Energy-Efficient Model Compression and Splitting for Collaborative Inference Over Time-Varying Channels

06/02/2021
by   Mounssif Krouka, et al.
0

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.

READ FULL TEXT
research
01/18/2022

DEFER: Distributed Edge Inference for Deep Neural Networks

Modern machine learning tools such as deep neural networks (DNNs) are pl...
research
09/14/2020

Leveraging Domain Knowledge using Machine Learning for Image Compression in Internet-of-Things

The emergent ecosystems of intelligent edge devices in diverse Internet ...
research
05/18/2023

Lyapunov-Driven Deep Reinforcement Learning for Edge Inference Empowered by Reconfigurable Intelligent Surfaces

In this paper, we propose a novel algorithm for energy-efficient, low-la...
research
10/31/2022

Variational Inference Aided Estimation of Time Varying Channels

One way to improve the estimation of time varying channels is to incorpo...
research
10/04/2012

A network of spiking neurons for computing sparse representations in an energy efficient way

Computing sparse redundant representations is an important problem both ...
research
12/21/2021

Offloading Algorithms for Maximizing Inference Accuracy on Edge Device Under a Time Constraint

With the emergence of edge computing, the problem of offloading jobs bet...
research
05/24/2021

AirNet: Neural Network Transmission over the Air

State-of-the-art performance for many emerging edge applications is achi...

Please sign up or login with your details

Forgot password? Click here to reset