典型文献
Convolutional Neural Network-Based Deep Q-Network(CNN-DQN)Resource Management in Cloud Radio Access Network
文献摘要：
The recent surge of mobile subscribers and user data traffic has accelerated the telecommunica-tion sector towards the adoption of the fifth-generation(5G)mobile networks.Cloud radio access network(CRAN)is a prominent framework in the 5G mobile network to meet the above requirements by deploy-ing low-cost and intelligent multiple distributed an-tennas known as remote radio heads(RRHs).How-ever,achieving the optimal resource allocation(RA)in CRAN using the traditional approach is still chal-lenging due to the complex structure.In this paper,we introduce the convolutional neural network-based deep Q-network(CNN-DQN)to balance the energy consumption and guarantee the user quality of service(QoS)demand in downlink CRAN.We first formulate the Markov decision process(MDP)for energy effi-ciency(EE)and build up a 3-layer CNN to capture the environment feature as an input state space.We then use DQN to turn on/off the RRHs dynamically based on the user QoS demand and energy consumption in the CRAN.Finally,we solve the RA problem based on the user constraint and transmit power to guaran-tee the user QoS demand and maximize the EE with a minimum number of active RRHs.In the end,we con-duct the simulation to compare our proposed scheme with nature DQN and the traditional approach.
文献关键词：
中图分类号：
作者姓名：
Amjad Iqbal;Mau-Luen Tham;Yoong Choon Chang
作者机构：
Department of Electrical and Electronic Engineering,Lee Kong Chian Faculty of Engineering and Science,Universiti Tunku Abdul Rahman(UTAR),Malaysia
文献出处：
引用格式：
[1]Amjad Iqbal;Mau-Luen Tham;Yoong Choon Chang-.Convolutional Neural Network-Based Deep Q-Network(CNN-DQN)Resource Management in Cloud Radio Access Network)[J].中国通信（英文版）,2022(10):129-142
A类：
subscribers,telecommunica,tennas,RRHs
B类：
Convolutional,Neural,Network,Based,Deep,DQN,Resource,Management,Cloud,Radio,Access,recent,surge,mobile,user,data,traffic,has,accelerated,sector,towards,adoption,fifth,generation,networks,radio,access,CRAN,prominent,framework,meet,above,requirements,by,deploy,low,cost,intelligent,multiple,distributed,known,remote,heads,How,ever,achieving,optimal,resource,allocation,using,traditional,approach,still,chal,lenging,due,complex,structure,In,this,paper,introduce,convolutional,neural,deep,balance,energy,consumption,guarantee,quality,service,QoS,demand,downlink,We,first,formulate,Markov,decision,process,MDP,effi,ciency,EE,build,up,layer,capture,environment,feature,input,state,space,then,turn,off,dynamically,Finally,solve,problem,constraint,transmit,power,maximize,minimum,number,active,end,duct,simulation,compare,proposed,scheme,nature
AB值：
0.551164
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。
