arXiv subjects

Ralf Mikut

Publications and source records attributed to Ralf Mikut.

At least 19 recordsLinked to original sources

arXiv2026

A Benchmark for Electrical Load Forecasting Across Grid Levels: Time-Series Transformers Outperform Established Methods

Accurate load forecasting at multiple grid levels is essential for future smart grids, ranging from aggregated control area forecasts for balancing supply and demand to forecasts of individual end-consumer loads for demand-side management and energy management systems. We present a comprehensive benchmark for load forecasting across grid levels, comprising three datasets that represent a transmission system operator control area, low-voltage grid feeders, and individual end consumers. We evaluate ten methods for short-term load forecasting and find that Transformer-based approaches consistently outperform established methods, reducing forecast error by 6.6-10.7 %. To analyze the impact of architectural design, we introduce YAformer, a flexible Transformer architecture that integrates modifications from prior work and is optimized via hyperparameter optimization. However, the standard Transformer achieves superior performance, suggesting that these architectural modifications are not required for accurate load forecasting. We further evaluate the Transformer-based time-series foundation model Chronos-2, which demonstrates competitive zero-shot performance on two datasets but fails to accurately capture special events in the TSO data. Detailed analyses reveal model-specific strengths and weaknesses, and ablation studies highlight the importance of long input contexts, covariates and continuous retraining - aspects that are often overlooked in the time-series forecasting literature.

cs.LG↗

arXiv2026

Probabilistic Low-Voltage Peak Load Forecasting with Time Series Foundation Models Evaluated on Application-Oriented Metrics

Low-voltage load forecasting is an important component in current and future energy systems with a high degree of electrification and decentralized generation. However, current forecasting methods require significant manual effort, often lack uncertainty estimation and proper peak prediction, and they are often not adequately evaluated in terms of grid requirements. In the present study, we provide an extensive evaluation of short-term net load forecasts of 200 real-world low-voltage feeders with a focus on the rapidly evolving time series foundation models. Our study compares Chronos-Bolt, Chronos-2 and TabPFN-TS to six baseline models and demonstrates superior performance, in particular for Chronos-2. An ablation study, in which weather covariates are omitted, shows that time series foundation models adapt to increased uncertainty, despite the importance of weather information. A novel application-oriented metric links the model's forecasting capabilities in peak prediction to the trade-off in grid asset planning and operation between cost reduction and minimizing the risk of failure.

cs.LG↗

arXiv2026

Explainable Load Forecasting with Covariate-Informed Time Series Foundation Models

Time Series Foundation Models (TSFMs) have recently emerged as general-purpose forecasting models and show considerable potential for applications in energy systems. However, applications in critical infrastructure like power grids require transparency to ensure trust and reliability and cannot rely on pure black-box models. To enhance the transparency of TSFMs, we propose an efficient algorithm for computing Shapley Additive Explanations (SHAP) tailored to these models. The proposed approach leverages the flexibility of TSFMs with respect to input context length and provided covariates. This property enables efficient temporal and covariate masking (selectively withholding inputs), allowing for a scalable explanation of model predictions using SHAP. We evaluate two TSFMs - Chronos-2 and TabPFN-TS - on a day-ahead load forecasting task for a transmission system operator (TSO). In a zero-shot setting, both models achieve predictive performance competitive with a Transformer model trained specifically on multiple years of TSO data. The explanations obtained through our proposed approach align with established domain knowledge, particularly as the TSFMs appropriately use weather and calendar information for load prediction. Overall, we demonstrate that TSFMs can serve as transparent and reliable tools for operational energy forecasting.

cs.LG↗

arXiv2026

Energy-Arena: A Dynamic Benchmark for Operational Energy Forecasting

Energy forecasting research faces a persistent comparability gap that makes it difficult to measure consistent progress over time. Reported accuracy gains are often not directly comparable because models are evaluated under study-specific datasets, time periods, information sets, and scoring setups, while widely used benchmarks and competition datasets are typically tied to fixed historical windows. This paper introduces the Energy-Arena, a dynamic benchmarking platform for operational energy time series forecasting that provides a continuously updated reference point as energy systems evolve. The platform operates as an open, API-based submission system and standardizes challenge definitions and submission deadlines aligned with operational constraints. Performance is reported on rolling evaluation windows via persistent leaderboards. By moving from retrospective backtesting to forward-looking benchmarking, the Energy-Arena enforces standardized ex-ante submission and ex-post evaluation, thereby improving transparency by preventing information leakage and retroactive tuning. The platform is publicly available at Energy-Arena.org.

econ.EM↗

arXiv2026

Data Synthesis Improves 3D Myotube Instance Segmentation

Myotubes are multinucleated muscle fibers serving as key model systems for studying muscle physiology, disease mechanisms, and drug responses. Mechanistic studies and drug screening thereby rely on quantitative morphological readouts such as diameter, length, and branching degree, which in turn require precise three-dimensional instance segmentation. Yet established pretrained biomedical segmentation models fail to generalize to this domain due to the absence of large annotated myotube datasets. We introduce a geometry-driven synthesis pipeline that models individual myotubes via polynomial centerlines, locally varying radii, branching structures, and ellipsoidal end caps derived from real microscopy observations. Synthetic volumes are rendered with realistic noise, optical artifacts, and CycleGAN-based Domain Adaptation (DA). A compact 3D U-Net with self-supervised encoder pretraining, trained exclusively on synthetic data, achieves a mean IPQ of 0.22 on real data, significantly outperforming three established zero-shot segmentation models, demonstrating that biophysics-driven synthesis enables effective instance segmentation in annotation-scarce biomedical domains.

cs.CV↗

arXiv2026

Stochastic Model Predictive Control based on Mixed Random Variables for Economic Energy Management

Optimal scheduling of batteries has significant potential to reduce electricity costs and to enhance grid resilience. However, effective battery scheduling must account for both physical constraints as well as uncertainties in consumption and generation of renewable energy sources. Instead of optimizing fixed battery power setpoints, we propose an approach that optimizes battery power intervals, allowing the optimization to explicitly account for uncertain consumption and generation as well as how the battery system should respond to them within its physical limits. Our method is based on mixed random variables, represented as mixtures of discrete and continuous probability distributions. Building on this representation, we develop an analytical stochastic formulation for minimizing electricity costs in a residential setting with load, photovoltaics, and battery storage. We demonstrate its effectiveness across real-world data from 15 residential buildings over five consecutive months. Compared with deterministic and probabilistic benchmark controllers, the proposed interval-based optimization achieves the lowest costs. These results show that mixed random variables are a practical and promising tool for decision-making under uncertainty.

math.OC↗

arXiv2026

Knowledge Distillation for Efficient Transformer-Based Reinforcement Learning in Hardware-Constrained Energy Management Systems

Transformer-based reinforcement learning has emerged as a strong candidate for sequential control in residential energy management. In particular, the Decision Transformer can learn effective battery dispatch policies from historical data, thereby increasing photovoltaic self-consumption and reducing electricity costs. However, transformer models are typically too computationally demanding for deployment on resource-constrained residential controllers, where memory and latency constraints are critical. This paper investigates knowledge distillation to transfer the decision-making behaviour of high-capacity Decision Transformer policies to compact models that are more suitable for embedded deployment. Using the Ausgrid dataset, we train teacher models in an offline sequence-based Decision Transformer framework on heterogeneous multi-building data. We then distil smaller student models by matching the teachers' actions, thereby preserving control quality while reducing model size. Across a broad set of teacher-student configurations, distillation largely preserves control performance and even yields small improvements of up to 1%, while reducing the parameter count by up to 96%, the inference memory by up to 90%, and the inference time by up to 63%. Beyond these compression effects, comparable cost improvements are also observed when distilling into a student model of identical architectural capacity. Overall, our results show that knowledge distillation makes Decision Transformer control more applicable for residential energy management on resource-limited hardware.

cs.LG↗

arXiv2026

Real-world energy data of 200 feeders from low-voltage grids with metadata in Germany over two years

The last mile of the distribution grid is crucial for a successful energy transition, as more low-carbon technology like photovoltaic systems, heat pumps, and electric vehicle chargers connect to the low-voltage grid. Despite considerable challenges in operation and planning, researchers often lack access to suitable low-voltage grid data. To address this, we present the FeederBW dataset with data recorded by the German distribution system operator Netze BW. It offers real-world energy data from 200 low-voltage feeders over two years (2023-2025) with weather information and detailed metadata, including changes in low-carbon technology installations. The dataset includes feeder-specific details such as the number of housing units, installed power of low-carbon technology, and aggregated industrial energy data. Furthermore, high photovoltaic feed-in and one-minute temporal resolution makes the dataset unique. FeederBW supports various applications, including machine learning for load forecasting, conducting non-intrusive load monitoring, generating synthetic data, and analyzing the interplay between weather, feeder measurements, and metadata. The dataset reveals insightful patterns and clearly reflects the growing impact of low-carbon technology on low-voltage grids.

eess.SY↗

arXiv2025

Explainable time-series forecasting with sampling-free SHAP for Transformers

Time-series forecasts are essential for planning and decision-making in many domains. Explainability is key to building user trust and meeting transparency requirements. Shapley Additive Explanations (SHAP) is a popular explainable AI framework, but it lacks efficient implementations for time series and often assumes feature independence when sampling counterfactuals. We introduce SHAPformer, an accurate, fast and sampling-free explainable time-series forecasting model based on the Transformer architecture. It leverages attention manipulation to make predictions based on feature subsets. SHAPformer generates explanations in under one second, several orders of magnitude faster than the SHAP Permutation Explainer. On synthetic data with ground truth explanations, SHAPformer provides explanations that are true to the data. Applied to real-world electrical load data, it achieves competitive predictive performance and delivers meaningful local and global insights, such as identifying the past load as the key predictor and revealing a distinct model behavior during the Christmas period.

cs.LG↗

arXiv2025

ComEMS4Build: Comfort-Oriented Energy Management System for Residential Buildings using Hydrogen for Seasonal Storage

Integrating flexible loads and storage systems into the residential sector contributes to the alignment of volatile renewable generation with demand. Besides batteries serving as a short-term storage solution, residential buildings can benefit from a Hydrogen (H2) storage system, allowing seasonal shifting of renewable energy. However, as the initial costs of H2 systems are high, coupling a Fuel Cell (FC) with a Heat Pump (HP) can contribute to the size reduction of the H2 system. The present study develops a Comfort-Oriented Energy Management System for Residential Buildings (ComEMS4Build) comprising Photovoltaics (PV), Battery Energy Storage System (BESS), and H2 storage, where FC and HP are envisioned as complementary technologies. The fuzzy-logic-based ComEMS4Build is designed and evaluated over a period of 12 weeks in winter for a family household building in Germany using a semi-synthetic modeling approach. The Rule-Based Control (RBC), which serves as a lower benchmark, is a scheduler designed to require minimal inputs for operation. The Model Predictive Control (MPC) is intended as a cost-optimal benchmark with an ideal forecast. The results show that ComEMS4Build, similar to MPC, does not violate the thermal comfort of occupants in 10 out of 12 weeks, while RBC has a slightly higher median discomfort of 0.68 Kh. The ComEMS4Build increases the weekly electricity costs by 12.06 EUR compared to MPC, while RBC increases the weekly costs by 30.14 EUR. The ComEMS4Build improves the Hybrid Energy Storage System (HESS) utilization and energy exchange with the main grid compared to the RBC. However, when it comes to the FC operation, the RBC has an advantage, as it reduces the toggling counts by 3.48% and working hours by 7.59% compared to MPC...

eess.SY↗

arXiv2025

Averaging favors MPC: How typical evaluation setups overstate MPC performance for residential battery scheduling

Residential prosumers with PV-battery systems increasingly manage their electricity exchange with the power grid to minimize costs. This study investigates the performance of Model Predictive Control (MPC) and Rule-Based Control (RBC) under 15/30/60 minute averaging commonly used in research, when Net Billing and battery degradation are considered. We simulate five consecutive months for 15 buildings in northern Germany, generating costs at up to 1-minute resolution while scheduling at 15/30/60 minutes. We find that time-averaged evaluations make MPC look consistently better than RBC, yet when costs are recomputed at minute-level ground-truth, the reported advantage shrinks by 69\% on average for hourly schedulers. For individual buildings, the finer evaluation can reverse conclusions, and simple RBC can achieve lower total costs than an MPC with perfect foresight. These findings caution against drawing conclusions from coarse averages and show how a fair assessment of battery scheduling approaches can be obtained.

math.OC↗

arXiv2025

Self-Supervised Learning Strategies for a Platform to Test the Toxicity of New Chemicals and Materials

High-throughput toxicity testing offers a fast and cost-effective way to test large amounts of compounds. A key component for such systems is the automated evaluation via machine learning models. In this paper, we address critical challenges in this domain and demonstrate how representations learned via self-supervised learning can effectively identify toxicant-induced changes. We provide a proof-of-concept that utilizes the publicly available EmbryoNet dataset, which contains ten zebrafish embryo phenotypes elicited by various chemical compounds targeting different processes in early embryonic development. Our analysis shows that the learned representations using self-supervised learning are suitable for effectively distinguishing between the modes-of-action of different compounds. Finally, we discuss the integration of machine learning models in a physical toxicity testing device in the context of the TOXBOX project.

cs.CV↗

arXiv2025

Are Foundation Models Ready for Industrial Defect Recognition? A Reality Check on Real-World Data

Foundation Models (FMs) have shown impressive performance on various text and image processing tasks. They can generalize across domains and datasets in a zero-shot setting. This could make them suitable for automated quality inspection during series manufacturing, where various types of images are being evaluated for many different products. Replacing tedious labeling tasks with a simple text prompt to describe anomalies and utilizing the same models across many products would save significant efforts during model setup and implementation. This is a strong advantage over supervised Artificial Intelligence (AI) models, which are trained for individual applications and require labeled training data. We test multiple recent FMs on both custom real-world industrial image data and public image data. We show that all of those models fail on our real-world data, while the very same models perform well on public benchmark datasets.

cs.CV↗

arXiv2025

LeDiFlow: Learned Distribution-guided Flow Matching to Accelerate Image Generation

Enhancing the efficiency of high-quality image generation using Diffusion Models (DMs) is a significant challenge due to the iterative nature of the process. Flow Matching (FM) is emerging as a powerful generative modeling paradigm based on a simulation-free training objective instead of a score-based one used in DMs. Typical FM approaches rely on a Gaussian distribution prior, which induces curved, conditional probability paths between the prior and target data distribution. These curved paths pose a challenge for the Ordinary Differential Equation (ODE) solver, requiring a large number of inference calls to the flow prediction network. To address this issue, we present Learned Distribution-guided Flow Matching (LeDiFlow), a novel scalable method for training FM-based image generation models using a better-suited prior distribution learned via a regression-based auxiliary model. By initializing the ODE solver with a prior closer to the target data distribution, LeDiFlow enables the learning of more computationally tractable probability paths. These paths directly translate to fewer solver steps needed for high-quality image generation at inference time. Our method utilizes a State-Of-The-Art (SOTA) transformer architecture combined with latent space sampling and can be trained on a consumer workstation. We empirically demonstrate that LeDiFlow remarkably outperforms the respective FM baselines. For instance, when operating directly on pixels, our model accelerates inference by up to 3.75x compared to the corresponding pixel-space baseline. Simultaneously, our latent FM model enhances image quality on average by 1.32x in CLIP Maximum Mean Discrepancy (CMMD) metric against its respective baseline.

cs.CV↗

arXiv2025

Rapid AI-based generation of coverage paths for dispensing applications

Coverage Path Planning of Thermal Interface Materials (TIM) plays a crucial role in the design of power electronics and electronic control units. Up to now, this is done manually by experts or by using optimization approaches with a high computational effort. We propose a novel AI-based approach to generate dispense paths for TIM and similar dispensing applications. It is a drop-in replacement for optimization-based approaches. An Artificial Neural Network (ANN) receives the target cooling area as input and directly outputs the dispense path. Our proposed setup does not require labels and we show its feasibility on multiple target areas. The resulting dispense paths can be directly transferred to automated manufacturing equipment and do not exhibit air entrapments. The approach of using an ANN to predict process parameters for a desired target state in real-time could potentially be transferred to other manufacturing processes.

cs.LG↗

arXiv2025

EAP4EMSIG -- Enhancing Event-Driven Microscopy for Microfluidic Single-Cell Analysis

Microfluidic Live-Cell Imaging (MLCI) yields data on microbial cell factories. However, continuous acquisition is challenging as high-throughput experiments often lack real-time insights, delaying responses to stochastic events. We introduce three components in the Experiment Automation Pipeline for Event-Driven Microscopy to Smart Microfluidic Single-Cell Analysis (EAP4EMSIG): a fast, accurate Multi-Layer Perceptron (MLP)-based autofocusing method predicting the focus offset, an evaluation of real-time segmentation methods and a real-time data analysis dashboard. Our MLP-based autofocusing achieves a Mean Absolute Error (MAE) of 0.105 $\mu$m with inference times from 87 ms. Among eleven evaluated Deep Learning (DL) segmentation methods, Cellpose reached a Panoptic Quality (PQ) of 93.36 %, while a distance-based method was fastest (121 ms, Panoptic Quality 93.02 %).

q-bio.QM↗

arXiv2025

Decision-Focused Fine-Tuning of Time Series Foundation Models for Dispatchable Feeder Optimization

Time series foundation models provide a universal solution for generating forecasts to support optimization problems in energy systems. Those foundation models are typically trained in a prediction-focused manner to maximize forecast quality. In contrast, decision-focused learning directly improves the resulting value of the forecast in downstream optimization rather than merely maximizing forecasting quality. The practical integration of forecast values into forecasting models is challenging, particularly when addressing complex applications with diverse instances, such as buildings. This becomes even more complicated when instances possess specific characteristics that require instance-specific, tailored predictions to increase the forecast value. To tackle this challenge, we use decision-focused fine-tuning within time series foundation models to offer a scalable and efficient solution for decision-focused learning applied to the dispatchable feeder optimization problem. To obtain more robust predictions for scarce building data, we use Moirai as a state-of-the-art foundation model, which offers robust and generalized results with few-shot parameter-efficient fine-tuning. Comparing the decision-focused fine-tuned Moirai with a state-of-the-art classical prediction-focused fine-tuning Morai, we observe an improvement of 9.45% in average total daily costs.

cs.LG↗

arXiv2024

AutoPQ: Automating Quantile estimation from Point forecasts in the context of sustainability

Optimizing smart grid operations relies on critical decision-making informed by uncertainty quantification, making probabilistic forecasting a vital tool. Designing such forecasting models involves three key challenges: accurate and unbiased uncertainty quantification, workload reduction for data scientists during the design process, and limitation of the environmental impact of model training. In order to address these challenges, we introduce AutoPQ, a novel method designed to automate and optimize probabilistic forecasting for smart grid applications. AutoPQ enhances forecast uncertainty quantification by generating quantile forecasts from an existing point forecast by using a conditional Invertible Neural Network (cINN). AutoPQ also automates the selection of the underlying point forecasting method and the optimization of hyperparameters, ensuring that the best model and configuration is chosen for each application. For flexible adaptation to various performance needs and available computing power, AutoPQ comes with a default and an advanced configuration, making it suitable for a wide range of smart grid applications. Additionally, AutoPQ provides transparency regarding the electricity consumption required for performance improvements. We show that AutoPQ outperforms state-of-the-art probabilistic forecasting methods while effectively limiting computational effort and hence environmental impact. Additionally and in the context of sustainability, we quantify the electricity consumption required for performance improvements.

cs.LG↗