Fuzzy Q-Learning Flow Control for High-Speed Networks

被引：1

作者：

Li, Xin ^{[1
]}

Zhao, Xin ^{[2
]}

Jing, Yuanwei ^{[1
]}

Zhang, Nannan ^{[1
]}

机构：

[1] Northeastern Univ, Coll Informat Sci & Engn, Shenyang 110004, Peoples R China

[2] Shenyang Inst Aeronaut Engn, Sch Elect & Informat Engn, Shenyang 110136, Peoples R China

来源：

2008 CHINESE CONTROL AND DECISION CONFERENCE, VOLS 1-11 | 2008年

基金：

中国国家自然科学基金;

关键词：

High-speed network; Flow control; Q-learning; fuzzy logic;

D O I：

10.1109/CCDC.2008.4597335

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 flow controller based on fuzzy Q-learning is proposed. Because of the uncertainties and highly time-varying, it is not easy to accurately obtain the complete information for high-speed networks. The Q-learning algorithm, which is independent of mathematic model, improves its behavior policy through interaction with the environment. The fuzzy inference is introduced to facilitate generalization in the state space. By means of learning procedures, the proposed controller can learn to take the best action to regulate source flow with the features of high throughput and low packet loss ratio. Simulation results show that the proposed method can promote the performance of the networks and avoid the occurrence of congestion effectively.

引用

下载

页码：383 / +

页数：2

共 50 条

[21] Traffic Signal Control and Speed Offset Coordination Using Q-Learning for Arterial Road Networks
Yuan, Tianchen
Ioannou, Petros A.
arXiv,
[22] HARQ Control Scheme by Fuzzy Q-Learning for HSPA+
Chung, Wen-Ching
Chen, Ying-Yu
Chang, Chung-Ju
2011 IEEE 73RD VEHICULAR TECHNOLOGY CONFERENCE (VTC SPRING), 2011,
[23] FUZZY Q-LEARNING APPROACH TO SIMULATE INTELLIGENT TRAFFIC CONTROL
Pacheco, Juan C.
Rossetti, Rosaldo J. F.
Rodriguez, Cesar H.
8TH INTERNATIONAL INDUSTRIAL SIMULATION CONFERENCE 2010, ISC 2010, 2010, : 257 - 261
[24] Ant Colony Optimization Incorporated With Fuzzy Q-Learning for Reinforcement Fuzzy Control
Juang, Chia-Feng
Lu, Chun-Ming
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART A-SYSTEMS AND HUMANS, 2009, 39 (03): : 597 - 608
[25] Fuzzy Q-Learning for generalization of reinforcement learning
Berenji, HR
FUZZ-IEEE '96 - PROCEEDINGS OF THE FIFTH IEEE INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS, VOLS 1-3, 1996, : 2208 - 2214
[26] Learning to control an inverted pendulum using Q-learning and neural networks
Jiang, Guofei
Wu, Cangpu
Zidonghua Xuebao/Acta Automatica Sinica, 1998, 24 (05): : 662 - 666
[27] Reinforcement distribution in fuzzy Q-learning
Bonarini, Andrea
Lazaric, Alessandro
Montrone, Francesco
Restelli, Marcello
FUZZY SETS AND SYSTEMS, 2009, 160 (10) : 1420 - 1443
[28] ENHANCEMENTS OF FUZZY Q-LEARNING ALGORITHM
Glowaty, Grzegorz
COMPUTER SCIENCE-AGH, 2005, 7 : 77 - 87
[29] Fuzzy Q-Learning with an Adaptive Representation
Waldock, A.
Carse, B.
2008 IEEE INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS, VOLS 1-5, 2008, : 720 - +
[30] Performance of feedback flow control mechanisms in large high-speed networks
Roche, C
IEEE GLOBECOM 1996 - CONFERENCE RECORD, VOLS 1-3: COMMUNICATIONS: THE KEY TO GLOBAL PROSPERITY, 1996, : 1085 - 1089

← 1 2 3 4 5 →