城市突发事件中基于事故演变的救援需求决策模型及其优化求解

针对城市突发事件中待救点对应急救援物资的需求状态随着事故的演变而发生变化的情况,将待救点对应急救援物质的需求设计成马尔可夫决策过程,并提出一种动态的物资调配策略,构建救援物资需求决策模型,然后通过花朵授粉算法进行优化求解。某市突发地震应急物资调配实例证明,本文方法能够给出合理的救援需求满足策略,使得待救点对物资的需求更低,需求变化更加平稳。花朵授粉算法对模型求解的效果相比粒子群算法和萤火虫算法有更快的收敛速度和更优的求解结果。

Decision Model of Rescue Demand in Urban Emergency Based on Accident Evolution and Its Optimization Solution

In view of the demand for emergency relief materials in urban emergencies change along with the evolution of the accident, the demand for emergency rescue material is designed as a Markov decision process, and a dynamic material allocation strategy is proposed to build a decision model for the demand for relief materials, and then the flower pollination algorithm is used for optimizing the model. A case of emergency material allocation in a city proves that the proposed method can give a reasonable rescue demand strategy, which makes the demand of the rescue point lower and the demand change more stable. Compared with particle swarm optimization and firefly algorithm, flower pollination algorithm has faster convergence speed and better solution results.