• DocumentCode
    1606024
  • Title

    BCID: An effective data center power mapping technology

  • Author

    Ferreira, A. ; El-Essawy, W. ; Rubio, J.C. ; Rajamani, K. ; Allen-Ware, M. ; Keller, T.

  • Author_Institution
    IBM Res.-Austin, Austin, TX, USA
  • fYear
    2012
  • Firstpage
    1
  • Lastpage
    10
  • Abstract
    The mapping of the power delivery network to the equipment in a data center is an essential step towards having intelligent and efficient control over data center power distribution. Visual identification of the power connectivity is error-prone and expensive while other methods require high-power signal injection and significant human labor or interruption in the power delivery, making them impractical. The use of power modulation in a server has been proposed but requires large power variations in order to do the mapping. In this paper we propose a new technique that reduces by over an order of magnitude the amount of signaling power necessary to less than 2.5W. Using this technique we show that a simple, USB device is able to generate that signal, allowing a non-intrusive method to identify the power connectivity for a system. The speed of detecting the connectivity reliably makes this a feasible solution for mapping entire data centers.
  • Keywords
    computer centres; power aware computing; power consumption; power control; system buses; BCID; USB device; data center equipment; data center power distribution; data center power mapping technology; data centers mapping; error-prone; high-power signal injection; power connectivity; power connectivity reliability; power delivery interruption; power delivery network; power variations; server power modulation; signaling power; visual identification; Detectors; Monitoring; Power distribution; Power supplies; Servers; Universal Serial Bus; branch circuit identification; data center power; power control; power distribution; power mapping; power monitoring; power signaling; stranded power;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Green Computing Conference (IGCC), 2012 International
  • Conference_Location
    San Jose, CA
  • Print_ISBN
    978-1-4673-2155-6
  • Electronic_ISBN
    978-1-4673-2153-2
  • Type

    conf

  • DOI
    10.1109/IGCC.2012.6322259
  • Filename
    6322259