Adaptive Multi-objective Reinforcement Learning for Pareto Frontier Approximation: A Case Study of Resource Allocation Network in Massive MIMO
2021
会议录名称29TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO 2021)
ISSN2076-1465
卷号2021-August
页码1631-1635
发表状态已发表
DOI10.23919/EUSIPCO54536.2021.9615934
摘要

Multi-Objective Optimization (MOO) has always been an important issue in the field of wireless communications. With the development of 5G networks, more objectives have been concerned to improve the user experience. The relationship between these multiple objectives is complex or even conflicting, which increases the difficulty of solving the MOO problems. Traditional multi-objective optimization algorithms (e.g., genetic algorithm) have higher computation complexity and require to store multiple models for the preference of different objectives. Therefore, in this paper, a multi-objective scheduling model based on the Actor-Critic framework is proposed, which can effectively solve the multi-user scheduling problem under Massive Multiple-Input Multiple-Output (MIMO), and utilize a single model to approximate the Pareto frontier. In the single-cell downlink scheduling scenario, the proposed model is applied to the two objective optimization, i.e., channel capacity and fairness. The simulation results show that the performance of our model is close to the theoretical optimal value in the single-objective case. The Pareto frontier can be uniformly approximated in the multi-objective case, and it has strong robustness to never-seen preference combinations.

关键词Massive MIMO multi-objective reinforcement learning (MORL) Pareto frontier single cell Multi-User (MU)-MIMO scheduling
会议名称29th European Signal Processing Conference (EUSIPCO)
出版地PO BOX 74251, KESSARIANI, 151 10, GREECE
会议地点ELECTR NETWORK
会议日期AUG 23-27, 2021
URL查看原文
收录类别EI ; CPCI ; CPCI-S
语种英语
WOS研究方向Acoustics ; Computer Science ; Engineering ; Imaging Science & Photographic Technology ; Telecommunications
WOS类目Acoustics ; Computer Science, Software Engineering ; Engineering, Electrical & Electronic ; Imaging Science & Photographic Technology ; Telecommunications
WOS记录号WOS:000764066600325
出版者EUROPEAN ASSOC SIGNAL SPEECH & IMAGE PROCESSING-EURASIP
EI入藏号20220411505662
引用统计
正在获取...
文献类型会议论文
条目标识符https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/176075
专题信息科学与技术学院_博士生
信息科学与技术学院_PI研究组_杨旸组
信息科学与技术学院_PI研究组_周勇组
信息科学与技术学院_硕士生
创意与艺术学院_特聘教授组_汪军组
通讯作者Chen, Ruiqing
作者单位
1.ShanghaiTech Univ, Shanghai, Peoples R China
2.UCL, London, England
3.Shanghai Inst Microsyst & Informat Technol, Shanghai, Peoples R China
4.Univ Chinese Acad Sci, Beijing, Peoples R China
第一作者单位上海科技大学
通讯作者单位上海科技大学
第一作者的第一单位上海科技大学
推荐引用方式
GB/T 7714
Chen, Ruiqing,Sun, Fanglei,Chen, Liang,et al. Adaptive Multi-objective Reinforcement Learning for Pareto Frontier Approximation: A Case Study of Resource Allocation Network in Massive MIMO[C]. PO BOX 74251, KESSARIANI, 151 10, GREECE:EUROPEAN ASSOC SIGNAL SPEECH & IMAGE PROCESSING-EURASIP,2021:1631-1635.
条目包含的文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
个性服务
查看访问统计
谷歌学术
谷歌学术中相似的文章
[Chen, Ruiqing]的文章
[Sun, Fanglei]的文章
[Chen, Liang]的文章
百度学术
百度学术中相似的文章
[Chen, Ruiqing]的文章
[Sun, Fanglei]的文章
[Chen, Liang]的文章
必应学术
必应学术中相似的文章
[Chen, Ruiqing]的文章
[Sun, Fanglei]的文章
[Chen, Liang]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。