Google Ads

Enter your email address:

Delivered by FeedBurner

This form does not yet contain any fields.
    « Thinking about how Intel is ready to change the Data Center | Main | Dave's Roasted Chicken using a Dashboard Approach »

    If I was going to give a University lecture on Data Centers I would …

    I have a friend who is Dean of Business and Economics school and he asked if I would participate in a graduate class by giving a lecture on data centers.  I said sure I'll do it.  What would I present?  

    Here are some ideas I have that are good to write and see how they sit in my mind.

    1)  I would explain how data centers align with the business models of companies and go through specifics of how data centers look at Google, Amazon, Facebook, Microsoft, Apple.

    2)  How many servers people have is the wrong way to look at data centers.  What is more useful is knowing the # of processor cores are in the data center.

    3)  Operations of data center is a good topic touch upon that relates to the business models.  Maybe this could be discussing the economics of data centers.

    If I stuck to Business Models, Technology, and Operation Economics that would seem like three categories to cover that would be good.

    I'll see what the Dean thinks of presenting data centers in this way.

    PrintView Printer Friendly Version

    EmailEmail Article to Friend

    Reader Comments (2)

    Hi, Dave. I also think adding a discussion about treating data enters as part of a cloud infrastructure supply chain would be of interest. It leads to different approaches to design, delivery and management. This could be a nice comparative discussion vs the tech/site operations approach to data centers.

    July 19, 2013 | Unregistered CommenterAmaya Souarez

    The Google, Amazon, Facebook, and similar data centers don't really represent the data centers that most biz school grads are likely to see. Their future company data centers are back level, in high rent areas, with high cost electric power, and incompletely or poorly virtualized. Their disaster recovery is poor or non existent and likely the last successful test was faked. You get the picture.

    I absolutely agree that what you're proposing to discuss reflects best practice in the industry, but first the industry has to work itself out of legacy doom.

    July 22, 2013 | Unregistered CommenterRich Hintz

    PostPost a New Comment

    Enter your information below to add a new comment.

    My response is on my own website »
    Author Email (optional):
    Author URL (optional):
    Some HTML allowed: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <code> <em> <i> <strike> <strong>