A Metropolis Criterion Based Fuzzy Q-Learning Flow Controller for High-Speed Networks

被引:1
|
作者
Liu, Wenwei [1 ]
Li, Xin [1 ]
Qin, Xiaoning [2 ]
Yu, Dan [1 ]
机构
[1] Shenyang Univ, Key Lab Mfg Ind Integrated Automat, Shenyang 110044, Peoples R China
[2] Shenyang Dongling Power Supply Branch Co, Shenyang 110043, Peoples R China
来源
INDUSTRIAL INSTRUMENTATION AND CONTROL SYSTEMS, PTS 1-4 | 2013年 / 241-244卷
关键词
Metropolis Criterion; Fuzzy Q-Learning; Flow Controller; High-Speed Networks;
D O I
10.4028/www.scientific.net/AMM.241-244.2327
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
For the congestion problems in high-speed networks, a Metropolis criterion based fuzzy Q-learning flow controller is proposed. Because of the uncertainties and highly time-varying, it is not easy to accurately obtain the complete information. In this case, the Q-leaming, which is independent of mathematic model, and prior-knowledge, has good performance. The fuzzy inference and Metropolis criterion are introduced in order to facilitate generalization in large state space and balance exploration and exploitation in action selection individually. Simulation results show that the controller can learn to take the best action to regulate source flow with the features of high throughput and low packet loss ratio, and can avoid the occurrence of congestion effectively.
引用
收藏
页码:2327 / +
页数:2
相关论文
共 50 条
  • [1] A Fuzzy Markov Game Based Flow Controller for High-speed Networks Employing Metropolis Criterion
    Li, Xin
    Jing, Yuanwei
    Zhang, Siying
    Dimirovski, Georgi M.
    IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN AND CYBERNETICS (SMC 2010), 2010,
  • [2] Fuzzy Q-Learning Flow Control for High-Speed Networks
    Li, Xin
    Zhao, Xin
    Jing, Yuanwei
    Zhang, Nannan
    2008 CHINESE CONTROL AND DECISION CONFERENCE, VOLS 1-11, 2008, : 383 - +
  • [3] A Q-Learning Model-Independent Flow Controller for High-speed Networks
    Li, Xin
    Dimirovski, Georgi M.
    Jing, Yuanwei
    Zhang, Siying
    2009 AMERICAN CONTROL CONFERENCE, VOLS 1-9, 2009, : 1544 - +
  • [4] A new Q-learning algorithm based on the Metropolis criterion
    Guo, MZ
    Liu, Y
    Malec, J
    IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS, 2004, 34 (05): : 2140 - 2143
  • [5] Research on Q-learning algorithm based on Metropolis criterion
    Jisuanji Yanjiu yu Fazhan/Computer Research and Development, 2002, 39 (06):
  • [6] Nash Q-Learning Multi-Agent Flow Control for High-Speed Networks
    Jing, Yuanwei
    Li, Xin
    Dimirovski, Georgi M.
    Zheng, Yan
    Zhang, Siying
    2009 AMERICAN CONTROL CONFERENCE, VOLS 1-9, 2009, : 3304 - +
  • [7] High-speed railway dynamic scheduling based on Q-learning method
    Han X.-C.
    Yu S.-P.
    Yuan Z.-M.
    Cheng L.-J.
    Kongzhi Lilun Yu Yingyong/Control Theory and Applications, 2021, 38 (10): : 1511 - 1521
  • [8] A Dynamic Adaptation Mechanism of Network Resource Based on Fuzzy Q-learning in High-speed Mobile Environment
    Li, Jialin
    Dong, Ping
    PROCEEDINGS OF 2020 IEEE 4TH INFORMATION TECHNOLOGY, NETWORKING, ELECTRONIC AND AUTOMATION CONTROL CONFERENCE (ITNEC 2020), 2020, : 1079 - 1083
  • [9] Q-learning based Handover Algorithm for High-Speed Rail Wireless Communications
    Wang, Siling
    Zhang, Li
    2023 IEEE WIRELESS COMMUNICATIONS AND NETWORKING CONFERENCE, WCNC, 2023,
  • [10] Modified fuzzy Q-learning based wind speed prediction
    Sharma, Rajneesh
    Shikhola, Tushar
    Kohli, Jaspreet Kaur
    JOURNAL OF WIND ENGINEERING AND INDUSTRIAL AERODYNAMICS, 2020, 206 (206)