基于仿真的优化及其在多级库存系统中的应用

Simulation-based Optimization and Its Application in Multi-echelon Inventory System

对于多制造商、多分销商和多零售商的三级网状随机性库存系统,难以用数学方法求解其最优的库存控制策略。基于离散事件系统仿真原理,建立了具有顾客到达时间服从泊松分布、随机顾客需求量、随机顾客购买行为、随机订货时间和生产容量有限制等特点的仿真模型。运用基于仿真的优化方法,将仿真方法与粒子群优化算法相结合来求解问题。通过仿真实例的比较分析,表明了基于仿真的优化方法的可行性和有效性及其在供应链管理中的适用性。

For a three-echelon network stochastic inventory system, it is difficult for the mathematical method to get the optimal inventory control policy. The simulation model, in which the customer arrival time followed a Possion process, all of the customer demand, the customer purchasing behavior and the lead time was stochastic and the production capacity was limited, was built on the basis of the discrete event system simulation theory. Then the simulation-based optimization method was used to solve the problem by combining the simulation model and the particle swarm optimization algorithm together. The simulation sample shows not only the feasibility and the effectiveness of the simulation-based optimization method but also its applicability in the supply chain management by comparisons and analyses.