Resource provisioning in Cloud Computing

Abstract

The Cloud Computing can be used as a buzzword for the big turn to an IT world where computing resources provided over the internet can be acquired from IaaS providers with different purchasing plans. A critical challenge is to determine the right amount of resources to minimize the financial cost from consumer’s perspective and to maximize resource utilization from provider’s perspective. Finding optimal provisioning solutions thus becomes an NP problem. In cloud computing, cloud providers can offer a vast amount of resources. There are two provisioning plans to choice computing resources, namely reservation and on-demand plans. In general, cost of utilizing computing resources provisioned by reservation plan is cheaper than that provisioned by on-demand plan. With the reservation plan, the consumer can reduce the total resource provisioning cost but the under-provisioning and over-provisioning problem can occurs. It is important for the cloud consumer to minimize the total cost of resource provisioning by reducing the on-demand cost and oversubscribed cost of under-provisioning and over-provisioning and it is a conflicting and challenging problem. Taking Amazon EC2 for instance, this dissertation work addresses the issue of how cloud consumers could make resource provisioning plan for their computation. Heuristic algorithm is devised to determine number of instances required to execute workload which can significantly reduce the total cost incurred to consumer.