Dataset and Analysis of Inference Workloads with AI Accelerators at the Edge

• The generated data used in the analysis phase can be found in the /data directory
• The Jupyter scripts used in the analysis phase can be found in the /jupyter directory
• The generated models for power consumption and inference time can be found in the /jupyter directory
• The generated plots from the analysis phase can be found in the /output directory

Publications

For more details in this work, you can read the published paper

@article{kasioulisenergy,
  title={Energy modeling of inference workloads with AI accelerators at the Edge: A benchmarking study},
  author={Kasioulis, Michalis and Symeonides, Moysis and Ioannou, Giorgos and Pallis, George and Dikaiakos, Marios D}
}

Acknowledgements

This work is part of GreenAnalyzer that has indirectly received funding from the European Union’s Horizon Europe research and innovation action programme, via the aerOS Open Call issued and executed under the aerOS project(Grant Agreement no. 101069732).