An adaptive neuro-fuzzy control is investigated for a class of non-affine nonlinear systems.To do so,rigorous description and quantification of the approximation error of the neuro-fuzzy controller are firstly discuss...An adaptive neuro-fuzzy control is investigated for a class of non-affine nonlinear systems.To do so,rigorous description and quantification of the approximation error of the neuro-fuzzy controller are firstly discussed.Applying this result and Lyapunov stability theory,a novel updating algorithm to adapt the weights,centers,and widths of the neuro-fuzzy controller is presented.Consequently,the proposed design method is able to guarantee the stability of the closed-loop system and the convergence of the tracking error.Simulation results illustrate the effectiveness of the proposed adaptive neuro-fuzzy control scheme.展开更多
In communication networks （CNs）, the uncertainty is caused by the dynamic nature of the traffic demands. Therefore there is a need to incorporate the uncertainty into the network bandwidth capacity design. For this ...In communication networks （CNs）, the uncertainty is caused by the dynamic nature of the traffic demands. Therefore there is a need to incorporate the uncertainty into the network bandwidth capacity design. For this purpose, this paper developed a fuzzy methodology for network bandwidth design under demand uncertainty. This methodology is usually used for offiine traffic engineering optimization, which takes a centralized view of bandwidth design, resource utilization, and performance evaluation. In this proposed methodology, uncertain traffic demands are first handled into a fuzzy number via a fuzzification method. Then a fuzzy optimization model for the network bandwidth allocation problem is formulated with the consideration of the trade-off between resource utilization and network performance. Accordingly, the optimal network bandwidth capacity can be obtained by maximizing network revenue in CNs. Finally, an illustrative numerical example is presented for the purpose of verification.展开更多
基金Shanghai Leading Academic Discipline Project,Project Number T0103Shanghai Municipal Education Commission Project,Project Number:05AZ22
文摘An adaptive neuro-fuzzy control is investigated for a class of non-affine nonlinear systems.To do so,rigorous description and quantification of the approximation error of the neuro-fuzzy controller are firstly discussed.Applying this result and Lyapunov stability theory,a novel updating algorithm to adapt the weights,centers,and widths of the neuro-fuzzy controller is presented.Consequently,the proposed design method is able to guarantee the stability of the closed-loop system and the convergence of the tracking error.Simulation results illustrate the effectiveness of the proposed adaptive neuro-fuzzy control scheme.
基金partially supported by the grants from the National Natural Science Foundation of Chinathe Knowledge Innovation Program of the Chinese Academy of Sciences+1 种基金the GRANT-IN-AID FOR SCIEN-TIFIC RESEARCH (No. 19500070)MEXT.ORC (2004-2008), Japan
文摘In communication networks （CNs）, the uncertainty is caused by the dynamic nature of the traffic demands. Therefore there is a need to incorporate the uncertainty into the network bandwidth capacity design. For this purpose, this paper developed a fuzzy methodology for network bandwidth design under demand uncertainty. This methodology is usually used for offiine traffic engineering optimization, which takes a centralized view of bandwidth design, resource utilization, and performance evaluation. In this proposed methodology, uncertain traffic demands are first handled into a fuzzy number via a fuzzification method. Then a fuzzy optimization model for the network bandwidth allocation problem is formulated with the consideration of the trade-off between resource utilization and network performance. Accordingly, the optimal network bandwidth capacity can be obtained by maximizing network revenue in CNs. Finally, an illustrative numerical example is presented for the purpose of verification.
