@article{64870, author = {{Meyer, Marcel and Zapata Gonzalez, David Ricardo and Kaltenpoth, Sascha Benjamin and Müller, Oliver}}, issn = {{2169-3536}}, journal = {{IEEE Access}}, pages = {{218141--218153}}, publisher = {{Institute of Electrical and Electronics Engineers (IEEE)}}, title = {{{Benchmarking Time Series Foundation Models for Short-Term Household Electricity Load Forecasting}}}, doi = {{10.1109/access.2025.3648056}}, volume = {{13}}, year = {{2025}}, } @inproceedings{60680, abstract = {{Classical machine learning techniques often struggle with overfitting and unreliable predictions when exposed to novel conditions. Introducing causality into the modelling process offers a promising way to mitigate these challenges by enhancing predictive robustness. However, constructing an initial causal graph manually using domain knowledge is time-consuming, particularly in complex time series with numerous variables. To address this, causal discovery algorithms can provide a preliminary causal structure that domain experts can refine. This study investigates causal feature selection with domain knowledge using a data center system as an example. We use simulated time-series data to compare different causal feature selection with traditional machine-learning feature selection methods. Our results show that predictions based on causal features are more robust compared to those derived from traditional methods. These findings underscore the potential of combining causal discovery algorithms with human expertise to improve machine learning applications.}}, author = {{Zapata Gonzalez, David Ricardo and Meyer, Marcel and Müller, Oliver}}, keywords = {{Causal Machine Learning, Causality in Time Series, Causal Discovery, Human-Machine Collaboration}}, location = {{Amman, Jordan}}, title = {{{Bridging the gap between data-driven and theory-driven modelling – leveraging causal machine learning for integrative modelling of dynamical systems}}}, year = {{2025}}, } @inproceedings{63397, abstract = {{Decarbonizing industrial process heat is a crucial step in mitigating climate change. While Process Mining (PM) has gained traction in sustainability research—such as optimizing production scheduling to reduce energy use or accounting for carbon footprints—it has largely overlooked the challenges and opportunities related to thermal energy, accounting for 66% of total energy demand in industrial processes. At the same time, Heat Integration (HI) is an established engineering discipline focused on maximizing the efficiency of thermal energy systems. However, HI traditionally relies on static or incomplete data about energy demands, limiting its effectiveness and accuracy. In this paper, we propose a novel framework that combines PM and HI to enable data-driven, process- and product-centric modeling of industrial energy demands. By integrating event logs and thermal energy data, our approach allows for a fine-grained analysis of heat demand patterns corresponding to specific process activities and product variants. We demonstrate the applicability and advantages of the framework by simulating a pharmaceutical manufacturing process and evaluating energy demands and heat recovery potentials. Our findings show that our PM-enabled HI framework provides more accurate and actionable insights into the temporal and product-specific variation of thermal energy demands. By capturing the causal relationships between process activities, product characteristics, and energy consumption, our approach enables improved analysis, planning, and optimization for heat recovery and process decarbonization. This integration of PM and HI expands the analytical tools for both disciplines and contributes to advancing the sustainable transformation of industrial processes.}}, author = {{Zapata Gonzalez, David Ricardo and Brennig, Katharina and Benkert, Kay and Schlosser, Florian and Müller, Oliver}}, booktitle = {{ACM SIGEnergy Energy Informatics Review}}, issn = {{2770-5331}}, number = {{3}}, pages = {{19--31}}, publisher = {{Association for Computing Machinery (ACM)}}, title = {{{Process Mining for Robust Heat Integration through Process- and Product-Centric Energy Demand Modeling}}}, doi = {{10.1145/3777518.3777520}}, volume = {{5}}, year = {{2025}}, } @inproceedings{63400, abstract = {{Data centers (DCs) form the backbone of our growing digital economy, but their rising energy demands pose challenges to our environment. At the same time, reusing waste heat from DCs also represents an opportunity, for example, for more sustainable heating of residential buildings. Modeling and optimizing these coupled and dynamic systems of heat generation and reuse is complex. On the one hand, physical simulations can be used to model these systems, but they are time-consuming to develop and run. Machine learning (ML), on the other hand, allows efficient data-driven modeling, but conventional correlation-based approaches struggle with the prediction of interventions and out-of-distribution generalization. Recent advances in causal ML, which combine principles from causal inference with flexible ML methods, are a promising approach for more robust predictions. Due to their focus on modeling interventions and cause-and-effect relationships, it is difficult to evaluate causal ML approaches rigorously. To address this challenge, we built a testbed of a miniature DC with an integrated waste heat network, equipped with sensors and actuators. This testbed allows conducting controlled experiments and automatic collection of realistic data, which can then be used to benchmark conventional and causal ML methods. Our experimental results highlight the strengths and weaknesses of each modeling approach, providing valuable insights on how to appropriately apply different types of machine learning to optimize data center operations and enhance their sustainability.}}, author = {{Zapata Gonzalez, David Ricardo and Meyer, Marcel and Müller, Oliver}}, booktitle = {{ACM SIGEnergy Energy Informatics Review}}, issn = {{2770-5331}}, number = {{2}}, pages = {{4--10}}, publisher = {{Association for Computing Machinery (ACM)}}, title = {{{Causal Machine Learning Approaches for Modelling Data Center Heat Recovery: A Physical Testbed Study}}}, doi = {{10.1145/3757892.3757893}}, volume = {{5}}, year = {{2025}}, }