Optimization of Region Distribution Using Binary Partition-based Matching Algorithm for Data Distribution Management

High Level Architecture (HLA) is an architecture for reuse and interoperation of simulations. In HLA paradigm, the Runtime Infrastructure (RTI) provides a set of services. Data Distribution Management (DDM) service reduces message traffic over the network. DDM aims to control and limit the data exchanged between federates during federation. Each federate may inform the RTI about its intention to publish some data or it may subscribe to receive a subset of the published data These services rely on the computation of the intersection between “update” and “subscription” regions. When calculating the intersection between update regions and subscription regions, the higher computation overhead can occur. Currently, there are several main DDM filtering algorithms. This paper proposes a region distribution detection algorithm to use in the binary partition-based matching algorithm for DDM in the HLA-based large-scale distributed simulations. The new region detection algorithm calculates the distribution of regions in the routing space after performing the partitioning of regions that contains in the projected routing space. The partitioning among regions performs based on the result of optimal pivot. Then, the proposed algorithm calculates the regions distribution and define the matching area of the selected partitions in routing space. The proposed algorithm provides the more definite matching area between update region and subscription region during matching process. This algorithm guarantees low computational overheads for matching process and reduces the irrelevant message among federates