Towards Resilient Energy Systems - Probabilistic Deep Learning for Forecasting and Control under Uncertainty

Arpogaus, Marcel

dc.contributor.advisor	Schubert, Gunnar Prof. Dr.
dc.contributor.author	Arpogaus, Marcel
dc.date.accessioned	2025-10-09T17:30:47Z
dc.date.available	2025-10-16T00:50:05Z
dc.date.issued	2025-10-09
dc.identifier.uri	http://resolver.sub.uni-goettingen.de/purl?ediss-11858/16272
dc.identifier.uri	http://dx.doi.org/10.53846/goediss-11536
dc.format.extent	156	de
dc.language.iso	eng	de
dc.rights.uri	http://creativecommons.org/licenses/by/4.0/
dc.subject.ddc	510	de
dc.title	Towards Resilient Energy Systems - Probabilistic Deep Learning for Forecasting and Control under Uncertainty	de
dc.type	doctoralThesis	de
dc.contributor.referee	Kneib, Thomas Prof. Dr.
dc.date.examination	2025-09-29	de
dc.description.abstracteng	The integration of variable renewable energy source (RES) and the electrification of end-use sectors introduce significant uncertainty into energy systems, challenging traditional deterministic modeling and operational paradigms. This cumulative dissertation addresses these challenges by exploring, developing and applying probabilistic deep learning methods to improve uncertainty quantification and management in power grids and related domains. This research advances novel probabilistic deep learning techniques, focusing on deep conditional transformation models (CTMs) and their extensions. Key contributions include: (i) Demonstrating that deep CTMs, particularly Bernstein normalizing flows (BNFs), deliver accurate and robust probabilistic short-term load forecasts at the low voltage (LV) level, outperforming conventional approaches, especially under data scarcity. (ii) Proposing a real-time grid operation framework that combines probabilistic forecasts with a graph neural network (GNN) based control model, enabling proactive management of distribution grids under uncertainty. (iii) Extending autoregressive deep CTMs to probabilistic indoor temperature forecasting, providing uncertainty estimates for heating, ventilation and air conditioning (HVAC) control through stochastic optimization strategies. (iv) Introducing hybrid Bernstein normalizing flows (HBNFs), a novel hybrid model class that integrates interpretable marginal modeling through CTMs with flexible multivariate modeling using neural network (NN) based autoregressive normalizing flows (NFs), addressing the trade-off between interpretability and expressiveness in multivariate density estimation. Together, these contributions offer advanced methods and tools for uncertainty quantification and control in energy systems. By advancing probabilistic forecasting and decision-making, this work supports the development of more resilient, efficient and adaptable energy grids. The findings underscore the practical value of distributional modeling and the potential of hybrid statistical and deep learning approaches for addressing the limited interpretability arising from the black-box nature of pure deep learning methods.	de
dc.contributor.coReferee	Baum, Marcus Prof. Dr.
dc.subject.eng	Normalizing Flows	de
dc.subject.eng	Probabilistic Regression	de
dc.subject.eng	Deep Learning	de
dc.subject.eng	Low-Voltage	de
dc.subject.eng	Probabilistic Load Forecasting	de
dc.subject.eng	Probabilistic Deep Learning	de
dc.subject.eng	Distributional Regression	de
dc.subject.eng	Transformation Models	de
dc.subject.eng	Bernstein Polynomials	de
dc.subject.eng	Conditional density estimation	de
dc.subject.eng	Indoor temperature	de
dc.subject.eng	Autoregressive Transformation Models	de
dc.subject.eng	Machine learning	de
dc.subject.eng	Multivariate Density Estimation	de
dc.subject.eng	Multivariate Conditional Transformation Models	de
dc.subject.eng	Resilient Energy Systems	de
dc.subject.eng	Grid Operation Management	de
dc.subject.eng	Renewable Energy Sources	de
dc.subject.eng	Electrical Vehicles	de
dc.identifier.urn	urn:nbn:de:gbv:7-ediss-16272-8
dc.affiliation.institute	Fakultät für Mathematik und Informatik	de
dc.subject.gokfull	Informatik (PPN619939052)	de
dc.description.embargoed	2025-10-16	de
dc.identifier.ppn	1938248635
dc.identifier.orcid	0000-0003-1417-3896	de
dc.notes.confirmationsent	Confirmation sent 2025-10-09T19:45:02	de

Files in this item

Name:20251002--Dissertation_Marcel_Arpogaus-online.pdf

Size:23.22Mb

Format:PDF

View/Open

Name:: 20251002--Dissertation_Marcel_ ...
Size:: 23.22Mb
Format:: PDF

View/Open

This item appears in the following Collection(s)

Fakultät für Mathematik und Informatik (inkl. GAUSS) [568]

Show simple item record