DISNET: Distributed Micro-Split Deep Learning in Heterogeneous Dynamic IoT

Samikwa, Eric; Di Maio, Antonio; Braun, Torsten (2023). DISNET: Distributed Micro-Split Deep Learning in Heterogeneous Dynamic IoT. IEEE internet of things journal, 11(1), p. 1. IEEE 10.1109/JIOT.2023.3313514

	Text DiSNet__Distributed_Micro_Split_Deep_Learning.pdf - Submitted Version Restricted to registered users only Available under License Publisher holds Copyright. Download (663kB) | Request a copy
	Text FINAL_VERSION.pdf - Published Version Restricted to registered users only Available under License Publisher holds Copyright. Download (3MB) | Request a copy

The key impediments to deploying deep neural networks (DNN) in IoT edge environments lie in the gap between the expensive DNN computation and the limited computing capability of IoT devices. Current state-of-the-art machine learning models have significant demands on memory, computation, and energy and raise challenges for integrating them with the decentralized operation of heterogeneous and resource-constrained IoT devices. Recent studies have proposed the cooperative execution of DNN models in IoT devices to enhance the reliability, privacy, and efficiency of intelligent IoT systems but disregarded flexible finegrained model partitioning schemes for optimal distribution of DNN execution tasks in dynamic IoT networks. In this paper, we propose DISNET, a distributed micro-split deep learning scheme for heterogeneous dynamic IoT. DISNET accelerates inference time and minimizes energy consumption by combining vertical (layer-based) and horizontal DNN partitioning to enable flexible, distributed, and parallel execution of neural network models on heterogeneous IoT devices. DISNET considers the IoT devices’ computing and communication resources and the network conditions for resource-aware cooperative DNN Inference. Experimental evaluation in dynamic IoT networks shows that DISNET reduces the DNN inference latency and energy consumption by up to 5.2× and 6×, respectively, compared to two state-of-the-art schemes without loss of accuracy.

Interest & Impact

Downloads

24 since deposited on 11 May 2023
24 in the past 12 months

Citations

5 Citations in Web of Science ®
6 Citations in Scopus

Search

in Google Scholar™

Services

Actions (login required)

Edit item

Actions (login required)

Edit item