Distributing deep neural networks for maximising computing capabilities and power efficiency in swarm - Archive ouverte HAL
Conference Papers Year : 2019

Distributing deep neural networks for maximising computing capabilities and power efficiency in swarm

Abstract

Deploying neural networks models over embedded devices have an increased interest and many works is ongoing on that topic. Energy consumption, model sizes and inference time are critical issues as explained in the literature. In the context of IoT and edge computing, tradeoff have been studied in order to get a low cost but rapid answer, robust to connection issue exploiting early exiting or distributing deep neural networks. Those approaches exploits the cloud as an endpoint, balancing the load with respect to different computing capabilities. In this paper, we propose to extend those approaches to networks of embedded devices such as a swarm of drones, where every device has the same computing capabilities (in terms of energy and speed). Computing load may be balanced among the whole swarm in order to maximise either the lifetime of specific devices or lifetime of the whole swarm. We develop criteria to best cut and distribute those networks, validate them through power measurement and express the different tradeoffs we have to address.
Fichier principal
Vignette du fichier
08702672.pdf (370.42 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-02434837 , version 1 (10-01-2020)

Identifiers

Cite

Victor Gacoin, Anthony Kolar, Chengfang Ren, Régis Guinvarc'H. Distributing deep neural networks for maximising computing capabilities and power efficiency in swarm. 2019 IEEE International Symposium on Circuits and Systems (ISCAS), May 2019, Sapporo, Japan. ⟨10.1109/ISCAS.2019.8702672⟩. ⟨hal-02434837⟩
67 View
158 Download

Altmetric

Share

More