Neural network predication for network routing

Authors:
Dong Jun;Song Ruixiang
Affiliations:
Software Engineering Institute, East China Normal University, Shanghai, P.R. China;Software Engineering Institute, East China Normal University, Shanghai, P.R. China
Venue:
ACST'06 Proceedings of the 2nd IASTED international conference on Advances in computer science and technology
Year:
2006

Citing 7
Cited 0

Measurement and performance of a cognitive packet network

Computer Networks: The International Journal of Computer and Telecommunications Networking - Special issue on networking middleware: selected papers from the TERENA networking conference 2001
Agent-based distance vector routing: a resource efficient and scalable approach to routing in large communication networks

Journal of Systems and Software - Special issue: Computer systems
Neural Information Processing: Research and Development

Neural Information Processing: Research and Development
NEURAL: A Self-Organizing Routing Algorithm for Ad Hoc Networks

WIOPT '05 Proceedings of the Third International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks
Prediction of chaotic time series based on the recurrent predictor neural network

IEEE Transactions on Signal Processing
Applications of agent technology in communications: a review

Computer Communications
Agent-based throughput response in presence of node and/or link failure (on demand) for circuit switched telecommunication networks

Computer Communications

Quantified Score

Hi-index	0.00

Visualization

Abstract

Routing is key issue for survivable network. Intelligent routing schemes have been investigated widely with fuzzy logic, genetic algorithms and neural networks, among which, agent-based approaches are paid more attentions recently. On the basis of demerit-analysis of routing being used, a new intelligent routing strategy based on multi-agent systems and neural network predication is presented. After overview on related works, the paper describes recurrent neural network that is used to predicate network load. The results show the new approach is better by virtue of its upstanding predication capabilities.