@misc{LindnerMehlBartoszuketal.2025, author = {Lindner, Niels and Mehl, Lukas and Bartoszuk, Karolina and Berendes, Sarah and Zittel, Janina}, title = {Demand Uncertainty in Energy Systems: Scenario Catalogs vs. Integrated Robust Optimization}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-102404}, year = {2025}, abstract = {Designing efficient energy systems is indispensable for shaping a more sustainable society. This involves making infrastructure investment decisions that must be valid for a long-term time horizon. While energy system optimization models constitute a powerful technique to support planning decisions, they need to cope with inherent uncertainty. For example, predicting future demand on a scale of decades is not only an intricate challenge in itself, but small fluctuations in such a forecast might also largely impact the layout of a complex energy system. In this paper, we compare two methodologies of capturing demand uncertainty for linear-programming based energy system optimization models. On one hand, we generate and analyze catalogs of varying demand scenarios, where each individual scenario is considered independently, so that the optimization produces scenario-specific investment pathways. On the other hand, we make use of robust linear programming to meet the demand of all scenarios at once. Since including a multitude of scenarios increases the size and complexity of the optimization model, we will show how to use warm-starting approaches to accelerate the computation process, by exploiting the similar structure of the linear program across different demand inputs. This allows to integrate a meaningful number of demand scenarios with fully-fledged energy system models. We demonstrate the practical use of our methods in a case study of the Berlin-Brandenburg area in Germany, a region that contains both a metropolitan area and its rural surroundings. As a backbone, we use the open-source framework oemof to create a sector-coupled optimization model for planning an energy system with up to 100\% reduction of greenhouse gas emissions. This model features a fine-grained temporal resolution of one hour for the full year 2050. We consider uncertainty in demand for electricity, hydrogen, natural gas, central, and decentral heat. Based on our computations, we analyze the trade-offs in terms of quality and computation time for scenario catalogs and the robust optimization approach. We further demonstrate that our procedure provides a valuable strategy for decision makers to gain insight on the robustness and sensitivity of solutions regarding demand variability.}, language = {en} } @misc{ZakiyevaPetkovic2025, author = {Zakiyeva, Nazgul and Petkovic, Milena}, title = {Large-scale functional network time series model solved with mathematical programming approach}, journal = {Econometrics and Statistics}, doi = {10.1016/j.ecosta.2025.10.001}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-101936}, year = {2025}, abstract = {A functional network autoregressive model is proposed for studying large-scale network time series observed at high temporal resolution. The model incorporates high-dimensional curves to capture both serial and cross-sectional dependence in large-scale network functional time series. Estimation of the model is approached using a Mixed Integer Optimization method. Simulation studies confirm the consistency of parameter and adjacency matrix estimation. The method is applied to data from a real-life natural gas supply network. Compared to alternative prediction models, the proposed model delivers more accurate day-ahead hourly out-of-sample forecasts of the gas inflows and outflows at most gas nodes.}, language = {en} } @misc{ShinanoVigerske2025, author = {Shinano, Yuji and Vigerske, Stefan}, title = {Smoothie: Mixing the strongest MIP solvers to solve hard MIP instances on supercomputers - Phase I development}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-101906}, year = {2025}, abstract = {Mixed-Integer Linear Programming (MIP) is applicable to such a wide range of real-world decision problems that the competition for the best code to solve such problems has lead to tremendous progress over the last decades. While current solvers can solve some of the problems that seemed completely out-of-reach just 10 years ago, there are always relevant MIP problems that currently cannot be solved. With the Smoothie solver we intend to solve extremely hard MIP problems by building on the many years that went into the development of several state-of-the-art MIP solvers and by utilizing some of the largest computing resources available. The high-level task parallelization framework UG (Ubiquity Generator) is used and extended by Smoothie to build a solver that uses large-scale parallelization to distribute the solution of a single MIP on a shared- or distributed-memory computing infrastructure, thereby employing several established MIP solvers simultaneously. For the first development phase, which is the topic of this report, both FICO Xpress and Gurobi are used in concurrent mode on a single machine, while information on incumbent solutions and explored branch-and-bound subtrees is exchanged. A dynamic restarting mechanism ensures that solver configurations are selected that promise most suitable for the MIP to be solved. We report on initial findings using this early version of Smoothie on unsolved problems from MIPLIB 2017.