Fraunhofer-Institut für Angewandte Informationstechnik FIT

Filters

Reset filters

Settings
Now showing 1 - 10 of 27
  • Publication
    Eine strukturierte Methode zur IT-Systemanalyse für Energieflexibilität in der Industrie
    ( 2023)
    Kaymakci, Can
    ;
    Bauer, Dennis
    ;
    Sauer, Alexander
    ;
    Fabri, Lukas
    ;
    Wenninger, Simon
    ;
    Kracker, Florian
    Der Beitrag befasst sich mit der Entwicklung einer strukturierten Methode - dem FLEXIT-Audit - um relevante IT-Systeme für industrielle Energieflexibilität im Zusammenspiel mit unternehmensspezifischen Flexibilitätsmaßnahmen zu identifizieren und schlussendlich Handlungsempfehlungen für die Praxis und Implementierung abzuleiten.
  • Publication
    Determining the Product-Specific Energy Footprint in Manufacturing
    ( 2023)
    Pelger, Philipp
    ;
    Kaymakci, Can
    ;
    Wenninger, Simon
    ;
    Fabri, Lukas
    ;
    Sauer, Alexander
    In the energy transition context, the manufacturing industry moves into the spotlight, as it is responsible for significant proportions of global greenhouse gas emissions. The consequent pressure to decarbonize leads to suppliers needing to report and continuously reduce the energy consumption incurred in manufacturing supplied goods. To track the energy footprint of their products, manufacturing companies need to integrate energy data with process and planning data, enabling the tracing of the product-specific energy consumption on the shop floor level. Since manufacturing processes are prone to disturbances such as maintenance, the energy footprint of each product differs. Meanwhile, the demand for energy-efficiently produced products is increasing, supporting the development of a sustainability-focused procurement by OEMs. This paper addresses this development and outlines the technical requirements as well as how companies can identify product-specific energy consumption. Furthermore, a case study is conducted detailing how to determine the product-specific energy footprint.
  • Publication
    Structuring Federated Learning Applications - A Literature Analysis and Taxonomy
    ( 2023)
    Karnebogen, Philip
    ;
    Kaymakci, Can
    ;
    Willburger, Lukas
    ;
    Häckel, Björn
    ;
    Sauer, Alexander
    Ensuring data privacy is an essential objective competing with the ever-rising capabilities of machine learning approaches fueled by vast amounts of centralized data. Federated learning addresses this conflict by moving the model to the data while ensuring that the data itself does not leave a client's device. However, maintaining privacy impels new challenges concerning algorithm performance or fairness of the algorithm's results that remain uncovered from a sociotechnical perspective. We tackle this research gap by conducting a structured literature review and analyzing 152 articles to develop a taxonomy of federated learning applications consisting of nine dimensions and 25 characteristics. Our taxonomy illustrates how different attributes of federated learning affect trade-offs between an algorithm's privacy, performance, and fairness. Despite an increasing interest in the technical implementation of federated learning, our work is one of the first to emphasize an information systems perspective on this emerging and promising topic.
  • Publication
    Deriving Digital Energy Platform Archetypes for Manufacturing - A Data-Driven Clustering Approach
    ( 2023)
    Duda, Sebastian
    ;
    Fabri, Lukas
    ;
    Kaymakci, Can
    ;
    Wenninger, Simon
    ;
    Sauer, Alexander
    External factors such as climate change and the current energy crisis due to global conflicts are leading to the increasing relevance of energy consumption and energy procurement in the manufacturing industry. In addition to the growing call for sustainability, companies are increasingly struggling with rising energy costs and the power grid’s reliability, which endangers the competitiveness of companies and regions affected by high energy prices. Appropriate measures for energy-efficient and, not least, energy-flexible production are necessary. In addition to innovations and optimizations of plants and processes, digital energy platforms for the visualization, analysis, optimization, and control of energy flows are becoming essential. Over time, several digital energy platforms emerged on the market. The number and the different functionalities of the platforms make it challenging for classic manufacturing companies to keep track of and select the right digital energy platform. The characteristics and functionalities of digital energy platforms have already been identified and structured in literature. However, classifying existing platforms into archetypes makes it easier for companies to select the platforms providing the missing functionality. To tackle this issue, we conducted an explorative and data-driven cluster analysis based on 47 existing digital energy platforms to identify digital energy platform archetypes and derive implications for research and practice. The results show four different archetypes that primarily differ in terms of energy market integration functionalities: Research-Driven Energy Platforms, Energy Flexibility Platforms, SaaS-Aggregators / Virtual Power Plants, and (Manufacturing) IoT-Platforms. Decision makers in manufacturing companies will benefit from the archetypes in future analyses as decision support in procurement processes and modifications of digital energy platforms.
