I am a research assistant and PhD student from Technische Universität Dresden, supervised by Wolfgang Lehner and Maik Thiele. My PhD thesis is on feature-based time series analytics. It focuses on statistical and learned representations for time series datasets and their use in data-mining tasks such as modification, generation, forecasting, classification, and clustering.
Current projects
GOFLEX
The GOFLEX project integrates a group of electricity smart-grid technologies, enabling the cost-effective use of demand response in distribution grids. The intermittent generation of renewable energy sources and the fluctuating electricity consumption require accurate and efficient forecast techniques in order to safely support an increasing share of renewable electricity generation.
Technische Universität Dresden has developed the benchmark framework ECAST for energy forecasts that allows transparent comparison of forecasting models for different forecast scenarios and requirements. I integrate ECAST as part of the GOFLEX cloud service and provide additional forecast models for energy forecasting.
GOFLEX Project (Generalized Operational FLEXibility for Integrating Renewables in the Distribution Grid)
Time Series Generation
For more than three decades, researchers have been developing generation methods for time series from the weather, energy, and economic domain. My goal is to provide a comparative and cross-domain assessment of generation methods and their expressiveness. Moreover, I propose generation methods based on different recombination techniques in order to evolve time series datasets that are highly similar to the given dataset.
Past projects
What-if
Time series usually represent actual data from organization and business processes. For critical tasks like decision-making, planning, predictions, and analytics, it is also desirable to apply them to alternative scenarios in order to prepare for developments that diverge from expectations or assess the robustness of current strategies. In this project, I proposed a generally applicable and easy-to-use method for creating what-if scenarios on time series datasets. The extraction of descriptive features allows the construction of an alternate version by means of filtering and modification of these features.
FFQ
The FFQ project (Flash Forward Query Framework) has the goal to integrate model-based forecasting into a database management system. It offers a simple interface to make forecasting usable for any database user. Within this project different topics are addressed that aim to speed up the forecasting approach inside the database while providing a high accuracy.
I developed techniques for maintaining forecast models in the DBMS so that they keep track of the updated underlying data. Moreover, I integrated maintenance techniques for derived forecasts such as, e.g, aggregated and disaggregated forecast schemes.
Publications (8)
@article{,
author = {Claudio Hartmann and Lars Kegel and Wolfgang Lehner},
title = {Feature-aware forecasting of large-scale time series data sets},
journal = {it - Information Technology},
year = {2020},
month = {6},
url = {https://doi.org/10.1515/itit-2019-0035}
}@article{,
author = {Martin Hahmann and Claudio Hartmann and Lars Kegel and Wolfgang Lehner},
title = {Large-Scale Time Series Analytics \&\#8211; Novel Approaches for Generation and Prediction},
journal = {Datenbank-Spektrum},
year = {2019},
month = {1},
url = {https://doi.org/10.1007/s13222-018-00304-5}
}@conference{,
author = {Lars Kegel and Martin Hahmann and Wolfgang Lehner},
title = {Feature-based Comparison and Generation of Time Series},
booktitle = {Proceedings of the 30th International Conference on Scientific and Statistical Database Management (SSDBM'18), Bozen-Bolzano, Italy, July 9-11, 2018},
year = {2018},
month = {7},
location = {Bozen-Bolzano, Italy},
numpages = {12},
url = {https://doi.org/10.1145/3221269.3221293}
}@conference{,
author = {Lars Kegel and Martin Hahmann and Wolfgang Lehner},
title = {Generating What-If Scenarios for Time Series Data},
booktitle = {Proceedings of the 29th International Conference on Scientific and Statistical Database Management (SSDBM’17), Chicago, IL, USA, June 27-29, 2017},
year = {2017},
month = {6},
location = {Chicago, IL, USA},
numpages = {12},
url = {https://doi.org/10.1145/3085504.3085507}
}@conference{,
author = {Lars Kegel and Martin Hahmann and Wolfgang Lehner},
title = {Feature-driven Time Series Generation},
booktitle = {Proceedings of the 29th Workshop on Foundations of Databases (GvDB'17), 30.05.2017 - 02.06.2017, Blankenburg/Harz, Germany},
year = {2017},
month = {5},
numpages = {6},
keywords = {time series analysis, data generation, business analytics}
}@article{,
author = {Martin Hahmann and Claudio Hartmann and Lars Kegel and Dirk Habich and Wolfgang Lehner},
title = {Big by blocks: modular analytics},
journal = {it - Information Technology},
volume = {58},
year = {2016},
pages = {176--185},
url = {http://dx.doi.org/10.1515/itit-2016-0003}
}@article{,
author = {Lars Kegel and Martin Hahmann and Wolfgang Lehner},
title = {Template-based Time Series Generation with Loom},
booktitle = {Proceedings of the Workshops of the EDBT/ICDT 2016 Joint Conference, EDBT/ICDT Workshops 2016, Bordeaux, France, March 15, 2016.},
series = {CEUR Workshop Proceedings},
volume = {1558},
year = {2016},
url = {http://ceur-ws.org/Vol-1558/paper18.pdf},
publisher = {Palpanas, Themis \& Stefanidis, Kostas}
}@article{,
author = {Robert Ulbricht and Ulrike Fischer and Lars Kegel and Dirk Habich and Hilko Donker and Wolfgang Lehner},
title = {ECAST: A Benchmark Framework for Renewable Energy Forecasting Systems},
booktitle = {Proceedings of the Workshops of the EDBT/ICDT 2014 Joint Conference (EDBT/ICDT 2014), Athens, Greece, March 28, 2014.},
series = {CEUR Workshop Proceedings},
volume = {1133},
year = {2014},
pages = {148--155},
url = {http://ceur-ws.org/Vol-1133/paper-23.pdf},
publisher = {Candan, K. Selçcuk; Amer-Yahia, Sihem; Schweikardt, Nicole; Christophides, Vassilis \& Leroy, Vincent}
}
