量子粒子群算法在易逝品多目标定价中的应用

Quantum-behaved Particle Swarm Optimization for multi-criterion optimal pricing model

对易逝品的多目标定价问题进行了研究。从利润最大化角度建立易逝品多目标最优定价模型。模型中涉及复杂的需求函数,常规函数极值法不易获得问题解析解,因此引入量子粒子群算法,结合惩罚函数对模型进行演化求解。根据给出的算例分析表明,利用量子粒子群算法,可以快速有效地得到不同订货量下的最优定价与折扣价组合。

Abstract： The problem of multi-criterion optimal pricing model for perishable commodities is mainly studied.According to the principle of profit maximization and based on a discrete demand function,the multi-criterion optimal pricing model for the perishable products is established.Since the model involves some different stochastic distributions of several variables,which is difficult for the normal numerical methods to solve,the Quantum-behaved Particle Swarm Optimization （QPSO） algorithm with a penalty function is introduced to settle it.The experiment results show that by using QPSO method,the optimal prices and discount prices for different inventory levels can be derived quickly and effectively.