Enabling Self-Management by Using Model-Based Design Space Exploration

Abstract

Reconfiguration and self-management are important properties for systems that operate in hazardous and uncontrolled environments, such as inter-planetary space. These systems need a reconfiguration mechanism that provides recovery from individual component failures as well as the ability to dynamically adapt to evolving mission goals. One way to provide this functionality is to define a model of alternative system configurations and allow the system to choose the current configuration based on its current state, including environmental parameters and goals. The primary difficulties with this approach are (1) the state space of configurations can grow very large, which can make explicit enumeration infeasible, and (2) the component failures and evolving system goals must be somehow encoded in the system configuration model. This paper describes an online reconfiguration method based on model-based design-space exploration. We symbolically encode the set of valid system configurations and assert the current system state and goals as symbolic constraints. Our initial work indicates that this method scales and is capable of providing effective online dynamic reconfiguration.