文献类型：期刊文献

英文题名：DRL-based Optimization of Privacy Protection and Computation Performance in MEC Computation Offloading

作者：Gao, Zhengjun[1];Wu, Guowen[1];Shen, Yizhou[2];Zhang, Hong[1];Shen, Shigen[3];Cao, Qiying[1]

机构：[1]Donghua Univ, Sch Comp Sci & Technol, Shanghai, Peoples R China;[2]Cardiff Univ, Sch Comp Sci & Informat, Cardiff, Wales;[3]Shaoxing Univ, Dept Comp Sci & Engn, Shaoxing, Peoples R China

年份：2022

外文期刊名：IEEE INFOCOM 2022 - IEEE CONFERENCE ON COMPUTER COMMUNICATIONS WORKSHOPS (INFOCOM WKSHPS)

收录：CPCI-S(收录号：WOS:000851573100031)、EI(收录号：20222912361207)、Scopus(收录号：2-s2.0-85133918672)、WOS

基金：This work was supported in part by the Zhejiang Provincial Natural Science Foundation of China under Grant LZ22F020002 and National Natural Science Foundation of China under Grant 61772018.

语种：英文

外文关键词：Mobile edge computing; computation offloading; privacy protection; deep reinforcement learning

外文摘要：The emergence of mobile edge computing (MEC) imposes an unprecedented pressure on privacy protection, although it helps the improvement of computation performance including energy consumption and computation delay by computation offloading. To this end, we propose a deep reinforcement learning (DRL)-based computation offloading scheme to optimize jointly privacy protection and computation performance. The privacy exposure risk caused by offloading history is investigated, and an analysis metric is defined to evaluate the privacy level. To find the optimal offloading strategy, an algorithm combining actor-critic, off-policy, and maximum entropy is proposed to accelerate the learning rate. Simulation results show that the proposed scheme has better performance compared with other benchmarks.