TY - JOUR
T1 - Bayesian Inference-Assisted Machine Learning for Near Real-Time Jamming Detection and Classification in 5G New Radio (NR)
AU - Jere, Shashank
AU - Wang, Ying
AU - Aryendu, Ishan
AU - Dayekh, Shehadi
AU - Liu, Lingjia
N1 - Publisher Copyright:
© 2002-2012 IEEE.
PY - 2024
Y1 - 2024
N2 - The increased flexibility and density of spectrum access in 5G New Radio (NR) has made jamming detection and classification a critical research area. To detect coexisting jamming and subtle interference, we introduce a Bayesian Inference-assisted machine learning (ML) methodology. Our methodology uses cross-layer Key Performance Indicator data collected on a Non-Standalone (NSA) 5G NR testbed to leverage supervised learning models, and is further assessed, calibrated, and revealed using Bayesian Network Model (BNM)-based inference. The models can operate on both instantaneous and sequential time-series data samples, achieving an Area under Curve above 0.954 for instantaneous models and above 0.988 for sequential models including the echo state network (ESN) from the Reservoir Computing (RC) family, across various jamming scenarios. The 180 ms instantaneous detection time allows for continuous tracking of the dynamic jamming condition due to UE mobility. Our approach serves as a validation method and a resilience enhancement tool for ML-based jamming detection while also enabling root cause identification for observed performance degradation. The introduced BNM-based inference proof-of-concept is successful in addressing 72.2% of the erroneous predictions of the RC-based sequential detection model caused by insufficient training data samples, thereby demonstrating its near real-time applicability in 5G NR and Beyond-5G networks.
AB - The increased flexibility and density of spectrum access in 5G New Radio (NR) has made jamming detection and classification a critical research area. To detect coexisting jamming and subtle interference, we introduce a Bayesian Inference-assisted machine learning (ML) methodology. Our methodology uses cross-layer Key Performance Indicator data collected on a Non-Standalone (NSA) 5G NR testbed to leverage supervised learning models, and is further assessed, calibrated, and revealed using Bayesian Network Model (BNM)-based inference. The models can operate on both instantaneous and sequential time-series data samples, achieving an Area under Curve above 0.954 for instantaneous models and above 0.988 for sequential models including the echo state network (ESN) from the Reservoir Computing (RC) family, across various jamming scenarios. The 180 ms instantaneous detection time allows for continuous tracking of the dynamic jamming condition due to UE mobility. Our approach serves as a validation method and a resilience enhancement tool for ML-based jamming detection while also enabling root cause identification for observed performance degradation. The introduced BNM-based inference proof-of-concept is successful in addressing 72.2% of the erroneous predictions of the RC-based sequential detection model caused by insufficient training data samples, thereby demonstrating its near real-time applicability in 5G NR and Beyond-5G networks.
KW - 5G NR
KW - Bayesian network model
KW - Jamming
KW - O-RAN
KW - causal analysis and inference
KW - interference
KW - machine learning
KW - near real-time
KW - network intrusion
KW - reservoir computing
UR - http://www.scopus.com/inward/record.url?scp=85179815852&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85179815852&partnerID=8YFLogxK
U2 - 10.1109/TWC.2023.3337058
DO - 10.1109/TWC.2023.3337058
M3 - Article
AN - SCOPUS:85179815852
SN - 1536-1276
VL - 23
SP - 7043
EP - 7059
JO - IEEE Transactions on Wireless Communications
JF - IEEE Transactions on Wireless Communications
IS - 7
ER -