DistrEdge: Speeding up Convolutional Neural Network Inference on Distributed Edge Devices

TL;DR

DistrEdge is a deep reinforcement learning-based method that optimizes CNN inference distribution across heterogeneous edge devices, significantly improving speedup and adaptability in practical IoT environments.

Contribution

It introduces a general, adaptive CNN inference distribution strategy for heterogeneous edge devices using deep reinforcement learning.

Findings

Achieves 1.1 to 3x speedup over existing methods.

Effectively adapts to device heterogeneity and network conditions.

Demonstrates practical applicability on embedded AI devices.

Abstract

As the number of edge devices with computing resources (e.g., embedded GPUs, mobile phones, and laptops) increases, recent studies demonstrate that it can be beneficial to collaboratively run convolutional neural network (CNN) inference on more than one edge device. However, these studies make strong assumptions on the devices' conditions, and their application is far from practical. In this work, we propose a general method, called DistrEdge, to provide CNN inference distribution strategies in environments with multiple IoT edge devices. By addressing heterogeneity in devices, network conditions, and nonlinear characters of CNN computation, DistrEdge is adaptive to a wide range of cases (e.g., with different network conditions, various device types) using deep reinforcement learning technology. We utilize the latest embedded AI computing devices (e.g., NVIDIA Jetson products) to construct cases of heterogeneous devices' types in the experiment. Based on our evaluations, DistrEdge can properly adjust the distribution strategy according to the devices' computing characters and the network conditions. It achieves 1.1 to 3x speedup compared to state-of-the-art methods.