EcoPull: Sustainable IoT Image Retrieval Empowered by TinyML Models

TL;DR

EcoPull is a sustainable IoT image retrieval framework that uses TinyML models to reduce energy consumption and bandwidth by filtering and compressing images in wireless sensor networks.

Contribution

This paper presents a novel IoT framework integrating TinyML models for image filtering and compression, significantly reducing energy and bandwidth use.

Findings

Energy savings of over 70% compared to baseline

Maintains image quality at the edge server

Effective filtering and compression in resource-constrained IoT devices

Abstract

This paper introduces EcoPull, a sustainable Internet of Things (IoT) framework empowered by tiny machine learning (TinyML) models for fetching images from wireless visual sensor networks. Two types of learnable TinyML models are installed in the IoT devices: i) a behavior model and ii) an image compressor model. The first filters out irrelevant images for the current task, reducing unnecessary transmission and resource competition among the devices. The second allows IoT devices to communicate with the receiver via latent representations of images, reducing communication bandwidth usage. However, integrating learnable modules into IoT devices comes at the cost of increased energy consumption due to inference. The numerical results show that the proposed framework can save > 70% energy compared to the baseline while maintaining the quality of the retrieved images at the ES.