arXiv subjects

Jochen L. Cremer

Publications and source records attributed to Jochen L. Cremer.

At least 19 recordsLinked to original sources

arXiv2026

Assessing the Generalization of Graph Neural Networks for Fault Location Across Increasing Distributed Energy Resource Penetration Levels

Accurate fault location is critical for distribution network reliability. However, increasing distributed energy resource (DER) penetration complicates fault location due to intermittent generation and bidirectional power flows that reshape fault signatures. Spatio-Temporal Graph Neural Networks (STGNNs) have shown promise by jointly modeling spatial and temporal dependencies, but their behavior under increasing DER penetration has not been studied rigorously. In this paper, we (i) systematically benchmark spatio-temporal graph attention network (STGATv2) against purely temporal (gated recurrent unit, GRU), purely spatial (GATv2) and traditional machine learning baselines, and (ii) evaluate how well models generalize across increasing DER penetration levels (10%, 25%, 50%) on a reconfigured IEEE 123-bus feeder with multiple DER injection points and moderate-to-high impedance faults. Results show that STGATv2 consistently outperforms neural baselines, achieving 92-94% macro F1 in-distribution. Notably, generalization across penetration levels is asymmetric: training at 50% penetration retains near in-distribution F1 score at lower levels, whereas training at 10% degrades considerably at 50% - with STGATv2 retaining 81-84% F1 under these drastic shifts, substantially higher than GATv2 and GRU which drop to 69-74% F1 and 73-75% F1 respectively. Under realistic measurement noise, STGATv2 maintains > 85% F1, while GRU drops as low as 33.5% F1, highlighting the critical role of topological awareness for robust fault location in active distribution networks.

cs.LG↗

arXiv2026

Deep Learning for Electricity Price Forecasting: A Review of Day-Ahead, Intraday, and Balancing Electricity Markets

Electricity price forecasting (EPF) plays a critical role in power system operation and market decision making. While existing review studies have provided valuable insights into forecasting horizons, market mechanisms, and evaluation practices, the rapid adoption of deep learning has introduced increasingly diverse model architectures, output structures, and training objectives that remain insufficiently analyzed in depth. This paper presents a structured review of deep learning methods for EPF in day-ahead, intraday, and balancing markets. Specifically, We introduce a unified taxonomy that decomposes deep learning models into backbone, head, and loss components, providing a consistent evaluation perspective across studies. Using this framework, we analyze recent trends in deep learning components across markets. Our study highlights the shift toward probabilistic, microstructure-centric, and market-aware designs. We further identify key gaps in the literature, including limited attention to intraday and balancing markets and the need for market-specific modeling strategies, thereby helping to consolidate and advance existing review studies.

q-fin.CP↗

arXiv2026

OrderFusion: Encoding Orderbook for End-to-End Probabilistic Intraday Electricity Price Forecasting

Probabilistic intraday electricity price forecasting is becoming increasingly important for short-term power-system operation. With increasing renewable generation, demand-side flexibility, and storage assets, market participants need to adjust their positions under uncertainty closer to delivery. Continuous intraday (CID) markets support this process by providing updated price signals, helping participants manage imbalance exposure and operational risk. Unlike auction markets, CID trading in many jurisdictions is characterized by the continuous posting of buy and sell orders. This dynamic orderbook microstructure of price formation presents special challenges for price forecasting. Conventional methods represent the orderbook via domain features aggregated from buy and sell trades, or by treating it as a multivariate time series, but such representations neglect the full buy-sell interaction structure of the orderbook. This research therefore develops a new order fusion methodology, which is an end-to-end and parameter-efficient probabilistic forecasting model that learns a interaction-aware representation of the buy-sell dynamics. Furthermore, as quantile crossing is often a problem in probabilistic forecasting, this approach hierarchically estimates the quantiles with non-crossing constraints. Extensive experiments on CID price indices across high- and low-liquidity European markets demonstrate consistent improvements over conventional baselines, and ablation studies highlight the contributions of the main components.The methodology is available at: https://runyao-yu.github.io/OrderFusion/.

q-fin.CP↗

arXiv2026

A Market-Rule-Informed Neural Network for Efficient Imbalance Electricity Price Forecasting

