支持服务区分的多智能体Q学习MAC算法

doi:10.3969/j.issn.1000-3428.2013.08.023

计算机工程 ›› 2013, Vol. 39 ›› Issue (8): 112-116,120.doi: 10.3969/j.issn.1000-3428.2013.08.023

支持服务区分的多智能体Q学习MAC算法

黄玉清，王英伦

(西南科技大学信息工程学院，四川绵阳 621010)

收稿日期:2012-02-14 出版日期:2013-08-15 发布日期:2013-08-13
作者简介:黄玉清(1962－)，女，教授，主研方向：无线通信；王英伦，硕士
基金项目:
国家自然科学基金资助项目(61072138)；四川省科技厅应用基础研究基金资助项目(2010jy0173)

Q-learning MAC Algorithm of Multi-agent Supporting Service Differentiation

HUANG Yu-qing, WANG Ying-lun

(School of Information Engineering, Southwest University of Science and Technology, Mianyang 621010, China)

Received:2012-02-14 Online:2013-08-15 Published:2013-08-13

摘要/Abstract

摘要： 媒体访问控制(MAC)协议负责协调所有认知用户的空闲信道接入服务，是认知Ad-hoc网络支持服务质量(QoS)的关键技术之一。在二进制指数退避算法基础上，提出一种支持服务区分的多智能体Q学习MAC算法。实时调整传输概率，使系统信道接入服务达到最优，建立传输概率调节的Markov链模型，导出分组的传输概率与协议参数的关系，给出基于服务区分的信道吞吐率模型，建立基于MAC协议参数学习的多智能体Q学习算法。实验结果表明，该算法能满足高优先级业务的QoS，且吞吐率和时延性能优于IEEE 802.11e EDCA机制。

关键词: 服务区分, Q学习, 多智能体, 认知无线电, 媒体访问控制, 传输概率

Abstract: The Media Access Control(MAC) protocol which coordinates idle channel accessing service among cognitive radio users, is one of the key technologies in cognitive Ad-hoc network supporting Quality of Service(QoS). This paper is based on the algorithm of binary exponential backoff, proposes a MAC algorithm with multi-agent Q-learning that supports service differentiation, real-time transmission probability adjusting is introduced to optimum the accessing service of system. Markov chain model is established with transmit probability adjusting, and the relationship between packet transmit probability and protocol parameters are derived. The channel throughput model with service differentiation is given. The multi-agent Q-learning architecture based on MAC protocol parameter is realized. Experimental result shows that this algorithm can satisfy the QoS of high priority service, the throughput rate and delay are better than IEEE 802.11e EDCA mechanism.

Key words: service differentiation, Q-learning, multi-agent, Cognitive Radio(CR), Media Access Control(MAC), transmission probability

中图分类号:

TN914

黄玉清, 王英伦. 支持服务区分的多智能体Q学习MAC算法[J]. 计算机工程, 2013, 39(8): 112-116,120.

HUANG Yu-Qing, WANG Yang-Lun. Q-learning MAC Algorithm of Multi-agent Supporting Service Differentiation[J]. Computer Engineering, 2013, 39(8): 112-116,120.

参考文献

[1] Mitola J. Cognitive Radio: An Integrated Agent Architecture for Software Defined Radio[D]. Stockholm, Sweden: Royal Institute of Technology, 2000.
[2] Haykin S. Cognitive Radio: Brain-empowered Wireless Com- munications[J]. IEEE Transactions on Selected Areas in Communications, 2005, 23(2): 201-220.
[3] Huang Yuqing, Jiang Hong, Hu Hong, et al. Design of Learning Engine Based on Support Vector Machine in Cognitive Radio[C]//Proc. of International Conference on Computational Intelligence and Software Engineering. Wuhan, China: [s. n.], 2009.
[4] Huang Yuqing, Wang Jiao, Jiang Hong. Modeling of Learning Inference and Decision-making Engine in Cognitive Radio[C]//Proc. of the 2nd International Conference on Networks Security, Wireless Communications and Trusted Computing. Wuhan, China: [s. n.], 2010.
[5] Aad I, Castelluccia C. Differentiation Mechanisms for IEEE 802.11[C]//Proc. of the 20th Annual Joint Conference of the IEEE Computer and Communications Societies. [S. l.]: IEEE Press, 2001.
[6] Muir A, Garcia J J. Supporting Real-time Multimedia Traffic in a Wireless LAN[C]//Proc. of SPIE’97. [S. l.]: SPIE Press, 1997.
(下转第120页)
(上接第116页)

