Department of Computer Science & Engineering

Power over-subscription can reduce costs for modern data centers. However, designing the power infrastructure for a lower operating power point than the aggregated peak power of all servers requires dynamic techniques to avoid high peak power costs and, even worse, tripping circuit breakers. This work presents an architecture for distributed per-server UPSs that stores energy during low activity periods and uses this energy during power spikes. This work advocates explicit sizing of the distributed UPS batteries for power capping and provides a methodology to properly select the properties of the battery in order to reduce total datacenter cost of ownership per server. Depending on workload diurnal patterns and oversubscription assumption this approach can achieve up 5-10% reduction in overall costs per server.

Pre-2018 CSE ID: CS2012-0985