M. Sc. Stephan Vogt

Teamleiter: Autonomous Energy Systems (AESy)

Fax: +49 561 804-6022
E-Mail: stephan.vogt[at]uni-kassel[dot]de

Website: Stephan Vogt

Publikationen

[ 2024 ]
[ 2023 ]
[ 2022 ]
[ 2021 ]
[ 2020 ]
[ 2019 ]
[ 2018 ]
[ 2017 ]
[ 2016 ]
[ 2015 ]

2024[ to top ]

1.
He, Y., Huang, Z., Vogt, S., Sick, B.: PrOuD: Probabilistic Outlier Detection Solution for Time Series Analysis on Real-world Photovoltaic Inverters. Energies (MDPI). 17, 64 (2024). https://doi.org/10.3390/en17010064.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Anomaly detection methods applied to time series are mostly viewed as a black box, which solely provides a deterministic answer to the detected target. Without a convincing explanation, domain experts can hardly trust the detection results and conduct a further time series diagnosis in real-world applications. To overcome the challenge, we mathematically analyzed the sources of anomalies and novelties in multivariate time series as well as their relationships from the perspective of Gaussian-distributed non-stationary noise. Furthermore, we proposed mathematical methods to generate artificial time series and synthetic anomalies, with the goal of solving the problem that it is difficult to train and evaluate models in real-world applications due to the lack of sufficient data. In addition, we designed extbfProbabilistic extbfOutlier extbfDetection (PrOuD), which is a general solution to provide interpretable detection results to assist domain experts in time series analysis. PrOuD can convert a predictive uncertainty of a trained model about a time series value into an estimated uncertainty of the detected outlier through Monte Carlo Estimation. The experimental results obtained on both artificial time series and real-world photovoltaic inverter data demonstrated that the proposed solution could detect emerging anomalies accurately and quickly. The implemented PrOuD demo case shows the potential to makes the detection results of the existing detection methods more convincing so that domain experts can more efficiently complete their tasks, such as time series diagnosis and anomalous pattern clustering.
@article{he2023proud, abstract = {Anomaly detection methods applied to time series are mostly viewed as a black box, which solely provides a deterministic answer to the detected target. Without a convincing explanation, domain experts can hardly trust the detection results and conduct a further time series diagnosis in real-world applications. To overcome the challenge, we mathematically analyzed the sources of anomalies and novelties in multivariate time series as well as their relationships from the perspective of Gaussian-distributed non-stationary noise. Furthermore, we proposed mathematical methods to generate artificial time series and synthetic anomalies, with the goal of solving the problem that it is difficult to train and evaluate models in real-world applications due to the lack of sufficient data. In addition, we designed extbf{Pr}obabilistic extbf{Ou}tlier extbf{D}etection (PrOuD), which is a general solution to provide interpretable detection results to assist domain experts in time series analysis. PrOuD can convert a predictive uncertainty of a trained model about a time series value into an estimated uncertainty of the detected outlier through Monte Carlo Estimation. The experimental results obtained on both artificial time series and real-world photovoltaic inverter data demonstrated that the proposed solution could detect emerging anomalies accurately and quickly. The implemented PrOuD demo case shows the potential to makes the detection results of the existing detection methods more convincing so that domain experts can more efficiently complete their tasks, such as time series diagnosis and anomalous pattern clustering.}, author = {He, Yujiang and Huang, Zhixin and Vogt, Stephan and Sick, Bernhard}, journal = {Energies (MDPI)}, keywords = {itegpub}, number = 1, pages = 64, publisher = {MDPI}, title = {PrOuD: Probabilistic Outlier Detection Solution for Time Series Analysis on Real-world Photovoltaic Inverters}, volume = 17, year = 2024 }
%0 Journal Article %1 he2023proud %A He, Yujiang %A Huang, Zhixin %A Vogt, Stephan %A Sick, Bernhard %D 2024 %I MDPI %J Energies (MDPI) %N 1 %P 64 %R 10.3390/en17010064 %T PrOuD: Probabilistic Outlier Detection Solution for Time Series Analysis on Real-world Photovoltaic Inverters %U https://www.mdpi.com/1996-1073/17/1/64 %V 17 %X Anomaly detection methods applied to time series are mostly viewed as a black box, which solely provides a deterministic answer to the detected target. Without a convincing explanation, domain experts can hardly trust the detection results and conduct a further time series diagnosis in real-world applications. To overcome the challenge, we mathematically analyzed the sources of anomalies and novelties in multivariate time series as well as their relationships from the perspective of Gaussian-distributed non-stationary noise. Furthermore, we proposed mathematical methods to generate artificial time series and synthetic anomalies, with the goal of solving the problem that it is difficult to train and evaluate models in real-world applications due to the lack of sufficient data. In addition, we designed extbfProbabilistic extbfOutlier extbfDetection (PrOuD), which is a general solution to provide interpretable detection results to assist domain experts in time series analysis. PrOuD can convert a predictive uncertainty of a trained model about a time series value into an estimated uncertainty of the detected outlier through Monte Carlo Estimation. The experimental results obtained on both artificial time series and real-world photovoltaic inverter data demonstrated that the proposed solution could detect emerging anomalies accurately and quickly. The implemented PrOuD demo case shows the potential to makes the detection results of the existing detection methods more convincing so that domain experts can more efficiently complete their tasks, such as time series diagnosis and anomalous pattern clustering.

