基于禁忌搜索和Q-learning的CR-NOMA系统的功率分配算法

doi:10.11772/j.issn.1001-9081.2020081249

计算机应用 ›› 2021, Vol. 41 ›› Issue (7): 2026-2032.DOI: 10.11772/j.issn.1001-9081.2020081249

所属专题：网络与通信

基于禁忌搜索和Q-learning的CR-NOMA系统的功率分配算法

周烁^1,2, 仇润鹤^1,2, 唐旻俊^1,2

1. 东华大学信息科学与技术学院, 上海 201620;
2. 数字化纺织服装技术教育部工程研究中心(东华大学), 上海 201620

收稿日期:2020-08-18 修回日期:2020-12-23 发布日期:2021-01-22 出版日期:2021-07-10
通讯作者: 周烁
作者简介:周烁(1996-),男,江西上饶人,硕士研究生,主要研究方向:认知无线电、非正交多址接入;仇润鹤(1961-),男,上海人,教授,博士,主要研究方向:无线通信系统、协作中继网络、认知无线电网络;唐旻俊(1994-),男,上海人,硕士研究生,主要研究方向:认知无线通信系统。
基金资助:
国家自然科学基金面上项目（61671143）。

Power allocation algorithm for CR-NOMA system based on tabu search and Q-learning

ZHOU Shuo^1,2, QIU Runhe^1,2, TANG Minjun^1,2

1. College of Information Sciences and Technology, Donghua University, Shanghai 201620, China;
2. Engineering Research Center of Digitized Textile and Fashion Technology, Ministry of Education(Donghua University), Shanghai 201620, China

Received:2020-08-18 Revised:2020-12-23 Online:2021-01-22 Published:2021-07-10
Supported by:
This work is partially supported by Surface Program of the National Natural Science Foundation of China (61671143).

摘要/Abstract

摘要： 针对下一代移动通信对于高速率和大规模连接的需求，对认知无线电（CR）-非正交多址接入（NOMA）混合系统中通过优化功率分配来提升次用户总传输速率进行研究，提出一种基于禁忌搜索和Q-learning的功率分配（PATSQ）算法。首先，认知基站在系统环境中观测并学习用户的功率分配，次用户采用NOMA方式接入授权信道。其次，将功率优化分配问题中的功率分配、信道状态和总传输速率分别表述为马尔可夫决策过程中的动作、状态和奖励，通过结合禁忌搜索和Q-learning的方法来解决该马尔可夫决策过程问题并得到一个最优的禁忌Q表。最后，在主次用户服务质量（QoS）和最大发射功率的约束下，认知基站通过查找禁忌Q表得到最优的功率分配因子，实现系统中次用户总传输速率的最大化。仿真结果表明，在总功率相同条件下，所提算法在次用户总传输速率和系统容纳用户数量上要优于认知移动无线网络（CMRN）算法、次用户预解码（SFDM）算法以及传统等功率分配算法。

关键词: 非正交多址接入, 认知无线电, 功率分配, 禁忌搜索, Q-learning, 服务质量, 马尔可夫决策过程

Abstract: For the demand of high speed and massive connections of next-generation mobile communication, improving the total secondary users' transmission rate by the optimization of power allocation in Cognitive Radio-Non-Orthogonal Multi-Access (CR-NOMA) hybrid system was studied, and an algorithm of Power Allocation based on Tabu Search and Q-learning (PATSQ) was proposed. Firstly, the users' power allocation was observed and learnt by the cognitive base station in the system environment, and the secondary users used NOMA to access the authorized channel. Then, the power allocation, channel state and total transmission rate in the power allocation problem were expressed as action, state and reward in the Markov decision process, which was solved by combining tabu search and Q-learning and an optimal tabu Q-table was obtained. Finally, under the constraints of primary and secondary users' Quality of Service (QoS) and maximum transmitting power, optimal power allocation factors were obtained by the cognitive base station by looking up the tabu Q-table, so as to maximize the total transmission rate of secondary users in the system. Simulation results show that under the same total power, the proposed algorithm is superior to Cognitive Mobile Radio Network (CMRN) algorithm, Secondary user First Decode Mode (SFDM) algorithm and the traditional equal power allocation algorithm in terms of the total transmission rate of secondary users and the number of users contained in the system.

