@phdthesis{Koehler2024,
  author    = {K{\"o}hler, Wolfgang},
  title     = {Challenges of efficient and compliant data processing},
  doi       = {10.25932/publishup-62784},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-627843},
  school      = {Universit{\"a}t Potsdam},
  pages     = {195},
  year      = {2024},
  abstract  = {Die fortschreitende Digitalisierung ver{\"a}ndert die Gesellschaft und hat weitreichende Auswirkungen auf Menschen und Unternehmen. Grundlegend f{\"u}r diese Ver{\"a}nderungen sind die neuen technologischen M{\"o}glichkeiten, Daten in immer gr{\"o}ßerem Umfang und f{\"u}r vielf{\"a}ltige neue Zwecke zu verarbeiten. Von besonderer Bedeutung ist dabei die Verf{\"u}gbarkeit großer und qualitativ hochwertiger Datens{\"a}tze, insbesondere auf Basis personenbezogener Daten. Sie werden entweder zur Verbesserung der Produktivit{\"a}t, Qualit{\"a}t und Individualit{\"a}t von Produkten und Dienstleistungen oder gar zur Entwicklung neuartiger Dienstleistungen verwendet. Heute wird das Nutzerverhalten, trotz weltweit steigender gesetzlicher Anforderungen an den Schutz personenbezogener Daten, aktiver und umfassender verfolgt als je zuvor. Dies wirft vermehrt ethische, moralische und gesellschaftliche Fragen auf, die nicht zuletzt durch popul{\"a}re F{\"a}lle des Datenmissbrauchs in den Vordergrund der politischen Debatte ger{\"u}ckt sind. Angesichts dieses Diskurses und der gesetzlichen Anforderungen muss heutiges Datenmanagement drei Bedingungen erf{\"u}llen: Erstens die Legalit{\"a}t bzw. Gesetzeskonformit{\"a}t der Nutzung, zweitens die ethische Legitimit{\"a}t. Drittens sollte die Datennutzung aus betriebswirtschaftlicher Sicht wertsch{\"o}pfend sein. Im Rahmen dieser Bedingungen verfolgt die vorliegende kumulative Dissertation vier Forschungsziele mit dem Fokus, ein besseres Verst{\"a}ndnis (1) der Herausforderungen bei der Umsetzung von Gesetzen zum Schutz von Privatsph{\"a}re, (2) der Faktoren, die die Bereitschaft der Kunden zur Weitergabe pers{\"o}nlicher Daten beeinflussen, (3) der Rolle des Datenschutzes f{\"u}r das digitale Unternehmertum und (4) der interdisziplin{\"a}ren wissenschaftlichen Bedeutung, deren Entwicklung und Zusammenh{\"a}nge zu erlangen.},
  language  = {en}
}
@phdthesis{Panzer2024,
  author    = {Panzer, Marcel},
  title     = {Design of a hyper-heuristics based control framework for modular production systems},
  doi       = {10.25932/publishup-63300},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-633006},
  school      = {Universit{\"a}t Potsdam},
  pages     = {vi, 334},
  year      = {2024},
  abstract  = {Volatile supply and sales markets, coupled with increasing product individualization and complex production processes, present significant challenges for manufacturing companies. These must navigate and adapt to ever-shifting external and internal factors while ensuring robustness against process variabilities and unforeseen events. This has a pronounced impact on production control, which serves as the operational intersection between production planning and the shop- floor resources, and necessitates the capability to manage intricate process interdependencies effectively. Considering the increasing dynamics and product diversification, alongside the need to maintain constant production performances, the implementation of innovative control strategies becomes crucial. In recent years, the integration of Industry 4.0 technologies and machine learning methods has gained prominence in addressing emerging challenges in production applications. Within this context, this cumulative thesis analyzes deep learning based production systems based on five publications. Particular attention is paid to the applications of deep reinforcement learning, aiming to explore its potential in dynamic control contexts. Analysis reveal that deep reinforcement learning excels in various applications, especially in dynamic production control tasks. Its efficacy can be attributed to its interactive learning and real-time operational model. However, despite its evident utility, there are notable structural, organizational, and algorithmic gaps in the prevailing research. A predominant portion of deep reinforcement learning based approaches is limited to specific job shop scenarios and often overlooks the potential synergies in combined resources. Furthermore, it highlights the rare implementation of multi-agent systems and semi-heterarchical systems in practical settings. A notable gap remains in the integration of deep reinforcement learning into a hyper-heuristic. To bridge these research gaps, this thesis introduces a deep reinforcement learning based hyper- heuristic for the control of modular production systems, developed in accordance with the design science research methodology. Implemented within a semi-heterarchical multi-agent framework, this approach achieves a threefold reduction in control and optimisation complexity while ensuring high scalability, adaptability, and robustness of the system. In comparative benchmarks, this control methodology outperforms rule-based heuristics, reducing throughput times and tardiness, and effectively incorporates customer and order-centric metrics. The control artifact facilitates a rapid scenario generation, motivating for further research efforts and bridging the gap to real-world applications. The overarching goal is to foster a synergy between theoretical insights and practical solutions, thereby enriching scientific discourse and addressing current industrial challenges.},
  language  = {en}
}