An Approach for Validation of Semantic Composability in Simulation Models

Abstract

Semantic composability aims to ensure that the composition of simulation components is meaningful in terms of their expressed behavior, and achieves the desired objective of the new composed model. Validation of semantic composability is a non-trivial problem because reused simulation components are heterogeneous in nature and validation must consider various orthogonal aspects including logical, temporal and formal. In this paper, we propose a layered approach to semantic composability validation with increasing accuracy and complexity. Firstly, concurrent process validation exploits model checking for logical properties of component coordination including deadlock, safety, and liveness. Secondly, meta-simulation addresses temporal properties by validating safety and liveness of the composition through simulation time. Thirdly, perfect model validation provides a formal composition validation guarantee by determining the behavioral equivalence between the composed model and a perfect model. In contrast to state-of-the-art validation approaches, we propose time-based formalisms to describe simulation components and compare the composition behaviors through time using semantically related composition states. As proof of concept, we discuss examples of queueing networks composition and implementation using existing model checkers and constraint solvers. Lastly, we evaluate the complexity of each layer as a function of the number of components.

An approach to semantic-based model discovery and selection

“…As discussed above, capturing domain specific knowledge is of crucial importance both in model discovery, and in semantic validation (Szabo and Teo 2009). We propose the COSMO (COmponent Simulation and Modeling Ontology) ontology for describing component-oriented simulation within and across application domains to support discovery, reuse, and validation of the composed models (Teo and Szabo 2008).…”

“…Once the conceptual model is drawn, its syntactic composability is verified, using our proposed Extended Backus-Naur Form (EBNF) composition grammar (Szabo and Teo 2007). If the conceptual model is syntactically correct, model discovery identifies appropriate components from the repository, and the composed model can then be semantically validated (Szabo and Teo 2009). …”

A time-based formalism for the validation of semantic composability

“…Definition 3 is the usual mathematical composability definition but only considers time moment values from the three coordinate function domain. This is because individual component states are irrelevant at this point in the validation, and input and output data has been previously validated (Szabo and Teo 2009a). A simulation represents the execution of the composition over the simulation time.…”

“…Next, logical composition properties such as safety and liveness (Owicki and Lamport 1982) over time have been previously validated. This is the case in the layered validation process in the CoDES framework in which logical properties are first validated in the context of instantaneous transitions and secondly, over time (Szabo and Teo 2009a). Lastly, to facilitate the calculation of V ε , a component-based ontology in which component-based simulation concepts as well as application domain notions are rigorously defined.…”

“…Space constraints prevent us from showing the example here. However, it is discussed in detail in (Szabo and Teo 2009b). For the case where the simulation components are very similar to the perfect components, the validation process validates the grid model.…”