gym-fog

The implemented gym-fog is a custom OpenAi Gym environment for the simulation of a fog-cloud infrastructure.

Installation

cd gym-fog
pip install -e .

How does it work?

The implemented environment is based on a previously presented Mixed-integer linear programming (MILP) model. Please see gym-fog/milp for further details.

The complete RL environment has been designed: actions, observations, reward function.

If you would like to know further details about our gym-fog, please read our papers mentioned below.

Citation

If you use our work, please cite our articles.

• JNCA 2020

@article{santos2020milp,
  title={Towards End-to-End resource provisioning in Fog Computing over Low Power Wide Area Networks},
  author={Santos, Jos{\'e} and Wauters, Tim and Volckaert, Bruno and De Turck, Filip},
  journal={Submitted to Journal of Network and Computer Applications},
  volume={},
  pages={},
  year={2020},
  publisher={Elsevier}
}

• Wiley 2020

@article{santosbookchapter,
  title={Reinforcement Learning for Service Function Chain Allocation in Fog Computing},
  author={Santos, Jos{\'e} and Wauters, Tim and Volckaert, Bruno and De Turck, Filip},
  journal={Book Chapter in revision, Submitted to Communications Network and Service Management In the Era of Artificial Intelligence and Machine Learning, IEEE Press},
  pages={},
  year={2020},
  publisher={Wiley Online Library}
}

Team

• Jose Santos

• Tim Wauters

• Bruno Volckaert

• Filip de Turck

Contact

If you want to contribute, please contact:

Lead developer: Jose Santos

For questions or support, please use GitHub's issue system.

License

Copyright (c) 2020 Ghent University and IMEC vzw.

Address: IDLab, Ghent University, iGent Toren, Technologiepark-Zwijnaarde 126 B-9052 Gent, Belgium

Email: info@imec.be.