Forschungsgruppe Applied Mathematics for Energy Markets

Die Reaktorkatastrophe von Fukushima führte in Deutschland zur sofortigen Abschaltung mehrerer Kernkraftwerke und markierte den Beginn eines tiefgreifenden Wandels hin zu erneuerbaren Energien. Da Wind- und Solarenergie stark von Wetterbedingungen abhängig sind und damit stochastischen Schwankungen unterliegen, werden neue und fortschrittliche Methoden benötigt, um beispielsweise:

• den Nettoenergiebedarf für den nächsten Tag vorherzusagen (Netzmanagement),
• reale Optionen wie Kraftwerke oder Energiespeicher effizient zu betreiben,
• Wetterentwicklungen zur Prognose der Stromerzeugung aus erneuerbaren Energien vorherzusagen,
• Preisentwicklungen für ein verbessertes Risikomanagement und den Energiehandel zu analysieren.

Mitwirkende: 

• Abhinav Das

• Prof. Dr. Stephan Schlüter

Mitwirkende: 

• Dr. Milena Kojić, PhD
• Dr. Petar Mitić, PhD 
• Prof. Dr. Stephan Schlüter

Working papers

• Lara Pinal E M, Das A, Schlüter S (2024). Development and Implementation of a Low-Cost Modular IoT Device for Environmental Monitoring and Solar Energy Forecasting Using Artificial Intelligence. Working Paper. Submitted.

Published papers

• Lebedev A, Das A, Pappert S, Schlüter S (2026): Analyzing Uncertainty Quantification in Statisticaland Deep Learning Models for Probabilistic Electricity Price Forecasting. IEEE Access. https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11430173
• Das A, Schlüter S, Schneider L (2026): Regime-aware conditional neural processes with multi-criteria decision support for operational electricity price forecasting. https://doi.org/10.1016/j.eneco.2026.109233.
• Das A, Schlüter S, Schneider L (2026): Electricity Price Prediction Using Multi-Kernel Gaussian Process Regression combined with Kernel-Based Support Vector Regression. Journal of Forecasting. https://onlinelibrary.wiley.com/doi/10.1002/for.70124.
• Hwang YS, Schlüter S, Park H, Um JS (2026). The Arctic vegetation is more sensitive to heatwave-induced photosynthetic decline than other climate zones in Europe (2009-2017). Scientific Reports.
• Hwang YS, Schlüter S, Lee JJ, Um JS (2026). Unlocking the potential of ChatGPT in investigating NDVI over the vineyard habitat of the Mediterranean coastal city. Joural of Coastal Conservation. 30:1. https://doi.org/10.1007/s11852-025-01184-0productivity.
• Hwang YS, Schlüter S, Pradha B,Um JS (2025). Unlocking the potential of ChatGPT in detecting the XCO2 hotspot captured by orbiting carbon observatory-3 satellite. Scientific Reports, 15, 28969.
• Vogl M, Kojic M, Schlüter S (2025): Decrypting the Triad of Climate Policies, Macroeconomic Interdependencies and Quantitative Modelling: A Literature REview on Quantifying Climate Risks. Accepted in Regional Science & Policy.
• Hwang YS, Um JS,  Pradha B, Schlüter S (2025). Using ChatGPT for detecting temperature anomalies in solar cells: potentials and constraints. Spatial Information Research, 33(37). https://doi.org/10.1007/s41324-025-00636-x
• Kojic M, Mitic, P, von Döllen A, Schlüter S, (2025). Nonlinear Dependence Structures in Energy Commodities and Power Prices -- What Fractals can tell Us About Power Price Behavior. Fractals, Vol. 33(5)
• Das A, Schlüter S (2025). Gaussian Process Regression with a Hybrid Risk Measure for Dynamic Risk Management in the Electricity Market. Risks 2025, 13(1), 13; doi.org/10.3390/risks13010013
• von Döllen A, Schlüter S (2024): Heat Pumps for Germany – Additional Pressure on the (Renewable) Supply-Demand Equilibrium and How to Cope with Hydrogen. Energies, 17(12), 3053; doi.org/10.3390/en17123053
• Hwang Y-S, Um Y-S,Pradhan B, Choudhury T, Schlüter S (2023): How does ChatGBT evaluate the value of spatial information in the 4th industrial revolution? Spatial Information Research. link.springer.com/article/10.1007/s41324-023-00567-5
• Mitić P, Kojić M, Hanić A, Schlüter S. Environment and Economy Interactions in the Western Balkans: Current Situation and Prospects (2023). In: Tufek-Memišević, T., Arslanagić-Kalajdžić, M., Ademović, N. (eds) Interdisciplinary Advances in Sustainable Development. ICSD 2022. Lecture Notes in Networks and Systems, vol 529. Springer, Cham. doi.org/10.1007/978-3-031-17767-5_1
• Hwang Y-S, Schlüter S, Um J-S. Cross-correlation of GOSAT CO2 Concentration with Repeated Heat-Wave-induced Photosynthetic Inhibition in Europe from 2009 to 2017. Remote Sensing, 2022. URL: https://www.mdpi.com/2072-4292/14/18/4536/pdf
• Das, A., Makogin, V., & Spodarev, E. (2022). Extrapolation of stationary random fields via level sets. Theory of Probability and Mathematical Statistics, 106, 85-103.
• Schlüter S, Jung S,  von Döllen A, Lee W. An Alternative to Index-Based Gas Sourcing Using Neural Networks. Energies, 2022, 15, 4708. https://www.mdpi.com/1996-1073/15/13/4708/pdf .
• Kojić M, Schlüter S, Mitić P, Hanić A. Economy-environment nexus in developed European countries: Evidence from multifractal and wavelet analysis. Chaos, Solitons and Fractals, 2022, 160, 112189.
• Schlüter S, Menz F, Kojić M, Mitić P, Hanić A. A Novel Approach to Generate Hourly Photovoltaic Power Scenarios. Sustainability, 2022, 14, 4617. https:// doi.org/10.3390/su14084617.
• Hwang Y-S, Schlüter S, Park S-I, Um J-S. Comparative Evaluation for Tracking the Capability of Solar Cell Malfunction Caused by Soil Debris between UAV Video versos Photo-Mosaic. Remote Sensing, 2022, 14, 1220.
• Hwang Y-S, Roh J W, Suh D, Otto M-O, Schlüter S, Choudhurry T, Huh J-S. No Evidence for Global Decrease in CO2 Concentration During the First Wave of COVID‑19 Pandemic. Environmental Monitoring and Assessment, 2021, 193:751.
• von Döllen A, Hwang Y, Schlüter S. The Future Is Colorful—An Analysis of the CO2 Bow Wave and Why Green Hydrogen Cannot Do It Alone. Energies 2021, 14, 5720.
• Hwang Y, Schlüter S, Choudhury, T, Um J-S. Comparative Evaluation of Top-Down GOSAT XCO2 vs. Bottom-Up National Reports in the European Countries. Sustainability, 2021.
• Liebermann S, Um J-S, Hwang Y, Schlüter, S. Performance Evaluation of Neural Network-Based Short-Term Solar Irradiation Forecasts. Energies 2021, 14, 3030. DOI: https://doi.org/10.3390/en14113030.
• Hwang Y, Um J-S,  Hwang J, Schlüter S. Evaluating the Causal Relations between the Kaya Identity Index and ODIAC-Based Fossil Fuel CO2 Flux. Energies 2020. www.mdpi.com/1996-1073/13/22/6009/pdf .
• Kreuzer D, Schlüter S, Munz M. Short-term temperature forecasts using a convolutional neural network — An application to different weather stations in Germany. Machine Learning with Applications 2020, 2, doi.org/10.1016/j.mlwa.2020.100007.
• Hwang Y, Um J-S, Schlüter S. Evaluating the Mutual Relationship between IPAT/Kaya Identity Index and ODIAC-Based GOSAT Fossil-Fuel CO2 Flux: Potential and Constraints in Utilizing Decomposed Variables. Int. J. Environ. Res. Public Health 2020, 17, 5976.
• Schlüter S, Kresoja M. Two Preprocessing Algorithms for Climate Time Series. Journal of Applied Statistics 2019, https://doi.org/10.1080/02664763.2019.1701637.

Conferences

• Schlüter S, Das A, Davison M (2024): Optimal Control of a Battery Storage On the Energy Market. 2024 IEEE/IAS Industrial and Commercial Power System Asia (I&CPS Asia). ieeexplore.ieee.org/document/10761266