A Study of Model-Order Reduction Techniques for Verification [chapter]

Yi Chou, Xin Chen, Sriram Sankaranarayanan
2017 Lecture Notes in Computer Science  
As formal verification techniques for cyber-physical systems encounter large plant models, techniques for simplifying these models into smaller approximate models are gaining increasing popularity. Model-order reduction techniques take large ordinary differential equation models and simplify them to yield models that are potentially much smaller in size. These approaches typically discover a suitable projection of the state space into a smaller subspace, such that by projecting the dynamics in
more » ... his subspace, an accurate approximation can be obtained for a given initial set and time horizon of interest. In this paper, we present a study of model-order reduction techniques for verification with non-rigorous error bounds. We design experiments based on the proper orthogonal decomposition technique for finding reduced order models. We find that reduced order models are particularly effective and precise whenever a suitable reduced order model can be found in the first place. We attempt to characterize these models and provide future directions for reduced order modeling.
doi:10.1007/978-3-319-63501-9_8 fatcat:7vrvqg2e35bitgwaeir42yvo44