Litcius/Paper detail

Machine Learning Applied to Anomaly Detection on 5G O-RAN Architecture

Pedro V. A. Alves, Mateus A.S.S. Goldbarg, Wysterlânya K. P. Barros, Iago Rêgo, Vinicius Filho, Allan Martins, Vicente A. de Sousa Jr., Ramon dos Reis Fontes, Eduardo Aranha, Augusto Neto, Marcelo A. C. Fernandes

2023Procedia Computer Science16 citationsDOIOpen Access PDF

Abstract

This article presents a study with feasibility and performance analysis of machine learning (ML) techniques using supervised techniques for anomaly detection problems in a 5G communication network. The proposed ML models (Multilayer Perceptron, Decision Tree, and Support Vector Machine) were used to classify data into anomaly or non-anomaly based on two 5G Open Radio Access Network (O-RAN) datasets with various key performance indicators (KPIs). Furthermore, we propose a strategy that devotes to labeling anomalous situations, leveraging the t-Distributed Stochastic Neighbor Embedding (tSNE) technique atop datasets enclosing multiple KPIs. The results were significant, with an accuracy above 90% for all use cases considered.

Topics & Concepts

Computer scienceAnomaly detectionDecision treeSupport vector machineKey (lock)Machine learningArtificial intelligenceAnomaly (physics)Performance indicatorData miningPerceptronMultilayer perceptronArtificial neural networkEconomicsComputer securityPhysicsManagementCondensed matter physicsAdvanced MIMO Systems OptimizationNetwork Security and Intrusion DetectionWireless Signal Modulation Classification
Machine Learning Applied to Anomaly Detection on 5G O-RAN Architecture | Litcius