Towards trustworthy self-optimization for distributed systems

Abstract

The increasing complexity of computer-based technical systems requires new ways to control them. The initiatives Organic Computing and Autonomic Computing address exactly this issue. They demand future computer systems to adapt dynamically and autonomously to their environment and postulate so-called self-* properties. These are typically based on decentralized autonomous cooperation of the system's entities. Trust can be used as a means to enhance cooperation schemes taking into account trust facets such as reliability. The contributions of this paper are algorithms to manage and query trust information. It is shown how such information can be used to improve self-* algorithms. To quantify our approach evaluations have been conducted. © IFIP International Federation for Information Processing 2009.