Research On Emergency Resource Scheduling Based On Genetic Algorithm

The scheduling of resource usually refers to the rational allocation and effective use of resources.The emergency resource scheduling refers to the rational allocation and effective use of resources in the context of emergencies,the purpose of which is to reduce casualties and property losses caused by emergencies.In the event of an emergency,it is necessary to develop the scheduling scheme of emergency resource scheduling to ensure the effective arrival of resources and minimize the casualties.However,in actual situation,the consequences of different suddent events vary a lot.The emergency resource scheduling research is devoted to the discussion in a variety of unexpected events.How to specify the efficient resources scheduling scheme and make rational allocation and effective use of resources,has an important guiding role in practical application.According to the actual situations and different focus of the rescue,this thesis discusses the effective transportation of emergency resources in different emergency scenarios.The main works are summarized as follows:(1)Emergency resource scheduling problem with multiple disaster points,multi demand points and single transportation mode is studied.Unexpected accidents,such as earthquakes,snowstorms,and tsunamis occur frequently at present.Emergency management is an important subject in both management science and social science,and has attracted increasing attentions.In emergency resource scheduling,how to quickly and effectively allocate resources from the emergency logistics center to the disaster points become more and more important.In order to improve the efficiency of supplying organization and reduce casualties and economic losses,a decision support model whose target is to minimize the earliest rescuing time,the latest rescuing time and the number of supply activities simultaneously is first designed.Then,a multi-agent genetic algorithm using natural coding is proposed to solve the designed problem model.Computational experiments show that the proposed model is reasonable and the proposed algorithm is valid.At the same time,the scheduling found by the proposed algorithm can help decision-makers make a rational decision.(2)Emergency resource scheduling problem with various transportation modes is studied.There are many transportation modes can be selected when emergency is occurred.Multiple transportation modes are used to rapidly and efficiently deliver relief goods to emergency location according to the severity of disaster.There are some features analyzed in the multiple transportation modes.Multiple transportation modes mainly focus on minimizing the transport time and the cost in transportation.A multiple transportation modes considering the transport cost is designed in this paper,which aims to balance the transport time and the transport cost.Then an improved multi-agent genetic algorithm(MAGA-MTERS)is proposed to solve the model where natural number coding is used and penalty function is designed according to constraint conditions.Then,we compare the experimental results obtained by traditional genetic algorithm(GA)and MAGA-MTERS.The results show that,MAGA-MTERS has found better solutions than traditional GA.At the same time,the results obtained by MAGA-MTERS can help decision makers make reasonable decisions.Finally,a case study on the Great Sichuan Earthquake is investigated.The experimentals show that the designed model has certain practicality.(3)A memetic algorithm for the problem of the rescue in a mass casualty incident is proposed.During a mass casualty incident(MCI),which hospital should each victim be sent to depends on resource availabilities(both transport and care)and the survival probabilities of patients.Based on this,this paper established a mathematical model to maximize the probability of survival of the wounded,and put forward an improved evolutionary algorithm,memetic algorithm for optimizing the designed model.The experimental results show that the proposed algorithm has higher searching ability compared with the existing algorithms.Memetic algorithm can get better solutions than the existing algorithm in solving the designed model.