电网建设项目物资需求预测研究  

Study on Material Demand Forecasting in Power Grid Construction Projects

作　　者：宋斌[1] 卜涛[2] 张洪青[2] 

机构地区：[1]河南省电力公司物资部,河南郑州450052 [2]华北电力大学经济与管理学院,北京102206

出　　处：《物流技术》2013年第3期319-321,336,共4页Logistics Technology

基　　金：国家电网公司科技资助项目(豫电WZBKJ[2011]342号)

摘　　要：为满足电网建设项目物资需求管理的发展要求,在现有企业资源计划(ERP)系统完成上线并能够提供初步数据支持的基础上,针对如何依据电网建设项目里程碑计划中的基本工程建设指标,合理预测物资需求的问题,借助支持向量机模型(SVM)和人工鱼群算法(AFSA),构建了电网建设项目物资需求预测模型。在支持向量回归机的基础上,融合添加混沌搜索后的改进人工鱼群算法,优化了向量机核函数选取和参数设置,通过省级电网建设项目物资需求历史数据测试,模型预测结果满足实际使用要求,能够有效解决电网建设项目物资需求预测的问题。In this paper, in order to satisfy the requirement of material demand management in power grid construction projects and on the basis of the successful launching of the ERP system which could provide preliminary data support, and in light of the basic construction index and reasonable material demand forecasting in the power grid construction milestone project, we established the material demand forecasting model for power grid construction projects using the methods of support-vector machine and artificial fish swarm algorithm. More specifically, we improved the artificial fish swarm algorithm by adding in the chaotic search function, integrated it on the basis of the support vector machine, optimized the function selection and parameter setting of the kernel of the vector machine and tested it with historical data of material demand in province-level power grid construction projects.

关 键 词：电网建设 物资需求预测 支持向量机 人工鱼群算法 混沌搜索 

分 类 号：F252.21[经济管理—国民经济]