@misc{MatthiesTeusnerHesse2018,
  author    = {Matthies, Christoph and Teusner, Ralf and Hesse, G{\"u}nter},
  title     = {Beyond Surveys},
  series = {2018 IEEE Frontiers in Education (FIE) Conference},
  journal   = {2018 IEEE Frontiers in Education (FIE) Conference},
  publisher = {IEEE},
  address   = {New York},
  isbn      = {978-1-5386-1174-6},
  issn      = {0190-5848},
  pages     = {9},
  year      = {2018},
  language  = {en}
}
@phdthesis{Hesse2022,
  author    = {Hesse, G{\"u}nter},
  title     = {A benchmark for enterprise stream processing architectures},
  doi       = {10.25932/publishup-56600},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-566000},
  school      = {Universit{\"a}t Potsdam},
  pages     = {ix, 148},
  year      = {2022},
  abstract  = {Data stream processing systems (DSPSs) are a key enabler to integrate continuously generated data, such as sensor measurements, into enterprise applications. DSPSs allow to steadily analyze information from data streams, e.g., to monitor manufacturing processes and enable fast reactions to anomalous behavior. Moreover, DSPSs continuously filter, sample, and aggregate incoming streams of data, which reduces the data size, and thus data storage costs. The growing volumes of generated data have increased the demand for high-performance DSPSs, leading to a higher interest in these systems and to the development of new DSPSs. While having more DSPSs is favorable for users as it allows choosing the system that satisfies their requirements the most, it also introduces the challenge of identifying the most suitable DSPS regarding current needs as well as future demands. Having a solution to this challenge is important because replacements of DSPSs require the costly re-writing of applications if no abstraction layer is used for application development. However, quantifying performance differences between DSPSs is a difficult task. Existing benchmarks fail to integrate all core functionalities of DSPSs and lack tool support, which hinders objective result comparisons. Moreover, no current benchmark covers the combination of streaming data with existing structured business data, which is particularly relevant for companies. This thesis proposes a performance benchmark for enterprise stream processing called ESPBench. With enterprise stream processing, we refer to the combination of streaming and structured business data. Our benchmark design represents real-world scenarios and allows for an objective result comparison as well as scaling of data. The defined benchmark query set covers all core functionalities of DSPSs. The benchmark toolkit automates the entire benchmark process and provides important features, such as query result validation and a configurable data ingestion rate. To validate ESPBench and to ease the use of the benchmark, we propose an example implementation of the ESPBench queries leveraging the Apache Beam software development kit (SDK). The Apache Beam SDK is an abstraction layer designed for developing stream processing applications that is applied in academia as well as enterprise contexts. It allows to run the defined applications on any of the supported DSPSs. The performance impact of Apache Beam is studied in this dissertation as well. The results show that there is a significant influence that differs among DSPSs and stream processing applications. For validating ESPBench, we use the example implementation of the ESPBench queries developed using the Apache Beam SDK. We benchmark the implemented queries executed on three modern DSPSs: Apache Flink, Apache Spark Streaming, and Hazelcast Jet. The results of the study prove the functioning of ESPBench and its toolkit. ESPBench is capable of quantifying performance characteristics of DSPSs and of unveiling differences among systems. The benchmark proposed in this thesis covers all requirements to be applied in enterprise stream processing settings, and thus represents an improvement over the current state-of-the-art.},
  language  = {en}
}
@misc{HesseMatthiesSinzigetal.2019,
  author    = {Hesse, G{\"u}nter and Matthies, Christoph and Sinzig, Werner and Uflacker, Matthias},
  title     = {Adding Value by Combining Business and Sensor Data},
  series = {Database Systems for Advanced Applications},
  volume    = {11448},
  journal   = {Database Systems for Advanced Applications},
  publisher = {Springer},
  address   = {Cham},
  isbn      = {978-3-030-18590-9},
  issn      = {0302-9743},
  doi       = {10.1007/978-3-030-18590-9_80},
  pages     = {528 -- 532},
  year      = {2019},
  abstract  = {Industry 4.0 and the Internet of Things are recent developments that have lead to the creation of new kinds of manufacturing data. Linking this new kind of sensor data to traditional business information is crucial for enterprises to take advantage of the data's full potential. In this paper, we present a demo which allows experiencing this data integration, both vertically between technical and business contexts and horizontally along the value chain. The tool simulates a manufacturing company, continuously producing both business and sensor data, and supports issuing ad-hoc queries that answer specific questions related to the business. In order to adapt to different environments, users can configure sensor characteristics to their needs.},
  language  = {en}
}