But later in the log shows: “Cbc0012I Integer solution of 8384771 found by RINS after 6986 iterations and 1239 nodes (31.55 seconds)”, then the next line is “Cbc0011I Exiting as integer gap of 1782 less than 1e-10 or 0.1%”. It also reflected the LP solution properly: “Continuous objective value is 3.61324e+06 –. I checked the “Last Solve Log” file, and saw that the tolerance is being set by the model properly: “ratioGap was changed from 0 to 0.001”. It doesn’t seem to be respective the 0.1% tolerance setting? I’ve played with the tolerance settings with similar results. However with OpenSolver set to 0.1% tolerance, the model quickly returns a solution of 8,384,771, or 132% larger than the relaxed solution. ![]() ![]() For example, when I solve the continuous/relaxed model, the objective value being minimized is 3,613,245 (relatively large due to my penalty costs being added). The model isn’t behaving as I expected with regards to the “Branch and Bound Tolerance (%)” integer setting, as the returned values do not seem to be within the % tolerance of the continuous solution. ![]() The decision variables for ‘production quantity’ are constrained to integers (discrete production process). I’ve used OpenSolver to create a production scheduling/location MIP model (determine the production location for each piece of demand to minimize lead time to customer, subject to capacity constraints, with penalty costs added for exceeding capacity). Thanks for all of your efforts creating such a useful resource! I have a question on integer tolerances.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |