计算机科学 ›› 2019, Vol. 46 ›› Issue (6): 124-127.doi: 10.11896/j.issn.1002-137X.2019.06.018

• 网络与通信 • 上一篇    下一篇

基于Q-learning的RFID多阅读器防碰撞算法

袁源, 郑嘉利, 石静, 王哲, 李丽   

  1. (广西大学计算机与电子信息学院 南宁530004)
    (广西多媒体通信与网络技术重点实验室 南宁530004)
  • 收稿日期:2018-05-14 发布日期:2019-06-24
  • 通讯作者: 郑嘉利(1979-),男,教授,主要研究方向为多媒体通信、物联网技术,E-mail:zhengjiali@vip.163.com
  • 作者简介:袁 源(1995-),女,硕士生,主要研究方向为多媒体通信网络理论与技术;石 静(1992-),女,硕士生,主要研究方向为多媒体通信网络理论与技术;王 哲(1993-),男,硕士生,主要研究方向为多媒体通信及其网络工程;李 丽(1994-),女,硕士生,主要研究方向多媒体通信网络理论与技术。
  • 基金资助:
    国家自然科学基金项目(61761004)资助。

Anti-collision Algorithm Based on Q-learning for RFID Multiple Readers

YUAN Yuan, ZHENG Jia-li, SHI Jing, WANG Zhe, LI Li   

  1. (School of Computer and Electronics Information,Guangxi University,Nanning 530004,China)
    (Guangxi Key Laboratory of Multimedia Communications and Network Technology,Nanning 530004,China)
  • Received:2018-05-14 Published:2019-06-24

摘要: 为了解决无线射频识别(RFID)系统中多阅读器与标签通信的碰撞问题,文中将此问题建模为马尔可夫决策过程,并提出了一种基于Q-learning的防碰撞算法。该算法通过智能体agent不断与周围环境进行交互和学习,从而产生Q值函数,得到最佳信道分配策略;取消了HiQ算法中复杂的分层结构,简化了系统模型,引入ε贪婪策略以得到全局最优解,改进奖赏函数以得到最优状态。仿真结果表明,与HiQ算法和EHiQ算法相比,该智能算法能够自适应地为阅读器分配不同的信道来进行数据传输,从而有效降低碰撞率,提高信道利用率和吞吐率。

关键词: Q-learning, Q值, 无线射频识别, 阅读器防碰撞

Abstract: Due to the collision problem between multiple readers and tags communication in RFID system,this paper modeled the problem as a Markov decision process,and proposed an anti-collision algorithm based on Q-learning.By continuously interacting with the environment,the Q-value function is generated,as well as the optimal channel resources allocation.The complex hierarchical structure in HiQ algorithm is eliminated for simplifying the system model.The algorithm not only imports the concept of ε-greedy strategy to obtain the global optimal solution,but also improves the reward function to get the best state.Simulation results show that compared with HiQ and EHiQ,this intelligent algorithm can adaptively assign different channels to the reader for data transmission,therefore reduces the collision rate and improves the channel utilization and throughput rate.

Key words: Q-learning, Q-value, Radio frequency identification, Reader anti-collision

中图分类号: 