Key words: Non-Orthogonal Multiple Access (NOMA), cognitive radio, power allocation, tabu search, Q-learning, Quality of Service (QoS), Markov decision process

中图分类号:

TN929.5

周烁, 仇润鹤, 唐旻俊. 基于禁忌搜索和Q-learning的CR-NOMA系统的功率分配算法[J]. 计算机应用, 2021, 41(7): 2026-2032.

ZHOU Shuo, QIU Runhe, TANG Minjun. Power allocation algorithm for CR-NOMA system based on tabu search and Q-learning[J]. Journal of Computer Applications, 2021, 41(7): 2026-2032.

参考文献

[1] BOCCARDI F,HEATH R W,LOZANO A,et al. Five disruptive technology directions for 5G[J]. IEEE Communications Magazine, 2014,52(2):74-80.
[2] 肖可鑫, 夏斌, 陈智勇. 非正交多址接入的关键技术研究[J]. 中兴通讯技术,2017,23(3):6-10.(XIAO K X,XIA B,CHEN Z Y. Key Technologies for non-orthogonal multiple access[J]. ZTE Technology Journal,2017,23(3):6-10.)
[3] XIAO Z,ZHU L,CHOI J,et al. Joint power allocation and beamforming for Non-Orthogonal Multiple Access(NOMA)in 5G millimeter wave communications[J]. IEEE Transactions on Wireless Communications,2018,17(5):2961-2974.
[4] LIANG Y C,CHEN K C,LI G Y,et al. Cognitive radio networking and communications:an overview[J]. IEEE Transactions on Vehicular Technology,2011,60(7):3386-3407.
[5] ARZYKULOV S,NAURYZBAYEV G,TSIFTSIS T A,et al. Outage performance of underlay CR-NOMA networks[C]//Proceedings of the 10th International Conference on Wireless Communications and Signal Processing. Piscataway:IEEE,2018:1-6.
[6] LI C,GUO D,GUO K,et al. Outage performance of partial relay selection in underlay CR-NOMA networks[C]//Proceedings of the 28th Wireless and Optical Communications Conference. Piscataway:IEEE,2019:1-5.
[7] ARZYKULOV S,TSIFTSIS T A,NAURYZBAYEV G,et al. Outage performance of cooperative underlay CR-NOMA with imperfect CSI[J]. IEEE Communications Letters,2019,23(1):176-179.
[8] LIU X,WANG Y,LIU S,et al. Spectrum resource optimization for NOMA-based cognitive radio in 5G communications[J]. IEEE Access,2018,6:24904-24911.
[9] XU W,QIU R,JIANG X. Resource allocation in heterogeneous cognitive radio network with non-orthogonal multiple access[J]. IEEE Access,2019,7:57488-57499.
[10] XU Y,SHU F,HU R Q,et al. Robust resource allocation in NOMA based cognitive radio networks[C]//Proceedings of the 2019 IEEE/CIC International Conference on Communications in China. Piscataway:IEEE,2019:243-248.
[11] JÁTIVA P P,CAÑIZARES M R,ARANCIBIA C S,et al. Nonorthogonal multiple access for cognitive mobile radio networks in 5G communications[C]//Proceedings of the 22nd Conference on Innovation in Clouds,Internet and Networks and Workshops. Piscataway:IEEE,2019:344-350.
[12] LIANG X,DENG Q,YANG F. Throughput optimization based on simultaneously decoding and accessing in cognitive NOMA system[C]//Proceedings of the 2018 IEEE/CIC International Conference on Communications in China. Piscataway:IEEE,2018:694-698.
[13] WANG X,NA Z,LAM K Y,et al. Energy efficiency optimization for NOMA-based cognitive radio with energy harvesting[J]. IEEE Access,2019,7:139172-139180.
[14] MIRIDAKIS N I,ARZYKULOV S,TSIFTSIS T A,et al. Green CR-NOMA:a new interweave energy harvesting transmission scheme for secondary access[C]//Proceedings of the 16th International Symposium on Wireless Communication Systems. Piscataway:IEEE,2019:571-576.
[15] 鲍慧, 佘蕊, 赵伟. 基于SWIPT的双向中继CR-NOMA系统研究[J]. 华中科技大学学报(自然科学版),2019,47(10):111-115,132.(BAO H,SHE R,ZHAO W. Research on two-way relay CR-NOMA system based on SWIPT[J]. Journal of Huazhong University of Science and Technology(Natural Science Edition), 2019,47(10):111-115,132.)
[16] PANDEY D, PANDEY P. Approximate Q-learning:an introduction[C]//Proceedings of the 2nd International Conference on Machine Learning and Computing. Piscataway:IEEE,2010:317-320.
[17] ZHANG S,LI L,YIN J,et al. A dynamic power allocation scheme in power-domain NOMA using Actor-critic reinforcement learning[C]//Proceedings of the 2018 IEEE/CIC International Conference on Communications in China. Piscataway:IEEE, 2018:719-723.
[18] DAS A,GHOSH S C,DAS N,et al. Q-learning based cooperative spectrum mobility in cognitive radio networks[C]//Proceedings of the IEEE 42nd Conference on Local Computer Networks. Piscataway:IEEE,2017:502-505.