Accurate and efficient imbalance electricity price forecasting is critical for industrial energy trading systems, especially as battery assets and automated bidding pipelines increasingly participate in balancing markets. However, real-time forecasting is complicated by nonlinear market-rule-based price formation, heterogeneous input signals, and incomplete data availability caused by communication delays, publication lags, and measurement outages. This paper proposes a market-rule-informed neural forecasting framework that embeds imbalance price formation rules into the latent space of an expressive neural network. The proposed framework preserves raw signal information while exploiting transparent market-rule priors. We further analyze operational robustness by removing price-component information and characterize how forecasting performance scales with input length and forecasting horizon. Experimental results show that the proposed model achieves competitive forecasting performance with substantially fewer trainable parameters and shorter training time than generic deep learning baselines. Experimental results show that the proposed model achieves competitive forecasting performance with substantially fewer trainable parameters and shorter training time than generic deep learning baselines, demonstrating that market-rule priors and expressive neural networks should be jointly used for accurate and computationally sustainable forecasting in industrial energy trading applications. The implementation is publicly available at https://runyao-yu.github.io/MRINN/.

q-fin.CP↗

arXiv2026

PriceFM: Foundation Model for Probabilistic Electricity Price Forecasting

Electricity price forecasting in Europe presents unique challenges due to increasing renewable generation variability, market integration, and the continent's physically interconnected power system. While recent advances in foundation models have led to substantial improvements in general time series forecasting, most existing approaches do not incorporate prior graph knowledge from the transmission topology, which can limit their ability to exploit meaningful cross-region dependencies in interconnected power systems, motivating a domain-specific foundation model. In this paper, we address this gap by first introducing a comprehensive and up-to-date dataset across 24 European countries (38 regions), spanning from 2022-01-01 to 2026-01-01. Building on this groundwork, we propose PriceFM, a probabilistic foundation model pretrained on this large dataset. Specifically, PriceFM maps each region's price and exogenous features, including load, solar, and wind generation forecasts, into a comparable latent embedding via a shared Mixture-of-Experts (MoE) projection layer, then injects prior graph knowledge by constructing a sparse graph mask derived from transmission topology. Across a large-scale European benchmark, PriceFM achieves strong performance and demonstrates superior generalization compared with multiple competitive baselines. The results highlight the value of topology-guided forecasting with increasing renewable generation and strong cross-border interconnections. The methodology is available at: https://runyao-yu.github.io/PriceFM/.

cs.CE↗

arXiv2026

Towards Generalization of Graph Neural Networks for AC Optimal Power Flow

AC Optimal Power Flow (ACOPF) is computationally intensive for large-scale grids, often requiring prohibitive solution times with conventional solvers. Machine learning offers significant speedups, but existing models struggle with scalability and topology flexibility. To address these challenges, we propose a Hybrid Heterogeneous Message Passing Neural Network (HH-MPNN) that integrates a heterogeneous graph neural network (GNN) with a scalable transformer and physics-informed positional encodings. Our architecture explicitly models distinct power system components to capture local features while using global attention for long-range dependencies. Evaluated on diverse benchmarks, including PGLearn and GridFM-DataKit datasets, HH-MPNN achieves less than 1% optimality gap on default topologies across grid sizes from 14 to 2,000 buses. For N-1 contingencies, our approach demonstrates zero-shot N-1 generalization with less than 3% optimality gap on several test cases despite training only on default topologies. We further develop an approach that ensures robust N-1 generalization to high-impact contingencies through targeted augmentation of the training data, showing that exhaustive simulation is unnecessary for topologically flexible models. Finally, size generalization experiments demonstrate that pre-training on small grids significantly improves performance on large-scale systems. Achieving computational speedups of up to 5,000 times compared to interior point solvers, these results advance practical, generalizable machine learning for real-time power system operations.

cs.LG↗

arXiv2026

Transferable Graph Learning for Transmission Congestion Management via Busbar Splitting

