Conclusions of the ARTIST2 Roadmap on Control of Computing Systems

he use of control-based methods for resource manage- ment in real-time computing and communication systems has gained a substantial interest recently. Applications ar- eas include performance control of web-servers, dynamic resource management in embedded systems, traffic con- trol in communication networks, transaction management in database servers, error control in software systems, and au- tonomic computing. Within the European EU/IST FP6 Net- work of Exellence ARTIST2 on Embedded System Design a roadmap on Control of Real-Time Computing Systems has recently been completed. The focus of the roadmap is how flexibility, adaptivity, performance and robustness can be achieved in a real-time computing or communication system through the use of control theory. The item that is controlled is in most cases the allocation of computing and communication resources, e.g., the distribution or schedul- ing of CPU time among different competing tasks, jobs, re- quests, or transactions, or the communication resources in a network. Due to this, control of computing systems also goes under the name of feedback scheduling. The roadmap is divided into six research areas: con- trol of server systems, control of CPU resources, control of communication networks, error control of software systems, feedback scheduling of control systems, and control mid- dleware. For each area an overview is given and challenges for future research are stated. The aim of this position paper is to summarize the conclusions concerning these research challenges