}, language = {en} } @misc{PedersenLindnerRehfeldtetal.2025, author = {Pedersen, Jaap and Lindner, Niels and Rehfeldt, Daniel and Koch, Thorsten}, title = {Comparing Branching Rules for the Quota Steiner Tree Problem with Interference}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-101250}, year = {2025}, abstract = {Branching decisions play a crucial role in branch-and-bound algorithms for solving combinatorial optimization problems. In this paper, we investigate several branching rules applied to the Quota Steiner Tree Problem with Interference (QSTPI). The Quota Steiner Tree Problem (QSTP) generalizes the classical Steiner Tree Problem (STP) in graphs by seeking a minimum-cost tree that connects a subset of profit-associated vertices to meet a given quota. The extended version, QSTPI, introduces interference among vertices: Selecting certain vertices simultaneously reduces their individual contributions to the overall profit. This problem arises, for example, in positioning and connecting wind turbines, where turbines possibly shadow other turbines, reducing their energy yield. While exact solvers for standard STP-related problems often rely heavily on reduction techniques and cutting-plane methods - rarely generating large branch-and-bound trees - experiments reveal that large instances of QSTPI require significantly more branching to compute provably optimal solutions. In contrast to branching on variables, we utilize the combinatorial structure of the QSTPI by branching on the graph's vertices. We adapt classical and problem-specific branching rules and present a comprehensive computational study comparing the effectiveness of these branching strategies.}, language = {en} } @misc{MehlLindnerBartoszuketal.2025, author = {Mehl, Lukas and Lindner, Niels and Bartoszuk, Karolina and Zittel, Janina}, title = {Prototypical warm-starts for demand-robust LP-based energy system optimization}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-101242}, year = {2025}, abstract = {The expressiveness of energy system optimization models (ESOMs) depends on a multitude of exogenous parameters. For example, sound estimates of the future energy demand are essential to enable qualified decisions on long-term investments. However, the enormous demand fluctuations even on a fine-grained scale diminish the computational performance of large-scale ESOMs. We therefore propose a clustering-and-decomposition method for linear programming based ESOMs that first identifies and solves prototypical demand scenarios with the dual simplex algorithm, and then composes dual optimal prototype bases to a warm-start basis for the full model. We evaluate the feasibility and computational efficiency our approach on a real-world case study, using a sector-coupled ESOM with hourly resolution for the Berlin-Brandenburg area in Germany, based on the oemof framework.}, language = {en} } @misc{RiedmuellerZittelKoch2025, author = {Riedm{\"u}ller, Stephanie and Zittel, Janina and Koch, Thorsten}, title = {Warm-starting Strategies in Scalarization Methods for Multi-Objective Optimization}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-101073}, year = {2025}, abstract = {We explore how warm-starting strategies can be integrated into scalarization-based approaches for multi-objective optimization in (mixed) integer linear programming. Scalarization methods remain widely used classical techniques to compute Pareto-optimal solutions in applied settings. They are favored due to their algorithmic simplicity and broad applicability across continuous and integer programs with an arbitrary number of objectives. While warm-starting has been applied in this context before, a systematic methodology and analysis remain lacking. We address this gap by providing a theoretical characterization of warm-starting within scalarization methods, focusing on the sequencing of subproblems. However, optimizing the order of subproblems to maximize warm-start efficiency may conflict with alternative criteria, such as early identification of infeasible regions. We quantify these trade-offs through an extensive computational study.