direkt zum Inhalt springen

direkt zum Hauptnavigationsmenü

Sie sind hier

TU Berlin

Page Content

There is no English translation for this web page.



Total Energy Management for PROfessional data centers

Project details
Project term
November 2016 to October 2019
Funding code
BMWI 03ET1418A-H 
Project management
Ken Jesse Lindenberg

As an cooperation partner of the TEMPRO-Project (Total Energy Management for PROfessional data centers), the Hermann-Rietschel-Institut build a new server rack test rig together with the Dc-ce GmbH. Within the cooperation two objects of research are investigated:

1. An inhomogeneous air flow within the cold aisle due to a specific perforated tile geometry or a directed flow through a raised floor causes a fluctuating condition for the server. The server-internal cooling system is capable of supplying a sufficient amount of air for the removal of waste heat due to the operation of electrical components on the server main board. Under certain conditions like an upstream located underpressure increases the amount of energy needed for the operation of the server fans. The effect of an inhomogeneous air flow on the server-internal cooling system is investigated under the terms of efficiency and safety.

2. The permanent air transport inside data centers is a major factor for energy efficiency. Therefore, the reduction to an absolute necessary minimum is desired. State of the art-methods use differential pressure- and velocity sensors to control the air flow. Often, these methods require system knowledge and experience to achieve a certain level of efficiency within the system. As both, pressure and air velocity, do not allow any direct conclusion about the state of server under any conditions, an efficient operation of the facility management is limited by safety requirements and the lack of information of the facility manager about a server's state. The conservative separation between IT and facility management can be seen as a problem. Based on the server health monitoring, a new method is evaluated to control the amount of supplied air with a direct relation to a server's demand.





Zusatzinformationen / Extras

Quick Access:

Schnellnavigation zur Seite über Nummerneingabe