The performance of three Run-Time Infrastructures (RTI) is measured. Two open source implementations (Portico version 0.8 and CERTI version 3.3.0) and one commercial implementation (MÄK version 3.2) have been subjected to a specific test under ideal conditions using a dedicated federate object model. This paper reports on the results of this test for each of the RTIs. Researchers looked at the round-trip time for a federate to send an attribute update to another federate, and then to received the same update back. The attribute size was varied. This test is the first of a series of tests to be conducted on different RTIs to evaluate the performance under ideal conditions, and then later under more realistic conditions. The first test also entailed getting to know the interfaces of the different RTIs. This also contributed to the reestablishment of the use of HLA in the research unit. It is also planned to use more RTIs, from different vendors initial results show that although the MÄK RTI implementation had a limitation in terms of the data size that can be transmitted for the best effort transport setting, it had a low round-trip time as compared to CERTI and Portico.
Reference:
Malinga, L and Le Roux, WH. 2009. HLA RTI performance evaluation. Simulation Interoperability Standards Organization: 2009 SISO European Simulation Interoperability Workshop, Istanbul, Turkey, 13-16 July, 2009. pp 1-6
Malinga, L., & Le Roux, W. (2009). HLA RTI performance evaluation. http://hdl.handle.net/10204/3591
Malinga, L, and WH Le Roux. "HLA RTI performance evaluation." (2009): http://hdl.handle.net/10204/3591