Self-managing systems: a control theory foundation

Summary form only given. The high cost of ownership of computing systems has resulted in a number of industry initiatives to reduce the burden of operations and management by making systems more self-managing. A major challenge in realizing self-managing systems is understanding how automated actions affect system behavior, especially system stability. Other disciplines such as mechanical, electrical, and aeronautical engineering make use of control theory to design feedback systems. The talk uses control theory as a way to identify a number of requirements for and challenges in building self-managing, or autonomic, systems. In essence, the autonomic computing architecture describes feedback control loops for self-managing systems. The talk has three goals: (1) educating systems oriented computer science researchers and practitioners on the concepts and techniques needed to apply control theory to computing systems; (2) describing how control theory can aid in building self-managing systems and identifying the challenges in doing so; (3) describing a deployable testbed for autonomic computing that is intended to foster research that addresses the challenges identified.