Simulation Model Selection Method Based on Semantic Search in Cloud Environment

Abstract

Search and selection of simulation model is an important process of building simulation application of complex system based on model composition in cloud architecture environment. This paper aims to solve the problem of lacking model correlation search and quality of service (QoS) weighted selection. The knowledge graph is used to describe the simulation models and their correlations. According to the model attributes (such as model name, domain, type, time scale, model granularity, etc.) and the model correlation (such as equipment model carrying relationship, etc.) set by users, the initial set of simulation models satisfying the requirements is found based on semantic search. Then, an optimization selection mechanism based on QoS is proposed to support users in customizing the weights of the QoS indices. The optimally ordered model candidate set is provided for selecting according to the weighting comparison of QoS indices. The experimental results show that the proposed method based on semantic search can support the effective selection of simulation models in cloud environment and the composite modeling of complex systems.