Train-Ticket: Anomaly Detection Data for Microservice Monitoring

Ten datasets contain logs, traces, and KPI data from the Train-Ticket microservice benchmark system. The data was collected by Monika Steidl at Universität Innsbruck and includes explanations of identified anomalies. Each dataset folder is structured by the changed microservice, third-party library, version, and collection date.

Use Cases

• Training anomaly detection models based on structured log files prepared for Loglizer.
• Analyzing system performance anomalies based on Prometheus KPI data.
• Investigating root causes of failures based on Jaeger trace data.
• Benchmarking monitoring tools against a known microservice system with labeled anomalies.

Strengths

• Includes three complementary data types: logs, traces, and KPI metrics.
• Contains short descriptions with explanations for identified anomalies.
• Data is organized by specific configuration changes (microservice, library, version).

Limitations

• Description metadata is limited; actual data quality requires manual inspection after download.
• Row count and file sizes are unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.

Provenance

Source

Universität Innsbruck

Collection Method

Monitoring data collected from the Train-Ticket benchmark microservice system.