  • TP301.6
[1]WEI D X,ZHENG J L,LI L L,et al.Study of Novel Adaptive Multi-tree Anti-collision Search Algorithm[J].Computer Scien-ce,2013,40(10):52-55.(in Chinese)
韦冬雪,郑嘉利,李亮亮,等.一种新颖的自适应多叉树防碰撞算法的研究[J].计算机科学,2013,40(10):52-55.
[2]XIE L,YIN Y F,CHEN X,et al.RFID Data Management:Algorithms,Protocols and Performance Evaluation[J].Chinese Journal of Computers,2013,36(3):457-470.(in Chinese)
谢磊,殷亚凤,陈曦,等.RFID数据管理:算法、协议与性能评测[J].计算机学报,2013,36(3):457-470.
[3]WALDROP J,ENGELS D W,SARMA S E.Colorwave:An Anticollision Algorithm for the Reader Collision Problem[C]∥IEEE International Conference on Communications.IEEE,2003:1206-1210.
[4]BIRARI S M,IYER S.PULSE:A MAC Protocol for RFID Net-works[C]∥International Conference on Embedded and Ubiquitous Computing.Springer-Verlag,2005:1036-1046.
[5]SEO H,LEE C.A New GA-Based Resource Allocation Scheme for a Reader-to-Reader Interference Problem in RFID Systems[C]∥IEEE International Conference on Communications.IEEE,2010:1-5.
[6]TIAN J,FAN Y,ZHU Y,et al.RFID Reader Anti-collision Using Chaos Neural network Based on Annealing Strategy[C]∥World Congress on Intelligent Control and Automation,2008(WCICA 2008).IEEE,2008:6128-6132.
[7]HO J,ENGELS D W,SARMA S E.HiQ:a Hierarchical Q-learning Algorithm to Solve the Reader Collision Problem[C]∥2006 International Symposium on Applications and the Internet Workshops.IEEE,2006:88-91.
[8]GOLSORKHTABARAMIRI M,ISSAZADEHKOJIDI N.A Distance Based RFID Reader Collision Avoidance Protocol for Dense Reader Environments[J].Wireless Personal Communications,2017,95(2):1-18.
[9]SAADI H,TOUHAMI R,YAGOUB M C E,et al.TDMA-SDMA based RFID algorithm for fast detection and efficient collision avoidance[J].International Journal of Communication Systems,2018,31(3).
[10]YANG J,WANG Y H,CAI Q L,et al.EHiQ:A RFID Reader MAC Protocol Based on Enhanced HiQ[J].Computer Science,2011,38(7):85-87.(in Chinese)
杨健,王永华,蔡庆玲,等.EHiQ:一种基于增强型HiQ的RFID读写器MAC协议[J].计算机科学,2011,38(7):85-87.
[11]LIU Q,ZHAI J W,ZHANG Z Z,et al.A Survey on Deep Reinforcement Learning[J].Chinese Journal of Computers,2017,40(1):1-28.(in Chinese)
刘全,翟建伟,章宗长,等.深度强化学习综述[J].计算机学报,2017,40(1):1-28.
[12]GU J Y,ZHANG G A,BAO Z H.Joint multi-path routing and channel assignment strategy for cognitive wireless mesh networks[J].Computer Science,2011,38(5):45-48.(in Chinese)
顾金媛,章国安,包志华.认知无线Mesh网络联合多路径路由和信道分配策略[J].计算机科学,2011,38(5):45-48.
[13]AVALLONE S,BANCHS A.A Channel Assignment and Routing Algorithm for Energy Harvesting Multiradio Wireless Mesh Networks[J].IEEE Journal on Selected Areas in Communications,2016,34(5):1463-1476.
[1] 周琴, 罗飞, 丁炜超, 顾春华, 郑帅.
基于逐次超松弛技术的Double Speedy Q-Learning算法
Double Speedy Q-Learning Based on Successive Over Relaxation
计算机科学, 2022, 49(3): 239-245. https://doi.org/10.11896/jsjkx.201200173
[2] 郑帅, 罗飞, 顾春华, 丁炜超, 卢海峰.
基于双估计器的改进Speedy Q-learning算法
Improved Speedy Q-learning Algorithm Based on Double Estimator
计算机科学, 2020, 47(7): 179-185. https://doi.org/10.11896/jsjkx.190500143
[3] 李龙飞,张泾周,王鹏德,郭鹏军.
基于节点兴趣和Q-learning的P2P网络搜索机制
P2P Network Search Mechanism Based on Node Interest and Q-learning
计算机科学, 2020, 47(2): 221-226. https://doi.org/10.11896/jsjkx.190400002
[4] 卢海峰, 顾春华, 罗飞, 丁炜超, 袁野, 任强.
强化学习下能耗优化的虚拟机放置策略
Virtual Machine Placement Strategy with Energy Consumption Optimization under Reinforcement Learning
计算机科学, 2019, 46(9): 291-297. https://doi.org/10.11896/j.issn.1002-137X.2019.09.044
[5] 梁媛,袁景凌,陈旻骋.
利用空间优化的增强学习Sarsa改进预取算法
Prefetching Algorithm of Sarsa Learning Based on Space Optimization
计算机科学, 2019, 46(3): 327-331. https://doi.org/10.11896/j.issn.1002-137X.2019.03.048
[6] 石静, 郑嘉利, 袁源, 王哲, 李丽.
基于Whittle索引的RFID多阅读器信道资源分配算法
RFID Multi-reader Channel Resources Allocation Algorithm Based on Whittle Index
计算机科学, 2019, 46(10): 122-127. https://doi.org/10.11896/jsjkx.180801602
[7] 甘勇, 王凯, 贺蕾.
一种全新的RFID标签所有权转移协议
New Ownership Transfer Protocol of RFID Tag
计算机科学, 2018, 45(11A): 369-372.
[8] 张亚力,郭亚军,崔建群,曾庆江.
一种新的超轻量级RFID认证协议
New Ultra-lightweight RFID Authentication Protocol
计算机科学, 2017, 44(1): 183-187. https://doi.org/10.11896/j.issn.1002-137X.2017.01.035
[9] 孟凡振,吴杰,卜旭松,冯锋.
基于马尔可夫链模型的井下目标轨迹预测算法
Underground Target Track Prediction Algorithm Based on Markov Chain Model
计算机科学, 2014, 41(Z6): 321-323.
[10] 任守纲,杨帆,王浩云,熊迎军,徐焕良.
基于判决门限的RFID防碰撞Q值算法
Decision Threshold-based Q Algorithm for RFID Anti-collision
计算机科学, 2014, 41(8): 154-157. https://doi.org/10.11896/j.issn.1002-137X.2014.08.034
[11] 任守纲,杨帆,徐焕良.
一种双权重参数的RFID防碰撞Q值算法研究
Research on Double Weight Parameter Anti-collision Q Value Algorithm in RFID System
计算机科学, 2014, 41(4): 256-259.
[12] 钱晓军,朱颖,吉根林.
一种改进的物联网二进制防碰撞算法
Improved Binary Anti-collision Algorithm for Internet of Things
计算机科学, 2012, 39(9): 24-27.
[13] 邓淼磊,黄照鹤,鲁志波.
EPCGen2标准下安全的RFID认证协议
Secure RFID Authentication Protocol for EPCGen2
计算机科学, 2010, 37(7): 115-117.
[14] 邓森磊,马玉军,石金娥,周利华.
安全的航空物品管理RFID系统
Secure RFID System for Aviation Goods Management
计算机科学, 2010, 37(11): 107-110.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!