Dynamic Distribution of Edge Intelligence at the Node Level for Internet of Things

TL;DR

This paper proposes a dynamic CNN deployment method for IoT devices that distributes computation horizontally, improving throughput, reducing energy use, and enhancing data privacy at the node level.

Contribution

It introduces a novel horizontal collaboration approach for CNN partitioning and pipelining among IoT devices, optimizing performance and privacy.

Findings

Throughput increased by 1.55x to 1.75x with CNN partitioning

Reduces computation and energy consumption on IoT devices

Enhances data privacy by processing data at the source

Abstract

In this paper, dynamic deployment of Convolutional Neural Network (CNN) architecture is proposed utilizing only IoT-level devices. By partitioning and pipelining the CNN, it horizontally distributes the computation load among resource-constrained devices (called horizontal collaboration), which in turn increases the throughput. Through partitioning, we can decrease the computation and energy consumption on individual IoT devices and increase the throughput without sacrificing accuracy. Also, by processing the data at the generation point, data privacy can be achieved. The results show that throughput can be increased by 1.55x to 1.75x for sharing the CNN into two and three resource-constrained devices, respectively.