典型文献
Multi-Objective Deep Reinforcement Learning Based Time-Frequency Resource Allocation for Multi-Beam Satellite Communications
文献摘要：
Resource allocation is an important prob-lem influencing the service quality of multi-beam satellite communications.In multi-beam satellite communications,the available frequency bandwidth is limited,users requirements vary rapidly,high service quality and joint allocation of multi-dimensional re-sources such as time and frequency are required.It is a difficult problem needs to be researched urgently for multi-beam satellite communications,how to ob-tain a higher comprehensive utilization rate of multi-dimensional resources,maximize the number of users and system throughput,and meet the demand of rapid allocation adapting dynamic changed the number of users under the condition of limited resources,with us-ing an efficient and fast resource allocation algorithm.In order to solve the multi-dimensional resource al-location problem of multi-beam satellite communi-cations,this paper establishes a multi-objective op-timization model based on the maximum the num-ber of users and system throughput joint optimization goal,and proposes a multi-objective deep reinforce-ment learning based time-frequency two-dimensional resource allocation (MODRL-TF) algorithm to adapt dynamic changed the number of users and the time-liness requirements.Simulation results show that the proposed algorithm could provide higher comprehen-sive utilization rate of multi-dimensional resources,and could achieve multi-objective joint optimization,and could obtain better timeliness than traditional heuristic algorithms,such as genetic algorithm (GA)and ant colony optimization algorithm (ACO).
文献关键词：
中图分类号：
作者姓名：
Yuanzhi He;Biao Sheng;Hao Yin;Di Yan;Yingchao Zhang
作者机构：
School of systems science and engineering,Sun Yat-Sen University,Guangzhou 100876,China;Institute of Systems Engineering,AMS,PLA,Beijing 100141,China
文献出处：
引用格式：
[1]Yuanzhi He;Biao Sheng;Hao Yin;Di Yan;Yingchao Zhang-.Multi-Objective Deep Reinforcement Learning Based Time-Frequency Resource Allocation for Multi-Beam Satellite Communications)[J].中国通信（英文版）,2022(01):77-91
A类：
MODRL,liness
B类：
Multi,Objective,Deep,Reinforcement,Learning,Based,Time,Frequency,Resource,Allocation,Beam,Satellite,Communications,allocation,important,influencing,service,quality,multi,beam,satellite,communications,In,available,frequency,bandwidth,limited,users,requirements,vary,rapidly,joint,dimensional,such,are,required,It,difficult,problem,needs,researched,urgently,higher,comprehensive,utilization,rate,resources,maximize,number,system,throughput,meet,demand,adapting,dynamic,changed,under,condition,efficient,fast,order,solve,this,paper,establishes,objective,model,maximum,optimization,goal,proposes,deep,reinforce,learning,two,TF,Simulation,results,show,that,proposed,could,provide,achieve,obtain,better,timeliness,than,traditional,heuristic,algorithms,genetic,GA,colony,ACO
AB值：
0.432087
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。