2023[ to top ]

1.
Heinrich, R., Scholz, C., Vogt, S., Lehna, M.: Targeted Adversarial Attacks on Wind Power Forecasts. Machine Learning. 113, 863–889 (2023). https://doi.org/10.1007/s10994-023-06396-9.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
In recent years, researchers proposed a variety of deep learning models for wind power forecasting. These models predict the wind power generation of wind farms or entire regions more accurately than traditional machine learning algorithms or physical models. However, latest research has shown that deep learning models can often be manipulated by adversarial attacks. Since wind power forecasts are essential for the stability of modern power systems, it is important to protect them from this threat. In this work, we investigate the vulnerability of two different forecasting models to targeted, semi-targeted, and untargeted adversarial attacks. We consider a Long Short-Term Memory (LSTM) network for predicting the power generation of individual wind farms and a Convolutional Neural Network (CNN) for forecasting the wind power generation throughout Germany. Moreover, we propose the Total Adversarial Robustness Score (TARS), an evaluation metric for quantifying the robustness of regression models to targeted and semi-targeted adversarial attacks. It assesses the impact of attacks on the model's performance, as well as the extent to which the attacker's goal was achieved, by assigning a score between 0 (very vulnerable) and 1 (very robust). In our experiments, the LSTM forecasting model was fairly robust and achieved a TARS value of over 0.78 for all adversarial attacks investigated. The CNN forecasting model only achieved TARS values below 0.10 when trained ordinarily, and was thus very vulnerable. Yet, its robustness could be significantly improved by adversarial training, which always resulted in a TARS above 0.46.
@article{heinrich2023targeted, abstract = {In recent years, researchers proposed a variety of deep learning models for wind power forecasting. These models predict the wind power generation of wind farms or entire regions more accurately than traditional machine learning algorithms or physical models. However, latest research has shown that deep learning models can often be manipulated by adversarial attacks. Since wind power forecasts are essential for the stability of modern power systems, it is important to protect them from this threat. In this work, we investigate the vulnerability of two different forecasting models to targeted, semi-targeted, and untargeted adversarial attacks. We consider a Long Short-Term Memory (LSTM) network for predicting the power generation of individual wind farms and a Convolutional Neural Network (CNN) for forecasting the wind power generation throughout Germany. Moreover, we propose the Total Adversarial Robustness Score (TARS), an evaluation metric for quantifying the robustness of regression models to targeted and semi-targeted adversarial attacks. It assesses the impact of attacks on the model's performance, as well as the extent to which the attacker's goal was achieved, by assigning a score between 0 (very vulnerable) and 1 (very robust). In our experiments, the LSTM forecasting model was fairly robust and achieved a TARS value of over 0.78 for all adversarial attacks investigated. The CNN forecasting model only achieved TARS values below 0.10 when trained ordinarily, and was thus very vulnerable. Yet, its robustness could be significantly improved by adversarial training, which always resulted in a TARS above 0.46.}, author = {Heinrich, René and Scholz, Christoph and Vogt, Stephan and Lehna, Malte}, journal = {Machine Learning}, keywords = {itegpub}, number = 2, pages = {863–889}, publisher = {Springer}, title = {Targeted Adversarial Attacks on Wind Power Forecasts}, volume = 113, year = 2023 }
%0 Journal Article %1 heinrich2023targeted %A Heinrich, René %A Scholz, Christoph %A Vogt, Stephan %A Lehna, Malte %D 2023 %I Springer %J Machine Learning %N 2 %P 863--889 %R 10.1007/s10994-023-06396-9 %T Targeted Adversarial Attacks on Wind Power Forecasts %V 113 %X In recent years, researchers proposed a variety of deep learning models for wind power forecasting. These models predict the wind power generation of wind farms or entire regions more accurately than traditional machine learning algorithms or physical models. However, latest research has shown that deep learning models can often be manipulated by adversarial attacks. Since wind power forecasts are essential for the stability of modern power systems, it is important to protect them from this threat. In this work, we investigate the vulnerability of two different forecasting models to targeted, semi-targeted, and untargeted adversarial attacks. We consider a Long Short-Term Memory (LSTM) network for predicting the power generation of individual wind farms and a Convolutional Neural Network (CNN) for forecasting the wind power generation throughout Germany. Moreover, we propose the Total Adversarial Robustness Score (TARS), an evaluation metric for quantifying the robustness of regression models to targeted and semi-targeted adversarial attacks. It assesses the impact of attacks on the model's performance, as well as the extent to which the attacker's goal was achieved, by assigning a score between 0 (very vulnerable) and 1 (very robust). In our experiments, the LSTM forecasting model was fairly robust and achieved a TARS value of over 0.78 for all adversarial attacks investigated. The CNN forecasting model only achieved TARS values below 0.10 when trained ordinarily, and was thus very vulnerable. Yet, its robustness could be significantly improved by adversarial training, which always resulted in a TARS above 0.46.
1.
Beinert, D., Holzhüter, C., Thomas, J., Vogt, S.: Power flow forecasts at transmission grid nodes using Graph Neural Networks. Energy and AI. 14, 100262 (2023). https://doi.org/10.1016/j.egyai.2023.100262.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
The increasing share of renewable energy in the electricity grid and progressing changes in power consumption have led to fluctuating, and weather-dependent power flows. To ensure grid stability, grid operators rely on power forecasts which are crucial for grid calculations and planning. In this paper, a Multi-Task Learning approach is combined with a Graph Neural Network (GNN) to predict vertical power flows at transformers connecting high and extra-high voltage levels. The proposed method accounts for local differences in power flow characteristics by using an Embedding Multi-Task Learning approach. The use of a Bayesian embedding to capture the latent node characteristics allows to share the weights across all transformers in the subsequent node-invariant GNN while still allowing the individual behavioral patterns of the transformers to be distinguished. At the same time, dependencies between transformers are considered by the GNN architecture which can learn relationships between different transformers and thus take into account that power flows in an electricity network are not independent from each other. The effectiveness of the proposed method is demonstrated through evaluation on two real-world data sets provided by two of four German Transmission System Operators, comprising large portions of the operated German transmission grid. The results show that the proposed Multi-Task Graph Neural Network is a suitable representation learner for electricity networks with a clear advantage provided by the preceding embedding layer. It is able to capture interconnections between correlated transformers and indeed improves the performance in power flow prediction compared to standard Neural Networks. A sign test shows that the proposed model reduces the test RMSE on both data sets compared to the benchmark models significantly.
@article{beinert2023power, abstract = {The increasing share of renewable energy in the electricity grid and progressing changes in power consumption have led to fluctuating, and weather-dependent power flows. To ensure grid stability, grid operators rely on power forecasts which are crucial for grid calculations and planning. In this paper, a Multi-Task Learning approach is combined with a Graph Neural Network (GNN) to predict vertical power flows at transformers connecting high and extra-high voltage levels. The proposed method accounts for local differences in power flow characteristics by using an Embedding Multi-Task Learning approach. The use of a Bayesian embedding to capture the latent node characteristics allows to share the weights across all transformers in the subsequent node-invariant GNN while still allowing the individual behavioral patterns of the transformers to be distinguished. At the same time, dependencies between transformers are considered by the GNN architecture which can learn relationships between different transformers and thus take into account that power flows in an electricity network are not independent from each other. The effectiveness of the proposed method is demonstrated through evaluation on two real-world data sets provided by two of four German Transmission System Operators, comprising large portions of the operated German transmission grid. The results show that the proposed Multi-Task Graph Neural Network is a suitable representation learner for electricity networks with a clear advantage provided by the preceding embedding layer. It is able to capture interconnections between correlated transformers and indeed improves the performance in power flow prediction compared to standard Neural Networks. A sign test shows that the proposed model reduces the test RMSE on both data sets compared to the benchmark models significantly.}, author = {Beinert, Dominik and Holzhüter, Clara and Thomas, Josephine and Vogt, Stephan}, journal = {Energy and AI}, keywords = {itegpub}, number = 1, pages = 100262, publisher = {Elsevier}, title = {Power flow forecasts at transmission grid nodes using Graph Neural Networks}, volume = 14, year = 2023 }
%0 Journal Article %1 beinert2023power %A Beinert, Dominik %A Holzhüter, Clara %A Thomas, Josephine %A Vogt, Stephan %D 2023 %I Elsevier %J Energy and AI %N 1 %P 100262 %R 10.1016/j.egyai.2023.100262 %T Power flow forecasts at transmission grid nodes using Graph Neural Networks %U https://www.sciencedirect.com/science/article/pii/S2666546823000344?via%3Dihub %V 14 %X The increasing share of renewable energy in the electricity grid and progressing changes in power consumption have led to fluctuating, and weather-dependent power flows. To ensure grid stability, grid operators rely on power forecasts which are crucial for grid calculations and planning. In this paper, a Multi-Task Learning approach is combined with a Graph Neural Network (GNN) to predict vertical power flows at transformers connecting high and extra-high voltage levels. The proposed method accounts for local differences in power flow characteristics by using an Embedding Multi-Task Learning approach. The use of a Bayesian embedding to capture the latent node characteristics allows to share the weights across all transformers in the subsequent node-invariant GNN while still allowing the individual behavioral patterns of the transformers to be distinguished. At the same time, dependencies between transformers are considered by the GNN architecture which can learn relationships between different transformers and thus take into account that power flows in an electricity network are not independent from each other. The effectiveness of the proposed method is demonstrated through evaluation on two real-world data sets provided by two of four German Transmission System Operators, comprising large portions of the operated German transmission grid. The results show that the proposed Multi-Task Graph Neural Network is a suitable representation learner for electricity networks with a clear advantage provided by the preceding embedding layer. It is able to capture interconnections between correlated transformers and indeed improves the performance in power flow prediction compared to standard Neural Networks. A sign test shows that the proposed model reduces the test RMSE on both data sets compared to the benchmark models significantly.
1.
