典型文献
Collaborative Clustering Parallel Reinforcement Learning for Edge-Cloud Digital Twins Manufacturing System
文献摘要：
To realize high-accuracy physical-cyber digital twin(DT)mapping in a manufacturing system,a huge amount of data need to be collected and an-alyzed in real-time.Traditional DTs systems are de-ployed in cloud or edge servers independently,whilst it is hard to apply in real production systems due to the high interaction or execution delay.This results in a low consistency in the temporal dimension of the physical-cyber model.In this work,we propose a novel efficient edge-cloud DT manufacturing system,which is inspired by resource scheduling technology.Specifically,an edge-cloud collaborative DTs system deployment architecture is first constructed.Then,deterministic and uncertainty optimization adaptive strategies are presented to choose a more powerful server for running DT-based applications.We model the adaptive optimization problems as dynamic pro-gramming problems and propose a novel collabora-tive clustering parallel Q-learning(CCPQL)algorithm and prediction-based CCPQL to solve the problems.The proposed approach reduces the total delay with a higher convergence rate.Numerical simulation results are provided to validate the approach,which would have great potential in dynamic and complex indus-trial internet environments.
文献关键词：
中图分类号：
作者姓名：
Fan Yang;Tao Feng;Fangmin Xu;Huiwen Jiang;Chenglin Zhao
作者机构：
School of Information and Communication Engineering,Beijing University of Posts and Telecommunications,Beijing 100876,China;China Tendering Center for Mechanical and Electrical Equipment,Ministry of Industry and Information Technology,Beijing 100142,China
文献出处：
引用格式：
[1]Fan Yang;Tao Feng;Fangmin Xu;Huiwen Jiang;Chenglin Zhao-.Collaborative Clustering Parallel Reinforcement Learning for Edge-Cloud Digital Twins Manufacturing System)[J].中国通信（英文版）,2022(08):138-148
A类：
CCPQL
B类：
Collaborative,Clustering,Parallel,Reinforcement,Learning,Edge,Cloud,Digital,Twins,Manufacturing,System,To,realize,accuracy,physical,cyber,digital,twin,mapping,manufacturing,huge,amount,data,need,collected,alyzed,Traditional,DTs,systems,are,ployed,cloud,edge,servers,independently,whilst,hard,apply,production,due,interaction,execution,delay,This,results,low,consistency,temporal,dimension,model,In,this,work,novel,efficient,which,inspired,by,resource,scheduling,technology,Specifically,collaborative,deployment,architecture,first,constructed,Then,deterministic,uncertainty,optimization,adaptive,strategies,presented,choose,more,powerful,running,applications,We,problems,dynamic,gramming,clustering,parallel,learning,algorithm,prediction,solve,proposed,approach,reduces,total,higher,convergence,Numerical,simulation,provided,validate,would,have,great,potential,complex,indus,trial,internet,environments
AB值：
0.626656
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
