Abstract– Geo-distributed clouds provide an intriguing platform to deploy online socialnetwork (OSN) services. To leverage the potential of clouds, a major concern ofOSN providers is optimizing the monetary cost spent in using cloud resourceswhile considering other important requirements, including providingsatisfactory quality of service (QoS) and data availability to OSN users. Inthis paper, we study the problem of cost optimization for the dynamic OSN onmultiple geo-distributed clouds over consecutive time periods while meetingpredefined QoS and data availability requirements. We model the cost, the QoS,as well as the data availability of the OSN, formulate the problem, and designan algorithm named. We carry out extensive experiments with a large-scalereal-world Twitter trace over 10 geo-distributed clouds all across the US. Ourresults show that, while always ensuring the QoS and the data availability asrequired, can reduce much more one-time cost than the state-of-the-art methods,and it can also significantly reduce the accumulative cost when continuouslyevaluated over 48 months, with OSN dynamics comparable to real-world cases.
Keywords – Cloud computing, online social network, optimizationmodels and methods, performance analysis and evaluation.