View/ Open
Date
2023-12-21Subject
333 Economics of land and energy 600 Technology AnomalieerkennungAusreißer <Statistik>FotovoltaikWechselrichterPrognoseZeitreihenanalyseMetadata
Show full item record
Aufsatz![](/themes/Mirage2/images/Open_Access_logo_PLoS_transparent.svg)
PrOuD: Probabilistic Outlier Detection Solution for Time-Series Analysis of Real-World Photovoltaic Inverters
Abstract
Anomaly detection methods applied to time series are mostly viewed as black boxes that solely provide a deterministic answer for the detected target. Without a convincing explanation, domain experts can hardly trust the detection results and must conduct further time-series diagnoses in real-world applications. To overcome this 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 of it being difficult to train and evaluate models for real-world applications due to the lack of sufficient data. In addition, we designed Probabilistic Outlier Detection (PrOuD), which is a general solution to provide interpretable detection results to assist domain experts with time-series analysis. PrOuD can convert the predictive uncertainty of a time-series value from a trained model into the 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 can detect emerging anomalies accurately and quickly. The implemented PrOuD demo case shows its potential to make the detection results of existing detection methods more convincing so that domain experts can more efficiently complete their tasks, such as time-series diagnosis and anomalous pattern clustering.
Citation
In: Energies Volume 17 / Issue 1 (2023-12-21) eissn:1996-1073Sponsorship
Gefördert durch den Publikationsfonds der Universität KasselCitation
@article{doi:10.17170/kobra-202401109353,
author={He, Yujiang and Huang, Zhixin and Vogt, Stephan and Sick, Bernhard},
title={PrOuD: Probabilistic Outlier Detection Solution for Time-Series Analysis of Real-World Photovoltaic Inverters},
journal={Energies},
year={2023}
}
0500 Oax 0501 Text $btxt$2rdacontent 0502 Computermedien $bc$2rdacarrier 1100 2023$n2023 1500 1/eng 2050 ##0##http://hdl.handle.net/123456789/15365 3000 He, Yujiang 3010 Huang, Zhixin 3010 Vogt, Stephan 3010 Sick, Bernhard 4000 PrOuD: Probabilistic Outlier Detection Solution for Time-Series Analysis of Real-World Photovoltaic Inverters / He, Yujiang 4030 4060 Online-Ressource 4085 ##0##=u http://nbn-resolving.de/http://hdl.handle.net/123456789/15365=x R 4204 \$dAufsatz 4170 5550 {{Anomalieerkennung}} 5550 {{Ausreißer <Statistik>}} 5550 {{Fotovoltaik}} 5550 {{Wechselrichter}} 5550 {{Prognose}} 5550 {{Zeitreihenanalyse}} 7136 ##0##http://hdl.handle.net/123456789/15365
2024-01-12T10:12:11Z 2024-01-12T10:12:11Z 2023-12-21 doi:10.17170/kobra-202401109353 http://hdl.handle.net/123456789/15365 Gefördert durch den Publikationsfonds der Universität Kassel eng Namensnennung 4.0 International http://creativecommons.org/licenses/by/4.0/ anomaly novelty outlier detection photovoltaic probabilistic forecasting explainability time series 333 600 PrOuD: Probabilistic Outlier Detection Solution for Time-Series Analysis of Real-World Photovoltaic Inverters Aufsatz Anomaly detection methods applied to time series are mostly viewed as black boxes that solely provide a deterministic answer for the detected target. Without a convincing explanation, domain experts can hardly trust the detection results and must conduct further time-series diagnoses in real-world applications. To overcome this 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 of it being difficult to train and evaluate models for real-world applications due to the lack of sufficient data. In addition, we designed Probabilistic Outlier Detection (PrOuD), which is a general solution to provide interpretable detection results to assist domain experts with time-series analysis. PrOuD can convert the predictive uncertainty of a time-series value from a trained model into the 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 can detect emerging anomalies accurately and quickly. The implemented PrOuD demo case shows its potential to make the detection results of existing detection methods more convincing so that domain experts can more efficiently complete their tasks, such as time-series diagnosis and anomalous pattern clustering. open access He, Yujiang Huang, Zhixin Vogt, Stephan Sick, Bernhard doi:10.3390/en17010064 Anomalieerkennung Ausreißer <Statistik> Fotovoltaik Wechselrichter Prognose Zeitreihenanalyse publishedVersion eissn:1996-1073 Issue 1 Energies Volume 17 false 64
The following license files are associated with this item: