The cost-efficient deployment of replica servers in virtual content distribution networks for data fusion

Content distribution networks (CDNs) play an important role in distributing content between end users and servers because they can effectively reduce response delays and bandwidth consumption by deploying sets of servers close to end users for service provision. A remaining challenge to CDN deployment is how to efficiently place the replica servers while guaranteeing the quality of service (QoS). As a newly emerging technology, network function virtualization (NFV) facilitates the use of network function software and enables the deployment of different network functions on networked commercial servers. Virtual CDNs are among the most relevant cases that could benefit from NFV. In this paper, we study the problem of efficiently deploying replica servers (middle boxes) in cloud data centers via NFV. We propose an approximation algorithm based on spectral clustering theory to solve the replica server placement problem within an NFV environment. We conduct simulations using local and large-scale data centers to evaluate the performance of our proposed algorithm. The simulation results show that our algorithm achieves lower deployment costs and improved data fusion while optimizing nodes, services and data processing.