New universal sustainability metrics to assess edge intelligence

https://doi.org/10.1016/j.suscom.2021.100580Get rights and content
Under a Creative Commons license
open access

Highlights

  • Sole focus during the last decade on deep learning accuracy (Red AI), ignored economic, or environmental cost.

  • Universal metric that balances accuracy, complexity, and carbon footprint helps to select better models, and frameworks.

  • Recognition and training efficiency RE, TE, compare deep learning models and platforms in a universal fashion.

  • Sustainability is assessed with deep learning lifecycle efficiency and life cycle recognition efficiency DLLCE, RELC.

  • Efficiency comparison among models with 4 – 30 – 1000 classes, on cloud and edge CPU, TPU, GPU, and NCS2.

Abstract

The single recent focus on deep learning accuracy ignores economic, and environmental cost. Progress towards Green AI is hindered by lack of universal metrics that equally reward accuracy and cost and can help to improve all deep learning algorithms and platforms. We define recognition and training efficiency as new universal metrics to assess deep learning sustainability and compare them to similar, less universal metrics. They are based on energy consumption measurements, on deep learning inference, on recognition gradients, and on number of classes and thus universally balance accuracy, complexity and energy consumption. Well-designed edge accelerators improve recognition and training efficiencies compared to cloud CPUs and GPUs due to reduced communication overhead. Cradle to grave sustainability of edge intelligence models and platforms is assessed with novel deep learning lifecycle efficiency and life cycle recognition efficiency metrics that include the number of times models are used. Artificial and natural intelligence efficiencies are compared leading to insights on deep learning scalability.

Keywords

Deep learning
Sustainability
Edge computing
Green AI
Accuracy
Accelerator

Cited by (0)