دانلود رایگان مقاله انگلیسی راه حل "بدون مرکز داده" برای محاسبات ابری - IEEE 2017

Abstract

Current Cloud Computing is primarily based on proprietary data centers, where hundreds of thousands of dedicated servers are setup to host the cloud services. In addition to the huge number of dedicated servers deployed in data centers, there are billions of underutilized Personal Computers (PCs), usually used only for a few hours per day, owned by individuals and organizations worldwide. The vast untapped compute and storage capacities of the underutilized PCs can be consolidated as alternative cloud fabrics to provision broad cloud services, primarily infrastructure as a service. This approach, thus referred to as “no data center” approach, complements the data center based cloud provision model. In this paper, we present our opportunistic Cloud Computing system, called cuCloud, that runs on scavenged resources of underutilized PCs within an organization/community. Our system demonstrates that the “no data center” solution indeed works. Besides proving our concept, model, and philosophy, our experimental results are highly encouraging.

V. Conclusion and Future Work

Credit Union Cloud Model, which aims at tapping into the underutilized computing resources available within an organization/community rather than dedicated servers, provides a promising alternative Cloud Computing solution for organizations and communities. Our work demonstrates that the “no data center” solution indeed works. Besides proving the concept, model, and philosophy of CUCM, our experimental study turned out to be highly encouraging – the “no data center” solution can gain highly competitive performance compared to its counterpart that depends on dedicated cloud servers.

The most significant aspect of our work so far is that by cuCloud we have setup a platform and have a door widely open for many exciting new research issues for the future. The resource pool over which VMs run in cuCloud is not dedicated but shared with native users/tasks. We need to devise a mechanism to provide cloud services reliably and efficiently, while keeping the services from interfering with the native users/tasks at member nodes. Another requirement of CUCM is to have a robust, dynamic and efficient resource management and provisioning mechanism. The resource management and provisioning module should consider the dynamic and unreliable nature of the member hosts that contribute resources to the resource pool of cuCloud. We also need to investigate novel and efficient scheduling algorithms that consider the availability, location, and reliability of the member nodes used by the system to deploy VMs. In addition, cuCloud requires strong security measures in order to insure the security of member nodes from malicious cloud client processes and client VMs from malicious native users at member nodes.