论文部分内容阅读
A state-dependent routing algorithm based on the neural network model, which takes advantage of other dynamic routing algorithm for circuit-switched network, is given in [1]. But, the Algorithm in [1] is a centralized control model with complex O (N 7), therefore, is difficult to realize by hardware. A simplified algorithm is put forward in this paper, in which routing can be controlled decentralizedly, and its complexity is reduced to O (10N 3). Computer simulations are made in a fully connected test network with eight nodes. The results show that the centralized control model has very effective performance that can match RTNR, and the centralized control model is not as good as the centralized one but better than DAR-1.
A state-dependent routing algorithm based on the neural network model, which takes advantage of other dynamic routing algorithms for circuit-switched network, is given in [1]. But, the Algorithm in [1] is a centralized control model with complex O (N 7), therefore, is difficult to realize by hardware. A simplified algorithm is put forward in this paper, in which routing can be controlled decentralizedly, and its complexity is reduced to O (10N 3). Computer simulations are made in a fully connected test network with eight nodes. The results show that the centralized control model has very effective performance that can match RTNR, and the centralized control model is not as good as the centralized one but better than DAR-1.