Research on Partition Parameter Design Method for Integrated Modular Avionics Based on MOEA/D-ADV

In the avionics industry, Integrated Modular Avionics (IMA) which introduces the concept of partition has been widely adopted for its isolating capability. However, the real-time performance of the IMA system mainly depends on the partition parameters. This leads to the question of how to design the partition parameters for satisfying the timing requirements of real-time applications. In this paper, the problem of partition parameter design for multiprocessors system is investigated. Firstly, the hierarchical scheduling strategy of IMA is analyzed, and a new schedulability analysis method is proposed to judge the schedulability of the partitions according to the partition period and execution time. Then, an approximation algorithm is developed to minimize the allocated bandwidth of the partitions while simultaneously guaranteeing tasks schedulability within the partitions. The harmonic period partitions, which are used as the constraint of partition parameter design, are realized by considering the scheduling mechanism of intra-partition and inter-partition. The total required bandwidth and the system overhead caused by partition scheduling are regarded as the optimization objective functions. Moreover, Multi-objective Evolutionary Algorithm Based on Decomposition (MOEA/D) method is improved by applying the Adjustment for the Direction Vectors (ADV) algorithm. Constrained Dominance Principle (CDP) is embedded into the improved algorithm to solve the constrained optimization problem. Consequently, simulation results show that the presented algorithm can achieve better coverage and uniformity than the compared algorithms while obtaining the partition parameters, and the system overhead and total required bandwidth can also be reduced.