Energy consumption optimization method for fixed priority periodic task in hybrid critical system

Abstract

The invention relates to an energy consumption optimization method for a fixed priority periodic task of a hybrid critical system, the method comprising the following steps: establishing a hybrid critical periodic task model comprising a plurality of hybrid critical periodic tasks; determining priority of hybrid critical periodic tasks by using the critical hierarchy partitioning method; calculating the lowest feasible speed S of hybrid critical period task scheduling; calculating an idle time ST generated by a task of a high critical level in a low mode, and determining an execution speed Siof the processor by using the idle time, wherein the low level critical tasks and high level critical tasks are always executed at speed Si in low mode, and the high critical level tasks are executedat maximum processor speed with extra load in high mode; using dynamic power management technology to reduce processor power consumption. The method of the invention effectively reduces the system energy consumption by utilizing the idle time generated by the high-critical-level tasks and the dynamic power consumption management technology.

Description

technical field [0001] The invention relates to low-energy real-time scheduling of a hybrid critical system, in particular to a method for optimizing energy consumption of a fixed-priority periodic task in a hybrid critical system. Background technique [0002] A hybrid critical system refers to an embedded real-time system that performs multiple functions on the same platform and meets the constraints of power consumption, cost, and volume. Mixed critical systems can perform functions at different critical levels. These functions can be broadly categorized into safety-critical functions and mission-critical functions. An example of a mixed-critical system is a drone, where trajectory calculation and flight control functions are considered safety-critical, while object tracking for surveillance purposes is considered mission-critical. Because the system is limited by weight and volume, and powered by batteries, coupled with the rapid development of processor technology, en...

AI Technical Summary

Problems solved by technology

[0003] At present, the research on hybrid critical systems mainly focuses on the feasibility analysis of the system. There are relatively few studies on the energy consumption of hybrid critical systems. The only few studies mainly use dynamic priority policy scheduling systems, which cannot be applied to fixed Scheduling systems with high-level strategies, and the energy consumption of these researches is high

Images