• Home
  • الگوریتم ژنتیک.
    • List of Articles الگوریتم ژنتیک.

      • Open Access Article

        1 - A Task Mapping and Scheduling Algorithm based on Genetic Algorithm for Embedded System Design
        mohadese nikseresht Mohsen Raji
        Embedded system designers face numerous design requirements and objectives (such as runtime, power consumption and reliability). Since meeting one of these requirements mostly contradicts other design requirements, it seem to be inevitable to apply multi-objective appr More
        Embedded system designers face numerous design requirements and objectives (such as runtime, power consumption and reliability). Since meeting one of these requirements mostly contradicts other design requirements, it seem to be inevitable to apply multi-objective approaches in various stages of designing embedded systems, including task scheduling step. In this paper, a multi-objective task mapping and scheduling in the design stage of the embedded system is presented. In this method, tasks are represented by task graphs assuming that the hardware architecture platform is given and determined. In order to manage the dependencies between tasks in the task graph, a segmentation method is used, in which the tasks that can be executed simultaneously are specified in a segment and is considered in the scheduling process. In the proposed method, the task mapping and scheduling problem is modeled as a genetic algorithm-based multi-objective optimization problem considering execution time, energy consumption, and reliability. In comparison to similar previous works, the proposed scheduling method respectively provides 21.4%, 19.2%, and 20% improvement in execution time, energy consumption, and reliability. Applying a multi-objective helps the designer to pick out the best outcome according to different considerations. Manuscript profile