基于模糊数据挖掘的灌区水资源配置研究  

Water Resources Allocation of Irrigation District Based on Fuzzy Data Mining

作　　者：包志炎[1,2] 郑高安 王萱[3] 邱雁 魏杰 BAO Zhiyan;ZHENG Gaoan;WANG Xuan;QIU Yan;WEI Jie(Institute of Computer Application Technology,Zhejiang University of Water Resources and Electric Power,Hangzhou 310018,China;Water Resources Information Management Center of Zhejiang Province,Hangzhou 310009,China;Hangzhou Qiantang New Area Construction Investment Group Co.,Ltd.,Hangzhou 311228,China)

机构地区：[1]浙江水利水电学院计算机应用技术研究所,杭州310018 [2]浙江省水利信息管理中心,杭州310009 [3]杭州钱塘新区建设投资集团有限公司,杭州311228

出　　处：《农业机械学报》2020年第8期270-277,共8页Transactions of the Chinese Society for Agricultural Machinery

基　　金：国家自然科学基金青年基金项目(41601461);浙江省公益技术研究计划项目(LGF19E090011);教育部人文社会科学研究青年基金项目(18YJCZH002)。

摘　　要：在分析灌区大数据资源构成的基础上,构建了面向水资源配置的数据挖掘算法;汇聚某行政区域水资源、经济、人口、行业用水等数据,运用模糊层次聚类分析方法,对行政区域内行业间的配水案例进行分类及特征分析;采用固定步长穷举法对灌区配水相关参数进行动态赋权;运用模糊距离匹配相似灌区,通过构造加权影响因子和采用指数平滑法,对基于实例推理的灌区进行需水量预测。将建立的方法应用于2018年浙江省11个市行政区行业间配水特征分析和中型灌区需水量预测,结果表明:浙江省不同区域行业间配水被划分为4类,呈现出不同行业间的配水特征,灌区需水量预测相对误差均不大于9.39%,说明该方法有效,可为制定合理的区域行业间配水方案、估算灌区需水量提供决策支持。Aiming to realize the reasonable allocation of water resources in irrigation district,the composition of big data resources of irrigation district was analyzed,and the corresponding data mining algorithms were proposed.The cosine correlation coefficient was introduced,and the fuzzy hierarchical cluster analysis was used to realize the case classification and characteristic analysis of department water distribution based on the data of regional water resources,economy,population and industrial water consumption.A variable step length exhaustive method was used to calculate the dynamic weight of relevant parameters of water distribution in irrigation district.Fuzzy distance was used to match the most similar irrigation district.Weighted influence factors and exponential smoothing method were used to estimate the water demand of irrigation area based on case-based reasoning.The proposed methodology demonstrated the effectiveness in the analysis of department water distribution characteristics and water demand prediction of medium-sized irrigation districts in 11 cities and administrative regions of Zhejiang Province in 2018.The results showed that water distribution among different regions in Zhejiang Province was divided into four categories,showing different characteristics of water distribution among different departments;the relative error of water demand prediction in irrigation area was not more than 9.39%.The established theoretical method could provide decision support for making reasonable regional inter industry water distribution scheme and estimating irrigation water requirement.

关 键 词：水资源配置 灌区 模糊数据挖掘 相关性分析 实例推理 

分 类 号：TV213.9[水利工程—水文学及水资源] TP391.1[自动化与计算机技术—计算机应用技术]