![]() The rest of the settings for the two search strategies follow the default configurations of the IBM ILOG CP Optimizer (IBM Documentation 2016). This experiment utilizes 50 random search points. The multipoint search strategy is typically known to be more diversified than depth-first, but it does not necessarily prove the optimality or the inexistence of a solution. On the other hand, the multipoint search strategy creates a set of solutions using the search points and combines the solutions in the set to produce better solutions. The number of branches generating is limited to 100,000 for the two search strategies. ![]() For computational efficiency, the termination criterion for the solution search process will be set to the maximum number of branches. The optimizer will not move to work on another section of the tree until the current one has been fully explored. The optimizer works on the subtree of one branch until it has found a solution or has proven that there is no solution in that subtree. The depth-first search strategy is a tree search algorithm such that each instantiation of a decision variable can be thought of as a branch in a search tree.
0 Comments
Leave a Reply. |
Details
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |