While traditional design-time and off-line approaches to testing and verification contribute significantly to improving and ensuring high dependability of software, they may not cover all possible fault scenarios that a system could encounter at runtime. Thus, runtime `health management' of complex embedded software systems is needed to improve their dependability. Our approach to Software Health Management uses concepts from the field of `Systems Health Management': detection, diagnosis and mitigation. In earlier work we had shown how to use a reactive mitigation strategy specified using a timed state machine model for system health manager. This paper describes the algorithm and key concepts for an alternative approach to system mitigation using a deliberative strategy, which relies on a function-allocation model to identify alternative component-assembly configurations that can restore the functions needed for the goals of the system.