Carbon Explorer evaluates solutions make datacenters operate on renewable energy holistically by including embodied and operational footprints. Solutions Carbon Explorer supports include:

• Capacity sizing with a mix of solar and wind power
• Battery storage
• Carbon aware workload scheduling

Details can be found here: A Holistic Approach for Designing Carbon Aware Datacenters (Acun et al, 2022).


The repository contains two notebooks:

• EIA_Energy_Data_Analysis.ipynb analyses EIA's hourly renewable energy data.
• Carbon_Explorer.ipynb combines EIA's data with DC power simulations, evaluates the solutions listed above and finally produces embodied and operational footprint analysis.
  Tested with Python 3.10 & pandas 2.1.1.
   

Citation

Carbon Explorer is accepted at ASPLOS'23. Please cite as:

@article{acun2022holistic,
  title={Carbon Explorer: A Holistic Approach for Designing Carbon Aware Datacenters},
  author={Acun, Bilge and Lee, Benjamin and Kazhamiaka, Fiodar and Maeng, Kiwan and Chakkaravarthy, Manoj and Gupta, Udit and Brooks, David and Wu, Carole-Jean},
  journal={Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems},
  year={2023}
}

License

Carbon Explorer is CC-BY-NC licensed.