Energy-aware hierarchical task scheduling method and device

Abstract

The invention discloses an energy-aware hierarchical task scheduling method and device. The method comprises the following steps: initially, calculating a coordination period value and an energy-saving task parameter offline in advance according to a task set parameter, and judging whether a task is schedulable or not; if the task set is schedulable, scheduling execution is started, and the application with the highest priority is selected to occupy the CPU; if the application Ai is selected to occupy the CPU core, the scheduler of the Ai sequentially executes tasks in the ready task set on the CPU core according to the descending order of the priorities of the tasks; and if a task arrives after the initial energy-saving task of the coordination period is executed and the processor is not in a working state when the task arrives, adding the task into the waiting queue until the task can be added into the ready queue to wait for execution in the next coordination period. According to the method, on the premise that the task meets the deadline requirement, the idle time of the processor can be converted into a sleep low-power state as much as possible, and the requirement of layered real-time task scheduling for saving energy consumption is met.

Description

technical field [0001] The invention belongs to the technical field of real-time task scheduling, and in particular relates to a real-time task scheduling method and device under an energy-aware hierarchical scheduling model. Background technique [0002] Hierarchical scheduling groups tasks in units of applications, one task belongs to one application, one application can have multiple tasks, and one system has multiple applications. Each application is independent of each other. If a task of an application fails, it will only affect the internal tasks of the application and will not affect the execution of other applications, so that the applications of the entire system are tightly integrated and isolated from each other. Hierarchical scheduling is divided into two levels of scheduling: the first level of global scheduling and the second level of local scheduling. Global scheduling is for the operating system to schedule applications. The operating system regards an appl...

AI Technical Summary

Problems solved by technology

[0004] Existing hierarchical scheduling strategies (such as two-layer EDF scheduling, graphical model task scheduling, etc.) only consider the task deadline constraints and do not consider the processor energy consumption generated by task operation, and support energy consumption control scheduling under hierarchical scheduling Method research is still blank

At the same time, the existing energy-aware task scheduling methods (such as the Double-Largest-Task-First algorithm using dynamic scaling voltage technology, the Rate-HarmonizedScheduling method using dynamic power management technology, etc.), although considering the energy consumption of the processor problem, but only for single-level task scheduling model, its method cannot be directly applied to hierarchical scheduling

Summarizing the existing research, it can be found that the scheduling method of real-time hierarchical scheduling energy consumption control is in a blank state

Images