A resource dynamic scheduling method for a Web application in a cloud computing environment

Abstract

The invention discloses a resource dynamic scheduling method for a Web application in a cloud computing environment. Dynamic change of a user request, time delay requirements of the application, heterogeneity of cloud resources, price fluctuation of bidding examples and the like are considered. The method comprises the following steps: A) determining an optimal resource quantity based on load prediction and application delay requirements; B) selecting a bidding type with the lowest cost based on bidding instance price prediction; and C) adopting pre-leasing to reduce time delay increase causedby resource requests and creation. The method is mainly characterized by comprising the steps that A, prediction loads serve as the arrival rate of a queuing model, and the minimum number of virtualmachines needing to be leased is solved in combination with delay constraint of an application; The step B is mainly characterized in that a bidding type with the lowest prediction cost is selected for leasing based on price prediction; The step C is mainly characterized in that pre-leasing is carried out before a charging point arrives. According to the invention, dynamic resource scheduling is realized through load prediction, application delay constraint, price prediction and pre-leasing, and the cloud resource leasing cost can be reduced while the application performance is ensured.

Description

technical field [0001] The invention belongs to the technical field of cloud computing resource scheduling, in particular to a resource dynamic scheduling method for Web applications in a cloud computing environment. Background technique [0002] As an emerging computing service model, cloud computing uses virtualization technology to pool and share computing resources, improve computing capabilities, reduce resource management overhead, and enable cloud users to pay-as-you-go and dynamically rent on-demand. Due to its flexibility, high efficiency, convenience and low cost, cloud computing has been widely used in fields such as data analysis and scientific computing. Small and medium-sized enterprises lease cloud computing hardware and software resources according to their needs, which solves the bottlenecks of high system cost investment and long deployment tasks that they face when processing massive data and computing-intensive applications, enabling enterprises to focus ...

AI Technical Summary

Problems solved by technology

At present, there are many methods and projects focusing on solving the resource scheduling problem of Web applications in the cloud environment, but most of these methods are based on the assumption that cloud instances are isomorphic, and few of them involve heterogeneous resource systems with bidding instances.

Images