Nivarthi, C.P., Vogt, S., Sick, B.: Multi-Task Representation Learning for Renewable-Power Forecasting: A Comparative Analysis of Unified Autoencoder Variants and Task-Embedding Dimensions. Machine Learning and Knowledge Extraction (MAKE). 5, 1214–1233 (2023). https://doi.org/10.3390/make5030062.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Typically, renewable-power-generation forecasting using machine learning involves creating separate models for each photovoltaic or wind park, known as single-task learning models. However, transfer learning has gained popularity in recent years, as it allows for the transfer of knowledge from source parks to target parks. Nevertheless, determining the most similar source park(s) for transfer learning can be challenging, particularly when the target park has limited or no historical data samples. To address this issue, we propose a multi-task learning architecture that employs a Unified Autoencoder (UAE) to initially learn a common representation of input weather features among tasks and then utilizes a Task-Embedding layer in a Neural Network (TENN) to learn task-specific information. This proposed UAE-TENN architecture can be easily extended to new parks with or without historical data. We evaluate the performance of our proposed architecture and compare it to single-task learning models on six photovoltaic and wind farm datasets consisting of a total of 529 parks. Our results show that the UAE-TENN architecture significantly improves power-forecasting performance by 10 to 19% for photovoltaic parks and 5 to 15% for wind parks compared to baseline models. We also demonstrate that UAE-TENN improves forecast accuracy for a new park by 19% for photovoltaic parks, even in a zero-shot learning scenario where there is no historical data. Additionally, we propose variants of the Unified Autoencoder with convolutional and LSTM layers, compare their performance, and provide a comparison among architectures with different numbers of task-embedding dimensions. Finally, we demonstrate the utility of trained task embeddings for interpretation and visualization purposes.
@article{nivarthi2023multi, abstract = {Typically, renewable-power-generation forecasting using machine learning involves creating separate models for each photovoltaic or wind park, known as single-task learning models. However, transfer learning has gained popularity in recent years, as it allows for the transfer of knowledge from source parks to target parks. Nevertheless, determining the most similar source park(s) for transfer learning can be challenging, particularly when the target park has limited or no historical data samples. To address this issue, we propose a multi-task learning architecture that employs a Unified Autoencoder (UAE) to initially learn a common representation of input weather features among tasks and then utilizes a Task-Embedding layer in a Neural Network (TENN) to learn task-specific information. This proposed UAE-TENN architecture can be easily extended to new parks with or without historical data. We evaluate the performance of our proposed architecture and compare it to single-task learning models on six photovoltaic and wind farm datasets consisting of a total of 529 parks. Our results show that the UAE-TENN architecture significantly improves power-forecasting performance by 10 to 19% for photovoltaic parks and 5 to 15% for wind parks compared to baseline models. We also demonstrate that UAE-TENN improves forecast accuracy for a new park by 19% for photovoltaic parks, even in a zero-shot learning scenario where there is no historical data. Additionally, we propose variants of the Unified Autoencoder with convolutional and LSTM layers, compare their performance, and provide a comparison among architectures with different numbers of task-embedding dimensions. Finally, we demonstrate the utility of trained task embeddings for interpretation and visualization purposes.}, author = {Nivarthi, Chandana Priya and Vogt, Stephan and Sick, Bernhard}, journal = {Machine Learning and Knowledge Extraction (MAKE)}, keywords = {itegpub}, number = 3, pages = {1214–1233}, publisher = {MDPI}, title = {Multi-Task Representation Learning for Renewable-Power Forecasting: A Comparative Analysis of Unified Autoencoder Variants and Task-Embedding Dimensions}, volume = 5, year = 2023 }
%0 Journal Article %1 nivarthi2023multi %A Nivarthi, Chandana Priya %A Vogt, Stephan %A Sick, Bernhard %D 2023 %I MDPI %J Machine Learning and Knowledge Extraction (MAKE) %N 3 %P 1214--1233 %R 10.3390/make5030062 %T Multi-Task Representation Learning for Renewable-Power Forecasting: A Comparative Analysis of Unified Autoencoder Variants and Task-Embedding Dimensions %U https://www.mdpi.com/2504-4990/5/3/62 %V 5 %X Typically, renewable-power-generation forecasting using machine learning involves creating separate models for each photovoltaic or wind park, known as single-task learning models. However, transfer learning has gained popularity in recent years, as it allows for the transfer of knowledge from source parks to target parks. Nevertheless, determining the most similar source park(s) for transfer learning can be challenging, particularly when the target park has limited or no historical data samples. To address this issue, we propose a multi-task learning architecture that employs a Unified Autoencoder (UAE) to initially learn a common representation of input weather features among tasks and then utilizes a Task-Embedding layer in a Neural Network (TENN) to learn task-specific information. This proposed UAE-TENN architecture can be easily extended to new parks with or without historical data. We evaluate the performance of our proposed architecture and compare it to single-task learning models on six photovoltaic and wind farm datasets consisting of a total of 529 parks. Our results show that the UAE-TENN architecture significantly improves power-forecasting performance by 10 to 19% for photovoltaic parks and 5 to 15% for wind parks compared to baseline models. We also demonstrate that UAE-TENN improves forecast accuracy for a new park by 19% for photovoltaic parks, even in a zero-shot learning scenario where there is no historical data. Additionally, we propose variants of the Unified Autoencoder with convolutional and LSTM layers, compare their performance, and provide a comparison among architectures with different numbers of task-embedding dimensions. Finally, we demonstrate the utility of trained task embeddings for interpretation and visualization purposes.

