Improving the quality of enterprise architecture models : processes and techniques

Hacks, Simon; Lichter, Horst (Thesis advisor); Johnson, Pontus (Thesis advisor)

Düren : Shaker Verlag (2019)
Book, Dissertation / PhD Thesis

In: Aachener Informatik Berichte, Software Engineering 43
Page(s)/Article-Nr.: 1 Online-Ressource (189 Seiten) : Illustrationen

Dissertation, RWTH Aachen University, 2019


Information technology (IT) pervades organizations more and more and becomes increasingly important for their business models. It has evolved from a purely supportive role to an important strategic pillar in many organizations. Even more, it is important that IT is aligned to the needs of the organization. Approaches that realize this are often subsumed under the term ``business-IT-alignment''. One instrument for achieving business-IT-alignment is Enterprise Architecture (EA). EAs provide a holistic perspective on the structure of the organization and provide a set of techniques to guide and steer the evolution of the organization to a desired goal state. A key artifact of EA is the EA model. It abstracts the elements and their relationships to an understandable and manageable measure. Usually enterprise architects model business processes, applications, hardware components, data models and customer relationships. Based on the information stored in the EA model, the organization's management makes important decisions regarding future focus. Contrary, also on the operational level, the model can provide important information, for example which application is used in which business environment and exchanges data with other applications. In order to be able to derive meaningful decisions from the EA model, their quality is of crucial importance. Therefore, this work is elaborates on developing different processes and techniques that ensure the quality of the EA model. First, we present a process to ensure the quality of the EA model, where model maintenance is understood as a continuous evolution. For this purpose, we define different steps, which have to be considered in such a process. This process will serve as foundation for a continuous delivery pipeline that will help automate as many of these steps as possible. Next, we present an approach that allows storing contrary information in EA models. In addition to the aforementioned processes, we developed also several techniques to improve the quality of EA models. However, for improvement, we need a method to evaluate the quality, which we also introduce within this work. Subsequently, we facilitate machine-learning techniques to support the modeler reuse existing elements of the model. In addition, we compare the performance of different algorithms to determine the best on in a certain situation. Additionally, we present a method to identify unnecessary elements in the model.