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

Inhalt:
In this paper, the inventive methods based on the neural network will be applied to construct the digital twins of the inverter-based feed-in generation in distribution power grid. By utilizing the digital twins model, the inverter can be replaced, which is able to be as the substitution to simulate the operation of the inverter. The paper is arranged in two parts: First of all, the average valule model of inverter is modelled. Afterwards, the proposed methods are clarified, which are, firstly, an online proportional integral 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 neural network identifier is, however, to replicate the dynamic character of the reference model by neural network which is initially trained offline with extensive test data and afterwards is applied to online tuning. Afterwards, two scenarios are simulated by digital twin based on the Cigré benchmark grid to estimate the states of inverter and the grid. The results illustrate that the state estimation by digital twinhas high similarity degree with the reference model.