2022[ to top ]

1.
Nivarthi, C.P., Vogt, S., Sick, B.: Unified Autoencoder with Task Embeddings for Multi-Task Learning in Renewable Power Forecasting. In: International Conference on Machine Learning and Applications (ICMLA). bll 1530–1536. IEEE (2022). https://doi.org/10.1109/ICMLA55696.2022.00240.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Renewable power generation forecasts using machine learning are typically implemented as single-task learning models, where a separate model is trained for each photovoltaic or wind park. In recent years, transfer learning is gaining popularity in these systems, as it can be used to transfer the knowledge gained from source parks to a target park. However, for transferring the knowledge to a target park, there is a need to determine the most similar source park(s) among the existing parks. This similarity determination using historical power measurements is challenging when the target park has limited to no historical data samples. Therefore, we propose a simple multi-task learning architecture that initially learns a common representation of input weather features among the tasks, using a Unified Autoencoder (UAE) and then learns the task specific information utilizing a Task Embedding layer in a Neural Network (TENN). This proposed architecture, UAE-TENN, can be easily extended to new parks with or without historical data. An elaborate performance comparison of single and multi-task learning models is performed on six photovoltaic and wind farm datasets comprising a total of 529 parks. UAE-TENN significantly improves the performance of power forecasting by 10 to 19% for photovoltaic parks and 5 to 22% for wind parks compared to the baseline models. Even in the zero-shot learning scenario, when there is no historical data, we successfully demonstrate that the UAE-TENN improves the forecast accuracy for a new park by 19% for photovoltaic parks.
@inproceedings{nivarthi2022unified, abstract = {Renewable power generation forecasts using machine learning are typically implemented as single-task learning models, where a separate model is trained for each photovoltaic or wind park. In recent years, transfer learning is gaining popularity in these systems, as it can be used to transfer the knowledge gained from source parks to a target park. However, for transferring the knowledge to a target park, there is a need to determine the most similar source park(s) among the existing parks. This similarity determination using historical power measurements is challenging when the target park has limited to no historical data samples. Therefore, we propose a simple multi-task learning architecture that initially learns a common representation of input weather features among the tasks, using a Unified Autoencoder (UAE) and then learns the task specific information utilizing a Task Embedding layer in a Neural Network (TENN). This proposed architecture, UAE-TENN, can be easily extended to new parks with or without historical data. An elaborate performance comparison of single and multi-task learning models is performed on six photovoltaic and wind farm datasets comprising a total of 529 parks. UAE-TENN significantly improves the performance of power forecasting by 10 to 19% for photovoltaic parks and 5 to 22% for wind parks compared to the baseline models. Even in the zero-shot learning scenario, when there is no historical data, we successfully demonstrate that the UAE-TENN improves the forecast accuracy for a new park by 19% for photovoltaic parks.}, author = {Nivarthi, Chandana Priya and Vogt, Stephan and Sick, Bernhard}, booktitle = {International Conference on Machine Learning and Applications (ICMLA)}, keywords = {itegpub}, pages = {1530–1536}, publisher = {IEEE}, title = {Unified Autoencoder with Task Embeddings for Multi-Task Learning in Renewable Power Forecasting}, year = 2022 }
%0 Conference Paper %1 nivarthi2022unified %A Nivarthi, Chandana Priya %A Vogt, Stephan %A Sick, Bernhard %B International Conference on Machine Learning and Applications (ICMLA) %D 2022 %I IEEE %P 1530--1536 %R 10.1109/ICMLA55696.2022.00240 %T Unified Autoencoder with Task Embeddings for Multi-Task Learning in Renewable Power Forecasting %U https://ieeexplore.ieee.org/document/10068974 %X Renewable power generation forecasts using machine learning are typically implemented as single-task learning models, where a separate model is trained for each photovoltaic or wind park. In recent years, transfer learning is gaining popularity in these systems, as it can be used to transfer the knowledge gained from source parks to a target park. However, for transferring the knowledge to a target park, there is a need to determine the most similar source park(s) among the existing parks. This similarity determination using historical power measurements is challenging when the target park has limited to no historical data samples. Therefore, we propose a simple multi-task learning architecture that initially learns a common representation of input weather features among the tasks, using a Unified Autoencoder (UAE) and then learns the task specific information utilizing a Task Embedding layer in a Neural Network (TENN). This proposed architecture, UAE-TENN, can be easily extended to new parks with or without historical data. An elaborate performance comparison of single and multi-task learning models is performed on six photovoltaic and wind farm datasets comprising a total of 529 parks. UAE-TENN significantly improves the performance of power forecasting by 10 to 19% for photovoltaic parks and 5 to 22% for wind parks compared to the baseline models. Even in the zero-shot learning scenario, when there is no historical data, we successfully demonstrate that the UAE-TENN improves the forecast accuracy for a new park by 19% for photovoltaic parks.
1.
Herde, M., Huang, Z., Huseljic, D., Kottke, D., Vogt, S., Sick, B.: Fast Bayesian Updates for Deep Learning with a Use Case in Active Learning. arXiv e-prints. arXiv:2210.06112 (2022).
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Retraining deep neural networks when new data arrives is typically computationally expensive. Moreover, certain applications do not allow such costly retraining due to time or computational constraints. Fast Bayesian updates are a possible solution to this issue. Therefore, we propose a Bayesian update based on Monte-Carlo samples and a last-layer Laplace approximation for different Bayesian neural network types, i.e., Dropout, Ensemble, and Spectral Normalized Neural Gaussian Process (SNGP). In a large-scale evaluation study, we show that our updates combined with SNGP represent a fast and competitive alternative to costly retraining. As a use case, we combine the Bayesian updates for SNGP with different sequential query strategies to exemplarily demonstrate their improved selection performance in active learning.
@article{herde2022fast, abstract = {Retraining deep neural networks when new data arrives is typically computationally expensive. Moreover, certain applications do not allow such costly retraining due to time or computational constraints. Fast Bayesian updates are a possible solution to this issue. Therefore, we propose a Bayesian update based on Monte-Carlo samples and a last-layer Laplace approximation for different Bayesian neural network types, i.e., Dropout, Ensemble, and Spectral Normalized Neural Gaussian Process (SNGP). In a large-scale evaluation study, we show that our updates combined with SNGP represent a fast and competitive alternative to costly retraining. As a use case, we combine the Bayesian updates for SNGP with different sequential query strategies to exemplarily demonstrate their improved selection performance in active learning.}, author = {Herde, Marek and Huang, Zhixin and Huseljic, Denis and Kottke, Daniel and Vogt, Stephan and Sick, Bernhard}, journal = {arXiv e-prints}, keywords = {itegpub}, pages = {arXiv:2210.06112}, title = {Fast Bayesian Updates for Deep Learning with a Use Case in Active Learning}, year = 2022 }
%0 Journal Article %1 herde2022fast %A Herde, Marek %A Huang, Zhixin %A Huseljic, Denis %A Kottke, Daniel %A Vogt, Stephan %A Sick, Bernhard %D 2022 %J arXiv e-prints %P arXiv:2210.06112 %T Fast Bayesian Updates for Deep Learning with a Use Case in Active Learning %U https://arxiv.org/abs/2210.06112 %X Retraining deep neural networks when new data arrives is typically computationally expensive. Moreover, certain applications do not allow such costly retraining due to time or computational constraints. Fast Bayesian updates are a possible solution to this issue. Therefore, we propose a Bayesian update based on Monte-Carlo samples and a last-layer Laplace approximation for different Bayesian neural network types, i.e., Dropout, Ensemble, and Spectral Normalized Neural Gaussian Process (SNGP). In a large-scale evaluation study, we show that our updates combined with SNGP represent a fast and competitive alternative to costly retraining. As a use case, we combine the Bayesian updates for SNGP with different sequential query strategies to exemplarily demonstrate their improved selection performance in active learning.

