Send Less, Save More: Energy-Efficiency Benchmark of Embedded CNN Inference vs. Data Transmission in IoT

TL;DR

This paper evaluates energy-efficient IoT solutions for environmental monitoring, showing that on-device CNN inference significantly reduces data transmission energy costs, enabling longer operation in remote areas.

Contribution

It provides an empirical benchmark comparing embedded CNN inference with raw data transmission on IoT devices, demonstrating substantial energy savings.

Findings

On-device CNN inference reduces energy consumption by up to five times.

Transmitting only inference results extends IoT device operational lifespan.

EmbeddedML enables sustainable, autonomous environmental monitoring in remote areas.

Abstract

The integration of the Internet of Things (IoT) and Artificial Intelligence offers significant opportunities to enhance our ability to monitor and address ecological changes. As environmental challenges become increasingly pressing, the need for effective remote monitoring solutions is more critical than ever. A major challenge in designing IoT applications for environmental monitoring - particularly those involving image data - is to create energy-efficient IoT devices capable of long-term operation in remote areas with limited power availability. Advancements in the field of Tiny Machine Learning allow the use of Convolutional Neural Networks (CNNs) on resource-constrained, battery-operated microcontrollers. Since data transfer is energy-intensive, performing inference directly on microcontrollers to reduce the message size can extend the operational lifespan of IoT nodes. This work evaluates the use of common Low Power Wide Area Networks and compressed CNNs trained on domain specific datasets on an ESP32-S3. Our experiments demonstrate, among other things, that executing CNN inference on-device and transmitting only the results reduces the overall energy consumption by a factor of up to five compared to sending raw image data. These findings advocate the development of IoT applications with reduced carbon footprint and capable of operating autonomously in environmental monitoring scenarios by incorporating EmbeddedML.