Starting the own business is sometimes a dream sometimes a nightmare but undoubtedly from a macro-economic perspective it is considered to be a promising concept to secure long-term economic growth and society’s welfare, at least in Germany. Strong efforts were made to support start ups and potential entrepreneurs to run their own business. A plethora of programs were launched which were supposed to facilitate the start up process – but reality is disenchanting: The published data in the 2004 GEM indicate that the idea of an entrepreneurial society in Germany is still far beyond its realization. Germany ranks 17th out of 31 GEM states in terms of “nascent entrepreneurs” and only 22nd regarding the “young entrepreneurs”. Compared to other GEM countries the German adults are considered to be more pessimistic in terms of entrepreneurial issues: The chances of establishing a successful business are evaluated lower than the years before. On the other hand the context factors which are considered to influence the start up opportunities especially in terms of governmental support and physical infrastructure were evaluated to be one of the best. Especially concerning the latter aspect strong efforts have been made to support entrepreneurs. In this context, and maybe because of - A “… post-1970s fascination with ‘high-tech’ regions worldwide” (Cooke/Leydesdorff 2006: 9), - A continuous liberalization of the world market and its impact on national production systems (which is well discussed in the context of the conversion of cooperatives), or - The dawn of the concept of national innovations systems (e.g. Lundvall 1988; Cozzens et al. 1990), For more than two decades, one promising concept of sustaining entrepreneurs was seen in the idea of incubators1 which mainly offer support in terms of infrastructure and funding opportunities. Meantime, we observe that questions emerge of how effective and efficient incubators work as one major instrument of macroentrepreneurial (Van de Veen 1995, Chiles/Meyer 2001) activities in order to facilitate start ups and to support the first steps of a new business from its start to its growth. The value of the incubator model as an effective means of technology and knowledge transfer especially from universities is continually discussed and questioned (Cunningham 1999). For example, a study run by Allen and Kahman (1985) concluded that incubators are tools for developing enterprises which create a positive environment for small businesses to succeed. Indeed, lots of studies brought up that incubators are an efficient and effective way to sustain spin-out processes and to contribute to regional development and prosperity. However, on the other hand some shortcomings are obvious: Finer and Holberton (2000) take into question the incubator model because it takes the initiative away from the start-up team. The paper refers to these observations. We assume by means of some international empirical studies that the functions of incubators are enhanced as a result of a (evolutional) learning process. On this basis we derive hypothesis about the dealing with the upcoming challenges and provide further research questions in an explorative way. Paragraph 2 introduces a three phased model of business incubators and classifies existing incubators. It will be obvious, that there is an increasing amount of functions that are allocated by incubators. Within paragraph 3 we examine recent developments from a macroeconomic perspective and contrast to this the evolution of incubators. Paragraph 4 presents two types of incubators that take these 1 In the context of this paper we primarly refer to non-profit incubators. contradictions into account and offers an alternative coping. Summarizing, we give an outlook on further research questions which will substantiate the evolutionary perspective on incubators.

Die Industrie ist im Wandel. Die Grenzen zwischen Industrien, Anwendungsbereichen und Unternehmen verschwinden immer weiter, sind teils kaum noch in ihrer alten Ausprägung zu erkennen. Auch die industrielle Automation kann und sollte sich diesem Trend nicht entziehen. Immer mehr Technologien und Paradigmen anderer Bereiche gewinnen an Bedeutung. Hinzu kommt, dass die Anzahl und die Vielfalt an Geräten, Anwendungen, Anforderungen und Technologien stetig wächst. Diese Arbeit befasst sich mit Ansätzen, die es ermöglichen, einigen Aspekten der wachsenden Komplexität zu begegnen. Dabei handelt es sich um Technologien und Konzepte zum Thema Management, genauer zum Netzwerk-, System- und Dienste-Management. Ziel ist es nicht nur einen Ansatz zu finden, der gegenwärtigen Ansprüchen genügt, sondern auch noch für kommende Entwicklungen geeignet ist.

Die Industrie ist im Wandel. Die Grenzen zwischen Industrien, Anwendungsbereichen und Unternehmen verschwinden immer weiter, sind teils kaum noch in ihrer alten Ausprägung zu erkennen. Auch die industrielle Automation kann und sollte sich diesem Trend nicht entziehen. Immer mehr Technologien und Paradigmen anderer Bereiche gewinnen an Bedeutung. Hinzu kommt, dass die Anzahl und die Vielfalt an Geräten, Anwendungen, Anforderungen und Technologien stetig wächst. Diese Arbeit befasst sich mit Ansätzen, die es ermöglichen, einigen Aspekten der wachsenden Komplexität zu begegnen. Dabei handelt es sich um Technologien und Konzepte zum Thema Management, genauer zum Netzwerk-, System- und Dienste-Management. Ziel ist es nicht nur einen Ansatz zu finden, der gegenwärtigen Ansprüchen genügt, sondern auch noch für kommende Entwicklungen geeignet ist.

In the pursuit for ever-increasing compute power, and with Moore's law slowly coming to an end, high-performance computing started to scale-out to larger systems. Alongside the increasing system size, the interconnection network is growing to accommodate and connect tens of thousands of compute nodes. These networks have a large influence on total cost, application performance, energy consumption, and overall system efficiency of the supercomputer. Unfortunately, state-of-the-art routing algorithms, which define the packet paths through the network, do not utilize this important resource efficiently. Topology-aware routing algorithms become increasingly inapplicable, due to irregular topologies, which either are irregular by design, or most often a result of hardware failures. Exchanging faulty network components potentially requires whole system downtime further increasing the cost of the failure. This management approach becomes more and more impractical due to the scale of today's networks and the accompanying steady decrease of the mean time between failures. Alternative methods of operating and maintaining these high-performance interconnects, both in terms of hardware- and software-management, are necessary to mitigate negative effects experienced by scientific applications executed on the supercomputer. However, existing topology-agnostic routing algorithms either suffer from poor load balancing or are not bounded in the number of virtual channels needed to resolve deadlocks in the routing tables. Using the fail-in-place strategy, a well-established method for storage systems to repair only critical component failures, is a feasible solution for current and future HPC interconnects as well as other large-scale installations such as data center networks. Although, an appropriate combination of topology and routing algorithm is required to minimize the throughput degradation for the entire system. This thesis contributes a network simulation toolchain to facilitate the process of finding a suitable combination, either during system design or while it is in operation. On top of this foundation, a key contribution is a novel scheduling-aware routing, which reduces fault-induced throughput degradation while improving overall network utilization. The scheduling-aware routing performs frequent property preserving routing updates to optimize the path balancing for simultaneously running batch jobs. The increased deployment of lossless interconnection networks, in conjunction with fail-in-place modes of operation and topology-agnostic, scheduling-aware routing algorithms, necessitates new solutions to solve the routing-deadlock problem. Therefore, this thesis further advances the state-of-the-art by introducing a novel concept of routing on the channel dependency graph, which allows the design of an universally applicable destination-based routing capable of optimizing the path balancing without exceeding a given number of virtual channels, which are a common hardware limitation. This disruptive innovation enables implicit deadlock-avoidance during path calculation, instead of solving both problems separately as all previous solutions.