ASTAW: Auto-Scaling Threshold-based Approach for Web Application in Cloud Computing Environment

Abstract

In recent years, the number of users and service providers are increasing in using cloud services so the accessibility and the effective management of the required resources, irrespective of the time and place, seem to be of great importance for both sides. Improving the performance and utilization of the cloud systems are gained by the auto-scaling of the applications; this is because of the fact that, some approaches have been proposed for auto scaling. This paper seeks to checking some value, based on the learning automata, for the scalability of the web applications, which combines virtual machine clusters and the learning automata in order to provide the best possible way for the scaling up and scaling down of the virtual machines. The results of this study indicate how an increased capacity of virtual machine which have been done by the value of thresholds could effect on SLA and overhead of responding. Cloud computing technology is currently one of the popular and developing technologies and a successful example of distributed computing. Cloud computing is a model for an easy provision of network access, based on demand, for a shared storage of configurable computing resources (i.e. networks, servers, applications, services, etc.), which is capable of being provided and released very quickly with minimal management efforts, and minimal interaction with the service provider (1,2). Cloud computing technology is an attempt to propose a new mechanism for the provision of the necessary infrastructures for the users and for the creation of the illusion of access to unlimited resources in the minds of the users. Those who work in the field of cloud computing technology have considered various advantages for it including flexibility, reliability, scalability, security, a decrease in costs, an unlimited capacity of the resources, etc. However, among all these capabilities, scalability seems to enjoy more popularity compared to the others and, one can find very few documents about cloud computing in which the issue of scalability has not been discussed. Since all applications, and in particular web applications, do not follow regular workload patterns, the scaling operations (i.e. scale up or scale down) must be carried out in real time and with minimal human intervention so that the recourses would be provided for the applications as soon as possible. Such a scaling of the resource, which is done automatically and with minimal human intervention, is called Auto-scaling (3). This paper seeks to propose a novel approach for the auto-scaling of the resources of the web applications. The proposed approach is derived from the threshold scalable algorithm and is based on the learning automata. The learning automata is defined using