Towards a Scalable and Flexible Simulation and Testing Environment Toolbox for Intelligent Microgrid Control

Bode, Henrik; Heid, Stefan; Weber, Daniel; Hüllermeier, Eyke und Wallscheid, Oliver (Mai 2020): Towards a Scalable and Flexible Simulation and Testing Environment Toolbox for Intelligent Microgrid Control. In: Journal of Open Source Software, Bd. 5, Nr. 54: S. 2435

Abstract

The OpenModelica Microgrid Gym (OMG) toolbox provides a transient simulation framework for local energy grids based on power electronic converters. OpenModelica is used as the backend, allowing users to set up arbitrary electric grid designs via its well-known graphical user interface in a plug-and-play fashion (Fritzson et al., 2018). Simulations can be configured using a python interface, making it easy to integrate software modules for the realization and testing of closed control loops. In addition, the OpenAI Gym interface is provided to connect data-driven reinforcement learning algorithms for investigating intelligent microgrid control approaches (Brockman et al., 2016).

• Dokumententyp: Zeitschriftenartikel
• Publikationsform: Publisher's Version
• Keywords: OpenModelica, Microgrids, Reinforcement Learning, Energy Systems, Simulation Testing, Control
• Fakultät: Mathematik, Informatik und Statistik > Informatik > Künstliche Intelligenz und Maschinelles Lernen
• Themengebiete: 000 Informatik, Informationswissenschaft, allgemeine Werke > 004 Informatik
• ISSN: 2475-9066
• Sprache: Englisch