An intelligent routing and CAC framework for large-scale networks based on cooperative agents

详细信息    查看全文

• 作者：Barolli ; Leonard ; Koyama ; Akio ; Yamada ; Takako ; Yokoyama ; Shoichi ; Suganuma ; Takuo ; Shiratori ; Norio
• 关键词：Genetic algorithms ; Fuzzy logic ; Large-scale networks ; Cooperative agents
• 刊名：Computer Communications
• 出版年：2002
• 出版时间：October 1, 2002
• 年：2002
• 卷：25
• 期：16
• 页码：1429-1442
• 全文大小：289 K

文摘

The routing algorithms can be classified into source, distributed and hierarchical routing. Source routing algorithms are conceptually simple, but they suffer from scalability problem. Distributed routing algorithms are more scalable, but loops may occur, which make the routing to fail. Hierarchical routing has been used to cope with the scalability problems of source routing in large internetworks. The hierarchical routing retains many advantages of source routing. It also has some advantages of distributed routing, because the routing computation is shared by many nodes. The traffic control methods for telecommunication networks must be adaptive, flexible, and intelligent. Use of intelligent algorithms based on fuzzy logic, genetic algorithms and neural networks can prove to be efficient for traffic control in telecommunication networks. In this paper, we propose an intelligent routing and Call Admission Control framework, which is based on cooperative agents. The proposed routing algorithm is a combination of source and distributed routing. It uses source routing inside a domain and hop-by-hop routing for inter-domain. The proposed framework is able to avoid flooding and routing loops, reduce the search space, and can be easily scaled-up to cope with large-scale networks. Performance evaluation via simulations shows that the proposed Fuzzy Admission Control and Intra Domain algorithm have better performance than the conventional methods.