DistrEdge: Speeding up Convolutional Neural Network Inference on Distributed Edge Devices
Document Type
Conference Proceeding
Publication Date
1-1-2022
Abstract
As the number of edge devices with computing resources (e.g., embedded GPUs, mobile phones, and laptops) in-creases, recent studies demonstrate that it can be beneficial to col-laboratively 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 3 x speedup compared to state-of-the-art methods.
Identifier
85134079638 (Scopus)
ISBN
[9781665481069]
Publication Title
Proceedings 2022 IEEE 36th International Parallel and Distributed Processing Symposium IPDPS 2022
External Full Text Location
https://doi.org/10.1109/IPDPS53621.2022.00110
First Page
1097
Last Page
1107
Grant
2047655
Fund Ref
National Science Foundation
Recommended Citation
Hou, Xueyu; Guan, Yongjie; Han, Tao; and Zhang, Ning, "DistrEdge: Speeding up Convolutional Neural Network Inference on Distributed Edge Devices" (2022). Faculty Publications. 3326.
https://digitalcommons.njit.edu/fac_pubs/3326