A column-generation approach for joint mobilization and evacuation planning

被引:15
作者
Pillac, Victor [1 ]
Cebrian, Manuel [1 ]
Van Hentenryck, Pascal [1 ,2 ]
机构
[1] NICTA Optimisat Res Grp, West Melbourne, Australia
[2] Australian Natl Univ, Canberra, ACT, Australia
基金
澳大利亚研究理事会;
关键词
Evacuation planning; Column generation; Behavioral operations research; OPTIMIZATION; ALGORITHMS; MODEL;
D O I
10.1007/s10601-015-9189-7
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Large-scale evacuations require authorities to decide and stage evacuation routes, mobilize resources, and issue evacuation orders under strict time constraints. These decisions must consider both the capacity of the road network and the evolution of the threat (e.g., a bushfire or a flood). This paper proposes, for the first time, an optimization model that jointly optimizes the mobilization and evacuation planning, taking into account the behavioral response of evacuees and the allocation of resources for communicating and implementing evacuation orders. From a technical standpoint, the model is solved by a column generation algorithm that jointly decides the evacuation route, evacuation time, and the resource allocation for each evacuated area in order to maximize the number of evacuees reaching safety and minimize the total duration of the evacuation.
引用
收藏
页码:285 / 303
页数:19
相关论文
共 28 条