摘要
为了有效提高电力物资细分科学性以及需求预测合理性,文章以物资需求特性为突破口,构建了基于NPCA-SOFM算法的电力物资细分模型.首先,为消除指标标准化造成的指标变异和信息丢失影响,采用非线性主成份分析法(NPCA)进行降维处理;然后,运用SOFM神经网络算法对降维后的主成份进行聚类分析;最后,通过算例分析验证文中方法的有效性,结果表明相较于PCA-SOFM和单独采用SOFM算法,NPCA-SOFM神经网络算法聚类性能更具优势,且降维效果更明显,可为电力物资集约化管理和企业运营决策提供参考意义.
In order to improve the scientificity of power material subdivision and the rationality of demand forecasting,this paper constructs the power material subdivision model based on NPCA-SOFM algorithm with the material demand characteristic as the breakthrough point. Firstly, the non-linear principal component analysis（NPCA） is used to reduce the dimensionality of the index and the loss of information caused by the standardization of indicators. Afterwards, we use the SOFM neural network algorithm to cluster the principal components after dimension reduction. Finally, the validity of the method is verified with an example. The results show that the clustering performance of NPCA-SOFM neural network algorithm is superior to PCA-SOFM and SOFM algorithm alone, and the dimension reduction effect is more obvious,which can provide reference value for intensive management of electric material and enterprise operation decision.
作者
牛庆松
蒋雷雷
刁柏青
NIU Qing-Song JIANG Lei-Lei DIAO Bai-Qing(State Grid Linyi Power Supply Company, Linyi 276003, China State Grid Shandong Electric Power Company, Jinan 250001, China)
出处
《计算机系统应用》
2017年第10期172-177,共6页
Computer Systems & Applications
基金
国家自然科学基金(71071089)
国家电网公司科技项目(520607160003)
关键词
物资细分
非线性主成份分析
自组织映射神经网络
智能电网
material subdivision
non-linear principal component analysis
self organization feature map
smart grid
