BARO: Robust Root Cause Analysis for Microservices via Multivariate Bayesian Online Change Point Detection
Project description
BARO: Robust Root Cause Analysis for Microservices via Multivariate Bayesian Online Change Point Detection
BARO is an end-to-end approach to perform anomaly detection and root cause analysis for microservices's failures. This repository contains the artifact for reproducing the main experimental results in our paper accepted to ESEC/FSE 2024, and reusing purposes.
Installation
Install from PyPI
pip install fse-baro
Or, build from source
git clone https://github.com/phamquiluan/baro.git && cd baro
pip install -e .
More details are in INSTALLATION.md.
How-to-use
from baro import BARO
m = BARO()
anomalies = m.detect_anomalies(data)
root_causes = m.rca(data, anomalies=anomalies)
print(root_causes)
Download Paper
TBD
Download Datasets
Our datasets are publicly available in Zenodo repository with the following information:
- Dataset DOI:
- Dataset URL: https://zenodo.org/records/11046533
Reproducibility
Check the Jupyter Notebook at tutorials/reproducibility.ipynb to reproduce the performance of BARO.
Citation
@inproceedings{pham2024baro,
title={BARO: Robust Root Cause Analysis for Microservices via Multivariate Bayesian Online Change Point Detection},
author={Luan Pham, Huong Ha, and Hongyu Zhang},
booktitle={Proceedings of the ACM on Software Engineering, Vol 1},
year={2024},
organization={ACM}
}
Contact
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.