Are you able to share the data?
One way to speed things up might be to exclude customer-facility pairs that are too far apart. The most efficient way to do this is to use sparse modeling to omit the corresponding variables, as illustrated in the Sparse Modeling example in the documentation.
here is the data. thank you
let me look at sparse modeling as well.
Hi Rob.
Were u able to see what was the problem in the data? I noticed that the MAXTIME of 600 seconds does not seem to be respected as it tries to solve more than that and would never finish. Not sure if something inherently problematic with dataset or sthg.
I am going to try to do sparse modeling today. But if you can let me know about anything to speed the solve it would be great.
I don't see anything wrong with the data. Can you please show the SOLVE statement you used, with the MAXTIME= option?
Rob
Here you go.
solve with nlp / ms feastol=1E-01 maxtime=600 timetype=real;
The MAXTIME=600 option that you specified limits each local solver call to 600 seconds. If you want to limit the overall multistart time, use the MAXTIME= suboption inside the MS= option. As mentioned in the NLP solver documentation:
"Because the local solver might be called many times, the maximum time that is specified for multistart is recommended to be greater than the maximum time specified for the local solver."
For example:
solve with nlp / ms=(maxtime=600) feastol=1E-01 maxtime=120 timetype=real;
oh ok. got it. thanks . it worked fine now
Are you ready for the spotlight? We're accepting content ideas for SAS Innovate 2025 to be held May 6-9 in Orlando, FL. The call is open until September 16. Read more here about why you should contribute and what is in it for you!
Learn how to run multiple linear regression models with and without interactions, presented by SAS user Alex Chaplin.
Find more tutorials on the SAS Users YouTube channel.