University of Oulu

M. Krouka, A. Elgabli, C. B. Issaid and M. Bennis, "Energy-Efficient Model Compression and Splitting for Collaborative Inference Over Time-Varying Channels," 2021 IEEE 32nd Annual International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC), 2021, pp. 1173-1178, doi: 10.1109/PIMRC50174.2021.9569707

Energy-efficient model compression and splitting for collaborative inference over time-varying channels

Saved in:
Author: Krouka, Mounssif1; Elgabli, Anis1; Ben Issaid, Chaouki1;
Organizations: 1Centre for Wireless Communications (CWC), University of Oulu, 90014 Oulu, Finland
Format: article
Version: accepted version
Access: open
Online Access: PDF Full Text (PDF, 5.6 MB)
Persistent link:
Language: English
Published: Institute of Electrical and Electronics Engineers, 2021
Publish Date: 2022-01-27


Today’s intelligent applications can achieve high performance accuracy using machine learning (ML) techniques, such as deep neural networks (DNNs). Traditionally, in a remote DNN inference problem, an edge device transmits raw data to a remote node that performs the inference task. However, this may incur high transmission energy costs and puts data privacy at risk. In this paper, we propose a technique to reduce the total energy bill at the edge device by utilizing model compression and time-varying model split between the edge and remote nodes. The time-varying representation accounts for time-varying channels and can significantly reduce the total energy at the edge device while maintaining high accuracy (low loss). We implement our approach in an image classification task using the MNIST dataset, and the system environment is simulated as a trajectory navigation scenario to emulate different channel conditions. Numerical simulations show that our proposed solution results in minimal energy consumption and CO 2 emission compared to the considered baselines while exhibiting robust performance across different channel conditions and bandwidth regime choices.

see all

Series: IEEE International Symposium on Personal, Indoor, and Mobile Radio Communications workshops
ISSN: 2166-9570
ISSN-E: 2166-9589
ISSN-L: 2166-9570
ISBN Print: 978-1-7281-7586-7
Pages: 1173 - 1178
DOI: 10.1109/PIMRC50174.2021.9569707
Host publication: 32nd IEEE Annual International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC 2021
Conference: IEEE Annual International Symposium on Personal, Indoor and Mobile Radio Communications
Type of Publication: A4 Article in conference proceedings
Field of Science: 213 Electronic, automation and communications engineering, electronics
Copyright information: © 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.