Cloud computing resource allocation method based on clonal selection algorithm

Abstract

The invention provides a cloud computing resource allocation method based on a clonal selection algorithm. The cloud computing resource allocation method comprises: randomly generating an initial antibody population, wherein each antibody corresponds to a cloud task allocation scheme; calculating the execution duration of each virtual machine in each allocation scheme and the total duration of each allocation scheme; cloning and mutating each antibody in the initial antibody population to form a new antibody, calculating the execution time of each virtual machine in the allocation scheme for each new antibody and the total duration of each allocation scheme, forming a new antibody population by combining the antibody population with the new antibodies produced by clonal mutation, and arranging the antibodies in the new antibody population in duration ascending order, and retaining first M antibodies as antibodies in the initial antibody population; repeating above procedures, and selecting the antibody with the shortest total duration of the allocation scheme from the remaining M antibodies. The method optimizes the allocation scheme, can complete all tasks in a shorter time, and improves the execution efficiency.

Description

technical field [0001] The invention relates to the field of cloud computing. More specifically, the present invention relates to a cloud computing resource allocation method based on a clone selection algorithm. Background technique [0002] Cloud computing is a computing model that enables access to shared resource pools anytime, anywhere and on-demand through the Internet. Cloud computing resource scheduling can be defined as the process of resource allocation among different user tasks according to certain resource usage rules in the cloud computing environment. In the prior art, scholars have proposed a sequential allocation strategy and a greedy strategy to allocate resources, but the above two methods also have their own shortcomings. [0003] The sequential allocation strategy is the strategy of assigning tasks in the order of tasks. In this method, assuming that there are n tasks and m virtual machines, they are assigned to the virtual machines one by one accordin...

AI Technical Summary

Problems solved by technology

However, this greedy strategy is often a local optimum, and it often falls into a local optimum when dealing with complex tasks with large demand changes, and cannot complete resource allocation tasks well.

Images