Empirical Study of Large-Scale HLA Simulation of Parallel Region-Matching Knowledge Recognition Algorithm Based on...

Area of Science:

• Computer Science
• Simulation Technology
• Distributed Systems

Background:

• Existing region-matching algorithms are computationally expensive, leading to resource waste and reduced network efficiency.
• There is a need for more efficient algorithms in High Level Architecture (HLA) distributed simulations.

Purpose of the Study:

• To develop a parallel region-matching knowledge recognition algorithm for HLA distributed simulation.
• To address the limitations of existing algorithms by reducing computational resource usage and improving data transmission efficiency.

Main Methods:

• A parallel region-matching knowledge recognition algorithm is proposed.
• The algorithm utilizes a simulation technology for parallel matching of multiple regions in HLA distributed simulation.
• It incorporates a mobile intersection approach and historical data within moving intervals for matching calculations.

Main Results:

• The algorithm enables parallel matching of multiple changed regions within a single simulation.
• It significantly reduces irrelevant calculations by limiting matching to moving intervals using historical data.
• Simulation results validate the algorithm's effectiveness in supporting HLA distributed simulation evaluation.

Conclusions:

• The parallel region-matching knowledge recognition algorithm is efficient and suitable for large-scale distributed simulations.
• The mobile intersection approach and use of historical data enhance computational efficiency.
• The algorithm is particularly well-suited for multi-core computing platforms.