Abstract
Congestion control is one of the key problems in high-speed networks, such as ATM. In this paper, a kind of traffic prediction and preventive congestion control scheme is proposed using neural network approach. Traditional predictor using BP neural network has suffered from long convergence time and dissatisfying error. Fuzzy neural network developed in this paper can solve these problems satisfactorily. Simulations show the comparison among no-feedback control scheme, reactive control scheme and neural network based control scheme.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Fan P M. Access flow control scheme for ATM networks using neural-network-based traffic prediction.IEE Proce.-Commun. Oct. 1997, 144(5): 295–300.
Melody Moh W, Chen Min-Jia, Chu Nui-Ming. Traffic prediction and dynamic bandwidth allocation over ATM: A neural network approachComputer Communications, Aug. 1995, 18(8): 563–571.
Habib A T, Saadawi T. A neural network controller for congestion control in ATM multiplexers.Computer Networks and ISDN Systems, 1997, 29: 325–334.
Ahmed A Tarraf, Ibrahim W Habib, Tarek N Saadawi. Intelligent traffic control for ATM broadband networks.IEEE Communications Magazine, Oct. 1995, 33(10): 76–82.
Park Y K, Lee G. Application of neural networks in high-speed communication networks.IEEE Communications Magazine, Oct. 1995, 33(10): 68–74.
Kartam Nabil, Tongthong Tanit. Potential of artificial neural networks for resource scheduling. Artificial Intelligence for Engineering Design, Analysis and Manufacturing: AIEDAM, Jun 1997, 11(3): 171–185.
Author information
Authors and Affiliations
Additional information
The project supported by National and Jiangsu Provincial Natural Science Foundation and National ‘973’ Fundamental Research Project of China, and Key Sci. & Tech. Project of Ministry of Education, China.
FEI Xiang received his B.Eng. and M.Eng. degrees from Dept. of Control Engineering, Southeast University, Nanjing, China in 1992 and 1995, respectively. He is currently working towards the Ph.D. degree from Dept. of Computer Science and Engineering, Southeast University. His research interests include high-speed computer network, protocol engineering and knowledge based network resource management and scheduling.
HE Xiaoyan is now a Ph.D. candidate of Dept. of Computer Science and Engineering, Southeast University. Her research interests include computer network and concurrent technique of database.
LUO Junzhou is a Professor of Dept. of Computer Science and Engineering, Southeast University, the secretary-general of Petri Net Committee of China Computer Federation, an active member of New York Academy of Science. His current research interests include Petri net based protocol engineering, computer network, and concurrent engineering.
WU Jieyi is the Vice President of Southeast University, a Professor of Dept. of Computer Science and Engineering, Southeast University, and a member of CIMS Expert Group of Jiangsu Province. His current research interests include network and information integration in CIMS.
GU Guanqun is the President of Southeast University, a member of the Chinese Academy of Engineering, and a member of CIMS Expert Group of National “863” Program. His current research interests include high-performance network, protocol engineering, intelligent computer network, and computer integrated manufacturing (CIM).
Rights and permissions
About this article
Cite this article
Fei, X., He, X., Luo, J. et al. Fuzzy neural network based traffic prediction and congestion control in high-speed networks. J. Comput. Sci. & Technol. 15, 144–149 (2000). https://doi.org/10.1007/BF02948798
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF02948798