Packet-Loss-Tolerant Split Inference for Delay-Sensitive Deep Learning in Lossy Wireless Networks

04/28/2021
by   Sohei Itahara, et al.
0

The distributed inference framework is an emerging technology for real-time applications empowered by cutting-edge deep machine learning (ML) on resource-constrained Internet of things (IoT) devices. In distributed inference, computational tasks are offloaded from the IoT device to other devices or the edge server via lossy IoT networks. However, narrow-band and lossy IoT networks cause non-negligible packet losses and retransmissions, resulting in non-negligible communication latency. This study solves the problem of the incremental retransmission latency caused by packet loss in a lossy IoT network. We propose a split inference with no retransmissions (SI-NR) method that achieves high accuracy without any retransmissions, even when packet loss occurs. In SI-NR, the key idea is to train the ML model by emulating the packet loss by a dropout method, which randomly drops the output of hidden units in a DNN layer. This enables the SI-NR system to obtain robustness against packet losses. Our ML experimental evaluation reveals that SI-NR obtains accurate predictions without packet retransmission at a packet loss rate of 60

READ FULL TEXT
research
12/17/2021

Communication-oriented Model Fine-tuning for Packet-loss Resilient Distributed Inference under Highly Lossy IoT Networks

The distributed inference (DI) framework has gained traction as a techni...
research
05/30/2023

Design and implementation of intelligent packet filtering in IoT microcontroller-based devices

Internet of Things (IoT) devices are increasingly pervasive and essentia...
research
05/25/2020

Dynamic Compression Ratio Selection for Edge Inference Systems with Hard Deadlines

Implementing machine learning algorithms on Internet of things (IoT) dev...
research
02/20/2023

Harris Hawks Feature Selection in Distributed Machine Learning for Secure IoT Environments

The development of the Internet of Things (IoT) has dramatically expande...
research
09/12/2023

Random Segmentation: New Traffic Obfuscation against Packet-Size-Based Side-Channel Attacks

Despite encryption, the packet size is still visible, enabling observers...
research
10/28/2019

The Effect of Erasure Coding on the Burstiness of Packet Loss

The perceived quality of real-time media delivered over IP networks depe...
research
06/21/2018

Transparent Recovery of Dynamic States on Constrained Nodes through Deep Packet Inspection

Many IoT applications make extensive use of constrained devices which ar...

Please sign up or login with your details

Forgot password? Click here to reset