IEEE Trans Cybern. 2019 Jun;49(6):2372-2384. doi: 10.1109/TCYB.2018.2827037. Epub 2018 May 18.
The neural-network (NN)-based output-feedback control is considered for a class of stochastic nonlinear systems under round-Robin (RR) scheduling protocols. For the purpose of effectively mitigating data congestions and saving energies, the RR protocols are implemented and the resulting nonlinear systems become the so-called protocol-induced periodic ones. Taking such a periodic characteristic into account, an NN-based observer is first proposed to reconstruct the system states where a novel adaptive tuning law on NN weights is adopted to cater to the requirement of performance analysis. In addition, with the established boundedness of the periodic systems in the mean-square sense, the desired observer gain is obtained by solving a set of matrix inequalities. Then, an actor-critic NN scheme with a time-varying step length in adaptive law is developed to handle the considered control problem with terminal constraints over finite-horizon. Some sufficient conditions are derived to guarantee the boundedness of estimation errors of critic and actor NN weights. In view of these conditions, some key parameters in adaptive tuning laws are easily determined via elementary algebraic operations. Furthermore, the stability in the mean-square sense is investigated for the discussed issue in infinite horizon. Finally, a simulation example is utilized to illustrate the applicability of the proposed control scheme.
基于神经网络（NN）的输出反馈控制被用于一类随机非线性系统，这些系统采用轮询（RR）调度协议。为了有效减轻数据拥塞和节约能源，实施了 RR 协议，这使得所得到的非线性系统成为所谓的协议诱导周期系统。考虑到这种周期性特征，首先提出了一种基于神经网络的观测器来重建系统状态，其中采用了一种新的神经网络权重自适应调整律来满足性能分析的要求。此外，通过求解一组矩阵不等式，获得了具有时变步长的自适应律的 Actor-Critic NN 方案，以处理具有终端约束的有限时域控制问题。导出了一些充分条件来保证评论家 NN 权重和演员 NN 权重的估计误差有界。根据这些条件，可以通过基本的代数运算轻松确定自适应调整律中的一些关键参数。此外，还研究了无限时域中讨论问题的均方稳定性。最后，通过一个仿真例子说明了所提出的控制方案的适用性。
