Combining Genetic Algorithms and Simulation to Search for Failure Scenarios in System Models

Large infrastructures, such as clouds, can exhibit substantial outages, sometimes caused by failure scenarios not predicted during system design. We define a method for modelbased prediction of system quality characteristics. The method uses a genetic algorithm to search system simulations for parameter combinations that result in system failures, so that designers can take mitigation steps before deployment. We apply the method to study an existing infrastructure-as-a-service cloud simulator. We characterize the dynamics, quality, effectiveness and cost of genetic search, when applied to seek a known failure scenario. Further, we iterate the search to reveal previously unknown failure scenarios. We find that, when schedule permits and failure costs are high, combining genetic search with simulation proves useful for exploring and improving system designs. Keywords—genetic algorithms; model-based prediction; simulation methodology; system design