Job scheduling method based on dual target optimization genetic algorithm

Abstract

The invention provides a job scheduling method based on a dual target optimization genetic algorithm. The method comprises the following steps of: generating an initial population; intersecting; mutating; evaluating; selecting; adding one to the number of genetic generations; calculating a priority function h(x) for each individual in the last population; and taking a minimum individual of the h(x) as a final solution, wherein a job scheduling sequence corresponding to the individual is a final result of the algorithm.

Description

technical field [0001] The invention relates to the field of job scheduling, in particular to a job scheduling method based on a double-objective optimization genetic algorithm. Background technique [0002] At present, most job scheduling algorithms do not consider the energy consumption of jobs, resulting in high energy consumption for completing jobs. [0003] With the substantial increase in the number and scale of computer rooms in recent years, the energy consumption of computer equipment and auxiliary facilities is getting higher and higher, which has become one of the main problems faced in the management of data center computer rooms, which not only brings heavy costs to users The pressure also puts forward higher requirements for power supply and heat dissipation. Reducing the energy consumption of operations is of great significance to the energy saving of computer rooms, especially data centers in the field of high-performance computing. [0004] The energy con...

AI Technical Summary

Problems solved by technology

Shortening the execution time generally requires high-load operation of computer nodes, thereby increasing real-time power consumption, and the total energy consumption of job execution will be relatively high

Images