Preventing and Rectifying Cloud Quality of Service Violation Through Adaptive Resource Scaling and Replication

Abstract

One major challenge in delivering and accessing cloud applications is the management of Quality of Services (QoS). It is mandatory for cloud service providers to ensure their performance and fulfil QoS, as defined in the Service Level Agreement (SLA). In this paper, we propose a Scaling and Fault Tolerance (SFT) algorithm to deploy preventive or remedial measures based on 16 decision rules for QoS violation detection and prediction. We simulate the SFT algorithm in a cloud simulator with four scenarios to measure its effectiveness in handling events such as faulty virtual machines (VMs), or over and under-provisioning of resources. Our experimental results show that the proposed SFT algorithm performs effectively (close to a 90%-100% effective rate) in providing preventive or remedial measures and reducing the number of VMs when they are not needed.

Keywords

• cloud computing
• fault tolerance
• quality of service violation
• replication
• scalability