Network topology optimization (NTO) via busbar splitting can mitigate transmission grid congestion and reduce redispatch costs. However, solving this mixed-integer nonlinear problem for large-scale systems in near-real-time is currently intractable with existing solvers. Machine learning (ML) approaches have emerged as a promising alternative, but they have limited generalization to unseen topologies, varying operating conditions, and different systems, which limits their practical applicability. This paper formulates NTO for congestion management considering linearized AC power flow, and proposes a graph neural network (GNN)-accelerated approach. We develop a heterogeneous edge-aware message passing GNN to predict effective nodes for busbar splitting actions as candidate NTO solutions. The proposed GNN captures local flow patterns, improves generalization to unseen topology changes, and enhances transferability across systems. Case studies show up to 4 orders-of-magnitude speed-up, delivering AC-feasible solutions within one minute and a 2.3% optimality gap on the GOC 2000-bus system. These results demonstrate a significant step toward near-real-time NTO for large-scale systems with topology and cross-system generalization.

cs.AI↗

arXiv2026

Security-Constrained Substation Reconfiguration Considering Busbar and Coupler Contingencies

Substation reconfiguration via busbar splitting can mitigate transmission grid congestion and reduce operational costs. However, existing approaches neglect the security of substation topology, particularly for substations without busbar splitting (i.e., closed couplers), which can lead to severe consequences. Additionally, the computational complexity of optimizing substation topology remains a challenge. This paper introduces a MILP formulation for security-constrained substation reconfiguration (SC-SR), considering N-1 line, coupler and busbar contingencies to ensure secure substation topology. To efficiently solve this problem, we propose a heuristic approach with multiple master problems (HMMP). A central master problem optimizes dispatch, while independent substation master problems determine individual substation topologies in parallel. Linear AC power flow equations ensure PF accuracy, while feasibility and optimality sub-problems evaluate contingency cases. The proposed HMMP significantly reduces computational complexity and enables scalability to large-scale power systems. Case studies on the IEEE 14-bus, 118-bus, and PEGASE 1354-bus system show the effectiveness of the approach in mitigating the impact of coupler and busbar tripping, balancing system security and cost, and computational efficiency.

eess.SY↗

arXiv2026

Probabilistic Hysteresis Factor Prediction for Electric Vehicle Batteries with Graphite Anodes Containing Silicon

Batteries with silicon-graphite-based anodes, which offer higher energy density and improved charging performance, introduce pronounced voltage hysteresis, making state-of-charge (SoC) estimation particularly challenging. Existing approaches to modeling hysteresis rely on exhaustive high-fidelity tests or focus on conventional graphite-based lithium-ion batteries, without considering uncertainty quantification or computational constraints. This work introduces a data-driven approach for probabilistic hysteresis factor prediction, with a particular emphasis on applications involving silicon-graphite anode-based batteries. A data harmonization framework is proposed to standardize heterogeneous driving cycles across varying operating conditions. Statistical learning and deep learning models are applied to assess performance in predicting the hysteresis factor with uncertainties while considering computational efficiency. Extensive experiments are conducted to evaluate the generalizability of the optimal model configuration in unseen vehicle models through retraining, zero-shot prediction, fine-tuning, and joint training. By addressing key challenges in SoC estimation, this research facilitates the adoption of advanced battery technologies. A summary page is available at: https://runyao-yu.github.io/Porsche_Hysteresis_Factor_Prediction/

cs.LG↗

arXiv2026

Customising Electricity Contracts at Scale with Large Language Models

The electricity system becomes more complex, connecting massive numbers of end-users and distributed generators. Adding or removing grid connections requires expert studies to align technical constraints with user requests. In times of labour shortages, carrying out these studies represents a significant amount of time that engineers at system operators spend in planning departments. As time is limited, only standard block connectivity contracts can be offered to end-users, or the requests pile up. Even if offers are made, these often do not perfectly match the user's requirements, leading to overpaying or underusing the grid capacity. This paper investigates whether end-users can negotiate individual, flexible time-of-use contracts directly with the grid using Large Language Models (LLMs) in chats at scale. This work addresses system-level technical challenges in automating contract design under grid constraints, integrating LLMs with power system models, and ensuring secure, reliable interaction. We develop a chat system using functional programs for power system analysis, enabling users to request customised, technically feasible contracts at scale. We demonstrate high accuracy in executing engineering studies, robustness to user input variations, self-assessment of connection requests by small and medium enterprises, and potential for secure, chat-enabled maintenance planning. This initial study paves the way toward developing a tailored LLM system, resulting in possible high-efficiency gains for grid planning and customer management. The code is available at: https://github.com/TU-Delft-AI-Energy-Lab/LLM-Electricity-Contracts

eess.SY↗

arXiv2026

Orderbook Feature Learning and Asymmetric Generalization in Intraday Electricity Markets

Accurate probabilistic forecasting of intraday electricity prices is critical for market participants to inform trading decisions. Existing studies rely on specific domain features, such as Volume-Weighted Average Price (VWAP) and the last price. However, the rich information in the orderbook remains underexplored. Furthermore, these approaches are often developed within a single country and product type, making it unclear whether the approaches are generalizable. In this paper, we extract 384 features from the orderbook and identify a set of powerful features via feature selection. Based on selected features, we present a comprehensive benchmark using classical statistical models, tree-based ensembles, and deep learning models across two countries (Germany and Austria) and two product types (60-min and 15-min). We further perform a systematic generalization study across countries and product types, from which we reveal an asymmetric generalization phenomenon: models trained on more liquid markets or products transfer well to less liquid ones, whereas the reverse transfer leads to substantial performance degradation.

q-fin.CP↗

arXiv2025

Multi-Objective Reinforcement Learning for Power Grid Topology Control

Transmission grid congestion increases as the electrification of various sectors requires transmitting more power. Topology control, through substation reconfiguration, can reduce congestion but its potential remains under-exploited in operations. A challenge is modeling the topology control problem to align well with the objectives and constraints of operators. Addressing this challenge, this paper investigates the application of multi-objective reinforcement learning (MORL) to integrate multiple conflicting objectives for power grid topology control. We develop a MORL approach using deep optimistic linear support (DOL) and multi-objective proximal policy optimization (MOPPO) to generate a set of Pareto-optimal policies that balance objectives such as minimizing line loading, topological deviation, and switching frequency. Initial case studies show that the MORL approach can provide valuable insights into objective trade-offs and improve Pareto front approximation compared to a random search baseline. The generated multi-objective RL policies are 30% more successful in preventing grid failure under contingencies and 20% more effective when training budget is reduced - compared to the common single objective RL policy.

cs.LG↗

arXiv2024

A Pioneering Roadmap for ML-Driven Algorithmic Advancements in Electrical Networks

Advanced control, operation, and planning tools of electrical networks with ML are not straightforward. 110 experts were surveyed to show where and how ML algorithms could advance. This paper assesses this survey and research environment. Then, it develops an innovation roadmap that helps align our research community with a goal-oriented realisation of the opportunities that AI upholds. This paper finds that the R&D environment of system operators (and the surrounding research ecosystem) needs adaptation to enable faster developments with AI while maintaining high testing quality and safety. This roadmap serves system operators, academics, and labs advancing next-generation electrical network tools.

eess.SY↗

arXiv2024

Learning a Reward Function for User-Preferred Appliance Scheduling

Accelerated development of demand response service provision by the residential sector is crucial for reducing carbon-emissions in the power sector. Along with the infrastructure advancement, encouraging the end users to participate is crucial. End users highly value their privacy and control, and want to be included in the service design and decision-making process when creating the daily appliance operation schedules. Furthermore, unless they are financially or environmentally motivated, they are generally not prepared to sacrifice their comfort to help balance the power system. In this paper, we present an inverse-reinforcement-learning-based model that helps create the end users' daily appliance schedules without asking them to explicitly state their needs and wishes. By using their past consumption data, the end consumers will implicitly participate in the creation of those decisions and will thus be motivated to continue participating in the provision of demand response services.

cs.AI↗

arXiv2023

Deep Statistical Solver for Distribution System State Estimation

Implementing accurate Distribution System State Estimation (DSSE) faces several challenges, among which the lack of observability and the high density of the distribution system. While data-driven alternatives based on Machine Learning models could be a choice, they suffer in DSSE because of the lack of labeled data. In fact, measurements in the distribution system are often noisy, corrupted, and unavailable. To address these issues, we propose the Deep Statistical Solver for Distribution System State Estimation (DSS$^2$), a deep learning model based on graph neural networks (GNNs) that accounts for the network structure of the distribution system and for the physical governing power flow equations. DSS$^2$ leverages hypergraphs to represent the heterogeneous components of the distribution systems and updates their latent representations via a node-centric message-passing scheme. A weakly supervised learning approach is put forth to train the DSS$^2$ in a learning-to-optimize fashion w.r.t. the Weighted Least Squares loss with noisy measurements and pseudomeasurements. By enforcing the GNN output into the power flow equations and the latter into the loss function, we force the DSS$^2$ to respect the physics of the distribution system. This strategy enables learning from noisy measurements, acting as an implicit denoiser, and alleviating the need for ideal labeled data. Extensive experiments with case studies on the IEEE 14-bus, 70-bus, and 179-bus networks showed the DSS$^2$ outperforms by a margin the conventional Weighted Least Squares algorithm in accuracy, convergence, and computational time, while being more robust to noisy, erroneous, and missing measurements. The DSS$^2$ achieves a competing, yet lower, performance compared with the supervised models that rely on the unrealistic assumption of having all the true labels.

cs.LG↗

arXiv2023

End-to-End Learning with Multiple Modalities for System-Optimised Renewables Nowcasting

With the increasing penetration of renewable power sources such as wind and solar, accurate short-term, nowcasting renewable power prediction is becoming increasingly important. This paper investigates the multi-modal (MM) learning and end-to-end (E2E) learning for nowcasting renewable power as an intermediate to energy management systems. MM combines features from all-sky imagery and meteorological sensor data as two modalities to predict renewable power generation that otherwise could not be combined effectively. The combined, predicted values are then input to a differentiable optimal power flow (OPF) formulation simulating the energy management. For the first time, MM is combined with E2E training of the model that minimises the expected total system cost. The case study tests the proposed methodology on the real sky and meteorological data from the Netherlands. In our study, the proposed MM-E2E model reduced system cost by 30% compared to uni-modal baselines.

eess.SY↗

arXiv2023

Regularised Learning with Selected Physics for Power System Dynamics

Due to the increasing system stability issues caused by the technological revolutions of power system equipment, the assessment of the dynamic security of the systems for changing operating conditions (OCs) is nowadays crucial. To address the computational time problem of conventional dynamic security assessment tools, many machine learning (ML) approaches have been proposed and well-studied in this context. However, these learned models only rely on data, and thus miss resourceful information offered by the physical system. To this end, this paper focuses on combining the power system dynamical model together with the conventional ML. Going beyond the classic Physics Informed Neural Networks (PINNs), this paper proposes Selected Physics Informed Neural Networks (SPINNs) to predict the system dynamics for varying OCs. A two-level structure of feed-forward NNs is proposed, where the first NN predicts the generator bus rotor angles (system states) and the second NN learns to adapt to varying OCs. We show a case study on an IEEE-9 bus system that considering selected physics in model training reduces the amount of needed training data. Moreover, the trained model effectively predicted long-term dynamics that were beyond the time scale of the collected training dataset (extrapolation).

eess.SY↗

arXiv2023

MARL-iDR: Multi-Agent Reinforcement Learning for Incentive-based Residential Demand Response

This paper presents a decentralized Multi-Agent Reinforcement Learning (MARL) approach to an incentive-based Demand Response (DR) program, which aims to maintain the capacity limits of the electricity grid and prevent grid congestion by financially incentivizing residential consumers to reduce their energy consumption. The proposed approach addresses the key challenge of coordinating heterogeneous preferences and requirements from multiple participants while preserving their privacy and minimizing financial costs for the aggregator. The participant agents use a novel Disjunctively Constrained Knapsack Problem optimization to curtail or shift the requested household appliances based on the selected demand reduction. Through case studies with electricity data from $25$ households, the proposed approach effectively reduced energy consumption's Peak-to-Average ratio (PAR) by $14.48$% compared to the original PAR while fully preserving participant privacy. This approach has the potential to significantly improve the efficiency and reliability of the electricity grid, making it an important contribution to the management of renewable energy resources and the growing electricity demand.

eess.SY↗