Composing Real-Time Systems

We present a method to construct real-time systems using as components anytime algorithms whose quality of results degrades gracefully as computation time decreases. Introducing computation time as a degree of freedom defines a scheduling problem involving the activation and interruption of the anytime components. This scheduling problem is especially complicated when trying to construct inter-ruptible algorithms, whose total run-time is unknown in advance. We introduce a framework to measure the performance of anytime algorithms and solve the problem of constructing interruptible algorithms by a mathematical reduction to the problem of constructing contract algorithms, which require the determination of the total run-time when activated. We show how the composition of anytime algorithms can be mechanized as part of a compiler for a LISP-like programming language for real-time systems. The result is a new approach to the construction of complex real-time systems that separates the arrangement of the performance components from the optimization of their scheduling, and automates the latter task. 1 Introduction Our objective in this research has been to develop and automate a methodology for the construction of utility-driven, real-time agents. A real-time agent is an agent whose utility function depends on time. For example, a utility function defined as the number of widgets assembled per hour depends on time; a robot designed to maximize this utility function is a real-time agent. Similarly , problems such as chess-playing, reentry navigation for a space shuttle, financial planning and trading, and medical monitoring in an intensive care unit have utility functions that depend on time, and therefore require the construction of real-time systems. This approach generalizes the traditional view of reai-time systems as systems that can guarantee a response after a fixed time has elapsed [Laffey et a/., 1988], in that deadlines can be expressed by a sharp drop in the utility function. We show in this paper how to construct real-time systems using anytime algorithms 1 as basic blocks. Anytime algorithms are algorithms whose quality of results degrades gracefully as computation time decreases, hence they introduce a tradeoff between computation time and quality of results. The algorithm's performance profile (PP) gives a probabilistic description of the quality of results as a function of time (we define and generalize this notion in section 2). For example, consider a hierarchical diagnosis algorithm that recursively performs a test to identify the defective component of an assembly. This algorithm can be interrupted at any time …