The Math Forum

Search All of the Math Forum:

Views expressed in these public forums are not endorsed by NCTM or The Math Forum.

Math Forum » Discussions » sci.math.* » sci.stat.math

Notice: We are no longer accepting new posts, but the forums will continue to be readable.

Topic: Mainframe Metrics MIPS Forecast
Replies: 0  

Advanced Search

Back to Topic List Back to Topic List  

Posts: 20
Registered: 10/18/06
Mainframe Metrics MIPS Forecast
Posted: Jan 9, 2008 11:42 AM
  Click to see the message monospaced in plain text Plain Text   Click to reply to this topic Reply

Given the following data sources and their availability:

-=-=-=- Quarterly -=-=-=-
Number of High MIP Users
Number of Med MIP Users
Number of Low MIP Users

Number of MIPS used by all HIGH MIP USERS
Number of MIPS used by all MED MIP USERS
Number of MIPS used by all LOW MIP USERS
(These two together give me the average MIPS used per user, per class)

-=-=-=- Monthly -=-=-=-
Number of Jobs Ran SHORT
Number of Jobs Ran MED
Number of Jobs Ran LONG
(user submitted and regularly scheduled jobs)

-=-=-=- Weekly -=-=-=-
Number of MIPS Used in Production
Number of MIPS Used in Test1
Number of MIPS Used in Test2
Number of MIPS Used in Test3
(What I am trying to forecast sans Production)

-=-=-=- Annually -=-=-=-
Test Schedule Dates

What is the best strategy to do a time series analysis when trying to
forecast the weekly MIPS to use? The only thing I can modifiy in a
planning effort is the Test Schedule and all the data is only for the
Test systems (so I am effectivly blind to the Production metrics
outside of it's MIP usage.)

I am guessing a regression analysis of sorts, comments and suggestions?

Point your RSS reader here for a feed of the latest messages in this topic.

[Privacy Policy] [Terms of Use]

© The Math Forum at NCTM 1994-2018. All Rights Reserved.