ABSTRACT

A scheduling algorithm is crucial for running a simulation model so that tasks can be performed efficiently.The traditionally used blade-based parallel engine system cannot be adapted to a new simulation model. This study proposed a combined dynamic priority and static method, that is, a hybrid load-balancing scheduling (HLB) algorithm. The algorithm is given priority according to the operating cycle of the model and system steps. The experimental results demonstrated that the algorithm outperformed the earliest deadline first and the time-stepped load-balancing scheduling algorithms. The results also demonstrated that the HLBhad a higher real-time operating efficiency than the other algorithms under a lower overhead guarantee. The HLB algorithm causedbetter performance while maintaining computation and communication efficiency. Simultaneously, the utilisation rate of the central processing unit was around 35%.The further study should be enhanced to generalise it so that it could be applied to incorporate load balancing.

摘要

调度算法对于运行仿真模型至关重要，这样才能有效地执行任务。传统使用的基于叶片的并行引擎系统无法适应新的仿真模型。本研究提出了一种动态优先级和静态相结合的方法，即混合负载均衡调度（HLB）算法。该算法根据模型的运行周期和系统步骤优先。实验结果表明，该算法优于最早期限优先和时间步长负载均衡调度算法。结果还表明，在较低的开销保证下，HLB 具有比其他算法更高的实时运行效率。HLB算法在保持计算和通信效率的同时带来了更好的性能。同时地，