Generating Application-Specific Benchmark Models for Complex Systems

Abstract

Automated generators for synthetic models and data can play a crucial role in designing new algorithms/modelframeworks, given the sparsity of benchmark models for empirical analysis and the cost of generating models by hand. We describe an automated generator for benchmark models that is based on using a compositional modeling framework and employs random-graph models for the system topology. We choose the system topology that best matches the topology of the realworld system using a domain-analysis algorithm. To show the range of models for which this approach is applicable, we demonstrate our model-generation process using two examples of model generation optimized for a specific domain: (1) model-based diagnosis for discrete Boolean circuits, and (2) E.coli TRN networks for simulating gene expression.