摘要
基于市场需求是随机的,并且在进行市场销售前,就要确定每个阶段的生产数量的背景下,建立了具有规避风险的多阶段库存凸随机规划模型.该模型以最小化损失函数的期望值为目标函数,以规避风险为约束条件,以价值风险(VaR)和条件价值风险(CVaR)为风险度量;采用样本平均近似方法(SAA)求解该模型,并分析样本平均近似方法的收敛性;最后,给出数值结果.
We constructed a stochastic convex programming model for multi-period inventory with risk-averse con- straints where the market demand is random and the order quantities of each period need to be decided before market selling. This model minimizes the expected loss subject to risk-averse constraints expressed by Value at Risk （ VaR ） and Conditional Value at Risk （ CVaR ） as the risk measures. A sample average approximation （ SAA ） method was proposed to solve the model and convergence analysis of the solutions of SAA was presented. At last, a numerical example was given.
出处
《经济数学》
2012年第3期27-31,共5页
Journal of Quantitative Economics
关键词
多阶段库存模型
CVAR
样本平均近似
随机规划
凸规划
multi-period inventory model
conditional value at risk
sample average approximation
stochastic programming
convex programming