[7] Su Hang, Zhang Xi. Cross-layer Based Opportunistic MAC Protocols for QoS Provisionings Over Cognitive Radio Wireless Networks[J]. IEEE Journal on Selected Areas in Communications, 2008, 26(1): 118-129.
[8] Song Hua, Lin Xiaola. A Group Based MAC Protocol for QoS Provisioning in Cognitive Radio Networks[C]//Proc. of the 11th IEEE Singapore International Conference on Communi- cation Systems. [S. l.]: IEEE Press, 2008.
[9] 冯文江, 陈倩, 李林, 等. 认知无线电网络分布式多信道MAC协议[J]. 计算机应用研究, 2011, 28(2): 639-641.
[10] Hu Junling, Wellman M P. Nash Q-learning for General-sum Stochastic Games[J]. The Journal of Machine Learning Research, 2003, 4: 1039-1069.
编辑刘冰

[1]	冉超, 方志军, 张彦宇. 基于SDR和改进能量检测算法的频谱感知[J]. 计算机工程, 2020, 46(9): 198-204.
[2]	李建岐, 黄毕尧, 杨婷婷, 吴玉成. 230 MHz电力专属频段频谱认知技术研究[J]. 计算机工程, 2020, 46(7): 173-178.
[3]	崔艳, 李庆华. 二阶多智能体系统参数自适应的有限时间一致性算法[J]. 计算机工程, 2020, 46(4): 273-278,286.
[4]	刘庆周, 吴锋. 多智能体路径规划研究进展[J]. 计算机工程, 2020, 46(4): 1-10.
[5]	管亮, 郑霖, 张文辉. 认知无线电中子谱缺失下的似然恢复算法[J]. 计算机工程, 2020, 46(2): 201-206,213.
[6]	吴孟礼, 陈跃斌, 吴海锋, 李敏, 孙祥晟. 抵御SSDF攻击的维纳滤波器检测算法研究[J]. 计算机工程, 2020, 46(11): 187-193.
[7]	王毅然, 经小川, 贾福凯, 孙宇健, 佟轶. 基于多智能体协同强化学习的多目标追踪方法[J]. 计算机工程, 2020, 46(11): 90-96.
[8]	顾洁, 朱宗卫, 徐友庆, 周世斌, 李奥, 张国鹏. NS-3仿真环境中IEEE802.11服务区分机制的研究[J]. 计算机工程, 2019, 45(8): 135-140.
[9]	唐丽萍, 江逸伦. 基于不完美频谱检测的认知无线电网络资源分配[J]. 计算机工程, 2019, 45(8): 173-177,197.
[10]	徐琳,赵知劲. 基于分布式协作Q学习的信道与功率分配算法[J]. 计算机工程, 2019, 45(6): 160-164,174.
[11]	韩晨,牛英滔. 基于分层Q学习的联合抗干扰算法[J]. 计算机工程, 2019, 45(5): 279-284.
[12]	冯刚,覃锡忠,贾振红,牛红梅,王哲辉. 认知无线电环境下无线能量通信网能效研究[J]. 计算机工程, 2019, 45(3): 142-147.
[13]	王少迪,高宝建,张育铖,赵泽. 基于中继联合优化选择的物理层安全方案[J]. 计算机工程, 2019, 45(2): 148-153.
[14]	赵季红, 王文科, 曲桦, 徐西光, 闫飞宇, 颜皓靓. 基于绝对值累积的主用户动态到达频谱感知算法[J]. 计算机工程, 2019, 45(11): 81-85.
[15]	彭军伟,韩志韧,彭开志. 基于权值分簇的多门限联合频谱检测算法[J]. 计算机工程, 2018, 44(6): 29-33.

支持服务区分的多智能体Q学习MAC算法

Q-learning MAC Algorithm of Multi-agent Supporting Service Differentiation

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 10