Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
476210 | Computers & Operations Research | 2006 | 18 Pages |
Abstract
We describe a simple adaptive memory search method for the 0/1 Multidemand Multidimensional Knapsack Problem (0/1 MDMKP). The search balances the level of infeasibility against the quality of the solution, and uses a simple dynamic tabu search mechanism. A weighting scheme to balance out the differences in the tightness of the constraints is also implemented. Computational results on a portfolio of test problems taken from the literature are reported, showing very favorable results, both in terms of solution quality and the ability of the search to find feasible solutions.
Related Topics
Physical Sciences and Engineering
Computer Science
Computer Science (General)
Authors
Halvard Arntzen, Lars M. Hvattum, Arne Løkketangen,