arXiv subjects

Fabian Leimgruber

Publications and source records attributed to Fabian Leimgruber.

5 recordsLinked to original sources

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↗

arXiv2018

Analyzing standardization needs for CHIL-based testing of power systems and components

Real-time simulation methods for investigations on electric networks and integration of grid connected generation units are increasingly in the focus of ongoing research areas. While laboratory testing methods are the predominant method for the verification of safety and quality related features of grid-connected generation units in the past, load flow modeling verification methods have been integrated in state-of-the-art standardization frameworks recently. The next step is comprised in real-time simulation methodologies applied for compliance testing of entire power electronic systems integrated in power distribution networks. The Controller Hardware-in-the-Loop (CHIL) approach is an appropriate methodology that combines numerical simulations with software modeling approaches and classical hardware testing in labs. Control boards represent the hardware device directly connected to the power electronic periphery, which is entirely simulated in a real-time simulation environment. Hereby, input signals from voltage and current measurements and output signals for power system control are exchanged in real-time. Thanks to this setup the testing of the true behavior of entire generation units within the electric network can be emulated precisely. With the application of CHIL a shorter time to market and a lower risk in the development phase can be achieved. However, an analysis from realized CHIL experiments shows the need for more harmonized procedures. This paper addresses this topic and provides an outlook about necessary future CHIL standardization needs.

eess.SY↗

arXiv2018

Hardware-in-the-Loop Co-Simulation Based Validation of Power System Control Applications

Renewables are key enablers for the realization of a sustainable energy supply but grid operators and energy utilities have to mange their intermittent behavior and limited storage capabilities by ensuring the security of supply and power quality. Advanced control approaches, automation concepts, and communication technologies have the potential to address these challenges by providing new intelligent solutions and products. However, the validation of certain aspects of such smart grid systems, especially advanced control and automation concepts is still a challenge. The main aim of this work therefore is to introduce a hardware-in-the-loop co-simulation-based validation framework which allows the simulation of large-scale power networks and control solutions together with real-world components. The application of this concept to a selected voltage control example shows its applicability.

eess.SY↗

arXiv2018

Coupling of Real-Time and Co-Simulation for the Evaluation of the Large Scale Integration of Electric Vehicles into Intelligent Power Systems

This paper addresses the validation of electric vehicle supply equipment by means of a real-time capable co-simulation approach. This setup implies both pure software and real-time simulation tasks with different sampling rates dependent on the type of the performed experiment. In contrast, controller and power hardware-in-the-loop simulations are methodologies which ask for real-time execution of simulation models with well-defined simulation sampling rates. Software and real-time methods are connected one to each other using an embedded software interface. It is able to process signals with different time step sizes and is called "LabLink". Its design implies both common and specific input and output layers (middle layer), as well as a data bus (core). The LabLink enables the application of the co-simulation methodology on the proposed experimental platform targeting the testing of electric vehicle supply equipment. The test setup architecture and representative examples for the implemented co-simulation are presented in this paper. As such, a validation of the usability of this testing platform can be highlighted aiming to support a higher penetration of electric vehicles.

eess.SY↗