Energy-aware AI-driven Framework for Edge Computing-based IoT Applications

Zawish, Muhammad, Ashraf, Nouman, Ansari, Rafay and Davy, Steven (2022) Energy-aware AI-driven Framework for Edge Computing-based IoT Applications. IEEE Internet of Things Journal. ISSN 2327-4662 (In Press)

[img]
Preview
Text
Energy_aware_AI_driven_Framework (1).pdf - Accepted Version

Download (1MB) | Preview
Official URL: https://doi.org/10.1109/JIOT.2022.3219202

Abstract

The significant growth in the number of Internetof- things (IoT) devices has given impetus to the idea of edge computing for several applications. In addition, energy harvestable or wireless-powered wearable devices are envisioned to empower the edge intelligence in IoT applications. However, the intermittent energy supply and network connectivity of such devices in scenarios including remote areas and hard-to-reach regions such as in-body applications can limit the performance of edge computing-based IoT applications. Hence, deploying stateof-the-art convolutional neural networks (CNNs) on such energy constrained devices is not feasible due to their computational cost. Existing model compression methods such as network pruning and quantization can reduce complexity, but these methods only work for fixed computational or energy requirements, which is not the case for edge devices with an intermittent energy source. In this work, we propose a pruning scheme based on deep reinforcement learning (DRL), which can compress the CNN model adaptively according to the energy dictated by the energy management policy and accuracy requirements for IoT applications. The proposed energy policy uses predictions of energy to be harvested and dictates the amount of energy that can be used by the edge device for deep learning inference. We compare the performance of our proposed approach with existing state-of-the-art CNNs and datasets using different filter-ranking criteria and pruning ratios.We observe that by using DRL driven pruning, the convolutional layers that consume relatively higher energy are pruned more as compared to their counterparts. Thereby, our approach outperforms existing approaches by reducing energy consumption and maintaining accuracy.

Item Type: Article
Additional Information: Funding information: This research was supported by Science Foundation Ireland and the Department of Agriculture, Food and Marine on behalf of the Government of Ireland VistaMilk research centre under the grant 16/RC/3835.
Uncontrolled Keywords: Artificial Intelligence, edge computing, energy efficiency, Internet of Things
Subjects: G400 Computer Science
G700 Artificial Intelligence
Department: Faculties > Engineering and Environment > Computer and Information Sciences
Depositing User: John Coen
Date Deposited: 02 Nov 2022 11:24
Last Modified: 02 Dec 2022 15:15
URI: https://nrl.northumbria.ac.uk/id/eprint/50505

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics