Veit Hagenmeyer

Maxime Schwarzer, Johannes F. Loevenich, Gustavo Sánchez et al.

Ensuring the protection of Artificial Intelligence (AI) models deployed in military Command and Control (C2) systems and critical infrastructure is essential for maintaining information superiority. Model Extraction Attacks (MEAs) pose a significant threat, as they enable adversaries to replicate proprietary models, compromise protected information, and prepare offline adversarial attacks. However, current defense strategies predominantly rely on the Single Client Assumption (SCA), which is the implicit assumption that attacks originate from isolated identities. This work systematically demonstrates that the SCA is fundamentally invalid in the presence of coordinated threat actors, such as Advanced Persistent Threats (APTs). We introduce a modular, open-source framework called CerberusAI for reproducible model-stealing research, and use it to simulate distributed attack scenarios. Our empirical evaluation shows that well-established defense mechanisms, such as Protecting Against Deep Neural Network Model Stealing Attacks (PRADA), can be bypassed by basic round-robin query distribution strategies, resulting in a significant reduction in detection performance. Furthermore, we demonstrate that even global aggregation approaches can be rendered operationally useless through adaptive traffic mixing. These results highlight the need for a paradigm shift towards stateful, identity-independent defense architectures in the field of model extraction attacks. This paper was originally presented at the International Conference on Military Communication and Information Systems (ICMCIS), organized by the Information Systems Technology (IST) Scientific and Technical Committee, IST-224-RSY - the ICMCIS, held in Bath, United Kingdom, 12-13 May 2026 and won the best paper award.

Maxime Schwarzer, Laurin Holz, Tobias Huerten et al.

Artificial Intelligence (AI)-based Intrusion Detection Systems (IDS) deployed in energy infrastructure are vulnerable to model theft attacks, which allow adversaries to create evasive traffic offline. Current defences against model extraction rely either on identity-bound query monitoring, which is ineffective against distributed attackers (Sybil), or on prediction poisoning through soft-label perturbation, which is inapplicable to hard-label IDS deployments. Therefore, we propose FlowGuard, an identity-independent defence based on flow matching that classifies incoming queries as out-of-distribution (OOD) prior to IDS processing. This approach exploits the fact that queries generated synthetically for data-free model stealing attacks occupy a lower-dimensional manifold than real network traffic. This results in measurably lower log-likelihoods when using a Continuous Normalizing Flow that has been trained on legitimate data. We evaluate our method against PRADA and FDINet using MAZE and DisGUIDE attacks in single-client and distributed (100-client Sybil) settings. While PRADA's detection rate dropped to 0% when the distribution changed, our defence maintained a stable detection rate across both settings without relying on identity information. We discuss the scope and limitations of the approach, and outline potential applications to data-dependent attacks.

Qi Liu, Kaibin Bao, Wajih Ul Hassan et al.

Due to its crucial role in identity and access management in modern enterprise networks, Active Directory (AD) is a top target of Advanced Persistence Threat (APT) actors. Conventional intrusion detection systems (IDS) excel at identifying malicious behaviors caused by malware, but often fail to detect stealthy attacks launched by APT actors. Recent advance in provenance-based IDS (PIDS) shows promises by exposing malicious system activities in causal attack graphs. However, existing approaches are restricted to intra-machine tracing, and unable to reveal the scope of attackers' traversal inside a network. We propose HADES, the first PIDS capable of performing accurate causality-based cross-machine tracing by leveraging a novel concept called logon session based execution partitioning to overcome several challenges in cross-machine tracing. We design HADES as an efficient on-demand tracing system, which performs whole-network tracing only when it first identifies an authentication anomaly signifying an ongoing AD attack, for which we introduce a novel lightweight authentication anomaly detection model rooted in our extensive analysis of AD attacks. To triage attack alerts, we present a new algorithm integrating two key insights we identified in AD attacks. Our evaluations show that HADES outperforms both popular open source detection systems and a prominent commercial AD attack detector.

Hallah Shahid Butt, Qiong Huang, Gökhan Demirel et al.

The increasing integration of renewable energy sources into power systems, particularly in buildings equipped with photovoltaic (PV) panels and energy storage systems, introduces significant complexity in energy systems. Volatile power generation, varying electricity tariffs, and increased entities, e.g., PV systems, and heat pumps, have increased the complexity and made the system harder to operate. This leads to the demand for additional control and optimization routes including data-based controls, such as reinforcement learning. While deep reinforcement learning (DRL) has emerged as a promising solution to optimize building operations in dynamic and ever more complex environments, its black-box nature impedes user trust and practical adoption. This paper presents a framework for explainable deep reinforcement learning (XRL) applied to energy management in residential buildings. We demonstrate its usage on both synthetic data but also on real-world data from the Living Lab Energy Campus (LLEC) at KIT. We train and compare both on-policy and off-policy DRL agents on an expanded state space that incorporates real-time measurements (demand, PV generation, battery power, state of charge), external signals (dynamic electricity price, local weather data), calendrical and holiday indicators, and forecasts for demand and price. Our experimental results indicate that on-policy algorithms, particularly Advantage Actor Critic (A2C) and Proximal Policy Optimization (PPO), outperform off-policy methods in terms of cumulative rewards and policy stability. To explain these models, we employ post-hoc interpretation techniques to elaborate the learned control policies. Our findings demonstrate that the XRL framework not only reduces electricity costs through optimal battery management, but also provides transparent, actionable insights into the agent's decision-making process.

Tillmann Mühlpfordt, Rolf Findeisen, Veit Hagenmeyer et al.

Methods based on polynomial chaos expansion allow to approximate the behavior of systems with uncertain parameters by deterministic dynamics. These methods are used in a wide range of applications, spanning from simulation of uncertain systems to estimation and control. For practical purposes the exploited spectral series expansion is typically truncated to allow for efficient computation, which leads to approximation errors. Despite the Hilbert space nature of polynomial chaos, there are only a few results in the literature that explicitly discuss and quantify these approximation errors. This work derives error bounds for polynomial chaos approximations of polynomial and non-polynomial mappings. Sufficient conditions are established, which allow investigating the question whether zero truncation errors can be achieved and which series order is required to achieve this. Furthermore, convex quadratic programs, whose argmin operator is a special case of a piecewise polynomial mapping, are studied due to their relevance in predictive control. Several simulation examples illustrate our findings.

Xuanhao Mu, Kundan Thota, Nan Liu et al.

Open-source energy system models disaggregate zonal electricity demand to substations through Voronoi-based preprocessing pipelines that combine socioeconomic weighting with auxiliary spatial corrections. Whether the same auxiliary data helps or harms when the weighting component shifts from rule-based to learned has not been investigated. We fix Voronoi partitioning and cross two design axes on metered demand from 1,891 British primary substations: the demand-weighting method and the mechanism through which Nighttime Light (NTL) intensity and substation-proximity signals enter the allocation, giving 15 configurations. Mechanism-isolation experiments further test additive post-correction and random-noise controls to pinpoint the structural cause of any performance reversal. The same auxiliary data reduces RMSE by 41 % on the static base but increases it by 21 % on the GNN base under multiplicative post-correction (p < 0.001 for both); the best static pipeline outperforms the best GNN variant by 19 %. Post-correction on the GNN improves rank-order correlation (p < 0.001) yet worsens absolute error, so correlation-only evaluation masks the calibration penalty. The isolation experiments trace this reversal to the multiplicative correction form under demand conservation constraints, not to signal redundancy; switching to additive post-correction eliminates the antagonism entirely. A transfer check on 13 German primary substations confirms directional replication and shows amplified antagonism where the GNN baseline already explains over 95 % of demand variance. The NTL and proximity signals behind the 41 % static improvement are publicly available at no cost and should be adopted as default corrections in static pipelines; method evaluation should report RMSE and correlation jointly, as the two metrics diverge under post-correction on learned representations.

Tillmann Mühlpfordt, Timm Faulwasser, Veit Hagenmeyer

Deregulated energy markets, demand forecasting, and the continuously increasing share of renewable energy sources call---among others---for a structured consideration of uncertainties in optimal power flow problems. The main challenge is to guarantee power balance while maintaining economic and secure operation. In the presence of Gaussian uncertainties affine feedback policies are known to be viable options for this task. The present paper advocates a general framework for chance-constrained OPF problems in terms of continuous random variables. It is shown that, irrespective of the type of distribution, the random-variable minimizers lead to affine feedback policies. Introducing a three-step methodology that exploits polynomial chaos expansion, the present paper provides a constructive approach to chance-constrained optimal power flow problems that does not assume a specific distribution, e.g. Gaussian, for the uncertainties. We illustrate our findings by means of a tutorial example and a 300-bus test case.

Matthias Hertel, Maximilian Beichter, Benedikt Heidrich et al.

In the smart grid of the future, accurate load forecasts on the level of individual clients can help to balance supply and demand locally and to prevent grid outages. While the number of monitored clients will increase with the ongoing smart meter rollout, the amount of data per client will always be limited. We evaluate whether a Transformer load forecasting model benefits from a transfer learning strategy, where a global univariate model is trained on the load time series from multiple clients. In experiments with two datasets containing load time series from several hundred clients, we find that the global training strategy is superior to the multivariate and local training strategies used in related work. On average, the global training strategy results in 21.8% and 12.8% lower forecasting errors than the two other strategies, measured across forecasting horizons from one day to one month into the future. A comparison to linear models, multi-layer perceptrons and LSTMs shows that Transformers are effective for load forecasting when they are trained with the global training strategy.

Timm Faulwasser, Alexander Engelmann, Tillmann Mühlpfordt et al.

The Energiewende is a paradigm change that can be witnessed at latest since the political decision to step out of nuclear energy. Moreover, despite common roots in Electrical Engineering, the control community and the power systems community face a lack of common vocabulary. In this context, this paper aims at providing a systems-and-control specific introduction to optimal power flow problems which are pivotal in the operation of energy systems. Based on a concise problem statement, we introduce a common description of optimal power flow variants including multi-stage-problems and predictive control, stochastic uncertainties, and issues of distributed optimization. Moreover, we sketch open questions that might be of interest for the systems and control community.

Jorge Ángel González Ordiano, Wolfgang Doneit, Simon Waczowicz et al.

The present contribution offers a simple methodology for the obtainment of data-driven interval forecasting models by combining pairs of quantile regressions. Those regressions are created without the usage of the non-differentiable pinball-loss function, but through a k-nearest-neighbors based training set transformation and traditional regression approaches. By leaving the underlying training algorithms of the data mining techniques unchanged, the presented approach simplifies the creation of quantile regressions with more complex techniques (e.g. artificial neural networks). The quality of the presented methodology is tested on the usecase of photovoltaic power forecasting, for which quantile regressions using polynomial models as well as artificial neural networks and support vector regressions are created. From the resulting evaluation values it can be concluded that acceptable interval forecasting models are created.

Gustav Keppler, Ghada Elbez, Veit Hagenmeyer

The rapid evolution and use of Large Language Models (LLMs) in professional workflows require an evaluation of their domain-specific knowledge against industry standards. We introduceCyberCertBench, a new suite of Multiple Choice Question Answering (MCQA) benchmarks derived from industry recognized certifications. CyberCertBench evaluates LLM domain knowledgeagainst the professional standards of Information Technology cybersecurity and more specializedareas such as Operational Technology and related cybersecurity standards. Concurrently, we propose and validate a novel Proposer-Verifier framework, a methodology to generate interpretable,natural language explanations for model performance. Our evaluation shows that frontier modelsachieve human expert level in general networking and IT security knowledge. However, theiraccuracy declines in questions that require vendor-specific nuances or knowledge in formalstandards, like, e.g., IEC 62443. Analysis of model scaling trend and release date demonstratesremarkable gains in parameter efficiency, while recent larger models show diminishing returns.Code and evaluation scripts are available at: https://github.com/GKeppler/CyberCertBench.

Stefan Meisenbacher, Benedikt Heidrich, Tim Martin et al.

Accurate PhotoVoltaic (PV) power generation forecasting is vital for the efficient operation of Smart Grids. The automated design of such accurate forecasting models for individual PV plants includes two challenges: First, information about the PV mounting configuration (i.e. inclination and azimuth angles) is often missing. Second, for new PV plants, the amount of historical data available to train a forecasting model is limited (cold-start problem). We address these two challenges by proposing a new method for day-ahead PV power generation forecasts called AutoPV. AutoPV is a weighted ensemble of forecasting models that represent different PV mounting configurations. This representation is achieved by pre-training each forecasting model on a separate PV plant and by scaling the model's output with the peak power rating of the corresponding PV plant. To tackle the cold-start problem, we initially weight each forecasting model in the ensemble equally. To tackle the problem of missing information about the PV mounting configuration, we use new data that become available during operation to adapt the ensemble weights to minimize the forecasting error. AutoPV is advantageous as the unknown PV mounting configuration is implicitly reflected in the ensemble weights, and only the PV plant's peak power rating is required to re-scale the ensemble's output. AutoPV also allows to represent PV plants with panels distributed on different roofs with varying alignments, as these mounting configurations can be reflected proportionally in the weighting. Additionally, the required computing memory is decoupled when scaling AutoPV to hundreds of PV plants, which is beneficial in Smart Grids with limited computing capabilities. For a real-world data set with 11 PV plants, the accuracy of AutoPV is comparable to a model trained on two years of data and outperforms an incrementally trained model.

Thorbjørn Lund Onsaker, Heidi S. Nygård, Damià Gomila et al.

Modelling, forecasting and overall understanding of the dynamics of the power grid and its frequency are essential for the safe operation of existing and future power grids. Much previous research was focused on large continental areas, while small systems, such as islands are less well-studied. These natural island systems are ideal testing environments for microgrid proposals and artificially islanded grid operation. In the present paper, we utilize measurements of the power grid frequency obtained in European islands: the Faroe Islands, Ireland, the Balearic Islands and Iceland and investigate how their frequency can be predicted, compared to the Nordic power system, acting as a reference. The Balearic islands are found to be particularly deterministic and easy to predict in contrast to hard-to-predict Iceland. Furthermore, we show that typically 2-4 weeks of data are needed to improve prediction performance beyond simple benchmarks.

Tillmann Mühlpfordt, Veit Hagenmeyer, Timm Faulwasser

The operation of power systems has become more challenging due to feed-in of volatile renewable energy sources. Chance-constrained optimal power flow (ccOPF) is one possibility to explicitly consider volatility via probabilistic uncertainties resulting in mean-optimal feedback policies. These policies are computed before knowledge of the realization of the uncertainty is available. On the other hand, the hypothetical case of computing the power injections knowing every realization beforehand---called in-hindsight OPF(hOPF)---cannot be outperformed w.r.t. costs and constraint satisfaction. In this paper, we investigate how ccOPF feedback relates to the full-information hOPF. To this end, we introduce different dimensions of the price of uncertainty. Using mild assumptions on the uncertainty we present sufficient conditions when ccOPF is identical to hOPF. We suggest using the total variational distance of probability densities to quantify the performance gap of hOPF and ccOPF. Finally, we draw upon a tutorial example to illustrate our results.

Qi Liu, Muhammad Shoaib, Mati Ur Rehman et al.

In Advanced Persistent Threat (APT) attacks, achieving stealthy persistence within target systems is often crucial for an attacker's success. This persistence allows adversaries to maintain prolonged access, often evading detection mechanisms. Recognizing its pivotal role in the APT lifecycle, this paper introduces Cyber Persistence Detector (CPD), a novel system dedicated to detecting cyber persistence through provenance analytics. CPD is founded on the insight that persistent operations typically manifest in two phases: the "persistence setup" and the subsequent "persistence execution". By causally relating these phases, we enhance our ability to detect persistent threats. First, CPD discerns setups signaling an impending persistent threat and then traces processes linked to remote connections to identify persistence execution activities. A key feature of our system is the introduction of pseudo-dependency edges (pseudo-edges), which effectively connect these disjoint phases using data provenance analysis, and expert-guided edges, which enable faster tracing and reduced log size. These edges empower us to detect persistence threats accurately and efficiently. Moreover, we propose a novel alert triage algorithm that further reduces false positives associated with persistence threats. Evaluations conducted on well-known datasets demonstrate that our system reduces the average false positive rate by 93% compared to state-of-the-art methods.

Matias Quintana, Till Stoeckmann, June Young Park et al.

Data-driven building energy prediction is an integral part of the process for measurement and verification, building benchmarking, and building-to-grid interaction. The ASHRAE Great Energy Predictor III (GEPIII) machine learning competition used an extensive meter data set to crowdsource the most accurate machine learning workflow for whole building energy prediction. A significant component of the winning solutions was the pre-processing phase to remove anomalous training data. Contemporary pre-processing methods focus on filtering statistical threshold values or deep learning methods requiring training data and multiple hyper-parameters. A recent method named ALDI (Automated Load profile Discord Identification) managed to identify these discords using matrix profile, but the technique still requires user-defined parameters. We develop ALDI++, a method based on the previous work that bypasses user-defined parameters and takes advantage of discord similarity. We evaluate ALDI++ against a statistical threshold, variational auto-encoder, and the original ALDI as baselines in classifying discords and energy forecasting scenarios. Our results demonstrate that while the classification performance improvement over the original method is marginal, ALDI++ helps achieve the best forecasting error improving 6% over the winning's team approach with six times less computation time.

Benedikt Heidrich, Kaleb Phipps, Oliver Neumann et al.

Probabilistic forecasts are essential for various downstream applications such as business development, traffic planning, and electrical grid balancing. Many of these probabilistic forecasts are performed on time series data that contain calendar-driven periodicities. However, existing probabilistic forecasting methods do not explicitly take these periodicities into account. Therefore, in the present paper, we introduce a deep learning-based method that considers these calendar-driven periodicities explicitly. The present paper, thus, has a twofold contribution: First, we apply statistical methods that use calendar-driven prior knowledge to create rolling statistics and combine them with neural networks to provide better probabilistic forecasts. Second, we benchmark ProbPNN with state-of-the-art benchmarks by comparing the achieved normalised continuous ranked probability score (nCRPS) and normalised Pinball Loss (nPL) on two data sets containing in total more than 1000 time series. The results of the benchmarks show that using statistical forecasting components improves the probabilistic forecast performance and that ProbPNN outperforms other deep learning forecasting methods whilst requiring less computation costs.

Kaleb Phipps, Benedikt Heidrich, Marian Turowski et al.

In various applications, probabilistic forecasts are required to quantify the inherent uncertainty associated with the forecast. However, numerous modern forecasting methods are still designed to create deterministic forecasts. Transforming these deterministic forecasts into probabilistic forecasts is often challenging and based on numerous assumptions that may not hold in real-world situations. Therefore, the present article proposes a novel approach for creating probabilistic forecasts from arbitrary deterministic forecasts. In order to implement this approach, we use a conditional Invertible Neural Network (cINN). More specifically, we apply a cINN to learn the underlying distribution of the data and then combine the uncertainty from this distribution with an arbitrary deterministic forecast to generate accurate probabilistic forecasts. Our approach enables the simple creation of probabilistic forecasts without complicated statistical loss functions or further assumptions. Besides showing the mathematical validity of our approach, we empirically show that our approach noticeably outperforms traditional methods for including uncertainty in deterministic forecasts and generally outperforms state-of-the-art probabilistic forecasting benchmarks.

Burak Dindar, Can Berk Saner, Hüseyin K. Çakmak et al.

Due to the transformation of the power system, the effective use of flexibility from the distribution system (DS) is becoming crucial for efficient network management. Leveraging this flexibility requires interoperability among stakeholders, including Transmission System Operators (TSOs) and Distribution System Operators (DSOs). However, data privacy concerns among stakeholders present significant challenges for utilizing this flexibility effectively. To address these challenges, we propose a machine learning (ML)-based method in which the technical constraints of the DSs are represented by ML models trained exclusively on non-sensitive data. Using these models, the TSO can solve the optimal power flow (OPF) problem and directly determine the dispatch of flexibility-providing units (FPUs), in our case, distributed generators (DGs), in a single round of communication. To achieve this, we introduce a novel neural network (NN) architecture specifically designed to efficiently represent the feasible region of the DSs, ensuring computational effectiveness. Furthermore, we incorporate various PQ charts rather than idealized ones, demonstrating that the proposed method is adaptable to a wide range of FPU characteristics. To assess the effectiveness of the proposed method, we benchmark it against the standard AC-OPF on multiple DSs with meshed connections and multiple points of common coupling (PCCs) with varying voltage magnitudes. The numerical results indicate that the proposed method achieves performant results while prioritizing data privacy. Additionally, since this method directly determines the dispatch of FPUs, it eliminates the need for an additional disaggregation step. By representing the DSs technical constraints through ML models trained exclusively on non-sensitive data, the transfer of sensitive information between stakeholders is prevented.

Manuel Treutlein, Marc Schmidt, Roman Hahn et al.

Distribution system operators (DSOs) must cope with new challenges such as the reconstruction of distribution grids along climate neutrality pathways or the ability to manage and control consumption and generation in the grid. In order to meet the challenges, measurements within the distribution grid often form the basis for DSOs. Hence, it is an urgent problem that measurement devices are not installed in many low-voltage (LV) grids. In order to overcome this problem, we present an approach to estimate pseudo-measurements for non-measured LV feeders based on the metadata of the respective feeder using regression models. The feeder metadata comprise information about the number of grid connection points, the installed power of consumers and producers, and billing data in the downstream LV grid. Additionally, we use weather data, calendar data and timestamp information as model features. The existing measurements are used as model target. We extensively evaluate the estimated pseudo-measurements on a large real-world dataset with 2,323 LV feeders characterized by both consumption and feed-in. For this purpose, we introduce peak metrics inspired by the BigDEAL challenge for the peak magnitude, timing and shape for both consumption and feed-in. As regression models, we use XGBoost, a multilayer perceptron (MLP) and a linear regression (LR). We observe that XGBoost and MLP outperform the LR. Furthermore, the results show that the approach adapts to different weather, calendar and timestamp conditions and produces realistic load curves based on the feeder metadata. In the future, the approach can be adapted to other grid levels like substation transformers and can supplement research fields like load modeling, state estimation and LV load forecasting.

Pascal Henrich, Jonas Sievers, Maximilian Beichter et al.

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.

Kundan Thota, Thorsten Schlachter, Veit Hagenmeyer

Determining the age distribution of the urban building stock is crucial for sustainable municipal heat planning and upgrade prioritization. However, existing approaches often rely on datasets gathered via sensors or remote sensing techniques, leaving inconsistencies and gaps in data. We present a multi-agent LLM system comprising three key agents, the Zensus agent, the OSM agent, and the Monument agent, that fuse data from heterogeneous sources. A data orchestrator and harmonizer geocodes and deduplicates building imprints. Using this fused ground truth, we introduce BuildingAgeCNN, a satellite-only classifier based on a ConvNeXt backbone augmented with a Feature Pyramid Network (FPN), CoordConv spatial channels, and Squeeze-and-Excitation (SE) blocks. Under spatial cross validation, BuildingAgeCNN attains an overall accuracy of 90.69% but a modest macro-F1 of 67.25%, reflecting strong class imbalance and persistent confusions between adjacent historical cohorts. To mitigate risk for planning applications, the address-to prediction pipeline includes calibrated confidence estimates and flags low-confidence cases for manual review. This multi-agent LLM system not only assists in gathering structured data but also helps energy demand planners optimize district-heating networks and target low-carbon sustainable energy systems.

Matthias Hertel, Sebastian Pütz, Ralf Mikut et al.

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.

Moritz Gstür, Gustav Keppler, Mohammed Ramadan et al.

Critical energy infrastructures increasingly rely on information and communication technology for monitoring and control, which leads to new challenges with regard to cybersecurity. Recent advancements in this domain, including attribute-based access control (ABAC), have not been sufficiently addressed by established standards such as IEC 61850 and IEC 62351. To address this issue, we propose a novel real-time server-aided attribute-based authorization and access control for time-critical applications called RTS-ABAC. We tailor RTS-ABAC to the strict timing constraints inherent to the protocols employed in substation automation systems (SAS). We extend the concept of conventional ABAC by introducing real-time attributes and time-dependent policy evaluation and enforcement. To safeguard the authenticity, integrity, and non-repudiation of SAS communication and protect an SAS against domain-typical adversarial attacks, RTS-ABAC employs mandatory authentication, authorization, and access control for any type of SAS communication using a bump-in-the-wire (BITW) approach. To evaluate RTS-ABAC, we conduct a testbed-based performance analysis and a laboratory-based demonstration of applicability. We demonstrate the applicability using intelligent electronic devices, merging units, and I/O boxes communicating via the GOOSE and SV protocol. The results show that RTS-ABAC is able to secure low-latency communication between SAS devices, as up to 99.82 % of exchanged packets achieve a round-trip time below 6 ms. Moreover, the results of the evaluation indicate that RTS-ABAC is a viable solution to enhance the cybersecurity not only in a newly constructed SAS but also via retrofitting of existing substations.

Gustav Keppler, Moritz Gstür, Veit Hagenmeyer

The advancement of Large Language Models (LLMs) has raised concerns regarding their dual-use potential in cybersecurity. Existing evaluation frameworks overwhelmingly focus on Information Technology (IT) environments, failing to capture the constraints, and specialized protocols of Operational Technology (OT). To address this gap, we introduce CritBench, a novel framework designed to evaluate the cybersecurity capabilities of LLM agents within IEC 61850 Digital Substation environments. We assess five state-of-the-art models, including OpenAI's GPT-5 suite and open-weight models, across a corpus of 81 domain-specific tasks spanning static configuration analysis, network traffic reconnaissance, and live virtual machine interaction. To facilitate industrial protocol interaction, we develop a domain-specific tool scaffold. Our empirical results show that agents reliably execute static structured-file analysis and single-tool network enumeration, but their performance degrades on dynamic tasks. Despite demonstrating explicit, internalized knowledge of the IEC 61850 standards terminology, current models struggle with the persistent sequential reasoning and state tracking required to manipulate live systems without specialized tools. Equipping agents with our domain-specific tool scaffold significantly mitigates this operational bottleneck. Code and evaluation scripts are available at: https://github.com/GKeppler/CritBench

Jan Niklas Lettner, Hadeer El Ashhab, Veit Hagenmeyer et al.

Large-scale renewable energy deployment introduces pronounced volatility into the electricity system, turning grid operation into a complex stochastic optimization problem. Accurate electricity price forecasting (EPF) is essential not only to support operational decisions, such as optimal bidding strategies and balancing power preparation, but also to reduce economic risk and improve market efficiency. Probabilistic forecasts are particularly valuable because they quantify uncertainty stemming from renewable intermittency, market coupling, and regulatory changes, enabling market participants to make informed decisions that minimize losses and optimize expected revenues. However, it remains an open question which models to employ to produce accurate forecasts. Should these be task-specific machine learning (ML) models or Time Series Foundation Models (TSFMs)? In this work, we compare four models for day-ahead probabilistic EPF (PEPF) in European bidding zones: a deterministic NHITS backbone with Quantile-Regression Averaging (NHITS+QRA) and a conditional Normalizing-Flow forecaster (NF) are compared with two TSFMs, namely Moirai and ChronosX. On the one hand, we find that TSFMs outperform task-specific deep learning models trained from scratch in terms of CRPS, Energy Score, and predictive interval calibration across market conditions. On the other hand, we find that well-configured task-specific models, particularly NHITS combined with QRA, achieve performance very close to TSFMs, and in some scenarios, such as when supplied with additional informative feature groups or adapted via few-shot learning from other European markets, they can even surpass TSFMs. Overall, our findings show that while TSFMs offer expressive modeling capabilities, conventional models remain highly competitive, emphasizing the need to weigh computational expense against marginal performance improvements in PEPF.

Benedikt Heidrich, Andreas Bartschat, Marian Turowski et al.

Time series data are fundamental for a variety of applications, ranging from financial markets to energy systems. Due to their importance, the number and complexity of tools and methods used for time series analysis is constantly increasing. However, due to unclear APIs and a lack of documentation, researchers struggle to integrate them into their research projects and replicate results. Additionally, in time series analysis there exist many repetitive tasks, which are often re-implemented for each project, unnecessarily costing time. To solve these problems we present \texttt{pyWATTS}, an open-source Python-based package that is a non-sequential workflow automation tool for the analysis of time series data. pyWATTS includes modules with clearly defined interfaces to enable seamless integration of new or existing methods, subpipelining to easily reproduce repetitive tasks, load and save functionality to simply replicate results, and native support for key Python machine learning libraries such as scikit-learn, PyTorch, and Keras.

Anton Ponomarev, Lutz Gröll, Veit Hagenmeyer

The classical asymptotic gain (AG) is a concept known from the input-to-state stability theory. Given a uniform input bound, AG estimates the asymptotic bound of the output. Sometimes, however, more information is known about the input than just a bound. In this paper we consider the case of a periodic input. Under the assumption that the system converges to a periodic solution, we introduce a new gain, called period-aware asymptotic gain (PAG), which employs periodicity to enable a sharper asymptotic estimation of the output. Since the PAG can distinguish between short-period ("high-frequency") and long-period ("low-frequency") signals, it is able to rigorously quantify such properties as bandwidth, resonant behavior, and high-frequency damping. We discuss how the PAG can be computed and illustrate it with a numerical example from the field of power electronics.

Xinyi Wen, Xiao Li, Leonardo Rydin Gorjão et al.

System identification plays a crucial role in physics and machine learning for discovering governing equations directly from data. A powerful approach is the Sparse Identification of Nonlinear Dynamics (SINDy) method, which assumes that only a few dominant terms drive the essential behavior of a nonlinear dynamical system. While SINDy methods have shown excellent results, they are most often illustrated on synthetic or simulated systems, leaving open the question of how well they perform on complex, noisy, real-world data. Power grid frequency dynamics provide a highly relevant and challenging environment for advancing system identification methods. In this work, we propose PowerSINDy as a framework for empirical power system data. We apply this framework to empirical frequency data from the Continental Europe (CE) and South Korea (SK) synchronous grids, two major power systems with distinct dynamical characteristics. PowerSINDy, which also includes time-dependent terms, can identify the dynamics of these complex real-world systems. Furthermore, we benchmark three sparsity-promoting regression strategies: Sequentially Thresholded Least Squares (STLSQ), Least Absolute Shrinkage and Selection Operator (LASSO), and Sparse Relaxed Regularized Regression (SR3) to evaluate trade-offs between accuracy, sparsity, and robustness. Results show that LASSO consistently achieves the lowest stable RMSEs, reaching 0.0101 for the CE, while STLSQ provides the best balance between accuracy and stability. SR3 exhibits higher variability and sensitivity to regularization, with L0 and L1 producing nearly indistinguishable outcomes.

Kundan Thota, Xuanhao Mu, Thorsten Schlachter et al.

Accurate heat-demand maps play a crucial role in decarbonizing space heating, yet most municipalities lack detailed building-level data needed to calculate them. We introduce HeatPrompt, a zero-shot vision-language energy modeling framework that estimates annual heat demand using semantic features extracted from satellite images, basic Geographic Information System (GIS), and building-level features. We feed pretrained Large Vision Language Models (VLMs) with a domain-specific prompt to act as an energy planner and extract the visual attributes such as roof age, building density, etc, from the RGB satellite image that correspond to the thermal load. A Multi-Layer Perceptron (MLP) regressor trained on these captions shows an $R^2$ uplift of 93.7% and shrinks the mean absolute error (MAE) by 30% compared to the baseline model. Qualitative analysis shows that high-impact tokens align with high-demand zones, offering lightweight support for heat planning in data-scarce regions.

Matthias Hertel, Alexandra Nikoltchovska, Sebastian Pütz et al.

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.

Max Kleinebrahm, Jonathan Berrisch, Philipp Eiser et al.

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.

Haozhen Cheng, Hüseyin K. Çakmak, Veit Hagenmeyer

Accurate building energy models are crucial for analyzing sector-coupled energy systems, where buildings interact with electrified heating, energy storage, and advanced control across various scenarios. High-fidelity (HiFi) white-box models that resolve hydronic distribution and emitter dynamics can capture short-term transients, yet their numerical stiffness and computational burden limit long-term simulations and large-scale scenario exploration. Conversely, reduced-order low-fidelity (LoFi) representations enable rapid annual assessments but may fail to capture the hydronic- and control-induced dynamics that govern transient and peak behavior. This paper proposes a dual-fidelity, multi-zone white-box building modeling framework, which is called JanusBM, built on a novel topology-driven modeling tool RoomFlex6D, coupling a HiFi hydronic model and a LoFi ideal-load surrogate that removes explicit hydronic states in Modelica. To ensure applicability and physical consistency across time scales, we introduce a two-stage hybrid validation and calibration pipeline that uses complementary data: the IEA EBC Annex 60 benchmark for energy-scale validation and time-series measurements from real-world experimental buildings for hydronic dynamics-scale calibration. Results show that the generated LoFi models achieve a high degree of consistency with Annex 60 benchmark on the energy scale, and the proposed calibration workflow robustly improves loop-level return water temperature transients and zone-level temperature dynamics. Moreover, the LoFi model achieves orders-of-magnitude faster simulations suited to annual energy analyses, whereas the HiFi model becomes necessary when the required heat differs from the actual delivered heat due to distribution and control limitations, especially in transient and peak-oriented assessments.

Stefan Meisenbacher, Kaleb Phipps, Oskar Taubert et al.

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.

Xuanhao Mu, Jakob Geiges, Nan Liu et al.

In energy system analysis, coupling models with mismatched spatial resolutions is a significant challenge. A common solution is assigning weights to high-resolution geographic units for aggregation, but traditional models are limited by using only a single geospatial attribute. This paper presents an innovative method employing a self-supervised Heterogeneous Graph Neural Network to address this issue. This method models high-resolution geographic units as graph nodes, integrating various geographical features to generate physically meaningful weights for each grid point. These weights enhance the conventional Voronoi-based allocation method, allowing it to go beyond simply geographic proximity by incorporating essential geographic information.In addition, the self-supervised learning paradigm overcomes the lack of accurate ground-truth data. Experimental results demonstrate that applying weights generated by this method to cluster-based Voronoi Diagrams significantly enhances scalability, accuracy, and physical plausibility, while increasing precision compared to traditional methods.

Gustavo Sánchez, Ghada Elbez, Veit Hagenmeyer

The escalating frequency and sophistication of cyber threats increased the need for their comprehensive understanding. This paper explores the intersection of geopolitical dynamics, cyber threat intelligence analysis, and advanced detection technologies, with a focus on the energy domain. We leverage generative artificial intelligence to extract and structure information from raw cyber threat descriptions, enabling enhanced analysis. By conducting a geopolitical comparison of threat actor origins and target regions across multiple databases, we provide insights into trends within the general threat landscape. Additionally, we evaluate the effectiveness of cybersecurity tools -- with particular emphasis on learning-based techniques -- in detecting indicators of compromise for energy-targeted attacks. This analysis yields new insights, providing actionable information to researchers, policy makers, and cybersecurity professionals.

Xuanhao Mu, Gökhan Demirel, Yuzhe Zhang et al.

To bridge the temporal granularity gap in energy network design and operation based on Energy System Models, resampling of time series is required. While conventional upsampling methods are computationally efficient, they often result in significant information loss or increased noise. Advanced models such as time series generation models, Super-Resolution models and imputation models show potential, but also face fundamental challenges. The goal of time series generative models is to learn the distribution of the original data to generate high-resolution series with similar statistical characteristics. This is not entirely consistent with the definition of upsampling. Time series Super-Resolution models or imputation models can degrade the accuracy of upsampling because the input low-resolution time series are sparse and may have insufficient context. Moreover, such models usually rely on supervised learning paradigms. This presents a fundamental application paradox: their training requires the high-resolution time series that is intrinsically absent in upsampling application scenarios. To address the mentioned upsampling issue, this paper introduces a new method utilizing Generative Adversarial Transformers (GATs), which can be trained without access to any ground-truth high-resolution data. Compared with conventional interpolation methods, the introduced method can reduce the root mean square error (RMSE) of upsampling tasks by 10%, and the accuracy of a model predictive control (MPC) application scenario is improved by 13%.

Maximilian Beichter, Nils Friederich, Janik Pinter et al.

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.

Stefan Meisenbacher, Silas Aaron Selzer, Mehdi Dado et al.

Renewable energies and their operation are becoming increasingly vital for the stability of electrical power grids since conventional power plants are progressively being displaced, and their contribution to redispatch interventions is thereby diminishing. In order to consider renewable energies like Wind Power (WP) for such interventions as a substitute, day-ahead forecasts are necessary to communicate their availability for redispatch planning. In this context, automated and scalable forecasting models are required for the deployment to thousands of locally-distributed onshore WP turbines. Furthermore, the irregular interventions into the WP generation capabilities due to redispatch shutdowns pose challenges in the design and operation of WP forecasting models. Since state-of-the-art forecasting methods consider past WP generation values alongside day-ahead weather forecasts, redispatch shutdowns may impact the forecast. Therefore, the present paper highlights these challenges and analyzes state-of-the-art forecasting methods on data sets with both regular and irregular shutdowns. Specifically, we compare the forecasting accuracy of three autoregressive Deep Learning (DL) methods to methods based on WP curve modeling. Interestingly, the latter achieve lower forecasting errors, have fewer requirements for data cleaning during modeling and operation while being computationally more efficient, suggesting their advantages in practical applications.

Stefan Meisenbacher, Marian Turowski, Kaleb Phipps et al.

Time series forecasting is fundamental for various use cases in different domains such as energy systems and economics. Creating a forecasting model for a specific use case requires an iterative and complex design process. The typical design process includes the five sections (1) data pre-processing, (2) feature engineering, (3) hyperparameter optimization, (4) forecasting method selection, and (5) forecast ensembling, which are commonly organized in a pipeline structure. One promising approach to handle the ever-growing demand for time series forecasts is automating this design process. The present paper, thus, analyzes the existing literature on automated time series forecasting pipelines to investigate how to automate the design process of forecasting models. Thereby, we consider both Automated Machine Learning (AutoML) and automated statistical forecasting methods in a single forecasting pipeline. For this purpose, we firstly present and compare the proposed automation methods for each pipeline section. Secondly, we analyze the automation methods regarding their interaction, combination, and coverage of the five pipeline sections. For both, we discuss the literature, identify problems, give recommendations, and suggest future research. This review reveals that the majority of papers only cover two or three of the five pipeline sections. We conclude that future research has to holistically consider the automation of the forecasting pipeline to enable the large-scale application of time series forecasting.

Oliver Neumann, Nicole Ludwig, Marian Turowski et al.

Deep Neural Networks are able to solve many complex tasks with less engineering effort and better performance. However, these networks often use data for training and evaluation without investigating its representation, i.e.~the form of the used data. In the present paper, we analyze the impact of data representations on the performance of Deep Neural Networks using energy time series forecasting. Based on an overview of exemplary data representations, we select four exemplary data representations and evaluate them using two different Deep Neural Network architectures and three forecasting horizons on real-world energy time series. The results show that, depending on the forecast horizon, the same data representations can have a positive or negative impact on the accuracy of Deep Neural Networks.

Stefan Meisenbacher, Janik Pinter, Tim Martin et al.

Undoubtedly, the increase of available data and competitive machine learning algorithms has boosted the popularity of data-driven modeling in energy systems. Applications are forecasts for renewable energy generation and energy consumption. Forecasts are elementary for sector coupling, where energy-consuming sectors are interconnected with the power-generating sector to address electricity storage challenges by adding flexibility to the power system. However, the large-scale application of machine learning methods in energy systems is impaired by the need for expert knowledge, which covers machine learning expertise and a profound understanding of the application's process. The process knowledge is required for the problem formalization, as well as the model validation and application. The machine learning skills include the processing steps of i) data pre-processing, ii) feature engineering, extraction, and selection, iii) algorithm selection, iv) hyperparameter optimization, and possibly v) post-processing of the model's output. Tailoring a model for a particular application requires selecting the data, designing various candidate models and organizing the data flow between the processing steps, selecting the most suitable model, and monitoring the model during operation - an iterative and time-consuming procedure. Automated design and operation of machine learning aim to reduce the human effort to address the increasing demand for data-driven models. We define five levels of automation for forecasting in alignment with the SAE standard for autonomous vehicles, where manual design and application reflect Automation level 0.

Moritz Weber, Marian Turowski, Hüseyin K. Çakmak et al.

A cornerstone of the worldwide transition to smart grids are smart meters. Smart meters typically collect and provide energy time series that are vital for various applications, such as grid simulations, fault-detection, load forecasting, load analysis, and load management. Unfortunately, these time series are often characterized by missing values that must be handled before the data can be used. A common approach to handle missing values in time series is imputation. However, existing imputation methods are designed for power time series and do not take into account the total energy of gaps, resulting in jumps or constant shifts when imputing energy time series. In order to overcome these issues, the present paper introduces the new Copy-Paste Imputation (CPI) method for energy time series. The CPI method copies data blocks with similar properties and pastes them into gaps of the time series while preserving the total energy of each gap. The new method is evaluated on a real-world dataset that contains six shares of artificially inserted missing values between 1 and 30%. It outperforms by far the three benchmark imputation methods selected for comparison. The comparison furthermore shows that the CPI method uses matching patterns and preserves the total energy of each gap while requiring only a moderate run-time.

Hatem Khalloof, Wilfried Jakob, Shadi Shahoud et al.

Recent years have seen an increasing integration of distributed renewable energy resources into existing electric power grids. Due to the uncertain nature of renewable energy resources, network operators are faced with new challenges in balancing load and generation. In order to meet the new requirements, intelligent distributed energy resource plants can be used which provide as virtual power plants e.g. demand side management or flexible generation. However, the calculation of an adequate schedule for the unit commitment of such distributed energy resources is a complex optimization problem which is typically too complex for standard optimization algorithms if large numbers of distributed energy resources are considered. For solving such complex optimization tasks, population-based metaheuristics -- as e.g. evolutionary algorithms -- represent powerful alternatives. Admittedly, evolutionary algorithms do require lots of computational power for solving such problems in a timely manner. One promising solution for this performance problem is the parallelization of the usually time-consuming evaluation of alternative solutions. In the present paper, a new generic and highly scalable parallel method for unit commitment of distributed energy resources using metaheuristic algorithms is presented. It is based on microservices, container virtualization and the publish/subscribe messaging paradigm for scheduling distributed energy resources. Scalability and applicability of the proposed solution are evaluated by performing parallelized optimizations in a big data environment for three distinct distributed energy resource scheduling scenarios. The new method provides cluster or cloud parallelizability and is able to deal with a comparably large number of distributed energy resources. The application of the new proposed method results in very good performance for scaling up optimization speed.

Jorge Ángel González Ordiano, Lutz Gröll, Ralf Mikut et al.

Parametric quantile regressions are a useful tool for creating probabilistic energy forecasts. Nonetheless, since classical quantile regressions are trained using a non-differentiable cost function, their creation using complex data mining techniques (e.g., artificial neural networks) may be complicated. This article presents a method that uses a new nearest neighbors quantile filter to obtain quantile regressions independently of the utilized data mining technique and without the non-differentiable cost function. Thereafter, a validation of the presented method using the dataset of the Global Energy Forecasting Competition of 2014 is undertaken. The results show that the presented method is able to solve the competition's task with a similar accuracy and in a similar time as the competition's winner, but requiring a much less powerful computer. This property may be relevant in an online forecasting service for which the fast computation of probabilistic forecasts using not so powerful machines is required.