Importance sampling to evaluate real-time system reliability: A case study

Real-time distributed computers are often used in life-critical application s. However, the complexity of such systems calls for extensive simulation s tudies to validate their performance and reliability before a design can be accepted and a prototype constructed. A simulator testbed has been built t o model a variety of such systems quickly from a few basic building blocks. Life-critical applications require reliability levels so high that brute-f orce simulation to validate these levels would take weeks of computer time. In this paper, we present studies we have conducted into the use of import ance sampling in simulating real-time systems. This paper presents a intere sting case-study of the use of importance sampling in an increasingly impor tant branch of computer engineering. Importance sampling may not work for a ll cases and over all parameter ranges. In this paper, we are interest in f inding out whether (and how well) this scheme works for the case of distrib uted real-time systems and also the range of failure bias values for which it works well. Specifically, we look at the implementation of two heuristic s called 'forcing' and 'failure biasing' in the testbed. This was validated by comparing the reliability estimates with that of normal (very long) sim ulation. The effect of the failure bias on the dynamics of the scheme is al so investigated to provide readers with some guidance on choosing appropria te bias values.