Multi-dimensional Taylor network adaptive predictive control for single-input single-output nonlinear systems with input time-delay

In this study, an adaptive predictive control approach based on the multi-dimensional Taylor network (MTN) is proposed for the real-time tracking control of single-input single-output nonlinear systems with input time-delay. Two MTNs are used to implement the accurate tracking control. First, to compensate for the influence of time-delay, MTN is taken as a predictor and the damped recursive least squares algorithm is used as its online learning algorithm. Second, a feed-forward MTN controller is developed on the basis of the proportional–integral–derivative controller, and the closed-loop errors between the reference input and the system output are directly chosen to be the MTN controller’s inputs. The back propagation algorithm is introduced for its learning which can update its weights online at stable learning rate by the errors caused by the system’s uncertain factors. Convergence and stability analysis are given to guarantee the performance of our proposed approach. Finally, two examples are given to verify the effectiveness of the proposed approach.

Intelligent monitoring of small sized supercapacitor in wind-penetrated power system

This work pertains to integration of supercapacitor energy storage system with wind-penetrated two-area power system. A small-sized SCES device is incorporated in automatic generation control of each area. For robust and optimum usage of SCES, a customized neuro-adaptive predictive control model is developed using level 1 S-function coding. This model feeds reference power command to the converter of storage system with its voltage used as feedback loop. A step load disturbance reflecting load outage is introduced back to back in the power system. It is seen through simulation studies carried out in MATLAB Simulink Environment that there is significant improvement in frequency response and tie power deviations. SCES converter power limits are fully maintained; besides, SCES voltage and power response is also depicted.