Developing Strong and Hybrid Formulation for the Single Stage Single Period Multi Commodity Warehouse Location Problem: Theoretical Framework and Empirical Investigation  

作　　者：R. R. K. Sharma Parag Tyagi Vimal Kumar Ajay Jha 

机构地区：[1]Department of Industrial & Management Engineering, IIT, Kanpur, India

出　　处：《American Journal of Operations Research》2015年第3期112-128,共17页美国运筹学期刊（英文）

摘　　要：We note that the Single Stage Single Period Multi Commodity Warehouse Location Problem (SSSPMCWLP) has been first attempted by Geoffrion and Graves [1], and that they use the weak formulation (in context of contribution of this paper). We give for the first time “strong” formulation of SSSPMCWLP. We notice advantages of strong formulation over weak formulation in terms of better bounds for yielding efficient Branch and Bound solutions. However, the computation time of “strong” formulation was discovered to be higher than that of the “weak” formulation, which was a major drawback in solving large size problems. To overcome this, we develop the hybrid strong formulation by adding only a few most promising demand and supply side strong constraints to the weak formulation of SSSPMCWLP. So, the formulations developed were put to test on various large size problems. Hybrid formulation is able to give better bound than the weak and takes much less CPU time than the strong formulation. So, a kind of trade off is achieved allowing efficiently solving large sized SSSPMCWLP in real times using hybrid formulation.We note that the Single Stage Single Period Multi Commodity Warehouse Location Problem (SSSPMCWLP) has been first attempted by Geoffrion and Graves [1], and that they use the weak formulation (in context of contribution of this paper). We give for the first time “strong” formulation of SSSPMCWLP. We notice advantages of strong formulation over weak formulation in terms of better bounds for yielding efficient Branch and Bound solutions. However, the computation time of “strong” formulation was discovered to be higher than that of the “weak” formulation, which was a major drawback in solving large size problems. To overcome this, we develop the hybrid strong formulation by adding only a few most promising demand and supply side strong constraints to the weak formulation of SSSPMCWLP. So, the formulations developed were put to test on various large size problems. Hybrid formulation is able to give better bound than the weak and takes much less CPU time than the strong formulation. So, a kind of trade off is achieved allowing efficiently solving large sized SSSPMCWLP in real times using hybrid formulation.

关 键 词：SSUWLP SSSPMCWLP STRONG and WEAK Constraints HYBRID FORMULATION RMIP 

分 类 号：O1[理学—数学]