2021[ to top ]

1.
Huang, Z., He, Y., Vogt, S., Sick, B.: Uncertainty and Utility Sampling with Pre-Clustering. In: Workshop on Interactive Adaptive Learning (IAL), ECML PKDD (2021).
- [ BibTeX ]
- [ EndNote ]
@inproceedings{huang2021uncertainty, author = {Huang, Zhixin and He, Yujiang and Vogt, Stephan and Sick, Bernhard}, booktitle = {Workshop on Interactive Adaptive Learning (IAL), ECML PKDD}, keywords = {itegpub}, note = {(accepted)}, title = {Uncertainty and Utility Sampling with Pre-Clustering}, year = 2021 }
%0 Conference Paper %1 huang2021uncertainty %A Huang, Zhixin %A He, Yujiang %A Vogt, Stephan %A Sick, Bernhard %B Workshop on Interactive Adaptive Learning (IAL), ECML PKDD %D 2021 %T Uncertainty and Utility Sampling with Pre-Clustering
1.
Gruhl, C., Hannan, A., Huang, Z., Nivarthi, C., Vogt, S.: The Problem with Real-World Novelty Detection -- Issues in Multivariate Probabilistic Models. In: Workshop on Self-Improving System Integration (SISSY), ACSOS. bll 204–209. IEEE (2021). https://doi.org/10.1109/acsos-c52956.2021.00055.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{gruhl2021problem, author = {Gruhl, Christian and Hannan, Abdul and Huang, Zhixin and Nivarthi, Chandana and Vogt, Stephan}, booktitle = {Workshop on Self-Improving System Integration (SISSY), ACSOS}, keywords = {itegpub}, pages = {204–209}, publisher = {IEEE}, title = {The Problem with Real-World Novelty Detection – Issues in Multivariate Probabilistic Models}, year = 2021 }
%0 Conference Paper %1 gruhl2021problem %A Gruhl, Christian %A Hannan, Abdul %A Huang, Zhixin %A Nivarthi, Chandana %A Vogt, Stephan %B Workshop on Self-Improving System Integration (SISSY), ACSOS %D 2021 %I IEEE %P 204--209 %R 10.1109/acsos-c52956.2021.00055 %T The Problem with Real-World Novelty Detection -- Issues in Multivariate Probabilistic Models
1.
Schreiber, J., Vogt, S., Sick, B.: Task Embedding Temporal Convolution Networks for Transfer Learning Problems in Renewable Power Time Series Forecast. In: European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD): Applied Data Science Track. bll 118–134. Springer (2021). https://doi.org/10.1007/978-3-030-86514-6_8.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{schreiber2021task, author = {Schreiber, Jens and Vogt, Stephan and Sick, Bernhard}, booktitle = {European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD): Applied Data Science Track}, keywords = {itegpub}, pages = {118–134}, publisher = {Springer}, title = {Task Embedding Temporal Convolution Networks for Transfer Learning Problems in Renewable Power Time Series Forecast}, year = 2021 }
%0 Conference Paper %1 schreiber2021task %A Schreiber, Jens %A Vogt, Stephan %A Sick, Bernhard %B European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD): Applied Data Science Track %D 2021 %I Springer %P 118--134 %R 10.1007/978-3-030-86514-6_8 %T Task Embedding Temporal Convolution Networks for Transfer Learning Problems in Renewable Power Time Series Forecast

2020[ to top ]

1.
Bremicker-Trübelhorn, S., Vogt, S., Siefert, M.: Statistical correction scheme for the wind power allocation to transformer stations in the transmission grid. Electric Power Systems Research. 189, 106623 (2020). https://doi.org/10.1016/j.epsr.2020.106623.
- [ BibTeX ]
- [ EndNote ]
@article{bremickertruebelhorn2020statistical, author = {Bremicker-Tr{\"u}belhorn, Sascha and Vogt, Stephan and Siefert, Malte}, journal = {Electric Power Systems Research}, keywords = {not_ies}, pages = 106623, publisher = {Elsevier}, title = {Statistical correction scheme for the wind power allocation to transformer stations in the transmission grid}, volume = 189, year = 2020 }
%0 Journal Article %1 bremickertruebelhorn2020statistical %A Bremicker-Trübelhorn, Sascha %A Vogt, Stephan %A Siefert, Malte %D 2020 %I Elsevier %J Electric Power Systems Research %P 106623 %R 10.1016/j.epsr.2020.106623 %T Statistical correction scheme for the wind power allocation to transformer stations in the transmission grid %V 189
1.
Bieshaar, M., Schreiber, J., Vogt, S., Gensler, A., Sick, B.: Quantile Surfaces -- Generalizing Quantile Regression to Multivariate Targets. arXiv e-prints. arXiv:2010.05898 (2020).
- [ BibTeX ]
- [ EndNote ]
@article{bieshaar2020quantile, author = {{Bieshaar}, Maarten and {Schreiber}, Jens and {Vogt}, Stephan and {Gensler}, Andr{\'e} and {Sick}, Bernhard}, journal = {arXiv e-prints}, keywords = {Applications,}, pages = {arXiv:2010.05898}, title = {{Quantile Surfaces – Generalizing Quantile Regression to Multivariate Targets}}, year = 2020 }
%0 Journal Article %1 bieshaar2020quantile %A Bieshaar, Maarten %A Schreiber, Jens %A Vogt, Stephan %A Gensler, André %A Sick, Bernhard %D 2020 %J arXiv e-prints %P arXiv:2010.05898 %T Quantile Surfaces -- Generalizing Quantile Regression to Multivariate Targets
1.
Lutz, M.-A., Vogt, S., Berkhout, V., Faulstich, S., Dienst, S., Steinmetz, U., Gück, C., Ortega, A.: Evaluation of Anomaly Detection of an Autoencoder Based on Maintenace Information and Scada-Data. Energies. 13, 1063 (2020). https://doi.org/10.3390/en13051063.
- [ BibTeX ]
- [ EndNote ]
@article{lutz2020evaluation, author = {Lutz, Marc-Alexander and Vogt, Stephan and Berkhout, Volker and Faulstich, Stefan and Dienst, Steffen and Steinmetz, Urs and G{\"u}ck, Christian and Ortega, Andres}, journal = {Energies}, keywords = {not_ies}, number = 5, pages = 1063, publisher = {MDPI}, title = {Evaluation of Anomaly Detection of an Autoencoder Based on Maintenace Information and Scada-Data}, volume = 13, year = 2020 }
%0 Journal Article %1 lutz2020evaluation %A Lutz, Marc-Alexander %A Vogt, Stephan %A Berkhout, Volker %A Faulstich, Stefan %A Dienst, Steffen %A Steinmetz, Urs %A Gück, Christian %A Ortega, Andres %D 2020 %I MDPI %J Energies %N 5 %P 1063 %R 10.3390/en13051063 %T Evaluation of Anomaly Detection of an Autoencoder Based on Maintenace Information and Scada-Data %V 13

