Artificial Intelligence-Based Controller for Grid-Forming Inverter-Based Generators

This paper aims at developing artificial intelligence (AI)-based controllers for grid-forming inverter-based generators. The paper illustrates the relevance of the controller on a simplified isolated microgrid. The adopted AI approach relies on supervised learning, thus implying the need for training datasets. Firstly, the case study and the use cases were selected, and the scenarios were defined to create the training datasets from an experimentally validated virtual synchronous generator (VSG) controller. The use cases represent the black-start of the grid-forming inverter and the variation of the load demands as well as its characteristics. Then, the collected datasets were used to train the AI model, which was integrated in the control of a simulated inverter for testing and comparison with the VSG controller on the selected use cases. The proposed AI-based controller ensures the stability of a simplified microgrid, maintaining voltage and frequency at their nominal values. The continuity of supply is guaranteed and robust to changes in loads characteristics. Furthermore, the proposed controller shows fast responses to load variations in addition to high stability during the transitions between loads.