摘要： 对于多任务、多进程实时系统中的周期性任务，有一系列静态分配调度算法能有效地解决各种特定条件下的任务分配和调度问题，但这些算法均要求被调度任务的特征参数为已知条件，在很多实时系统中，周期性任务的运行时间或任务数量常常是一些具有一定规律的随机过程，上述静态算法的效能将受到限制。该文描述的神经网络能够充分利用不同时间和空间的数据信息，有较强的学习功能，提高了系统的性能和效率。

关键词: 嵌入式操作系统, 多任务调度, BP算法

Abstract: For periodic tasks in a distributed real-time system, a number of static allocation algorithms are developed which solve the problem of assigning and scheduling tasks effectively under some determined conditions. The principal limitation of these approaches is that the attributes of the tasks have to be known. Sometimes the execution time or the number of subtasks of a periodic task might be a stochastic process obeying some rule. In such cases, the performance of the static schemes will decrease greatly. This paper proposes Neural Network(NN) that can make full use of the information from various time and space, it has a strong learning ability. Moreover, NN improves system’s performance and efficiency and extends its functions.

Key words: embedded operating system, multi-task scheduling, BP algorithm

中图分类号: 

• TP311