TY - GEN
T1 - ENodeB Failure Detection from Aggregated Performance KPIs in Smart-city LTE Infrastructures
AU - Manzanilla-Salazar, Orestes
AU - Malandra, Filippo
AU - Sanso, Brunilde
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/5/13
Y1 - 2019/5/13
N2 - In this paper we show how Supervised Binary Classification techniques can be used to tackle the problem of eNodeB failure detection in an LTE network carrying Machine-to-Machine (M2M) smart-city traffic. 22 different classifiers are trained with data from two 24 hrs simulations with different levels of traffic volume. Input features for the classification models are built aggregating packet generation and access collisions from the eNodeB on which failures are being detected, as well as from its closest neighbors, by computing statistics for each time-bin. Given that network service providers generally process real-time data to produce periodic aggregated summaries, we explore the effect of different levels of granularity in data aggregation and their effect on our ability to detect failures. The M2M traffic data was gathered from a simulated LTE network that uses publicly available geographic databases from the city of Montreal. With Linear Support Vector Machines (L-SVMs) and Bagged Decision Trees (BDT), failure detection rates above 97.5 % were achieved, with false positive rates under 2.8 %, showing that, even with 30 minutes aggregations, it is feasible to extract meaningful failure information.
AB - In this paper we show how Supervised Binary Classification techniques can be used to tackle the problem of eNodeB failure detection in an LTE network carrying Machine-to-Machine (M2M) smart-city traffic. 22 different classifiers are trained with data from two 24 hrs simulations with different levels of traffic volume. Input features for the classification models are built aggregating packet generation and access collisions from the eNodeB on which failures are being detected, as well as from its closest neighbors, by computing statistics for each time-bin. Given that network service providers generally process real-time data to produce periodic aggregated summaries, we explore the effect of different levels of granularity in data aggregation and their effect on our ability to detect failures. The M2M traffic data was gathered from a simulated LTE network that uses publicly available geographic databases from the city of Montreal. With Linear Support Vector Machines (L-SVMs) and Bagged Decision Trees (BDT), failure detection rates above 97.5 % were achieved, with false positive rates under 2.8 %, showing that, even with 30 minutes aggregations, it is feasible to extract meaningful failure information.
KW - Binary classification
KW - Failure detection
KW - IoT (Internet-of-things)
KW - LTE networks
KW - M2M (Machine-to-machine) communications
KW - Machine learning
KW - MTC (Machine Type Communications)
KW - Smart city
KW - Supervised learning
UR - https://www.scopus.com/pages/publications/85066735838
U2 - 10.1109/DRCN.2019.8713687
DO - 10.1109/DRCN.2019.8713687
M3 - Conference contribution
AN - SCOPUS:85066735838
T3 - 2019 15th International Conference on the Design of Reliable Communication Networks, DRCN 2019
SP - 51
EP - 58
BT - 2019 15th International Conference on the Design of Reliable Communication Networks, DRCN 2019
A2 - Chemouil, Prosper
A2 - Melo, Paulo
A2 - Schupke, Dominic A.
A2 - Jorge, Luisa Maria Garcia
A2 - Gomes, Teresa
A2 - Tipper, David
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 15th International Conference on the Design of Reliable Communication Networks, DRCN 2019
Y2 - 19 March 2019 through 21 March 2019
ER -