A Discrete-event-based Simulator for Deep Learning at Edge

12/02/2021

∙

by   Xiaoyan Liu, et al.

∙

New Jersey Institute of Technology

∙

Institute of Computing Technology, Chinese Academy of Sciences

∙

0

∙

share

Novel smart environments, such as smart home, smart city, and intelligent transportation, are driving increasing interest in deploying deep neural networks (DNN) at edge devices. Unfortunately, deploying DNN on resource-constrained edge devices poses a huge challenge. If a simulator can interact with deep learning frameworks, it can facilitate researches on deep learning at edge. The existing simulation frameworks, such as Matlab, NS-3, etc., haven't been extended to support simulations of edge learning. To support large-scale training simulations on edge nodes, we propose a discrete-event-based edge learning simulator. It includes a deep learning module and a network simulation module. Specifically, it enable simulations as an environment for deep learning. Our framework is generic and can be used in various deep learning problems before the deep learning model is deployed. In this paper, we give the design and implementation details of the discrete-event-based learning simulator and present an illustrative use case of the proposed simulator.