Investigation of inventive Tuning Algorithm for the realization of Digital Twins of Inverter Model in Inverter-dominated Power Distribution Grid

Abstract

In this paper, the inventive methods based on the neural network will be applied to construct the digital twins of the inverter. By utilizing the digital twins (DT) model, the inverter can be replaced, which is able to be as the substitution to simulate the operation of the inverter. The paper can be arranged as two parts: First of all, the modelling of the inverter in electromechanical transient will be illustrated. Afterwards, the proposed methods are clarified, which are, firstly, an online PI tuner for the controllers of the inverter and then an neural network based identifier is operated to approximate the nonlinear functional dynamic state of it. The design of PI tuner is based on the deviation between the output of the model and the reference output from measurement data. Then, according to the difference, the tuner can calculate the appropriate parameter of the current and voltage controller to track the dynamic behaviour of the reference model. The NN identifier is, however, to replicate the dynamic character of the reference model by NN which is initially trained offline with extensive test data and afterwards is applied to online tuning.