摘要：As Artificial Intelligence (AI) becomes increasingly prevalent, Deep Neural Networks (DNNs) have become a crucial tool for developing and advancing AI applications. Considering limited computing and energy resources on mobile devices (MDs), it is a challenge to perform compute-intensive DNN tasks on MDs. To attack this challenge, mobile edge computing (MEC) provides a viable solution through DNN partitioning and task offloading. However, as the communication conditions between different devices change over time, DNN partitioning on different devices must also change synchronously. This is a dynamic process, which aggravates the complexity of DNN partitioning. In this paper, we delve into the issue of jointly optimizing energy and delay for DNN partitioning and task offloading in a dynamic MEC scenario where each MD and the server adopt the pre-trained DNNs for task inference. Taking advantage of the characteristics of DNN, we first propose a strategy for layered partitioning of DNN tasks to divide the task of each MD into subtasks that can be either processed on the MD or offloaded to the server for computation. Then, we formulate the trade-off between energy and delay as a joint optimization problem, which is further represented as a Markov decision process (MDP). To solve this, we design a DNN partitioning and task offloading (DPTO) algorithm utilizing deep reinforcement learning (DRL), which enables MDs to make optimal offloading decisions. Finally, experimental results demonstrate that our algorithm outperforms existing non-DRL and DRL algorithms with respect to processing delay and energy consumption, and can be applied to different DNN types.

关键字：Deep neural networks(DNNs); Mobile edge computing(MEC); DNN partitioning; Task offloading; Deep reinforcement learning (DRL)

ISSN号：2192-113X

卷、期、页：卷: 12期: 1

发表日期：2023-08-03

影响因子：0.000000

期刊分区（SCI为中科院分区）：三区

收录情况：SCI（科学引文索引印刷版）,SCIE（科学引文索引网络版）

发表期刊名称：JOURNAL OF CLOUD COMPUTING-ADVANCES SYSTEMS AND APPLICATIONS

通讯作者：马淑芳,严泽枭

第一作者：张建兵,黄霁崴

论文类型：期刊论文

论文概要：张建兵,马淑芳,严泽枭,黄霁崴，Joint DNN partitioning and task offloading in mobile edge computing via deep reinforcement learning，JOURNAL OF CLOUD COMPUTING-ADVANCES SYSTEMS AND APPLICATIONS，2023，卷: 12期: 1

论文题目：Joint DNN partitioning and task offloading in mobile edge computing via deep reinforcement learning