Dataset for Federated Learning for Anomaly Detection in Open RAN: Security Architecture Wi

Key Performance Indicators (KPIs) recorded from gNBs in a simulated Open Radio Access Network (RAN) architecture. The dataset was generated for a digital twin experiment featuring three 5G traffic slices (eMBB, mMTC, URLLC) with both normal and anomalous attack traffic. It was created by Joshua Groen et al. and used for a paper presented at the EuCNC & 6G Summit in March 2024.

Use Cases

• Training federated learning models for network security based on distributed KPI data from multiple gNBs.
• Developing anomaly detection algorithms based on KPI patterns from normal and attack traffic slices.
• Benchmarking machine learning models for 5G slice management (eMBB, mMTC, URLLC) using simulated digital twin data.
• Studying the security architecture of Open RAN systems within a controlled experimental environment.

Strengths

• Data is explicitly generated for a peer-reviewed conference paper (EuCNC & 6G Summit 2024).
• Description specifies a controlled experimental architecture with three distinct 5G traffic slices.
• Includes both normal and anomalous attack traffic, which is necessary for supervised anomaly detection tasks.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count, file formats, and data size are unknown, which may limit suitability assessment.
• Data may reflect the specific biases of the experimental digital twin simulation.

Provenance

Source

Texas Data Repository Harvested Dataverse, author Joshua Groen.

Collection Method

Generated from a digital twin experiment simulating an Open RAN architecture with gNBs reporting KPIs to a near-RT RIC.

Time Range

Likely corresponds to the experimental period for the 2024 conference paper.

Freshness

Last updated 2025-10 15 06:30:22; freshness should be verified.

Geography

null