Prune2Edge: A Multi-Phase Pruning Pipelines to Deep Ensemble Learning in IIoT

TL;DR

This paper introduces a multi-phase pruning pipeline for ensemble learning on IIoT edge devices, significantly reducing model size and computational requirements while improving prediction accuracy.

Contribution

It proposes a novel multi-phase pruning and ensemble method tailored for resource-constrained IIoT devices, enhancing efficiency and accuracy.

Findings

Up to 7% accuracy improvement over baseline models

Models reduced in size by up to 90%

Effective ensemble generation on CIFAR datasets

Abstract

Most recently, with the proliferation of IoT devices, computational nodes in manufacturing systems IIoT(Industrial-Internet-of-things) and the lunch of 5G networks, there will be millions of connected devices generating a massive amount of data. In such an environment, the controlling systems need to be intelligent enough to deal with a vast amount of data to detect defects in a real-time process. Driven by such a need, artificial intelligence models such as deep learning have to be deployed into IIoT systems. However, learning and using deep learning models are computationally expensive, so an IoT device with limited computational power could not run such models. To tackle this issue, edge intelligence had emerged as a new paradigm towards running Artificial Intelligence models on edge devices. Although a considerable amount of studies have been proposed in this area, the research is still in the early stages. In this paper, we propose a novel edge-based multi-phase pruning pipelines to ensemble learning on IIoT devices. In the first phase, we generate a diverse ensemble of pruned models, then we apply integer quantisation, next we prune the generated ensemble using a clustering-based technique. Finally, we choose the best representative from each generated cluster to be deployed to a distributed IoT environment. On CIFAR-100 and CIFAR-10, our proposed approach was able to outperform the predictability levels of a baseline model (up to 7%), more importantly, the generated learners have small sizes (up to 90% reduction in the model size) that minimise the required computational capabilities to make an inference on the resource-constraint devices.