Article
Transform-Based Multiresolution Decomposition for
Degradation Detection in Cellular Networks
Sergio Fortes
1,
* , Pablo Muñoz
2
, Inmaculada Serrano
3
and Raquel Barco
1
1
Departamento de Ingeniería de Comunicaciones, Campus de Teatinos s/n, Andalucía Tech,
Universidad de Málaga, 29071 Málaga, Spain; rbm@ic.uma.es
2
Department of Signal Theory, Telematics and Communications (TSTC), Universidad de Granada,
18071 Granada, Spain; pabloml@ugr.es
3
Ericsson, 29590 Málaga, Spain; inmaculada.serrano@ericsson.com
* Correspondence:sfr@ic.uma.es
Received: 24 August 2020; Accepted: 29 September 2020; Published: 2 October 2020
Abstract:
Anomaly detection in the performance of the huge number of elements that are part
of cellular networks (base stations, core entities, and user equipment) is one of the most time
consuming and key activities for supporting failure management procedures and ensuring the
required performance of the telecommunication services. This activity originally relied on direct
human inspection of cellular metrics (counters, key performance indicators, etc.). Currently,
degradation detection procedures have experienced an evolution towards the use of automatic
mechanisms of statistical analysis and machine learning. However, pre-existent solutions typically
rely on the manual definition of the values to be considered abnormal or on large sets of labeled data,
highly reducing their performance in the presence of long-term trends in the metrics or previously
unknown patterns of degradation. In this field, the present work proposes a novel application
of transform-based analysis, using wavelet transform, for the detection and study of network
degradations. The proposed system is tested using cell-level metrics obtained from a real-world LTE
cellular network, showing its capabilities to detect and characterize anomalies of different patterns
and in the presence of varied temporal trends. This is performed without the need for manually
establishing normality thresholds and taking advantage of wavelet transform capabilities to separate
the metrics in multiple time-frequency components. Our results show how direct statistical analysis of
these components allows for a successful detection of anomalies beyond the capabilities of detection
of previous methods.
Keywords: cellular management; failure detection; self-healing; transform-based; wavelet
1. Introduction
The complexity of cellular networks is continuously growing. This complexity increases the costs
of the network infrastructure and those of its operation, administration, and management (OAM)
activities. The huge number of indicators, counters, alarms, and configuration parameters transform
network monitoring into a complicated task.
In this field, the concept of self-healing, as part of the self-organizing network (SON)
paradigm [1,2]
, aims to automate the tasks associated with network failure management, achieving a
more reliable service provision with minimum operational costs. Self-healing includes the tasks of the
detection of degradations in the network service (familiarly known also as problems), diagnosis of the
root cause or fault generating the problem, compensation of the degradation, and the recovery of the
system to its original state.
Sensors 2020, 20, 5645; doi:10.3390/s20195645 www.mdpi.com/journal/sensors
