Settings

Now showing1 - 4 of 4
  • Some of the metrics are blocked by your 
    consent settings
    Item type:Publication, Access status: with files ,
    Kategoriebasierte Lastprognose in Niederspannungsnetzen zur Day-Ahead-Koordinierung haushaltsnaher Flexibilität
    (2025)
    Lindner, Joost Henning
    The increasing share of decentralized producers and flexible consumers complicates the maintenance of grid stability and raises the requirements for the control and monitoring of distribution networks. As part of a research project, a coordination function (COF) is being developed that performs day-ahead scheduling of flexible household loads to proactively prevent grid congestion. Since the schedule data of many households are incomplete, uncertainties arise in grid assessment and flexibility planning. This work addresses this issue and extends the existing concept by developing a forecasting method that provides the COF with a complete and reliable data basis. To this end, a data-driven approach is developed that applies the HDBSCAN clustering algorithm to categorize households with similar technical characteristics and consumption behavior, thereby forming representative load profiles. Missing schedules can thus be plausibly reconstructed. Subsequently, a gradient boosting regression refines the cluster-based forecasts by incorporating additional influencing factors such as weather, price, and grid data. The results demonstrate that the combination of clustering and regression analysis provides an effective approach for forecasting household schedules. This highly improves the data foundation for the COF and enables robust load forecasting even under limited data availability. The cluster forecast provides a high level of predictive accuracy at the aggregated level, while the regression analysis further improves accuracy at the household level. Individual households with highly specific consumption patterns can only be represented to a limited extent, which may affect the efficient use of flexibility in the grid but has only a minor impact on the overall reliability of the forecast. Future work should integrate real smart meter data to validate and improve the model quality and examine the use of deep learning-based methods to capture complex temporal patterns and short-term consumption changes even more accurately.
    Publicationtype: Master Thesis
      65  39
  • Some of the metrics are blocked by your 
    consent settings
    Item type:Publication, Access status: with files ,
    Deep learning assisted heuristics and exact methods for the vehicle routing problem with side constraints
    (2025)
    Dornemann, Jorin
    ;
    Taraz, Anusch
    This thesis addresses vehicle routing problems (VRP) with complex side constraints, focusing on developing deep learning-assisted heuristic methods that deliver near-optimal solutions. We propose novel approaches for the capacitated VRP with time windows by integrating graph convolutional neural networks into heuristic methods. These networks predict promising edges that are utilized to enhance the efficiency of heuristics. Additionally,we explore the integration of quantum-inspired computing within heuristic frameworks, designing a hybrid heuristic that combines deep learning with specialized quantum-inspired hardware to enhance scalability and solve larger instances more effectively.
    Publicationtype: Doctoral Thesis
      58  437
  • Some of the metrics are blocked by your 
    consent settings
    Item type:Publication, Access status: with files ,
    Entwicklung und öko-temporale Analyse von Ansätzen zur Regulierung von Flugfrequenzen
    (Deutsches Zentrum für Luft- und Raumfahrt e.V. (DLR), 2023)
    Presto, Felix
    ;
    Gollnick, Volker
    In this thesis, different approaches to regulate flight frequency (number of daily flights on a route) are analyzed according to ecologic-economic-temporal criteria. For this purpose, a two-step model for frequency reduction (FRED) is developed. The first step consists of 8 alternative frequency regulation approaches. In the second step, a fleet mix is assigned to frequency-reduced routes by keeping the available seat capacity constant. As a result of operating larger aircraft and fewer flights, minor (aircraft direct operating cost, fuel consumption) to notable (delays) efficiency gains are possible, however, these are limited by aircraft type availability, seasonal demand and regulatory risks.
    Publicationtype: Doctoral Thesis
      146  575
  • Some of the metrics are blocked by your 
    consent settings
    Item type:Publication, Access status: with files ,
    Optimierung der Auftragszuordnung in strategischen Projektnetzwerken unter Berücksichtigung von Risiken : dargestellt am Beispiel der Windenergiebranche
    (2020-02-15)
    Koschate, Bernd-Paul
    ;
    Kersten, Wolfgang
    Optimization of order allocations considering risks in strategic project networks - Applied in the wind energy sector Existing methods focus on the design of enduring value networks. However, the historical development of value chains shows a shift towards project-based cooperation in temporary production networks, for example in the wind energy sector. The present study examines the question of how an overall cost reduction can be achieved consisting of components, logistics and risk related costs using a network and order allocation optimization. The developed methodology covers a planning process that assess-es the total network cost and optimizes the allocation of suppliers and wind farms. In a case study, the methodology is evaluated and the embedded optimization model is validated.
    Publicationtype: Doctoral Thesis
      714  951