A Machine Learning Framework for Sleeping Cell Detection in a Smart-City IoT Telecommunications Infrastructure

The smooth operation of largely deployed Internet of Things (IoT) applications will depend on, among other things, effective infrastructure failure detection. Access failures in wireless network Base Stations (BSs) produce a phenomenon called “sleeping cells”, which can render...

Full description

Bibliographic Details
Main Authors: Orestes G. Manzanilla-Salazar, Filippo Malandra, Hakim Mellah, Constant Wette, Brunilde Sanso
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
IoT
Online Access:https://ieeexplore.ieee.org/document/9046847/
id doaj-28f7a95cfb4b4cb2aa3acc2ea0244968
record_format Article
spelling doaj-28f7a95cfb4b4cb2aa3acc2ea02449682021-03-30T01:29:32ZengIEEEIEEE Access2169-35362020-01-018612136122510.1109/ACCESS.2020.29833839046847A Machine Learning Framework for Sleeping Cell Detection in a Smart-City IoT Telecommunications InfrastructureOrestes G. Manzanilla-Salazar0https://orcid.org/0000-0001-6287-6516Filippo Malandra1https://orcid.org/0000-0002-1817-0310Hakim Mellah2https://orcid.org/0000-0002-1540-3449Constant Wette3https://orcid.org/0000-0002-9188-3587Brunilde Sanso4https://orcid.org/0000-0002-6055-4625Polytechnique Montréal, Montreal, QC, CanadaDepartment of Electrical Engineering, University at Buffalo, Buffalo, NY, USAPolytechnique Montréal, Montreal, QC, CanadaEricsson, Stockholm, SwedenPolytechnique Montréal, Montreal, QC, CanadaThe smooth operation of largely deployed Internet of Things (IoT) applications will depend on, among other things, effective infrastructure failure detection. Access failures in wireless network Base Stations (BSs) produce a phenomenon called “sleeping cells”, which can render a cell catatonic without triggering any alarms or provoking immediate effects on cell performance, making them difficult to discover. To detect this kind of failure, we propose a Machine Learning (ML) framework based on the use of Key Performance Indicators (KPIs) statistics from the BS under study, as well as those of the neighboring BSs with propensity to have their performance affected by the failure. A simple way to define neighbors is to use adjacency in Voronoi diagrams. In this paper, we propose a much more realistic approach based on the nature of radio-propagation and the way devices choose the BS to which they send access requests. We gather data from large-scale simulators that use real location data for BSs and IoT devices and pose the detection problem as a supervised binary classification problem. We measure the effects on the detection performance by the size of time aggregations of the data, the level of traffic and the parameters of the neighborhood definition. The Extra Trees and Naive Bayes classifiers achieve Receiver Operating Characteristic (ROC) Area Under the Curve (AUC) scores of 0.996 and 0.993, respectively, with False Positive Rates (FPRs) under 5%. The proposed framework holds potential for other pattern recognition tasks in smart-city wireless infrastructures, that would enable the monitoring, prediction and improvement of the Quality of Service (QoS) experienced by IoT applications.https://ieeexplore.ieee.org/document/9046847/Failure detectionIoTM2M communicationsmachine learningsleeping cellssmart cities
collection DOAJ
language English
format Article
sources DOAJ
author Orestes G. Manzanilla-Salazar
Filippo Malandra
Hakim Mellah
Constant Wette
Brunilde Sanso
spellingShingle Orestes G. Manzanilla-Salazar
Filippo Malandra
Hakim Mellah
Constant Wette
Brunilde Sanso
A Machine Learning Framework for Sleeping Cell Detection in a Smart-City IoT Telecommunications Infrastructure
IEEE Access
Failure detection
IoT
M2M communications
machine learning
sleeping cells
smart cities
author_facet Orestes G. Manzanilla-Salazar
Filippo Malandra
Hakim Mellah
Constant Wette
Brunilde Sanso
author_sort Orestes G. Manzanilla-Salazar
title A Machine Learning Framework for Sleeping Cell Detection in a Smart-City IoT Telecommunications Infrastructure
title_short A Machine Learning Framework for Sleeping Cell Detection in a Smart-City IoT Telecommunications Infrastructure
title_full A Machine Learning Framework for Sleeping Cell Detection in a Smart-City IoT Telecommunications Infrastructure
title_fullStr A Machine Learning Framework for Sleeping Cell Detection in a Smart-City IoT Telecommunications Infrastructure
title_full_unstemmed A Machine Learning Framework for Sleeping Cell Detection in a Smart-City IoT Telecommunications Infrastructure
title_sort machine learning framework for sleeping cell detection in a smart-city iot telecommunications infrastructure
publisher IEEE
series IEEE Access
issn 2169-3536
publishDate 2020-01-01
description The smooth operation of largely deployed Internet of Things (IoT) applications will depend on, among other things, effective infrastructure failure detection. Access failures in wireless network Base Stations (BSs) produce a phenomenon called “sleeping cells”, which can render a cell catatonic without triggering any alarms or provoking immediate effects on cell performance, making them difficult to discover. To detect this kind of failure, we propose a Machine Learning (ML) framework based on the use of Key Performance Indicators (KPIs) statistics from the BS under study, as well as those of the neighboring BSs with propensity to have their performance affected by the failure. A simple way to define neighbors is to use adjacency in Voronoi diagrams. In this paper, we propose a much more realistic approach based on the nature of radio-propagation and the way devices choose the BS to which they send access requests. We gather data from large-scale simulators that use real location data for BSs and IoT devices and pose the detection problem as a supervised binary classification problem. We measure the effects on the detection performance by the size of time aggregations of the data, the level of traffic and the parameters of the neighborhood definition. The Extra Trees and Naive Bayes classifiers achieve Receiver Operating Characteristic (ROC) Area Under the Curve (AUC) scores of 0.996 and 0.993, respectively, with False Positive Rates (FPRs) under 5%. The proposed framework holds potential for other pattern recognition tasks in smart-city wireless infrastructures, that would enable the monitoring, prediction and improvement of the Quality of Service (QoS) experienced by IoT applications.
topic Failure detection
IoT
M2M communications
machine learning
sleeping cells
smart cities
url https://ieeexplore.ieee.org/document/9046847/
work_keys_str_mv AT orestesgmanzanillasalazar amachinelearningframeworkforsleepingcelldetectioninasmartcityiottelecommunicationsinfrastructure
AT filippomalandra amachinelearningframeworkforsleepingcelldetectioninasmartcityiottelecommunicationsinfrastructure
AT hakimmellah amachinelearningframeworkforsleepingcelldetectioninasmartcityiottelecommunicationsinfrastructure
AT constantwette amachinelearningframeworkforsleepingcelldetectioninasmartcityiottelecommunicationsinfrastructure
AT brunildesanso amachinelearningframeworkforsleepingcelldetectioninasmartcityiottelecommunicationsinfrastructure
AT orestesgmanzanillasalazar machinelearningframeworkforsleepingcelldetectioninasmartcityiottelecommunicationsinfrastructure
AT filippomalandra machinelearningframeworkforsleepingcelldetectioninasmartcityiottelecommunicationsinfrastructure
AT hakimmellah machinelearningframeworkforsleepingcelldetectioninasmartcityiottelecommunicationsinfrastructure
AT constantwette machinelearningframeworkforsleepingcelldetectioninasmartcityiottelecommunicationsinfrastructure
AT brunildesanso machinelearningframeworkforsleepingcelldetectioninasmartcityiottelecommunicationsinfrastructure
_version_ 1724186875093057536