2019[ to top ]

1.
Vogt, S., Braun, A., Dobschinski, J., Sick, B.: Wind Power Forecasting Based on Deep Neural Networks and Transfer Learning. In: Wind Integration Workshop. , Dublin, Ireland (2019). https://doi.org/10.24406/publica-fhg-406413.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{vogt2019wind, address = {Dublin, Ireland}, author = {Vogt, Stephan and Braun, Axel and Dobschinski, Jan and Sick, Bernhard}, booktitle = {Wind Integration Workshop}, keywords = {imported}, title = {Wind Power Forecasting Based on Deep Neural Networks and Transfer Learning}, year = 2019 }
%0 Conference Paper %1 vogt2019wind %A Vogt, Stephan %A Braun, Axel %A Dobschinski, Jan %A Sick, Bernhard %B Wind Integration Workshop %C Dublin, Ireland %D 2019 %R 10.24406/publica-fhg-406413 %T Wind Power Forecasting Based on Deep Neural Networks and Transfer Learning
1.
Vogt, S., Berkhout, V., Lutz, M.-A., Zhou, Q.: Deep Learning Based Failure Prediction in Wind Turbines Using SCADA Data. In: Conference for Wind Power Drives (CWD). bll 391–404 (2019).
- [ BibTeX ]
- [ EndNote ]
@inproceedings{vogt2019deep, author = {Vogt, Stephan and Berkhout, Volker and Lutz, Marc-Alexander and Zhou, Qixin}, booktitle = {Conference for Wind Power Drives (CWD)}, keywords = {not_ies}, pages = {391–404}, title = {Deep Learning Based Failure Prediction in Wind Turbines Using SCADA Data}, year = 2019 }
%0 Conference Paper %1 vogt2019deep %A Vogt, Stephan %A Berkhout, Volker %A Lutz, Marc-Alexander %A Zhou, Qixin %B Conference for Wind Power Drives (CWD) %D 2019 %P 391--404 %T Deep Learning Based Failure Prediction in Wind Turbines Using SCADA Data
1.
Saint-Drenan, Y.-M., Vogt, S., Killinger, S., Bright, J.M., Fritz, R., Potthast, R.: Bayesian parameterisation of a regional photovoltaic model--Application to forecasting. Solar Energy. 188, 760–774 (2019). https://doi.org/10.1016/j.solener.2019.06.053.
- [ BibTeX ]
- [ EndNote ]
@article{saintdrenan2019bayesian, author = {Saint-Drenan, Yves-Marie and Vogt, Stephan and Killinger, Sven and Bright, Jamie M and Fritz, Rafael and Potthast, Roland}, journal = {Solar Energy}, keywords = {not_ies}, pages = {760–774}, publisher = {Elsevier}, title = {Bayesian parameterisation of a regional photovoltaic model–Application to forecasting}, volume = 188, year = 2019 }
%0 Journal Article %1 saintdrenan2019bayesian %A Saint-Drenan, Yves-Marie %A Vogt, Stephan %A Killinger, Sven %A Bright, Jamie M %A Fritz, Rafael %A Potthast, Roland %D 2019 %I Elsevier %J Solar Energy %P 760--774 %R 10.1016/j.solener.2019.06.053 %T Bayesian parameterisation of a regional photovoltaic model--Application to forecasting %V 188

2018[ to top ]

