Enterprise IT departments must decide whether to build a private cloud themselves or lease space in a cloud instead. Actually, most enterprise cloud systems are heterogeneous simultaneously consisting partly of private cloud and partly of public cloud. An enterprise needs to know the optimal mixing ratio to achieve the lowest cost. However, the optimal ratio is a dynamic value because the popularity of data changes constantly and the data increases rapidly. In this paper, we formulate maximizing the net present value (NPV) of the investment revenue as a dynamic decision-making problem and propose a model to simplify the decision-making problem. We use the K-means algorithm to cluster the devices into groups. In addition, we also provide a solution with the kNN algorithm for locating data. Furthermore, our system provides a cost-saving solution that requires no additional devices or investment. Subsequently, as the system grows larger, the decision-making solution can be employed again to determine how to best extend the cloud system at the lowest cost.
KEYWORDScloud storage, decision-making, net present value
INTRODUCTIONIn recent years, with the development of the cloud technology, the enterprises are interested in high I/O capabilities, huge storage and processing capacities, built-in fault-tolerance, and any cost savings that using a cloud system might offer. Traditional systems such as SAN and NAS provide good solutions. However, it is too expensive when capacity and throughput needs increase rapidly. There is no doubt that cloud storage systems can be both economical and efficient. Some enterprises construct their own private clouds, while others lease capacity directly from public clouds. Both public and private clouds can meet enterprise needs because of their scalability, flexibility, and potentially low costs. However, the costs between public and private clouds can differ significantly. This cost difference can confuse enterprises: most tend to lease public services because rental costs appear to be lower than the costs of constructing a private cloud. However, cloud rental is not as inexpensive as it sometimes appears. In fact, in some cases, leasing can be much more expensive than purchasing. For enterprises, choosing between public and private clouds is a tough problem.Moreover, it is even more difficult to design a mixed system that is cost effective.Modern hard disk drives have been greatly improved. The capacity and throughput of hard disks has increased steadily, even as their prices have fallen. In particular, the SSD technology has improved dramatically. Compared with a traditional hard disk drive (HDD), an SSD has low latency, low energy consumption, high throughput, and many other advantages. Although SSD prices have fallen, SSDs are still more expensive than HDDs.Still, as one of the main features of cloud computing technology, we can now use inexpensive domestic devices rather than expensive commercial devices, which can save money. A traditional cloud storage system typically uses huge num...