Can I read EdgeWise: Energy-efficient CNN Computation on Edge Devices under Stochastic Communication Delays on EtoBox?

EdgeWise: Energy-efficient CNN Computation on Edge Devices under Stochastic Communication Delays by Mehdi Ghasemi; Daler Rakhmatov; Carole-Jean Wu; Sarma Vrudhula is a Computer Science article available to read on EtoBox.

What is EdgeWise: Energy-efficient CNN Computation on Edge Devices under Stochastic Communication Delays about?

This article presents a framework to enable the energy-efficient execution of convolutional neural networks (CNNs) on edge devices. The framework consists of a pair of edge devices connected via a wireless network: a performance and energy-constrained device D as the first recipient of data and an energy-unconstrained device N as an accelerator for D . Device D decides on-the-fly how to distribute the workload with the objective of minimizing its energy consumption while accounting for the inherent uncertainty in network delay and the overheads involved in data transfer. These challenges are tackled by adopting the data-driven modeling framework of Markov Decision Processes, whereby an optimal policy is consulted by D in O (1) time to make layer-by-layer assignment decisions. As a special case, a linear-time dynamic programming algorithm is also presented for finding optimal layer assignment at once, under the assumption that the network delay is constant throughout the execution of the application. The proposed framework is demonstrated on a platform comprised of a Raspberry PI 3 as D and an NVIDIA Jetson TX2 as N . An average improvement of 31% and 23% in energy consumption is ac

Who reads EdgeWise: Energy-efficient CNN Computation on Edge Devices under Stochastic Communication Delays?

Author

Mehdi Ghasemi; Daler Rakhmatov; Carole-Jean Wu; Sarma Vrudhula

Publisher

Association for Computing Machinery (ACM)

Published

2022

Language

EN

Field

Computer Science (Physical Sciences)