  • Publication
    Structuring the Digital Energy Platform Jungle: Development of a Multi-Layer Taxonomy and Implications for Practice
    ( 2022)
    Duda, Sebastian
    ;
    Bank, Lukas
    ;
    Kaymakci, Can
    ;
    Köberlein, Jana
    ;
    Wenninger, Simon
    ;
    Haubner, Tobias
    ;
    Sauer, Alexander
    ;
    Schilp, Johannes
    Rising and volatile energy prices are forcing production companies to optimize their consumption patterns and reduce carbon emissions to remain competitive. Demand-side management (DSM) or energy flexibility (EF) is a promising option for the active management of electricity demand. With DSM, energy procurement costs can be effectively reduced, for example, by reducing peak loads and taking advantage of volatile energy prices. In addition, renewable energies can be better integrated to reduce carbon emissions while stabilizing the power grid. Although the benefits of DSM for production companies are well known, implementation is not yet widespread. A key barrier is the high requirements of IT systems and the associated effort and complexity involved in setting them up. Companies often lack appropriate IT systems or have historically grown systems that do not allow continuous communication from the machine to the energy market. A variety of different platforms promise solutions to address these challenges. However, when selecting platforms, it is often unclear which aspects and functionalities of a platform are relevant for a company s specific application. To address this gap, we developed a multi-layer taxonomy of digital platforms for energy-related applications in the industry that includes a general, as well as a more specific data-centric and transaction-centric perspective. We develop, revise, and evaluate our taxonomy using insights from literature and analysis of 46 commercially available platforms or platforms developed through research projects. Based on our taxonomy, we derive implications for research and practice. Our results contribute to the descriptive knowledge of digital platforms in energy-related applications. Our taxonomy enables researchers and practitioners to classify such platforms and make informed decisions about their deployment.
  • Publication
    Energieflexibilität in der deutschen Industrie
    (Fraunhofer Verlag, 2022)
    Sauer, Alexander
    ;
    Buhl, Hans Ulrich
    ;
    Mitsos, Alexander
    ;
    Weigold, Matthias
    Energie aus erneuerbaren Ressourcen ist nicht immer beliebig verfügbar. Je nach Jahreszeit und Witterung variiert beispielsweise die durch Photovoltaik oder Windkraft zur Verfügung gestellte Leistung. Durch den kontinuierlichen Ausbau der erneuerbaren Energien wird sich die Volatilität im Energiesystem in Zukunft immer stärker ausprägen. Die Industrie auf die sich ändernden Versorgungsstrukturen vorzubereiten und anzupassen ist eine große Herausforderung der nächsten Jahrzehnte. Unternehmen müssen zukünftig ihre Prozesse und Betriebsorganisation so gestalten können, dass sich der Energieverbrauch zumindest in Teilen flexibel an das volatile Energieangebot anpassen kann – ein Paradigmenwechsel weg vom kontinuierlichen und rein nachfraggetriebenen Energieverbrauch hin zum anpassbaren, energieflexiblen Betrieb. Neben der Entwicklung von Technologien, Konzepten und Maßnahmen zur energetischen Flexibilisierung von industriellen Prozessen liegt ein zweiter Schwerpunkt zukünftiger Arbeiten auf der Entwicklung einer durchgängigen IT-Infrastruktur, mit der Unternehmen und Energieanbieter in Zukunft Energieflexibilität bestmöglich einsetzen können. Dieses Nachschlagewerk zeigt die Herausforderungen und Rahmenbedingungen von energieflexiblen Fabriken sowie Managementsysteme und Technologien für deren Realisierung. Es baut auf den wichtigsten Ergebnissen der Forschung im Rahmen der zweiten Phase des Kopernikus-Projekts SynErgie auf.
