A Compact Cooling-System Model for Transient Data Center Simulations

Energy, exergy and computing efficiency based data center workload and cooling management

“…where 𝑋 𝑠 is the thermal mass of a 2U server (available from the literature) [40], 𝑇 𝑖,𝑗 𝑒 and 𝑇 𝑖,𝑗 𝑓 are the server exhaust and inlet air temperatures, 𝜌 𝑎 the density of air, 𝐶 𝑝,𝑎 the specific heat capacity of air, ∆𝑡 the time step, and 𝑃 ̇𝑖,𝑗 𝑧 the power consumption of the server zone with horizontal rack index i, and vertical zone index j. We note that a server's power consumption depends on its utilization, which is one of our decision variables for which the appropriate function is provided in Eq.…”

Towards a Holistic Controller

“…Thermal model for the datacenter. VanGilder et al [15] proposed a compact model for the thermal dynamics in the datacenter with a chilled-water cooling system. It included discretized numerical models for heat sources (servers) and cooling by assuming a simple counterflow heat exchanger, which alternatively can be replaced by a quasi-steady-state model for applications when accuracy can be traded for model simplicity.…”

Physical and Data-Driven Models for Edge Data Center Cooling System

“…CFD models target the air flow and heat transfer in data centers, but usually only for the air interactions in the server room. Physical models make broad simplifications in describing the dynamics of the cooling system, such as with the chiller and dry cooler, in for example [3,21], or with the chilled-water heat exchanger [18], compact models that additionally include the thermal mass for room, plenum, walls, floor, ceiling and a water storage tank [9], or use networks of thermal nodes to model the internal dynamics of servers [14]. Moreover, neural networks have been used to directly predict the effectiveness of DC cooling systems [6,16], and more rarely the system thermal responses [1].…”