Workload Analysis of Cloud Resources using Time Series and Machine Learning Prediction

Most of the businesses now-a-days have started using cloud platforms to host their software applications. A Cloud platform is shared resource that provides various services like software as a service (SAAS), infrastructure as a service (IAAS) or anything as a service (XAAS) that is required to develop and deploy any business application. These cloud services are provided as virtual machines (VM) that can handle the end user's requirements. The cloud providers must ensure efficient resource handling mechanisms for different time intervals to avoid wastage of resources. Auto-scaling mechanisms would take care of using these resources appropriately along with providing an excellent quality of service. Auto-scaling supports the cloud service providers achieve the goal of supplying the required resources automatically. It use methods that will calculate the number of requests and decides the resources to release based on workload. The workload consists of some quantity of application program running on the machine and usually some number of users connected to and communicating with the computer's applications. The researchers have used various approaches to perform autoscaling which is a process to predict the workload that is required to handle the end users request and provide required resources as Virtual Machines (VM) disruptively. Along with providing uninterrupted service, the businesses also only pay for the service they use, thus increasing the popularity of Cloud computing. Based on the workload identified the resources are provisioned. The resource provisioning techniques is a model used for enabling convenient, on-demand network access to a shared pool of configurable computing resources (e.g., networks, servers, applications, and services) required resources are released. In this regard, the aim of this paper is to develop a framework to predict the workload using deep learning which would be able to handle provisioning of cloud resources dynamically. This framework would handle the user request efficiently and allocate the required virtual machines. As a result, an efficient dynamic method of provisioning of cloud services would be implemented supporting both the cloud providers and users.