摘要
采用可加速收敛的压缩遗传算法(ACGA)来解决实时供应链中的网上采购优化问题,供应商根据零售商的订单需求,在最短的时间内综合考虑利润、库存和交货时间等因素进行优化,进而为决策提供依据.在ACGA中,用压缩遗传算法(CGA)运行少量代数得到的概率值组成一个观测样本,借助统计学中的最小二乘法,估算几万代以后的概率值,进而组成新的概率矩阵,并根据该矩阵产生新的个体.文中结合实时供应链中的分销优化问题进行了仿真,结果表明,ACGA是适应实时场合的高效遗传算法.
Based on ACGA (accelerated compact genetic algorithm), the real time optimization problems in real time supply chain were studied to maximize the revenue, cut down the inventory and delivery on time. In the ACGA, with the probability values got by CGA (compact genetic algorithm) in the beginning generations, the probability values in thousands of generations are estimated by the least square method. Thus the new probability matrix is formed and from the probability matrix the new offspring is generated. The simulations show that this algorithm is of high efficiency in real time case.
出处
《上海交通大学学报》
EI
CAS
CSCD
北大核心
2005年第3期357-360,共4页
Journal of Shanghai Jiaotong University
基金
国家自然科学基金资助项目(70418013)
关键词
实时供应链
压缩遗传算法
最小二乘法
real time supply chain
compact genetic algorithm
least square method
