Energy-Efficient AI on the Edge

Witt N, Deutel M, Sobel C, Schubert J, Woller P (2024)


Publication Language: English

Publication Type: Book chapter / Article in edited volumes

Publication year: 2024

Publisher: Springer Link

Edited Volumes: Unlocking Artificial Intelligence: From Theory to Applications

Pages Range: 359 - 380

DOI: 10.1007/978-3-031-64832-8_19

Open Access Link: https://link.springer.com/chapter/10.1007/978-3-031-64832-8_19

Abstract

This chapter shows methods for the resource-optimized design of AI
functionality for edge devices powered by microprocessors or microcontrollers. The
goal is to identify Pareto-optimal solutions that satisfy both resource restrictions
(energy and memory) and AI performance. To accelerate the design of energy-
efficient classical machine learning pipelines, an AutoML tool based on evolutionary
algorithms is presented, which uses an energy prediction model from assembly
instructions (prediction accuracy 3.1%) to integrate the energy demand into a multi-
objective optimization approach. For the deployment of deep neural network-based
AI models, deep compression methods are exploited in an efficient design space
exploration technique based on reinforcement learning. The resulting DNNs can be
executed with a self-developed runtime for embedded devices (dnnruntime), which
is benchmarked using the MLPerf Tiny benchmark. The developed methods shall
enable the fast development of AI functions for the edge by providing AutoML-like
solutions for classical as well as for deep learning. The developed workflows shall
narrow the gap between data scientist and hardware engineers to realize working
applications. By iteratively applying the presented methods during the development
process, edge AI systems could be realized with minimized project risks.

Authors with CRIS profile

Involved external institutions

How to cite

APA:

Witt, N., Deutel, M., Sobel, C., Schubert, J., & Woller, P. (2024). Energy-Efficient AI on the Edge. In Christopher Mutschler, Christian Münzenmayer, Norman Uhlmann, Alexander Martin (Eds.), Unlocking Artificial Intelligence: From Theory to Applications. (pp. 359 - 380). Springer Link.

MLA:

Witt, Nicolas, et al. "Energy-Efficient AI on the Edge." Unlocking Artificial Intelligence: From Theory to Applications. Ed. Christopher Mutschler, Christian Münzenmayer, Norman Uhlmann, Alexander Martin, Springer Link, 2024. 359 - 380.

BibTeX: Download