https://www.mdu.se/

Many complex software-intensive systems have a long life time, and undergo substantial evolution. These evolutions are either additions of functionality or system refactoring, i.e., updating the architecture to improve quality attributes without changing functionality. However, the return of investment for such a system refactoring is not easily measured due to a lack of understanding of its effects. In order to improve our understanding of these effects, we have conducted a systematic literature review of the reported effects of one such refactoring: the introduction of AUTOSAR, an open automotive software architecture standard. The effects include both benefits, like lower complexity and more efficient system development, and costs, like performance risks. We have investigated how the effects depend on different elements in AUTOSAR, and how the reports correspond to the stated objectives of the standard. It is also discussed to what extent these effects can be generalized to other types of refactoring.

This paper describes an empirical study of decision-making when changing the architecture in embedded systems. A refactoring of the system architecture often gives effects on both system properties and functions in the company organization, and there is a lack of efficient analysis methods for decision support in the system architecture process. This study investigates the information needed to make a decision about a system refactoring. Scenario-based interviews have been conducted with managers and system architects from companies developing embedded systems. The results show that the companies investigate similar issues regardless of their industry sector. The most wanted information prior to a decision is also presented.

This paper presents an exploratory study of an automotive manufacturer, which develops embedded software for over 150 products and has adopted a company-wide software product-line approach. The company is facing the introduction of a new software architecture in all products in near time. This architecture introduces new paradigms more explicitly, such as explicit software components and signal-based communication, newer technologies, and adheres to new standards. Concretely, the architecture consists of common infrastructure and other generic components. Such a fundamental and drastic technology change can be expected to have far-reaching consequences, both of technical and non-technical nature. In this study we systematically investigate the introduction of the new software architecture, by mapping individual elements of the architectural change to system properties and company functions. The study implies that the whole organization is affected, and the new architecture also influences the cooperation with suppliers.