测试任务调度多考虑资源约束和任务优先级约束, 在对消息实时性要求较高的航空总线测试设备中, 需要将任务调度的实时性能作为关键衡量指标。将剩余可调度时间和总线负载均衡程度作为优化目标, 在满足资源限制的前提下结合总线协议特征, 提出一种包含精英集的动态粒子群算法进行多目标优化, 得到Pareto前沿和非劣解集, 并从中选择非劣解作为测试消息队列。实验仿真证明了该调度方法的有效性, 且测试消息队列能够满足高实时性要求, 并平衡总线间负载。

The real-time performance of a scheduling method should also be regarded as one of the main goals in avionics data bus test equipment in which the real-time property of messages is highly demanded.A dynamic multi-objective particle swarm optimization algorithm is proposed, in which elitism archived strategy is used, to optimize the message queue in the objectives of maximizing the available scheduling time and balancing the bus load.The Pareto front and a non-dominated solution set are obtained.The validity and rapidity of the method are verified through simulation and a message queue is generated, which satisfies the demand of high real-time property and the balance of bus load.