Novel operating theatre scheduling method based on estimation of distribution algorithm  

基于分布估计的新型手术室调度算法（英文）

作　　者：周炳海[1] 殷萌[1] 

机构地区：[1]同济大学机械与能源工程学院,上海201804

出　　处：《Journal of Southeast University(English Edition)》2016年第1期112-118,共7页东南大学学报（英文版）

基　　金：The National Natural Science Foundation of China(No.61273035,71471135)

摘　　要：In order to improve the efficiency of operating rooms,reduce the costs for hospitals and improve the level of service qualities, a scheduling method was developed based on an estimation of distribution algorithm（ EDA）. First, a scheduling problem domain is described. Based on assignment constraints and resource capacity constraints, the mathematical programming models are set up with an objective function to minimize the system makespan. On the basis of the descriptions mentioned above, a solution policy of generating feasible scheduling solutions is established. Combined with the specific constraints of operating theatres, the EDA-based algorithm is put forward to solve scheduling problems. Finally, simulation experiments are designed to evaluate the scheduling method. The orthogonal table is chosen to determine the parameters in the proposed method. Then the genetic algorithm and the particle swarm optimization algorithm are chosen for comparison with the EDA-based algorithm, and the results indicate that the proposed method can decrease the makespan of the surgical system regardless of the size of operations. Moreover, the computation time of the EDA-based algorithm is only approximately 5 s when solving the large scale problems, which means that the proposed algorithm is suitable for carrying out an on-line scheduling optimization of the patients.为了提高手术室的利用率、降低医院的成本、提高服务质量的水平,提出了一种基于分布估计的调度算法(EDA).首先,对问题域进行描述,以最大完成时间最小为优化目标,在考虑手术分配约束和资源能力约束的基础上,建立数学规划模型;在此基础上,建立可行调度解策略,结合手术室特有的约束条件,提出基于分布估计的手术室调度算法;最后,设计仿真实验,采用正交试验确定算法中的参数后,与遗传算法和粒子群算法进行对比,不同规模的实验结果表明该算法能够减少手术系统总完成时间,且在大规模情况下运行时间仅为5 s,说明该算法适应大规模实际情况下的手术室调度.

关 键 词：operating theatre scheduling estimation of distribution algorithm MAKESPAN 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]