The Industrial Internet is a promising technology combining industrial systems with Internet connectivity to significantly improve the product efficiency and reduce production cost by cooperating with intelligent devi...The Industrial Internet is a promising technology combining industrial systems with Internet connectivity to significantly improve the product efficiency and reduce production cost by cooperating with intelligent devices,in which the advanced computing,big data analysis and intelligent perception techniques have been involved.This paper comprehensively surveys the recent advances of the Industrial Internet,including reference architectures,key technologies,relative applications and future challenges.Reference architectures which have been proposed for different application scenarios and their corresponding characteristics are summarized.Key technologies,such as cloud computing,mobile edge computing,fog computing,which are classified according to different layers in the architecture,are presented to support a variety of applications in the Industrial Internet.Meanwhile,future challenges and research trends are discussed as well to promote further research of the Industrial Internet.展开更多
The rapid development of emerging technologies,such as edge intelligence and digital twins,have added momentum towards the development of the Industrial Internet of Things(IIo T).However,the massive amount of data gen...The rapid development of emerging technologies,such as edge intelligence and digital twins,have added momentum towards the development of the Industrial Internet of Things(IIo T).However,the massive amount of data generated by the IIo T,coupled with heterogeneous computation capacity across IIo T devices,and users’data privacy concerns,have posed challenges towards achieving industrial edge intelligence(IEI).To achieve IEI,in this paper,we propose a semi-federated learning framework where a portion of the data with higher privacy is kept locally and a portion of the less private data can be potentially uploaded to the edge server.In addition,we leverage digital twins to overcome the problem of computation capacity heterogeneity of IIo T devices through the mapping of physical entities.We formulate a synchronization latency minimization problem which jointly optimizes edge association and the proportion of uploaded nonprivate data.As the joint problem is NP-hard and combinatorial and taking into account the reality of largescale device training,we develop a multi-agent hybrid action deep reinforcement learning(DRL)algorithm to find the optimal solution.Simulation results show that our proposed DRL algorithm can reduce latency and have a better convergence performance for semi-federated learning compared to benchmark algorithms.展开更多
基金the State Major Science and Technology Special Projects(Grant 2018ZX03001023-005)the National Natural Science Foundation of China under Grant No.61831002,61728101,and 61671074the Beijing Natural Science Foundation under Grant No.JQ18016.
文摘The Industrial Internet is a promising technology combining industrial systems with Internet connectivity to significantly improve the product efficiency and reduce production cost by cooperating with intelligent devices,in which the advanced computing,big data analysis and intelligent perception techniques have been involved.This paper comprehensively surveys the recent advances of the Industrial Internet,including reference architectures,key technologies,relative applications and future challenges.Reference architectures which have been proposed for different application scenarios and their corresponding characteristics are summarized.Key technologies,such as cloud computing,mobile edge computing,fog computing,which are classified according to different layers in the architecture,are presented to support a variety of applications in the Industrial Internet.Meanwhile,future challenges and research trends are discussed as well to promote further research of the Industrial Internet.
基金supported in part by the National Nature Science Foundation of China under Grant 62001168in part by the Foundation and Application Research Grant of Guangzhou under Grant 202102020515。
文摘The rapid development of emerging technologies,such as edge intelligence and digital twins,have added momentum towards the development of the Industrial Internet of Things(IIo T).However,the massive amount of data generated by the IIo T,coupled with heterogeneous computation capacity across IIo T devices,and users’data privacy concerns,have posed challenges towards achieving industrial edge intelligence(IEI).To achieve IEI,in this paper,we propose a semi-federated learning framework where a portion of the data with higher privacy is kept locally and a portion of the less private data can be potentially uploaded to the edge server.In addition,we leverage digital twins to overcome the problem of computation capacity heterogeneity of IIo T devices through the mapping of physical entities.We formulate a synchronization latency minimization problem which jointly optimizes edge association and the proportion of uploaded nonprivate data.As the joint problem is NP-hard and combinatorial and taking into account the reality of largescale device training,we develop a multi-agent hybrid action deep reinforcement learning(DRL)algorithm to find the optimal solution.Simulation results show that our proposed DRL algorithm can reduce latency and have a better convergence performance for semi-federated learning compared to benchmark algorithms.
