Intelligent resource allocation in mobile blockchain for privacy and security transactions: a deep reinforcement learning based approach

作     者：Zhaolong NING Shouming SUN Xiaojie WANG Lei GUO Guoyin WANG Xinbo GAO Ricky Y.K.KWOK Zhaolong NING;Shouming SUN;Xiaojie WANG;Lei GUO;Guoyin WANG;Xinbo GAO;Ricky Y.K.KWOK

作者机构：School of Communication and Information EngineeringChongqing University of Posts and Telecommunications School of SoftwareDalian University of Technology State Key Laboratory of Industrial Control TechnologyZhejiang University Chongqing Key Laboratory of Computational IntelligenceChongqing University of Posts and Telecommunications Chongqing Key Laboratory of Image CognitionChongqing University of Posts and Telecommunications Department of Electrical and Electronic EngineeringUniversity of Hong Kong 

出 版 物：《Science China(Information Sciences)》 (中国科学:信息科学(英文版))

年 卷 期：2021年第64卷第6期

页      面：172-187页

核心收录：

学科分类：0810[工学-信息与通信工程] 12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 0808[工学-电气工程] 08[工学] 0839[工学-网络空间安全] 081201[工学-计算机系统结构] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported in part by National Key R&D Program of China (Grant No. 2018YFE0206800) National Natural Science Foundation of China (Grant Nos. 61701406, 61971084, 62001073) National Natural Science Foundation of Chongqing (Grant Nos. cstc2019jcyjcxttX0002, cstc2019jcyj-msxmX0208) Chongqing Talent Program (Grant No.CQYC2020058659) 

主　　题：mobile blockchain deep reinforcement learning mobile edge computing power allocation bandwidth allocation 

摘      要：In order to protect the privacy and data security of mobile devices during the transactions in the industrial Internet of Things(IIoT), we propose a mobile edge computing(MEC)-based mobile blockchain framework by considering the limited bandwidth and computing power of small base stations(SBSs). First,we formulate a joint bandwidth and computing resource allocation problem to maximize the long-term utility of all mobile devices, and take into account the mobility of devices as well as the blockchain throughput. We decompose the formulated problem into two subproblems to decrease the dimension of action space. Then,we propose a deep reinforcement learning additional particle swarm optimization(DRPO) algorithm to solve the two subproblems, in which a particle swarm optimization algorithm is leveraged to avoid the unnecessary search of a deep deterministic policy gradient approach. Simulation results demonstrate the effectiveness of our method from various aspects.