7371
eng
reportzib
0
--
2019-06-18
--
Prediction of Intermitted Flows in Large Gas Networks
1438-0064
urn:nbn:de:0297-zib-73717
Inken Gamrath
Inken Gamrath
Milena Petkovic
ZIB-Report
19-29
Mathematical Optimization
MODAL-GasLab
Gamrath, Inken
MODAL-Gesamt
Petkovic, Milena
Energy Network Optimization
https://opus4.kobv.de/opus4-zib/files/7371/Zero_Opt_Prognosis.pdf
8122
eng
reportzib
0
--
2021-01-11
--
Deep learning for spatio-temporal supply and demand forecasting in natural gas transmission networks
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.
1438-0064
urn:nbn:de:0297-zib-81221
publish
Milena Petkovic
Milena Petkovic
Thorsten Koch
Janina Zittel
ZIB-Report
21-01
Koch, Thorsten
Zittel, Janina
Petkovic, Milena
Applied Algorithmic Intelligence Methods
MODAL-EnergyLab
https://opus4.kobv.de/opus4-zib/files/8122/ZIB_Report_21-01.pdf
7584
2020
eng
article
Springer
0
2020-10-27
--
--
Advances in Verification of ReLU Neural Networks
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.
Journal of Global Optimization
10.1007/s10898-020-00949-1
urn:nbn:de:0297-zib-74174
yes
Ansgar Rössig
Milena Petkovic
Milena Petkovic
Mathematical Optimization
MODAL-GasLab
MODAL-Gesamt
Petkovic, Milena
Applied Algorithmic Intelligence Methods
MODAL-EnergyLab
Freie Universität Berlin
7104
2018
eng
158
171
vol 10710
Lecture Notes in Computer Science
article
0
--
--
--
Forecasting Natural Gas Flows in Large Networks
Natural gas is the cleanest fossil fuel since it emits the lowest amount of other remains after being burned. Over the years, natural gas usage has increased significantly. Accurate forecasting is crucial for maintaining gas supplies, transportation and network stability. This paper presents two methodologies to identify the optimal configuration o parameters of a Neural Network (NN) to forecast the next 24 h of gas flow for each node of a large gas network.
In particular the first one applies a Design Of Experiments (DOE) to obtain a quick initial solution. An orthogonal design, consisting of 18 experiments selected among a total of 4.374 combinations of seven parameters (training algorithm, transfer function, regularization, learning rate, lags, and epochs), is used. The best result is selected as initial solution of an extended experiment for which the Simulated Annealing is run to find the optimal design among 89.100 possible combinations of parameters.
The second technique is based on the application of Genetic Algorithm for the selection of the optimal parameters of a recurrent neural network for time series forecast. GA was applied with binary representation of potential solutions, where subsets of bits in the bit string represent different values for several parameters of the recurrent neural network.
We tested these methods on three municipal nodes, using one year and half of hourly gas flow to train the network and 60 days for testing. Our results clearly show that the presented methodologies bring promising results in terms of optimal configuration of parameters and forecast error.
Machine Learning, Optimization, and Big Data. MOD 2017.
https://doi.org/10.1007/978-3-319-72926-8_14
yes
M. Dell’Amico
Janina Zittel
Natalia Selini Hadjidimitriou
Thorsten Koch
Milena Petkovic
Mathematical Optimization
Koch, Thorsten
MODAL-GasLab
MODAL-Gesamt
Petkovic, Milena
7352
eng
reportzib
0
--
2019-06-13
--
A Hybrid Approach for High Precision Prediction of Gas Flows
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
1438-0064
urn:nbn:de:0297-zib-73525
Milena Petkovic
Milena Petkovic
Ying Chen
Inken Gamrath
Uwe Gotzes
Natalia Selini Hadjidimitriou
Janina Zittel
Xiaofei Xu
Thorsten Koch
ZIB-Report
19-26
OPERATIONS RESEARCH, MATHEMATICAL PROGRAMMING
Mathematical Optimization
Koch, Thorsten
Zittel, Janina
MODAL-GasLab
Gamrath, Inken
MODAL-Gesamt
Petkovic, Milena
https://opus4.kobv.de/opus4-zib/files/7352/High_Precision_Prediction_of_Gas_Flows-38.pdf
https://opus4.kobv.de/opus4-zib/files/7352/High_Precision_Prediction_of_Gas_Flows-V2.pdf