Secure and reliable computation offloading in blockchain-assisted cyber-physical IoT systems

作     者：Dan Wang Bin Song Yingjie Liu Mingjun Wang 

作者机构：The State Key Laboratory of Integrated Services NetworksXidian UniversityXi'an710071China 

出 版 物：《Digital Communications and Networks》 (数字通信与网络（英文版）)

年 卷 期：2022年第8卷第5期

页      面：625-635页

核心收录：

学科分类：0810[工学-信息与通信工程] 08[工学] 0804[工学-仪器科学与技术] 080402[工学-测试计量技术及仪器] 

基　　金：This work has been supported by the National Natural Science Foundation of China(Nos.62071354) Open Research Projects of Zhejiang Lab(No.2019KD0AD01/013) the Key Research and Development Program of Shaanxi(ProgramNo.2022ZDLGY05-08) also supported by the ISN State Key Laboratory. 

主　　题：Cyber-physical internet of things system Blockchain Reinforcement learning(RL) Edge-cloud computing 

摘      要：With the development of the Cyber-Physical Internet of Things System(CPIoTS),the number of Cyber-Physical System(CPS)applications accessed in networks has increased dramatically.Latency-sensitive resource orchestration in CPS applications is extraordinarily essential for maintaining the Quality of Experience(QoE)for users.Although edge-cloud computing performs effectively in achieving latency-aware resource allocation in CPIoTS,existing methods fail to jointly consider the security and reliability requirements,thereby increasing the process latency of tasks and degrading the QoE of users.This paper aims to minimize the system latency of edge-cloud computing coupled with CPS while simultaneously considering the security and reliability requirements.We first consider a time-varying channel model as a Finite-State Markov Channel(FSMC)and propose a distributed blockchain-assisted CPIoTS to realize secure consensus and reliable resource orchestration by offloading computation tasks in edge-cloud computing.Moreover,we propose an efficient resource allocation algorithm,PPO-SRRA,that optimizes computing offloading and multi-dimension resource(e.g.,communication,computation,and consensus resource)allocation by using a policy-based Deep Reinforcement Learning(DRL)method.The experimental results show that the proposed resource allocation scheme can reduce the system latency and ensure consensus security.