Research on the Key technologies of Simulation Grid Resource Scheduling Based on Machine Learning

According to characteristics of simulation grid resources (SGR), an extend Web service description language (WSDL) was adopted to describe the attributes of SGRs, in order to facilitate the application of machine learning algorithms for SGR scheduling on a centralized-distributed SGR management model. By analyzing the specific requirements of distributed interactive simulation (DIS) task, a SGR scheduling model based on machine learning was proposed. Support vector machine (SVM) and incremental SVM were applied to implement SGRs classification when the features vectors were extracted from the WSDL documents. Scheduling agents can then carried out the SGR scheduling on classified SGRs. Experiments showed that the scheduling model can get federation overall optimal result with better performance.