}, language = {en} } @inproceedings{KuntBuchholzKhebourietal.2025, author = {Kunt, Tim and Buchholz, Annika and Khebouri, Imene and Koch, Thorsten and Litzel, Ida and Vu, Thi Huong}, title = {Mapping the Web of Science, a large-scale graph and text-based dataset with LLM embeddings}, booktitle = {Operations Research Proceedings 2025. OR 2025}, issn = {1438-0064}, doi = {10.12752/10064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-100646}, year = {2025}, abstract = {Large text data sets, such as publications, websites, and other text-based media, inherit two distinct types of features: (1) the text itself, its information conveyed through semantics, and (2) its relationship to other texts through links, references, or shared attributes. While the latter can be described as a graph structure and can be handled by a range of established algorithms for classification and prediction, the former has recently gained new potential through the use of LLM embedding models. Demonstrating these possibilities and their practicability, we investigate the Web of Science dataset, containing ~56 million scientific publications through the lens of our proposed embedding method, revealing a self-structured landscape of texts.}, language = {en} } @misc{KempkeKoch2025, author = {Kempke, Nils-Christian and Koch, Thorsten}, title = {A GPU accelerated variant of Schroeppel-Shamir's algorithm for solving the market split problem}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-100554}, year = {2025}, abstract = {The market split problem (MSP), introduced by Cornu{\´e}jols and Dawande (1998), is a challenging binary optimization problem that performs poorly on state-of-the-art linear programming-based branch-and-cut solvers. We present a novel algorithm for solving the feasibility version of this problem, derived from Schroeppel-Shamir's algorithm for the one-dimensional subset sum problem. Our approach is based on exhaustively enumerating one-dimensional solutions of MSP and utilizing GPUs to evaluate candidate solutions across the entire problem. The resulting hybrid CPU-GPU implementation efficiently solves instances with up to 10 constraints and 90 variables. We demonstrate the algorithm's performance on benchmark problems, solving instances of size (9, 80) in less than fifteen minutes and (10, 90) in up to one day.}, language = {en} } @misc{VuLitzelKoch2025, author = {Vu, Thi Huong and Litzel, Ida and Koch, Thorsten}, title = {Similarity-based fuzzy clustering scientific articles: potentials and challenges from mathematical and computational perspectives}, arxiv = {http://arxiv.org/abs/2506.04045}, year = {2025}, abstract = {Fuzzy clustering, which allows an article to belong to multiple clusters with soft membership degrees, plays a vital role in analyzing publication data. This problem can be formulated as a constrained optimization model, where the goal is to minimize the discrepancy between the similarity observed from data and the similarity derived from a predicted distribution. While this approach benefits from leveraging state-of-the-art optimization algorithms, tailoring them to work with real, massive databases like OpenAlex or Web of Science -- containing about 70 million articles and a billion citations -- poses significant challenges. We analyze potentials and challenges of the approach from both mathematical and computational perspectives. Among other things, second-order optimality conditions are established, providing new theoretical insights, and practical solution methods are proposed by exploiting the problem's structure. Specifically, we accelerate the gradient projection method using GPU-based parallel computing to efficiently handle large-scale data.}, language = {en} } @misc{VuKoch2025, author = {Vu, Thi Huong and Koch, Thorsten}, title = {Clustering scientific publications: lessons learned through experiments with a real citation network}, arxiv = {http://arxiv.org/abs/2505.18180}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-100418}, year = {2025}, abstract = {Clustering scientific publications helps uncover research structures within bibliographic databases. Graph-based methods such as spectral, Louvain, and Leiden clustering are commonly used due to their ability to model citation networks. However, their effectiveness can diminish when applied to real-world data. This study evaluates these clustering algorithms on a citation graph of about 700,000 articles and 4.6 million citations from the Web of Science. The results show that while scalable methods like Louvain and Leiden perform efficiently, their default settings often yield poor partitioning. Meaningful outcomes require careful parameter tuning, especially for large networks with uneven structures, including a dense core and loosely connected papers. These findings highlight practical lessons about the challenges of large-scale data, method selection and tuning based on specific structures of bibliometric clustering tasks.}, language = {en} }