IMPROVING ENERGY EFFICIENCY THROUGH THERMAL CONTROL OF A MODULAR DATA CENTER

As the IT industry's demand for greater power density racks grows, the operating cost associated with power and cooling IT equipment remains an ever present concern facing data centers. A key component in reducing Total Cost of Ownership (TCO) for a facility is to optimize their cooling system design. Hewlett-Packard has developed a self contained enclosure for high density servers and mass storage devices called a Modular Data Center (MDC). This unit is intended to reduce issues that have plagued large scale data centers by increasing cooling capacity and efficiency. This paper takes a look at the thermal control logic for the MDC and explains ways to decrease energy costs by developing a thermal control scheme centered on optimizing Power Usage Efficiency (PUE). Tests were conducted to understand the relationships between fan power and fan speed, facility power and thermal capacity. Areas of large power drains were isolated and analyzed. Tests showed that there are two parts in managing power usage on the MDC, system and facility control. In the development of a smarter control algorithm, the fans and water valve ("system") performance curves provided a road map to the hardware's capability. This was accomplished by understanding how key variables such as inlet water temperature, water flow rate and fan speed impact the behavior of server inlet air temperature and cooling capacity. Facility control comes from optimizing what equipment is in place to support the MDC (i.e. dedicated chiller, campus chiller, pumps, etc...) within a data center. A significant goal of this project was to minimize the dependency MDC has on external cooling by optimizing the variables that affect facility power. For instance controlling heat removal rate and exiting water temperature affects chiller power; while water flow rate affects pump power. Knowledge of your system and facility's capabilities directly impacts power management. Thermal performance testing of the heat exchanger in the MDC provided insight into how increasing thermal efficiency at the heat exchanger produced an overall drop in facility power. Tests revealed that the optimized thermal control system achieved an infrastructure energy savings up to 33% with a PUE improvement from 1.35 to 1.23 for a 100KW IT heat load. The results show that characterizing and incorporating the behavior of the fans and heat exchanger into the thermal control system produced an improved Power Usage Efficiency (PUB) and a smarter control method.