Abstract
Currently, a transition of the electrical power system occurs that results in replacing large-scale thermal power plants at transmission grid level by small generation units mainly installed in the distribution grid. A shift from the transmission to the distribution grid level and an increase in ancillary service demand is a direct result of this transition, demanding delegation of liabilities to distributed, small energy resources. Decoder-based methods currently are not able to cope with ensembles of individually acting energy resources. Aggregating flexibilities results in folded distributions with unfavorable properties for machine learning decoders. Nevertheless, a combined training set is needed to integrate e. g., a hotel, a small business, or similar with an ensemble of co-generation, heat pump, solar power, or controllable consumers to a single flexibility model. Thus, we improved the training process and use evolution strategies for sampling ensembles.
Zusammenfassung
Aktuell ist ein Umbruch in der Energieversorgung zu beobachten, bei dem große Thermalkraftwerke im Übertragungsnetz ersetzt werden durch kleine regenerative Erzeuger im Verteilnetz. Diese Verlagerung zusammen mit einem steigenden Bedarf an Regelenergie erfordert einen stärkeren Einbezug kleiner verteilter Anlagen in die verantwortliche Netzführung. Dekoder-basierte Methoden zur Sicherstellung der Umsetzbarkeit algorithmischer Planung können aktuell keine Zusicherungen für Anlagenverbünde beschreiben. Die Aggregation von Flexibilitäten in Verbünden resultiert in gefalteten Verteilungen, welche sich für Machine-Learning-Verfahren als ungeeignet erweisen. Dennoch werden zukünftig Erweiterungen für Verbünde wie beispielsweise Hotels, Fertigungsstraßen, o.ä. benötigt, um die Verbundflexibilitäten geeignet zu modellieren. Dieser Beitrag untersucht den Einsatz einer Evolutionsstrategie für die Erstellung geeigneter Flexibilitätsmodelle von Verbünden.
About the authors
Jörg Bremer works as a postdoctoral researcher at the department of Energy Informatics at the University of Oldenburg. He received his doctorate at the University of Oldenburg in 2015 and has been working in many national and international research projects in the field of computational intelligence and decentralized algorithms for smart energy management at the university and at the OFFIS Institute for Information Technology. At the University of Oldenburg he also teaches in the field of algorithmics and smart grid - in the past also in cooperation with the Technical Universities of Brunswick and Clausthal. His research interests include theoretical computational intelligence and its application to the environmental and energy domain as well as decentralized artificial intelligence and agent-based systems. Dr. Bremer is author of more than 70 refereed and peer-reviewed scientific publications.
Sebastian Lehnhoff is a Full Professor for Energy Informatics at the University of Oldenburg. He received his doctorate at the TU Dortmund University in 2009. Prof. Lehnhoff is a member of the executive board of the OFFIS Institute for Information Technology and speaker of its Energy R&D division. He is speaker of the section „Energy Informatics“ within the German Informatics Society (GI), assoc. editor of the IEEE Computer Society’s Computing and Smart Grid Special Technical Community as well as an active member of numerous committees and working groups focusing on ICT in future Smart Grids. Prof. Lehnhoff is CTO of openKONSEQUENZ e.G. – registered co-operative industry association for the development of modular open source SCADA/EMS. He serves as an Executive Committee Member of the ACM Emerging Interest Group on Energy Systems and Informatics (EIG-ENERGY), Steering Committee member of the EIG flagship conference E-Energy and as a founding Board Member of SpringerOpen journal on Energy Informatics. Prof. Lehnhoff is author of over 150 refereed and peer-reviewed scientific publications.
References
1. M. Sonnenschein, O. Lünsdorf, J. Bremer and M. Tröschel, “Decentralized control of units in smart grids for the support of renewable energy supply,” Environmental Impact Assessment Review, 2014.10.1016/j.eiar.2014.08.004Search in Google Scholar
2. Ł. B. Nikonowicz and J. Milewski, “Virtual power plants – general review: structure, application and optimization.” Journal of Power Technologies, vol. 92, no. 3, 2012. [Online]. Available: http://papers.itc.pw.edu.pl/index.php/JPT/article/view/284/492.Search in Google Scholar
3. S. Thiem, V. Danov, M. Metzger, J. Schäfer and T. Hamacher, “Project-level multi-modal energy system design-novel approach for considering detailed component models and example case study for airports,” Energy, vol. 133, pp. 691–709, 2017.10.1016/j.energy.2017.05.159Search in Google Scholar
4. M. Pehnt, M. Cames, C. Fischer, B. Praetorius, L. Schneider, K. Schumacher and J.-P. Voß, “Micro cogeneration,” in: Towards decentralized energy systems. Berlin/Heidelberg, 2005.Search in Google Scholar
5. C. Hinrichs and M. Sonnenschein, “A distributed combinatorial optimisation heuristic for the scheduling of energy resources represented by self-interested agents,” International Journal of Bio-Inspired Computation, vol. 10, p. 69, 07 2017.10.1504/IJBIC.2017.085895Search in Google Scholar
6. A. Nieße, S. Lehnhoff, M. Tröschel, M. Uslar, C. Wissing, H. J. Appelrath and M. Sonnenschein, “Market-based self-organized provision of active power and ancillary services: An agent-based approach for smart distribution grids,” in Complexity in Engineering (COMPENG), 2012, June 2012, pp. 1–5.10.1109/CompEng.2012.6242953Search in Google Scholar
7. J. Bremer and M. Sonnenschein, “Constraint-handling for optimization with support vector surrogate models – a novel decoder approach,” in ICAART 2013 – Proceedings of the 5th International Conference on Agents and Artificial Intelligence, J. Filipe and A. Fred, Eds., vol. 2. Barcelona, Spain: SciTePress, 2013, pp. 91–105.Search in Google Scholar
8. J. Bremer and S. Lehnhoff, Hybrid Multi-ensemble Scheduling. Cham: Springer International Publishing, 2017, pp. 342–358. [Online]. Available: http://dx.doi.org/10.1007/978-3-319-55849-3_23.10.1007/978-3-319-55849-3_23Search in Google Scholar
9. J. Bremer and S. Lehnhoff, “Phase-space sampling of energy ensembles with cma-es,” in Applications of Evolutionary Computation, K. Sim and P. Kaufmann, Eds. Cham: Springer International Publishing, 2018, pp. 222–230.10.1007/978-3-319-77538-8_16Search in Google Scholar
10. J. Bremer and S. Lehnhoff, “Unfolding ensemble training sets for improved support vector decoders in energy management,” in Proceedings of the 10th International Conference on Agents and Artificial Intelligence – Volume 2: ICAART, INSTICC. SciTePress, 2018, pp. 322–329.10.5220/0006543503220329Search in Google Scholar
11. C. Hinrichs, J. Bremer and M. Sonnenschein, “Distributed Hybrid Constraint Handling in Large Scale Virtual Power Plants,” in IEEE PES Conference on Innovative Smart Grid Technologies Europe (ISGT Europe 2013). IEEE Power & Energy Society, 2013.10.1109/ISGTEurope.2013.6695312Search in Google Scholar
12. S. McArthur, E. Davidson, V. Catterson, A. Dimeas, N. Hatziargyriou, F. Ponci and T. Funabashi, “Multi-agent systems for power engineering applications, Part I,” IEEE Transactions on Power Systems, vol. 22, no. 4, pp. 1743–1752, 2007.10.1109/TPWRS.2007.908471Search in Google Scholar
13. J. Bremer and S. Lehnhoff, “A decentralized PSO with decoder for scheduling distributed electricity generation,” in Applications of Evolutionary Computation: 19th European Conference EvoApplications (1), Lecture Notes in Computer Science, vol. 9597. G. Squillero and P. Burelli, Eds., Porto, Portugal: Springer, 2016, pp. 427–442.10.1007/978-3-319-31204-0_28Search in Google Scholar
14. G. Weiss, Multiagent Systems: A Modern Approach to Distributed Artificial Intelligence, vol. 1 07 (2000), pp. 648.Search in Google Scholar
15. M. Wooldridge, “Intelligent agents: The key concepts,” vol. 2322, pp. 3–43, 07 2001.10.1007/3-540-45982-0_1Search in Google Scholar
16. S. D. Ramchurn, P. Vytelingum, A. Rogers and N. R. Jennings, “Putting the ‘smarts’ into the smart grid: A grand challenge for artificial intelligence,” Commun. ACM, vol. 55, no. 4, pp. 86–97, Apr. 2012.10.1145/2133806.2133825Search in Google Scholar
17. J. Bremer, B. Rapp and M. Sonnenschein, “Support vector based encoding of distributed energy resources’ feasible load spaces,” in IEEE PES Conference on Innovative Smart Grid Technologies Europe, Chalmers Lindholmen, Gothenburg, Sweden, 2010.10.1109/ISGTEUROPE.2010.5638940Search in Google Scholar
18. D. M. J. Tax and R. P. W. Duin, “Support vector data description,” Mach. Learn., vol. 54, no. 1, pp. 45–66, 2004.10.1023/B:MACH.0000008084.60811.49Search in Google Scholar
19. J. Neugebauer, J. Bremer, C. Hinrichs, O. Kramer and M. Sonnenschein, “Generalized cascade classification model with customized transformation based ensembles,” in IJCNN, 2016.10.1109/IJCNN.2016.7727727Search in Google Scholar
20. J. Bremer and S. Lehnhoff., “A cascading chi-shapes based decoder for constraint-handling in distributed energy management,” in: Proceedings of the 10th International Joint Conference on Computational Intelligence – Volume 1: IJCCI, INSTICC. SciTePress, 2018, pp. 184–191.10.5220/0006926101840191Search in Google Scholar
21. P. Hall, “The distribution of means for samples of size n drawn from a population in which the variate takes values between 0 and 1, all such values being equally probable,” Biometrika, vol. 19, no. 3/4, pp. pp. 240–245, 1927.10.1093/biomet/19.3-4.240Search in Google Scholar
22. M. Duckham, L. Kulik, M. Worboys and A. Galton, “Efficient generation of simple polygons for characterizing the shape of a set of points in the plane,” Pattern Recognition, vol. 41, no. 10, pp. 3224–3236, 2008. [Online]. Available: http://www.sciencedirect.com/science/article/pii/S0031320308001180.10.1016/j.patcog.2008.03.023Search in Google Scholar
23. N. Hansen, “The CMA Evolution Strategy: A Tutorial,” Tech. Rep., 2011. [Online]. Available: www.lri.fr/ hansen/cmatutorial.pdf.Search in Google Scholar
© 2020 Walter de Gruyter GmbH, Berlin/Boston
