GreenAuto: An Automated Platform for Sustainable AI Model Design on Edge Devices
This work addresses the challenge of energy-efficient AI deployment on edge devices, which is incremental as it builds on existing NAS methods with added sustainability focus.
The paper tackled the problem of designing sustainable AI models for edge devices by developing GreenAuto, an automated platform that uses neural architecture search and energy predictors to optimize models, resulting in efficient identification of sustainable solutions without human intervention.
We present GreenAuto, an end-to-end automated platform designed for sustainable AI model exploration, generation, deployment, and evaluation. GreenAuto employs a Pareto front-based search method within an expanded neural architecture search (NAS) space, guided by gradient descent to optimize model exploration. Pre-trained kernel-level energy predictors estimate energy consumption across all models, providing a global view that directs the search toward more sustainable solutions. By automating performance measurements and iteratively refining the search process, GreenAuto demonstrates the efficient identification of sustainable AI models without the need for human intervention.