Prepositioning emergency earthquake response supplies: A new multi-objective particle swarm optimization algorithm

•A multi-objective stochastic programming model is developed for pre-positioning and distributing emergency supply.•A new multi-objective particle swarm optimization algorithm is proposed to generate Pareto-fronts.•A new adaptive strategy based on Pareto-dominance concept is applied to set the inert...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Applied mathematical modelling Ročník 40; číslo 9-10; s. 5183 - 5199
Hlavní autoři: Mohammadi, R., Ghomi, S.M.T. Fatemi, Jolai, F.
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier Inc 01.05.2016
Témata:
Algorithms
Decisions
Earthquake response
Emergency response
Facility location
Mathematical models
Multi-objective particle swarm optimization
Prepositioning emergency supplies
Searching
Seismic response
Stochastic programming
Strategy
Swarm intelligence
Facility location
Multi-objective particle swarm optimization
Prepositioning emergency supplies
Earthquake response
Stochastic programming
ISSN:0307-904X
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:•A multi-objective stochastic programming model is developed for pre-positioning and distributing emergency supply.•A new multi-objective particle swarm optimization algorithm is proposed to generate Pareto-fronts.•A new adaptive strategy based on Pareto-dominance concept is applied to set the inertia weight.•The effects of the equity measure on the facility location and distribution decisions are analysed. The development of an efficient emergency response plan to provide critical daily supplies to affected people facilitates efficient relief operations. In this study, we propose a multi-objective stochastic programming model for developing an earthquake response plan, which integrates pre-and post-disaster decisions. This three-objective model attempts to maximize the total expected demand coverage, to minimize the total expected cost, and to minimize the difference in the satisfaction rates between nodes. We develop a new multi-objective particle swarm optimization (MOPSO) algorithm to solve this model. Genotype-phenotype-based binary particle swarm optimization (PSO) and continuous PSO are designed to deal with the binary location and other continuous decision variables, respectively. A new strategy is employed to select two types of guides in order to enhance the search ability. Furthermore, a new adaptive inertia weight strategy and two mutation operators are used to ensure that the diversity is sufficient and to regulate the exploration and exploitation capacities, respectively. We present an illustrative real-world case study and some randomly generated instances for computational applications. The results obtained by the proposed MOPSO algorithm were compared with those obtained using a modified time-variant MOPSO, the non-dominated sorting genetic algorithm, strength Pareto evolutionary algorithm, and the exact solution method where possible.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0307-904X
DOI:10.1016/j.apm.2015.10.022