Study of self-adaptive scheduling model for open real-time embedded system
Li Gang · 2007
In the open real-time embedded environment,different kinds of real-time tasks coexist in one system.This brings new requirements and challenges to the real-time scheduling mechanism.A formal self-adaptive scheduling model for open real-time embedded system is presented in this paper,which comprises four key components:accept control,resource management,scheduling server and adaptive control.To guarantee the schedulability in the open environment,this model only accepts the task whose computing bandwidth requirement is no higher than the system’s spare one.In this model,the scheduling server components provide concurrent scheduling mechanism for multi-constraint tasks,and each of them is assigned to a bandwidth-independent computing bandwidth and has its specific scheduling policy to schedule its own task queue.To adapt to the change in the open environment,the adaptive control tries to tune the real-time priority so as to make full use of the system computing capability.This model has been used in an airborne system.Compared with other system,it actually improved the schedulability of system and systematic stability.