@article{PetkovicZittel2025, author = {Petkovic, Milena and Zittel, Janina}, title = {Leveraging Transfer Learning to Overcome Data Limitations in Czochralski Crystal Growth}, volume = {8}, journal = {Advanced Theory and Simulations}, number = {11}, doi = {10.1002/adts.202500677}, year = {2025}, language = {en} } @inproceedings{HadjidimitriouKochLippietal.2024, author = {Hadjidimitriou, Natalia Selini and Koch, Thorsten and Lippi, Marco and Petkovic, Milena and Mamei, Marco}, title = {Analysis of the Impact of COVID-19 and Russo-Ukraine War on Natural Gas Flow Using Time Series Forecasting}, booktitle = {Preceedings of the 16th International Conference on Management of Digital Ecosystems}, year = {2024}, language = {en} } @misc{PetkovicZakiyevaZittel2021, author = {Petkovic, Milena and Zakiyeva, Nazgul and Zittel, Janina}, title = {Statistical analysis and modeling for detecting regime changes in gas nomination time series}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-82988}, year = {2021}, abstract = {As a result of the legislation for gas markets introduced by the European Union in 2005, separate independent companies have to conduct the transport and trading of natural gas. The current gas market of Germany, which has a market value of more than 54 billion USD, consists of Transmission System Operators (TSO), network users, and traders. Traders can nominate a certain amount of gas anytime and anywhere in the network. Such unrestricted access for the traders, on the other hand, increase the uncertainty in the gas supply management. Some customers' behaviors may cause abrupt structural changes in gas flow time series. In particular, it is a challenging task for the TSO operators to predict gas nominations 6 to 10 hours ahead. In our study, we aim to investigate the regime changes in the time series of nominations to predict the 6 to 10 hours ahead of gas nominations.}, language = {en} } @article{PetkovicChenGamrathetal.2022, author = {Petkovic, Milena and Chen, Ying and Gamrath, Inken and Gotzes, Uwe and Hadjidimitrou, Natalia Selini and Zittel, Janina and Xu, Xiaofei and Koch, Thorsten}, title = {A hybrid approach for high precision prediction of gas flows}, volume = {13}, journal = {Energy Systems}, doi = {10.1007/s12667-021-00466-4}, pages = {383 -- 408}, year = {2022}, abstract = {About 23\% of the German energy demand is supplied by natural gas. Additionally, for about the same amount Germany serves as a transit country. Thereby, the German network represents a central hub in the European natural gas transport network. The transport infrastructure is operated by transmissions system operators (TSOs). The number one priority of the TSOs is to ensure the security of supply. However, the TSOs have only very limited knowledge about the intentions and planned actions of the shippers (traders). Open Grid Europe (OGE), one of Germany's largest TSO, operates a high-pressure transport network of about 12,000 km length. With the introduction of peak-load gas power stations, it is of great importance to predict in- and out-flow of the network to ensure the necessary flexibility and security of supply for the German Energy Transition ("Energiewende"). In this paper, we introduce a novel hybrid forecast method applied to gas flows at the boundary nodes of a transport network. This method employs an optimized feature selection and minimization. We use a combination of a FAR, LSTM and mathematical programming to achieve robust high-quality forecasts on real-world data for different types of network nodes.}, language = {en} } @misc{ZakiyevaPetkovic2021, author = {Zakiyeva, Nazgul and Petkovic, Milena}, title = {Modeling and forecasting gas network flows with multivariate time series and mathematical programming approach}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-82966}, year = {2021}, abstract = {With annual consumption of approx. 95 billion cubic me-ters and similar amounts of gas just transshipped through Germany toother EU states, Germany's gas transport system plays a vital role inEuropean energy supply. The complex, more than 40,000 km long high-pressure transmission network is controlled by several transmission sys-tem operators (TSOs) whose main task is to provide security of supplyin a cost-efficient way. Given the slow speed of gas flows through the gastransmission network pipelines, it has been an essential task for the gasnetwork operators to enhance the forecast tools to build an accurate andeffective gas flow prediction model for the whole network. By incorpo-rating the recent progress in mathematical programming and time seriesmodeling, we aim to model natural gas network and predict gas in- andout-flows at multiple supply and demand nodes for different forecastinghorizons. Our model is able to describe the dynamics in the network bydetecting the key nodes, which may help to build an optimal manage-ment strategy for transmission system operators.}, language = {en} } @article{PetkovicKochZittel2021, author = {Petkovic, Milena and Koch, Thorsten and Zittel, Janina}, title = {Deep learning for spatio-temporal supply anddemand forecasting in natural gas transmission networks}, journal = {Energy Science and Engineering}, doi = {https://doi.org/10.1002/ese3.932}, year = {2021}, abstract = {Germany is the largest market for natural gas in the European Union, with an annual consumption of approx. 