基于禁忌搜索和Q-learning的CR-NOMA系统的功率分配算法

Power allocation algorithm for CR-NOMA system based on tabu search and Q-learning

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	唐睿, 庞川林, 张睿智, 刘川, 岳士博. D2D通信增强的蜂窝网络中基于DDPG的资源分配[J]. 《计算机应用》唯一官方网站, 2024, 44(5): 1562-1569.
[2]	唐睿, 岳士博, 张睿智, 刘川, 庞川林. UAV协助下非正交多址接入使能的数据采集系统中能效优化机制[J]. 《计算机应用》唯一官方网站, 2024, 44(4): 1209-1218.
[3]	陈玉枚, 扈红超, 王亚文. 多变体系统服务质量及损耗评估方法[J]. 《计算机应用》唯一官方网站, 2023, 43(3): 876-884.
[4]	周玉清, 韩晓龙. 双循环策略下岸桥与跨运车的联合调度[J]. 《计算机应用》唯一官方网站, 2023, 43(2): 645-653.
[5]	孙源, 沈文建, 倪朋勃, 毛敏, 谢雅琪, 徐朝农. 实时工业物联网的功率域非正交多址接入基站选址算法[J]. 《计算机应用》唯一官方网站, 2023, 43(1): 209-214.
[6]	吴仁彪, 张振驰, 贾云飞, 乔晗. 云平台下基于截止时间的自适应调度策略[J]. 《计算机应用》唯一官方网站, 2023, 43(1): 176-184.
[7]	罗飞, 白梦伟. 基于强化学习的交通情景问题决策优化[J]. 《计算机应用》唯一官方网站, 2022, 42(8): 2361-2368.
[8]	李学明, 吴国豪, 周尚波, 林晓然, 谢洪斌. 基于分数阶网络和强化学习的图像实例分割模型[J]. 《计算机应用》唯一官方网站, 2022, 42(2): 574-583.
[9]	张俊杰, 仇润鹤. 认知超密集网络用户关联与资源分配联合优化遗传算法[J]. 《计算机应用》唯一官方网站, 2022, 42(12): 3856-3862.
[10]	孙洋洋, 姚俊萍, 李晓军, 范守祥, 王自维. 面向单记录的混合负载下物化视图异步增量维护任务生成[J]. 《计算机应用》唯一官方网站, 2022, 42(12): 3763-3768.
[11]	徐雪敏, 张秀国, 肖媛元, 曹志英. 基于优化的灰狼算法的大规模Web服务组合[J]. 《计算机应用》唯一官方网站, 2022, 42(10): 3162-3169.
[12]	王大为, 刘新浩, 李竹, 芦宾, 郭爱心, 柴国强. 离散蝠鲼觅食优化算法及在频谱分配中的应用[J]. 《计算机应用》唯一官方网站, 2022, 42(1): 215-222.
[13]	曾柏森, 钟勇, 牛宪华. 基于因子分解机用于安全探索的Q表初始化方法[J]. 《计算机应用》唯一官方网站, 2022, 42(1): 209-214.
[14]	尚芳剑, 李信, 翟迪, 陆阳, 张东磊, 钱玉文. 智能电网中两阶段网络切片资源分配技术[J]. 计算机应用, 2021, 41(7): 2033-2038.
[15]	施安妮, 李陶深, 王哲, 何璐. 基于缓存辅助的全双工无线携能通信系统的中继选择策略[J]. 计算机应用, 2021, 41(6): 1539-1545.