Dynamic workflow scheduling optimization method of hybrid heuristic rule and genetic algorithm

Abstract

The invention discloses a dynamic workflow scheduling optimization method of a hybrid heuristic rule and a genetic algorithm. The method comprises the following steps: 1) setting a heuristic rule; 2) coding the heuristic rule into chromosomes according to the numbers, and initializing a population; 3) calculating the fitness value of each chromosome according to the fitness function; 4) screening and eliminating part of individuals according to the fitness value; 5) generating new offspring individuals through crossover and variation until the number of the individuals in the population is recovered to the original number; (6) if iteration reaches a threshold value, executing the step (7), otherwise, executing the step (3); 7) recording the solution represented by the individual with the highest fitness in the current population, and starting to execute the solution for one cycle; 8) after the end of one cycle time, collecting tasks which are not scheduled and work tasks which arrive in the execution period to form a new task set; and 9) on the basis of the new task set, executing the step 2) to obtain a new scheduling scheme.

Description

technical field [0001] The invention relates to two major fields of workflow scheduling and intelligent computing, and mainly relates to a dynamic workflow scheduling optimization method of mixing heuristic rules and genetic algorithms. [0002] technical background [0003] Cloud platform workflow scheduling can effectively improve the utilization of resources and speed up the overall completion time of tasks by scheduling the execution order of tasks and resource allocation strategies. With the rise of the cloud computing industry, in order to pursue an efficient and low-energy cloud platform environment, the platform has higher and higher requirements for scheduling algorithms. [0004] The main methods of workflow scheduling include traditional task scheduling algorithm and task scheduling algorithm based on heuristic thought. One of the traditional task scheduling algorithms is a greedy algorithm, such as OLB, MET, and MCT algorithms, which respectively adopt the strate...

AI Technical Summary

Problems solved by technology

[0005] Ozdamar (Ozdamar L.A genetic algorithm approach to a general category project scheduling problem[J].Systems Man&Cybernetics Part C Applications&Reviews IEEE Transactions on,1999,29(1):44-59.) proposed to use a combination of heuristic rules and genetic algorithms, using It is suitable for scheduling a single workflow, but the genetic algorithm is mainly aimed at fixed-scale problems, and is not compatible with dynamic workflows

Images