Research Of Workflow Scheduling Technology Based On Collaboration

Workflow scheduling problem has been a hot topic in the field of workflow and research.An efficient workflow scheduling algorithm can greatly improve and improve the service quality of applications.The role of workflow scheduling algorithm is to allocate a variety of computing resources to different workflow tasks reasonably,so as to meet customer's service quality requirements.In recent years,with the rapid development of the Internet,people have higher and higher requirements on the efficiency of workflow scheduling algorithms.Under this background,the problem of workflow human resource scheduling is paid more and more attention by researchers.Unlike other resource scheduling problems,human resource scheduling has more controllability.On the one hand,each executive is an independent individual with different individual attributes;on the other hand,the characteristics exhibited by different actors vary with the external environment.In general,the main factors that affect human resource dispatching include the degree of collaboration among executors and the performer's capabilities and load.In this paper,we first focus on the scheduling model under the influence of collaboration and develop the objective function with the greatest degree of coordination.In order to accurately measure the degree of collaboration among executors,this paper presents a method to judge the pros and cons of collaborators by analyzing the information in the historical log of the process and proves its validity from the mathematical point of view.Then,a task allocation algorithm based on the maximum degree of cooperation is proposed to reduce the execution time of the whole process by reducing the time of interaction between executors.Aiming at the above two factors that affect human resource scheduling,a multi-objective task assignment model is constructed.Then a workflow task assignment method based on ant colony algorithm is proposed.The algorithm measures the weight of two influencing factors in the actual allocation,and can allocate more suitable performers to the tasks.Improve the efficiency of the process instance.Finally,this paper selected two sets of data sets to verify the experiment.Experimental results show that compared with the other three algorithms,thealgorithm proposed in this paper can ensure that the total collaboration is as large as possible.On the other hand,it can ensure that the total task load is as small as possible and the allocation efficiency is high.The task allocation algorithm studied in this paper can also be applied to similar problems,with a certain degree of universality.