{"_id":"19603","publication":"arXiv:2005.04869","language":[{"iso":"eng"}],"title":"Towards a Scalable and Flexible Simulation and Testing Environment Toolbox for Intelligent Microgrid Control","year":"2020","author":[{"first_name":"Henrik","last_name":"Bode","full_name":"Bode, Henrik"},{"orcid":"0000-0002-9461-7372","last_name":"Heid","full_name":"Heid, Stefan Helmut","first_name":"Stefan Helmut","id":"39640"},{"last_name":"Weber","full_name":"Weber, Daniel","first_name":"Daniel"},{"id":"48129","first_name":"Eyke","full_name":"Hüllermeier, Eyke","last_name":"Hüllermeier"},{"first_name":"Oliver","last_name":"Wallscheid","full_name":"Wallscheid, Oliver"}],"oa":"1","user_id":"39640","abstract":[{"text":"Micro- and smart grids (MSG) play an important role both for integrating\r\nrenewable energy sources in conventional electricity grids and for providing\r\npower supply in remote areas. Modern MSGs are largely driven by power\r\nelectronic converters due to their high efficiency and flexibility.\r\nNevertheless, controlling MSGs is a challenging task due to highest\r\nrequirements on energy availability, safety and voltage quality within a wide\r\nrange of different MSG topologies. This results in a high demand for\r\ncomprehensive testing of new control concepts during their development phase\r\nand comparisons with the state of the art in order to ensure their feasibility.\r\nThis applies in particular to data-driven control approaches from the field of\r\nreinforcement learning (RL), whose stability and operating behavior can hardly\r\nbe evaluated a priori. Therefore, the OpenModelica Microgrid Gym (OMG) package,\r\nan open-source software toolbox for the simulation and control optimization of\r\nMSGs, is proposed. It is capable of modeling and simulating arbitrary MSG\r\ntopologies and offers a Python-based interface for plug \\& play controller\r\ntesting. In particular, the standardized OpenAI Gym interface allows for easy\r\nRL-based controller integration. Besides the presentation of the OMG toolbox,\r\napplication examples are highlighted including safe Bayesian optimization for\r\nlow-level controller tuning.","lang":"eng"}],"date_created":"2020-09-21T10:01:36Z","type":"preprint","status":"public","citation":{"mla":"Bode, Henrik, et al. “Towards a Scalable and Flexible Simulation and Testing Environment Toolbox for Intelligent Microgrid Control.” ArXiv:2005.04869, 2020.","apa":"Bode, H., Heid, S. H., Weber, D., Hüllermeier, E., & Wallscheid, O. (2020). Towards a Scalable and Flexible Simulation and Testing Environment Toolbox for Intelligent Microgrid Control. ArXiv:2005.04869.","bibtex":"@article{Bode_Heid_Weber_Hüllermeier_Wallscheid_2020, title={Towards a Scalable and Flexible Simulation and Testing Environment Toolbox for Intelligent Microgrid Control}, journal={arXiv:2005.04869}, author={Bode, Henrik and Heid, Stefan Helmut and Weber, Daniel and Hüllermeier, Eyke and Wallscheid, Oliver}, year={2020} }","short":"H. Bode, S.H. Heid, D. Weber, E. Hüllermeier, O. Wallscheid, ArXiv:2005.04869 (2020).","ieee":"H. Bode, S. H. Heid, D. Weber, E. Hüllermeier, and O. Wallscheid, “Towards a Scalable and Flexible Simulation and Testing Environment Toolbox for Intelligent Microgrid Control,” arXiv:2005.04869. 2020.","ama":"Bode H, Heid SH, Weber D, Hüllermeier E, Wallscheid O. Towards a Scalable and Flexible Simulation and Testing Environment Toolbox for Intelligent Microgrid Control. arXiv:200504869. 2020.","chicago":"Bode, Henrik, Stefan Helmut Heid, Daniel Weber, Eyke Hüllermeier, and Oliver Wallscheid. “Towards a Scalable and Flexible Simulation and Testing Environment Toolbox for Intelligent Microgrid Control.” ArXiv:2005.04869, 2020."},"date_updated":"2022-01-06T06:54:07Z","main_file_link":[{"url":"https://arxiv.org/pdf/2005.04869.pdf","open_access":"1"}]}