Performance Anomaly Detection In Microservice Architectures Under Continuous Change

Supplementary material for a master's thesis from the University of Stuttgart. The data likely contains monitoring logs and event logs from a microservices experiment setup, including injected anomalies. The dataset includes raw monitoring data, anomaly logs, and results from different detection thresholds.

Use Cases

• Evaluating anomaly detection algorithms based on Kieker monitoring data.
• Benchmarking performance monitoring approaches using injected real and change anomalies.
• Training models to detect performance anomalies in microservice architectures under load.
• Analyzing the correlation between system events and performance metrics.

Strengths

• Includes raw monitoring data from a controlled experiment environment.
• Contains logs of injected real anomalies and change events for ground truth.
• Provides results from evaluations with different detection thresholds.

Limitations

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

Provenance

Source

University of Stuttgart

Collection Method

Data collected from a controlled experiment setup using microservices and monitoring tools like Kieker.