On-demand self-adaptivity of service availability for cloud multi-tier applications

摘要: Cloud data centers are increasingly becoming the first choice for many Internet enterprises (especially medium-sized and small ones) to deploy their online application. However, scaling service availability autonomously is a critical issue applications. Surplus supply may take lot of unnecessary money insufficient resources reserve will result in denial when meeting sudden massive requests. A general idea address increasing resource utilization through workload balancing dynamic management. In this paper, we propose self-adaptive approach that suitable multi-tier cloud The tries scale applications' on demand reduce infrastructure costs by improving already billed. Moreover, order cope with unexpected requests, an evaluation method adopted estimate trend requests' development then decide add or remove working servers. Finally, compare proposed algorithms consolidation quantitative analysis, showing superiorities performance some situations.