Leveraging Time Series Foundation Models to Detect Performance Anomalies in Software Systems

Requirements

The experiment has been conducted using Python 3.12. The required Python packages are listed in requirements.txt file.

---

Experimental Setup

• Install the recommended version of Python 3.
• Clone the repository
• Navigate the repository root: cd fm-tsad-software
• Create a virtual environment and activate it: python3 -m venv .venv, source .venv/bin/activate
• Install the required dependencies: pip install -r requirements.txt

---

Usage

Experiment pipeline

The complete_exp.py script contains the entire experiment conducted in this paper, including both foundation models and baselines. The eval.py script uses the saved results to compute the evaluation metrics employed in the study. Notebooks for generating the results are included within the notebooks/results folder.

---

License

This project is licensed under the MIT License - see the LICENSE file for details.