1.
Vogt, S., Otterson, S., Berkhout, V.: Multi-task distribution learning approach to anomaly detection of operational states of wind turbines. In: Journal of Physics: Conference Series. bl 012040 (2018). https://doi.org/10.1088/1742-6596/1102/1/012040.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{vogt2018multi, author = {Vogt, Stephan and Otterson, Scott and Berkhout, Volker}, booktitle = {Journal of Physics: Conference Series}, keywords = {not_ies}, number = 1, pages = {012040}, title = {Multi-task distribution learning approach to anomaly detection of operational states of wind turbines}, volume = 1102, year = 2018 }
%0 Conference Paper %1 vogt2018multi %A Vogt, Stephan %A Otterson, Scott %A Berkhout, Volker %B Journal of Physics: Conference Series %D 2018 %N 1 %P 012040 %R 10.1088/1742-6596/1102/1/012040 %T Multi-task distribution learning approach to anomaly detection of operational states of wind turbines %V 1102
1.
Vogt, S., Braun, A., Koch, J., Jost, D., Dobschinski, J.: Benchmark of Spatio-temporal Shortest-Term Wind Power Forecast Models. In: Wind Integration Workshop (2018).
- [ BibTeX ]
- [ EndNote ]
@inproceedings{vogt2018benchmark, author = {Vogt, Stephan and Braun, Axel and Koch, Jonas and Jost, Dominik and Dobschinski, Jan}, booktitle = {Wind Integration Workshop}, keywords = {not_ies}, title = {Benchmark of Spatio-temporal Shortest-Term Wind Power Forecast Models}, year = 2018 }
%0 Conference Paper %1 vogt2018benchmark %A Vogt, Stephan %A Braun, Axel %A Koch, Jonas %A Jost, Dominik %A Dobschinski, Jan %B Wind Integration Workshop %D 2018 %T Benchmark of Spatio-temporal Shortest-Term Wind Power Forecast Models
1.
Gensler, A., Sick, B., Vogt, S.: A review of uncertainty representations and metaverification of uncertainty assessment techniques for renewable energies. Renewable and Sustainable Energy Reviews. 96, 352–379 (2018). https://doi.org/10.1016/j.rser.2018.07.042.
- [ BibTeX ]
- [ EndNote ]
@article{gensler2018review, author = {Gensler, Andr{\'e} and Sick, Bernhard and Vogt, Stephan}, journal = {Renewable and Sustainable Energy Reviews}, keywords = {imported}, pages = {352–379}, publisher = {Elsevier}, title = {A review of uncertainty representations and metaverification of uncertainty assessment techniques for renewable energies}, volume = 96, year = 2018 }
%0 Journal Article %1 gensler2018review %A Gensler, André %A Sick, Bernhard %A Vogt, Stephan %D 2018 %I Elsevier %J Renewable and Sustainable Energy Reviews %P 352--379 %R 10.1016/j.rser.2018.07.042 %T A review of uncertainty representations and metaverification of uncertainty assessment techniques for renewable energies %V 96

2017[ to top ]

1.
Heppelmann, T., Steiner, A., Vogt, S.: Application of numerical weather prediction in wind power forecasting: Assessment of the diurnal cycle. Meteorologische Zeitschrift. 26, 319–331 (2017). https://doi.org/10.1127/metz/2017/0820.
- [ BibTeX ]
- [ EndNote ]
@article{heppelmann2017application, author = {Heppelmann, Tobias and Steiner, Andrea and Vogt, Stephan}, journal = {Meteorologische Zeitschrift}, keywords = {not_ies}, number = 3, pages = {319–331}, publisher = {Schweizerbart}, title = {Application of numerical weather prediction in wind power forecasting: Assessment of the diurnal cycle}, volume = 26, year = 2017 }
%0 Journal Article %1 heppelmann2017application %A Heppelmann, Tobias %A Steiner, Andrea %A Vogt, Stephan %D 2017 %I Schweizerbart %J Meteorologische Zeitschrift %N 3 %P 319--331 %R 10.1127/metz/2017/0820 %T Application of numerical weather prediction in wind power forecasting: Assessment of the diurnal cycle %V 26

2016[ to top ]

1.
Gensler, A., Sick, B., Vogt, S.: A Review of Deterministic Error Scores and Normalization Techniques for Power Forecasting Algorithms. In: IEEE Symposium Series on Computational Intelligence (SSCI). bll 1–9. IEEE, Athens, Greece (2016). https://doi.org/10.1109/ssci.2016.7849848.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{gensler2016review, address = {Athens, Greece}, author = {Gensler, A. and Sick, B. and Vogt, S.}, booktitle = {IEEE Symposium Series on Computational Intelligence (SSCI)}, keywords = {imported}, pages = {1–9}, publisher = {IEEE}, title = {A Review of Deterministic Error Scores and Normalization Techniques for Power Forecasting Algorithms}, year = 2016 }
%0 Conference Paper %1 gensler2016review %A Gensler, A. %A Sick, B. %A Vogt, S. %B IEEE Symposium Series on Computational Intelligence (SSCI) %C Athens, Greece %D 2016 %I IEEE %P 1--9 %R 10.1109/ssci.2016.7849848 %T A Review of Deterministic Error Scores and Normalization Techniques for Power Forecasting Algorithms

2015[ to top ]

1.
Saint-Drenan, Y.-M., Bofinger, S., Fritz, R., Vogt, S., Good, G., Dobschinski, J.: An empirical approach to parameterizing photovoltaic plants for power forecasting and simulation. Solar Energy. 120, 479–493 (2015). https://doi.org/10.1016/j.solener.2015.07.024.
- [ BibTeX ]
- [ EndNote ]
@article{saintdrenan2015empirical, author = {Saint-Drenan, Yves-Marie and Bofinger, Stefan and Fritz, Rafael and Vogt, Stefan and Good, GH and Dobschinski, Jan}, journal = {Solar Energy}, keywords = {not_ies}, pages = {479–493}, publisher = {Elsevier}, title = {An empirical approach to parameterizing photovoltaic plants for power forecasting and simulation}, volume = 120, year = 2015 }
%0 Journal Article %1 saintdrenan2015empirical %A Saint-Drenan, Yves-Marie %A Bofinger, Stefan %A Fritz, Rafael %A Vogt, Stefan %A Good, GH %A Dobschinski, Jan %D 2015 %I Elsevier %J Solar Energy %P 479--493 %R 10.1016/j.solener.2015.07.024 %T An empirical approach to parameterizing photovoltaic plants for power forecasting and simulation %V 120