Joint server selection and replica placement in urban content delivery networks

摘要

In this article, we formulate the problem of optimum joint replica server deployment and content placement in urban content delivery networks as a bi-objective binary integer programming model namely JSSRPP. The proposed formulation results in an optimum design such that the miss ratio of requests, the client response time and the cost of server deployment are minimised. In practice, the popularity of files may change over the course of time, thus, a novel adaptive file replacement algorithm namely UDCR is also proposed in which files are scored according to different criteria including the time and the number of recent requests and the size of requested files. Then, in discrete points of time, the files with the lowest score are replaced with the one experiencing the highest number of misses. Results of extensive simulation study with NS-2, confirms that the hit ratio of UDCR approaches that of JSSRPP in steady state.