EnergyMap: Energy-efficient embedding of MapReduce-based virtual networks and controlling incast queuing delay

Abstract

Energy consumption is a major concern for today's data centers. MapReduce is a cloud computing paradigm that is widely deployed in many data centers. In this paper, we propose EnergyMap, a novel energy-efficient embedding method that maps heterogeneous MapReduce-based virtual networks onto a heterogeneous data center network. EnergyMap also tries to constrain the incast queuing delay that may happen in Virtualized Data Centers (VDCs). Simulation results show that EnergyMap significantly reduces a data center's energy consumption and effectively controls the queuing delay caused by incast traffic.