Time constraint scientific workflow optimization method based on ant colony algorithm

Abstract

The invention discloses a time constraint scientific workflow optimization method based on an ant colony algorithm, and the method comprises the following steps: initializing information, initializingall ants, and constructing a mapping sequence between a task and a resource through employing an initial pheromone and heuristic information; utilizing a decoding algorithm to construct a complete scheduling scheme for the information in the codes; locally updating pheromones and globally updating pheromones according to requirements; updating the heuristic information, and updating the heuristicinformation distributed to the virtual machine by the task according to the price and the cost factor. According to the invention, the ant colony algorithm is combined with time constraint. Comparedwith the prior art, the method has the advantages that the optimization result quality is guaranteed, different enlightenment information and penalty functions are adopted for different solutions, thetime constraint and the solution space diversity of the workflow can be better balanced, meanwhile, by optimizing available resources, the execution efficiency is further improved, and good performance is achieved in optimization.

Description

technical field [0001] The invention relates to the research field of cloud service platform and intelligent computing, in particular to a time-constrained scientific workflow optimization method based on ant colony algorithm. Background technique [0002] In the scientific computing environment, a workflow is defined as a series of atomic tasks, a collection of tasks formed by data or computational dependencies. Workflows have been applied in many fields such as e-commerce, bioinformatics, astronomy and physics. In these domains, tasks are typically classified as computationally intensive and data-intensive, both of which require execution within a time frame acceptable to the user. To meet quality of service, large-scale workflows are usually deployed and executed in a distributed environment. How to coordinate the requests of multiple tasks on different resources and optimize the task completion time and task cost is one of the current research hotspots. [0003] Cloud...

AI Technical Summary

Problems solved by technology

Under such a model, the virtual computing power is either the same, or is linearly related to its price, so the cost of running a task on different virtual machines is almost the same, which is often inconsistent with the reality

In practice, when a cloud service needs to process a task, it is not enough to only consider CPU resources

Images