Power management schemes for heterogeneous clusters under quality of service requirements

Abstract

For modern computer systems, both performance and power consumption must be considered to reduce the maintenance cost for quality of service guarantees. This paper proposes efficient and effective power management schemes for heterogeneous clusters. Distinct from existing heuristic approaches, we propose power management schemes with approximation factor guarantees, compared to the optimal power management. Our greedy power management schemes have 1.5-approximation or 2-approximation guarantees depending on the complexity. We also propose dynamic-programming approach which can trade the quality of the resulting solutions with different time/space complexity. Simulation results wrt different power consumption models show that the proposed schemes are effective for the minimization of the power consumption for large scale clusters.