT Measurements. In: 2014 IEEE 25th Annual International Symposium on Personal, Indoor, and Mobile Radio Communication (PIMRC), Washington, DC, USA, 02-05 Sep 2014, pp. 1626-1630. ISBN 9781479949120 (doi:10.1109/PIMRC.2014.7136428)

[img]
Preview
Text
136677.pdf - Accepted Version

908kB

Abstract

Automatic detection of cells which are in outage has been identified as one of the key use cases for Self Organizing Networks (SON) for emerging and future generations of cellular systems. A special case of cell outage, referred to as Sleeping Cell (SC) remains particularly challenging to detect in state of the art SON because in this case cell goes into outage or may perform poorly without triggering an alarm for Operation and Maintenance (O&M) entity. Consequently, no SON compensation function can be launched unless SC situation is detected via drive tests or through complaints registered by the affected customers. In this paper, we present a novel solution to address this problem that makes use of minimization of drive test (MDT) measurements recently standardized by 3GPP and NGMN. To overcome the processing complexity challenge, the MDT measurements are projected to a low-dimensional space using multidimensional scaling method. Then we apply state of the art k-nearest neighbor and local outlier factor based anomaly detection models together with pre-processed MDT measurements to profile the network behaviour and to detect SC. Our numerical results show that our proposed solution can automate the SC detection process with 93 accuracy.

Item Type:Conference Proceedings
Additional Information:This work was made possible by NPRP grant No. 5-1047- 2437 from the Qatar National Research Fund (a member of The Qatar Foundation).
Status:Published
Refereed:Yes
Glasgow Author(s) Enlighten ID:Imran, Professor Muhammad
Authors: Zoha, A., Saeed, A., Imran, A., Imran, M. A., and Abu-Dayya, A.
College/School:College of Science and Engineering > School of Engineering
ISBN:9781479949120
Copyright Holders:Copyright © 2015 IEEE
Publisher Policy:Reproduced in accordance with the copyright policy of the publisher

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