Partial Migration of Business Data to The Cloud

Cloud computing has led to large pools of interconnected computer resources that can be acquired or released in a matter of minutes. No long-term contracts or large upfront investment required; resources are available on a pay-per-use basis. Consequently, a thousand servers used for an hour are as expensive as using one server for a thousand hours. It also enables resources to be provisioned according to demand, reducing unnecessary costs, while simultaneously making it resilient against significant and unexpected increases in demand. This model greatly reduces the risk and startup costs to innovate and disrupt. The rise of cloud computing has placed existing application owners in a challenging position. Their application is often not designed with this level of flexibility in mind. Because of the time and money invested in an existing application it is likely preferable to use this investment rather than abandoning it. Starting anew would also require a larger and relatively long-term investment that carries more risk. For this reason a hybrid approach to cloud computing could be an attractive means to leverage past investments as well as benefit from cloud computing. Through the use of an industrial test case we have explored some of the opportunities and challenges of cloud computing from the perspective of an application that was not designed with cloud computing in mind. These insights as well as the system's current limitations to scale led us to create a working prototype to store a subset of data to Amazon's Simple Storage Service (S3). Based on our results, storage costs for this subset of data are reduced twenty fold, the administrative burden to scale is completely transferred to Amazon and performance remains acceptable despite an overhead of 88 milliseconds due to internet latency. The prototype serves as a concrete proof of concept that demonstrates hybrid cloud computing can be a viable means to improve an existing system.Web Information SystemsElectrical Engineering, Mathematics and Computer Scienc