Kevin Förderer (M.Sc.)

Wissenschaftlicher Mitarbeiter

Werdegang

Kevin Förderer studierte von 2009 bis 2012 Wirtschaftsingenieurwesen und anschließend bis 2016 den Master-Studiengang Wirtschaftsmathematik am Karlsruher Institut für Technologie (KIT). Während des Studiums befasste er sich besonders mit den Themengebieten Operations Research, Statistik und Finance. Seit 2012 war er als Tutor und wissenschaftliche Hilfskraft am KIT tätig. Seine Tätigkeit umfasste unter anderem die Veranstaltungen "Einführung in das Operations Research", "Statistik" und "Algorithms for Internet Applications". In seiner Master Thesis "Optimal usage of decentralized energy in buildings" befasste sich Kevin Förderer mit Strategien zur Verwendung von dezentral erzeugter Energie in Gebäuden.

Seit 2016 ist Kevin Förderer als wissenschaftlicher Mitarbeiter am FZI Forschungszentrum Informatik im Forschungsbereich Intelligent Systems and Production Engineering (ISPE) tätig, wo er sich mit Energiemanagementsystemen für intelligente Gebäude beschäftigt.

Publikationen

Zeitungs- oder Zeitschriftenartikel (1)

1. Modeling flexibility using artificial neural networksInfoDetails

   Förderer, Kevin and Ahrens, Mischa and Bao, Kaibin and Mauser, Ingo and Schmeck, Hartmut, 2018

   The flexibility of distributed energy resources (DERs) can be modeled in various ways. Each model that can be used for creating feasible load profiles of a DER represents a potential model for the flexibility of that particular DER. Based on previous work, this paper presents generalized patterns for exploiting such models. Subsequently, the idea of using artificial neural networks in such patterns is evaluated. We studied different types and topologies of ANNs for the presented realization patterns and multiple device configurations, achieving a remarkably precise representation of the given devices in most of the cases. Overall, there was no single best ANN topology. Instead, a suitable individual topology had to be found for every pattern and device configuration. In addition to the best performing ANNs for each pattern and configuration that is presented in this paper all data from our experiments is published online. The paper is concluded with an evaluation of a classification based pattern using data of a real combined heat and power plant in a smart building.

Konferenzbeitrag (3)

1. Towards the Modeling of Flexibility Using Artificial Neural Networks in Energy Management and Smart Grids: NoteDetails

   Förderer, Kevin and Ahrens, Mischa and Bao, Kaibin and Mauser, Ingo and Schmeck, Hartmut, ACM, 2018

2. Demo abstract: a building energy management system in the context of the smart grid traffic light conceptInfoDetails

   Förderer, Kevin and Schmeck, Hartmut, 2017

   The BDEW smart grid traffic light concept is a framework to tackle some of the challenges posed by the transition of the energy system. In the project grid-control a system based on this concept has been implemented. This paper gives an overview of the system and outlines the building energy management system (BEMS) that will be installed and tested in a district battery storage system and five households as a part of this system. The BEMS utilizes a generic interface for exchanging and scheduling flexibility. The interface is based on an ideal battery model with time dependent constraints for power and energy. Daily, a schedule forecast for the following day is created by maximizing self-consumption utilizing consumption and production forecasts and locally available flexibility. An aggregated flexibility is then derived from this schedule forecast. The aggregated flexibility combined with the schedule forecast serve as basis for the actual schedule that is issued to the BEMS. Goal of the BEMS is schedule compliance while permitted by the traffic light phase.

3. Definition, Modeling, and Communication of Flexibility in Smart Buildings and Smart GridsDetails

   Mauser, Ingo and Müller, Jan and Förderer, Kevin and Schmeck, Hartmut, VDE, 2017

Export Suchergebnis .bib

Kontakt

Telefon: +49 721 9654-568
E-Mail: foerderer@dont-want-spam.fzi.de

Zurück