A neural branch-and-price for truck scheduling in cross-docks

作     者：Rahimeh Neamatian Monemi Shahin Gelareh Nelson Maculan Wei-Kun Chen 

作者机构：Sharkey Predictim GlobeVilleneuve d’Ascq59650France Département R&TIUT de BéthuneUniversitéd’ArtoisBéthuneF-62000France Federal University of Rio de JaneiroCOPPE-PESCRio de JaneiroRJ 21941-972Brazil School of Mathematics and StatisticsBeijing Institute of TechnologyBeijing100081China 

出 版 物：《Science China Mathematics》 (中国科学（数学）（英文版）)

年 卷 期：2024年第67卷第6期

页      面：1341-1358页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 07[理学] 070105[理学-运筹学与控制论] 0701[理学-数学] 

主　　题：cross-docking MILP modeling Dantzig-Wolfe decomposition graph convolutional network 

摘      要：In this paper,we address the complex problem of dock-door assignment and truck scheduling within cross-docking *** is a problem that requires frequent resolution throughout the operational day,as disruptions often invalidate the optimal *** the problem s highly combinatorial nature,finding an optimal solution demands significant computational time and ***,the distribution of data across problem instances over a lengthy planning horizon remains consistently stable,with minimal concern regarding distribution *** factors collectively establish the problem as an ideal candidate for a learn-to-optimize solution *** propose a Dantzig-Wolfe reformulation,solving it via both a conventional branch-and-price approach and a neural branch-and-price approach,the latter of which employs imitation ***,we introduce some classes of valid inequalities to enhance and refine the pricing problem through a branch-and-cut *** computational experiments demonstrate that this methodology is not only feasible but also presents a viable alternative to the traditional branch-and-price algorithms typically utilized for such challenges.