From chip to cooling tower data center modeling: Part I Influence of server inlet temperature and temperature rise across cabinet

Abstract

To achieve reductions in the power consumption of the data center cooling infrastructure, the current strategy in data center design is to increase the inlet temperature to the rack, while the current strategy for energy-efficient system thermal design is to allow increased temperature rise across the rack. Either strategy, or a combination of both, intuitively provides enhancements in the coefficient of performance (COP) of the data center in terms of computing energy usage relative to cooling energy consumption. However, this strategy is currently more of an empirically based approach from practical experience, rather than a result of a good understanding of how the impact of varying temperatures and flow rates at rack level influences each component in the chain from the chip level to the cooling tower. The aim of this paper is to provide a model to represent the physics of this strategy by developing a modeling tool that represents the heat flow from the rack level to the cooling tower for an air cooled data center with chillers. This model presents the performance of a complete data center cooling system infrastructure. After detailing the model, two parametric studies are presented that illustrate the influence of increasing rack inlet air temperature, and temperature rise across the rack, on different components in the data center cooling architecture. By considering the total data center, and each component's influence on the greater infrastructure, it is possible to identify the components that contribute most to the resulting inefficiencies in the heat flow from chip to cooling tower and thereby identify the components in need of possible redesign. For the data center model considered here it is shown that the strategy of increasing temperature rise across the rack may be a better strategy than increasing inlet temperature to the rack. Part II of this work expands on this paper with further parametric studies to evaluate the robustness of this data center cooling strategy, with conditions for optimal strategy deployment.

Modeling and Identification of Data Center HVAC System with Super-Multipoint Temperature Sensing System

“…It can be seen that the locations of the cold and hot regions differ according to the fan mode. This raises the possibility that appropriate fan control could avoid having to lower the set point, thereby avoiding unnecessary power consumption [5]. Finally, we regard the heat generated by each server as a disturbance.…”

“…4 If the reduction scheme is applied to all 723 sensing data instead of only roughly 70 in each loop, each value of λ j − λ j−1 in Step 2 is too small for the division. 5 Except for the selection of the similarity measure or entropy between data, there is little difference between the PSD-based approach in Step 1 and the mutual information-based approach presented by [22].…”

Power-Thermal Modeling and Control of Energy-Efficient Servers and Datacenters

“…In [42], A. Qouneh et al provide a comparative and quantitative analysis of cooling power as varying processor utilization and adjusting the server room temperature accordingly. For further analysis of the power consumption of the cooling facility, some models have been presented in [40,41] which model the power consumption based on thermo-fluid principles. However, based on our analysis of real datacenter setups of our industrial partners in this work, we have observed that an alternative procedure can be used, where PUE mainly depends on the temperature set-point of server room (T room ), outside temperature (T out ), and total power consumed by servers (P cl ).…”

Experimental and numerical analysis for potential heat reuse in liquid cooled data centres

“…However, Moore's 46 law [6], which states that transistor density doubles every 2 years, continues to be true 47 nowadays. This means that, due to the exponential increase in IT energy density, in few years 48 the energy density of the IT equipment will reach values up to 50 kW/rack and therefore the 49 solely use of air cooling system will be insufficient to evacuate all the heat generated by the 50 servers [7]. To overcome this problem the data centre industry is already investigating and 51 implementing the use of liquid cooling systems due to the higher heat removal capacity and the 52 ability to cool specific system components to a greater degree [8].…”

“…Generally the servers and the cooling system are modelled 88 with the heat transfer equation, considering convection and conduction mechanisms. Breen et al 89 [7] performed a thermal equilibrium model of an air cooled rack to obtain flow rate, pressure 90 drop and heat transfer coefficients that were used to characterize the system. Douchet et al [8] According to the water cooling piping configuration, the system can be defined to be in parallel 132 or in series configuration.…”