TY - JOUR A1 - Nolting, Lars A1 - Spiegel, Thomas A1 - Reich, Marius A1 - Adam, Mario A1 - Praktiknjo, Aaron T1 - Can energy system modeling benefit from artificial neural networks? Application of two-stage metamodels to reduce computation of security of supply assessments JF - Computers & Industrial Engineering KW - KIVi Y1 - 2020 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:hbz:due62-opus-26979 SN - 0360-8352 VL - 142 PB - Elsevier ER - TY - CHAP A1 - Nolting, Lars A1 - Spiegel, Thomas A1 - Reich, Marius A1 - Adam, Mario A1 - Praktiknjo, Aaron T1 - Can Energy System Modeling benefit from Artificial Neural Networks? Application of Two-Stage Metamodels to Reduce Computation of Security of Supply Assessments (Best Application Paper Award) T2 - CIE – 48th International Conference on Computers & Industrial Engineering, 02.-05.12.2018, Auckland / New Zealand KW - KIVi Y1 - 2018 CY - Auckland ER - TY - JOUR A1 - Münch, Justin A1 - Priesmann, Jan A1 - Reich, Marius A1 - Tillmanns, Marius A1 - Praktiknjo, Aaron A1 - Adam, Mario T1 - Uplifting the Complexity of Analysis for Probabilistic Security of Electricity Supply Assessments using Artificial Neural Networks JF - Energy and AI N2 - The energy sector faces rapid decarbonisation and decision-makers demand reliable assessments of the security of electricity supply. For this, detailed simulation models with a high temporal and technological resolution are required. When confronted with increasing weather-dependent renewable energy generation, probabilistic simulation models have proven. The significant computational costs of calculating a scenario, however, limit the complexity of further analysis. Advances in code optimization as well as the use of computing clusters still lead to runtimes of up to eight hours per scenario. However ongoing research highlights that tailor-made approximations are potentially the key factor in further reducing computing time. Consequently, current research aims to provide a method for the rapid prediction of widely varying scenarios. In this work artificial neural networks (ANN) are trained and compared to approximate the system behavior of the probabilistic simulation model. To do so, information needs to be sampled from the probabilistic simulation in an efficient way. Because only a limited space in the whole design space of the 16 independent variables is of interest, a classification is developed. Finally it required only around 35 minutes to create the regression models, including sampling the design space, simulating the training data and training the ANNs. The resulting ANNs are able to predict all scenarios within the validity range of the regression model with a coefficient of determination of over 0.9998 for independent test data (1.051.200 data points). They need only a few milliseconds to predict one scenario, enabling in-depth analysis in a brief period of time. KW - Security of electricity supply KW - Probabilistic simulation KW - Metamodeling KW - Artificial neural networks KW - Regression KW - HSD Publikationsfonds KW - DFG Publikationskosten KW - KIVi Y1 - 2024 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:hbz:due62-opus-45359 SN - 2666-5468 N1 - Funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) - 532148125 and supported by the central publication fund of Hochschule Düsseldorf University of Applied Sciences. PB - Elsevier ER - TY - JOUR A1 - Priesmann, Jan A1 - Münch, Justin A1 - Tillmanns, Marius A1 - Ridha, E. A1 - Spiegel, Thomas A1 - Reich, Marius A1 - Adam, Mario A1 - Nolting, L. A1 - Praktiknjo, Aaron T1 - Artificial intelligence and design of experiments for resource adequacy assessment in power systems JF - Energy Strategy Reviews KW - KiVi KW - Design of experiments KW - Resource adequacy KW - Security of supply KW - Artificial intelligence KW - KIVi Y1 - 2024 U6 - https://doi.org/10.1016/j.esr.2024.101368 SN - 2211-467X VL - 53 PB - Elsevier ER - TY - CHAP A1 - Dörr, Dominik A1 - Münch, Justin A1 - Adam, Mario ED - Wesselak, Viktor T1 - Hochaufgelöste Langzeitprognose des deutschen Strom-Importpotenzials mithilfe von Methoden des Maschinellen Lernens T2 - RET.Con 2024. 7. Regenerative Energietechnik Konferenz in Nordhausen, 08.-09. Februar 2024. Tagungsband KW - KIVi Y1 - 2024 UR - https://web.archive.org/web/20250814134117/https://www.hs-nordhausen.de/wp-content/uploads/sites/8/2024/08/RETCon_2024_Tagungsband.pdf SN - 978-3-940820-23-5 SP - 71 EP - 78 CY - Nordhausen ER -