SLA Based Dynamic Provisioning of Cloud Resource in OLTP Systems

In the era of cloud computing, an increasing amount of services are moving online. Also increasing is the amount of cloud resource to power these services. Among these modern online transactions, many belong to the category of Online Transaction Processing (OLTP), which can be processed with predictable time and resource. However, with a large user base and fluctuated usage patterns, providing OLTP services efficiently remains a major challenge. In this paper we present an online algorithm that solves for a cost-minimizing provision scheme under fluctuated user requests, constrained by a tail-distribution-based Service Level Agreement (SLA), and incorporated with Neural Network prediction. Experiment shows that the algorithm delivers significant savings in provision, and outperforms a simple look-forward provision plan with the same SLA compliance.