Adaptive server allocation for peer-assisted Video-on-Demand

Abstract

Dedicated servers are an undesirable but inevitable resource in peer-assisted streaming systems. Their provision is necessary to guarantee a satisfying quality of experience to consumers, yet they cause significant, and largely avoidable cost for the provider, which can be minimized. We propose two adaptive server allocation schemes that estimate the capacity situation and service demand of the system to adaptively optimize allocated resources. Extensive simulations support the efficiency of our approach, which, without considering any prior knowledge, allows achieving a competitive performance compared to systems that are well dimensioned using global knowledge.