  • Publication
    Explainable Long-Term Building Energy Consumption Prediction using QLattice
    ( 2022)
    Wenninger, Simon
    ;
    Kaymakci, Can
    ;
    Wiethe, Christian
    The global building sector is responsible for nearly 40% of total carbon emissions, offering great potential to move closer to set climate goals. Energy performance certificates designed to increase the energy efficiency of buildings require accurate predictions of building energy performance. With significant advances in information and communication technology, data-driven methods have been introduced into building energy performance research demonstrating high computational efficiency and prediction performance. However, most studies focus on prediction performance without considering the potential of explainable artificial intelligence. To bridge this gap, the novel QLattice algorithm, designed to satisfy both aspects, is applied to a dataset of over 25,000 German residential buildings for predicting annual building energy performance. The prediction performance, computation time, and explainability of the QLattice is compared to the established machine learning algorithms artificial neural network, support vector regression, extreme gradient boosting, and multiple-linear regression in a case study, variable importance analyzed, and appropriate applications proposed. The results show quite strongly that the QLattice should be further considered in the research of energy performance certificates and may be a potential alternative to established machine learning algorithms for other prediction tasks in energy research.
  • Publication
    How Sustainable is Machine Learning in Energy Applications? - The Sustainable Machine Learning Balance Sheet
    ( 2022)
    Wenninger, Simon
    ;
    Kaymakci, Can
    ;
    Wiethe, Christian
    ;
    Römmelt, Jörg
    ;
    Baur, Lukas
    ;
    Häckel, Björn
    ;
    Sauer, Alexander
    Information Systems play a central role in the energy sector for achieving climate targets. With increasing digitization and data availability in the energy sector, data-driven machine learning (ML) approaches emerged, showing high potential. So far, research has focused on optimizing ML approaches’ prediction performance. However, this is a one-sided perspective. ML approaches require large computation times and capacities leading to high energy consumption. With the goal of sustainable energy systems, research on ML approaches should be extended to include the application’s energy consumption. ML solutions must be designed in such a way that the resulting savings in energy (and emissions) are greater than the energy consumption caused using the ML solution. To address this need, we develop the Sustainable Machine Learning Balance Sheet as a framework allowing to holistically evaluate and develop sustainable ML solutions which we validated in a case study and through expert interviews.
  • Publication
    Electricity Market Design 2030-2050: Shaping future electricity markets for a climate-neutral Europe
    ( 2021)
    Ahunbay, Mette Seref
    ;
    Ashour Novirdoust, Amir
    ;
    Bhuiyan, Rajon
    ;
    Bichler, Martin
    ;
    Bindu, Shilpa
    ;
    Bjørndal, Endre
    ;
    Bjørndal, Mette
    ;
    Buhl, Hans Ulrich
    ;
    Chaves-Ávila, José Pablo
    ;
    Gerard, Helena
    ;
    Gross, Stephan
    ;
    Hanny, Lisa
    ;
    Knörr, Johannes
    ;
    Köhnen, Clara Sophie
    ;
    Marques, Luciana
    ;
    Monti, Antonello
    ;
    Neuhoff, Karsten
    ;
    Neumann, Christoph
    ;
    Ocenic, Elena
    ;
    Ott, Marion
    ;
    Pichlmeier, Markus
    ;
    Richstein, Jörn C.
    ;
    Rinck, Maximilian
    ;
    Röhrich, Felix
    ;
    Röhrig, Paul Maximilian
    ;
    Sauer, Alexander
    ;
    Strüker, Jens
    ;
    Troncia, Matteo
    ;
    Wagner, Johannes
    ;
    Weibelzahl, Martin
    ;
    Zilke, Philip
  • Publication
    A Holistic Framework for AI Systems in Industrial Applications
    ( 2021)
    Kaymakci, Can
    ;
    Wenninger, Simon
    ;
    Sauer, Alexander
    Although several promising use cases for artificial intelligence (AI) for manufacturing companies have been identified, these are not yet widely used. Existing literature covers a variety of frameworks, methods and processes related to AI systems. However, the application of AI systems in manufacturing companies lacks a uniform understanding of components and functionalities as well as a structured process that supports developers and project managers in planning, implementing, and optimizing AI systems. To close this gap, we develop a generic conceptual model of an AI system for the application in manufacturing systems and a four-phase model to guide developers and project managers through the realization of AI systems.