典型文献
Demand Prediction Based Slice Reconfiguration Using Dueling Deep Q-Network
文献摘要：
To satisfy diversified service demands of vertical industries,network slicing enables efficient re-source allocation of a common infrastructure by creat-ing isolated logical networks.However,uncertainty and dynamics of service demands will cause perfor-mance degradation.Due to operation costs and re-source constraints,it is challenging to maintain high quality of user experience while obtaining high rev-enue for service providers(SPs).This paper devel-ops an optimal and fast slice reconfiguration(OFSR)framework based on reinforcement learning,where a novel scheme is proposed to offer optimal decisions for reconfiguring diverse slices.A demand prediction model is proposed to capture changes in resource re-quirements,based on which the OFSR scheme is trig-gered to determine whether to perform slice reconfig-uration.Considering the large state and action spaces generated from uncertain service time and resource requirements,deep dueling architecture is adopted to improve the convergence rate.Extensive simulations validate the effectiveness of the proposed framework in achieving higher long-term revenue for SPs.
文献关键词：
中图分类号：
作者姓名：
Wanqing Guan;Haijun Zhang
作者机构：
School of Computer&Communication Engineering,University of Science and Technology Beijing,Beijing 100083,China;Beijing Engineering and Technology Research Center for Convergence Networks and Ubiquitous Services,Institute of Artificial Intelligence,University of Science and Technology Beijing,Beijing 100083,China
文献出处：
引用格式：
[1]Wanqing Guan;Haijun Zhang-.Demand Prediction Based Slice Reconfiguration Using Dueling Deep Q-Network)[J].中国通信（英文版）,2022(05):267-285
A类：
creat,enue,ops,OFSR
B类：
Demand,Prediction,Based,Slice,Reconfiguration,Using,Dueling,Deep,Network,To,satisfy,diversified,service,demands,vertical,industries,slicing,enables,efficient,allocation,common,infrastructure,by,isolated,logical,networks,However,uncertainty,dynamics,will,cause,mance,degradation,operation,costs,constraints,challenging,maintain,quality,user,experience,while,obtaining,providers,SPs,This,paper,devel,optimal,fast,reconfiguration,framework,reinforcement,learning,where,novel,scheme,proposed,offer,decisions,reconfiguring,diverse,slices,prediction,model,capture,changes,resource,which,trig,gered,determine,whether,perform,Considering,large,state,action,spaces,generated,from,requirements,deep,dueling,architecture,adopted,improve,convergence,Extensive,simulations,validate,effectiveness,achieving,higher,long,revenue
AB值：
0.613084
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。