95 billion cubic meters. Germany's high-pressure gas pipeline network is roughly 40,000 km long, which enables highly fluctuating quantities of gas to be transported safely over long distances. Considering that similar amounts of gas are also transshipped through Germany to other EU states, it is clear that Germany's gas transport system is essential to the European energy supply. Since the average velocity of gas in a pipeline is only 25km/h, an adequate high-precision, high-frequency forecasting of supply and demand is crucial for efficient control and operation of such a transmission network. We propose a deep learning model based on spatio-temporal convolutional neural networks (DLST) to tackle the problem of gas flow forecasting in a complex high-pressure transmission network. Experiments show that our model effectively captures comprehensive spatio-temporal correlations through modeling gas networks and consistently outperforms state-of-the-art benchmarks on real-world data sets by at least 21\%. The results demonstrate that the proposed model can deal with complex nonlinear gas network flow forecasting with high accuracy and effectiveness.}, language = {en} } @article{RoessigPetkovic2020, author = {R{\"o}ssig, Ansgar and Petkovic, Milena}, title = {Advances in Verification of ReLU Neural Networks}, journal = {Journal of Global Optimization}, publisher = {Springer}, doi = {10.1007/s10898-020-00949-1}, year = {2020}, abstract = {We consider the problem of verifying linear properties of neural networks. Despite their success in many classification and prediction tasks, neural networks may return unexpected results for certain inputs. This is highly problematic with respect to the application of neural networks for safety-critical tasks, e.g. in autonomous driving. We provide an overview of algorithmic approaches that aim to provide formal guarantees on the behavior of neural networks. Moreover, we present new theoretical results with respect to the approximation of ReLU neural networks. On the other hand, we implement a solver for verification of ReLU neural networks which combines mixed integer programming (MIP) with specialized branching and approximation techniques. To evaluate its performance, we conduct an extensive computational study. For that we use test instances based on the ACAS Xu System and the MNIST handwritten digit data set. Our solver is publicly available and able to solve the verification problem for instances which do not have independent bounds for each input neuron.}, language = {en} } @misc{PetkovicChenGamrathetal.2019, author = {Petkovic, Milena and Chen, Ying and Gamrath, Inken and Gotzes, Uwe and Hadjidimitriou, Natalia Selini and Zittel, Janina and Xu, Xiaofei and Koch, Thorsten}, title = {A Hybrid Approach for High Precision Prediction of Gas Flows}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-73525}, year = {2019}, abstract = {About 20\% of the German energy demand is supplied by natural gas. Ad- ditionally, for about twice the amount Germany serves as a transit country. Thereby, the German network represents a central hub in the European natural gas transport network. The transport infrastructure is operated by so-called transmissions system operators or TSOs. The number one priority of the TSOs is to ensure security of supply. However, the TSOs have no knowledge of the intentions and planned actions of the shippers (traders). Open Grid Europe (OGE), one of Germany's largest TSO, operates a high- pressure transport network of about 12.000 km length. Since flexibility and security of supply is of utmost importance to the German Energy Transition ("Energiewende") especially with the introduction of peak-load gas power stations, being able to predict in- and out-flow of the network is of great importance. In this paper we introduce a new hybrid forecast method applied to gas flows at the boundary nodes of a transport network. The new method employs optimized feature minimization and selection. We use a combination of an FAR, LSTM DNN and mathematical programming to achieve robust high quality forecasts on real world data for different types of network nodes. Keywords: Gas Forecast, Time series, Hybrid Method, FAR, LSTM, Mathematical Optimisation}, language = {en} } @misc{GamrathPetkovic2019, author = {Gamrath, Inken and Petkovic, Milena}, title = {Prediction of Intermitted Flows in Large Gas Networks}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-73717}, year = {2019}, language = {en} } @inproceedings{PetkovicZittel2025, author = {Petkovic, Milena and Zittel, Janina}, title = {Resilient Forecasting of High-Dimensional Network Time Series in the Energy Domain: A Hybrid Approach}, booktitle = {Operations Research Proceedings 2023. OR 2023}, publisher = {Springer}, doi = {10.1007/978-3-031-58405-3_48}, pages = {375 -- 381}, year = {2025}, abstract = {Energy systems are complex networks consisting of various interconnected components. Accurate energy demand and supply forecasts are crucial for efficient system operation and decision-making. However, high-dimensional data, complex network structures, and dynamic changes and disruptions in energy networks pose significant challenges for forecasting models. To address this, we propose a hybrid approach for resilient forecasting of network time series (HRF-NTS) in the energy domain. Our approach combines mathematical optimization methods with state-of-the-art machine learning techniques to achieve accurate and robust forecasts for high-dimensional energy network time series. We incorporate an optimization framework to account for uncertainties and disruptive changes in the energy system. The effectiveness of the proposed approach is demonstrated through a case study of forecasting energy demand and supply in a complex, large-scale natural gas transmission network. The results show that the hybrid approach outperforms alternative prediction models in terms of accuracy and resilience to structural changes and disruptions, providing stable, multi-step ahead forecasts for different short to mid-term forecasting horizons.}, language = {en} }