深圳市供水智能组合预测分析
Intelligent Combined Forecasting Analysis for Shenzhen City Water Supply
DOI: 10.12677/JWRR.2021.102023, PDF,   
作者: 郭 瑜：珠江水利委员会珠江水利科学研究院，广东 广州；刘学智：广州珠科院工程勘察设计有限公司，广东 广州
关键词: 城市供水量；线性回归；非线性二元转折；模糊优选BP神经网络；智能预测；City Water Supply； Linear Regressive； Nonlinear Binary Transition； Fuzzy Optimization BP Neural Networks； Intelligent Combined Forecasting
摘要: 通过对深圳市的供水量分析，建立线性回归模型、非线性二元转折模型及模糊优选BP神经网络模型，分别对深圳市的中远期供水量进行预测，并将这三个模型的预测结果联立起来，作为模糊优选BP神经网络的输入，对深圳市供水量进行再次的网络训练。计算结果表明，智能组合预测模型的预测结果优于三个模型的单独预测结果。
Abstract: In this paper, water supply status of Shenzhen city is first analyzed; then linear regressive model, nonlinear binary transition model and fuzzy optimization BP neural networks model are employed to forecast medium and long-term water supply quantity, respectively. Finally, the three obtained forecasting results are combined and took as input of fuzzy optimization BP neural networks to train again, the output is just intelligent combined water supply forecasting results of Shenzhen city. Apparently, the accuracy of combined forecasting results is better than these single models.
文章引用：郭瑜, 刘学智. 深圳市供水智能组合预测分析[J]. 水资源研究, 2021, 10(2): 219-227. https://doi.org/10.12677/JWRR.2021.102023

参考文献

[1] 郑爽英. 城市供水量的预测模型研究[J]. 成都科技大学学报, 1995, 87(6): 19-26. ZHENG Shuangying. Research on forecasting model of urban water supply quantity. Journal of Chengdu University of Science and Technology, 1995, 87(6): 19-26. (in Chinese)
[2] ZHOU, S. L., MCMAHON, T. A. and WALTON, A. Forecasting operational demand for an urban water supply zone. Journal of Hydrology, 2002(259): 189-202. [Google Scholar] [CrossRef] 
[3] 张昌. 城市自来水供水量的灰色预测[J]. 武汉纺织工学院学报, 1999, 12(3): 8-10. ZHANG Chang. Grey forecasting of the suppliers of tap water in cities. Journal of Wuhan Textile University, 1999, 12(3): 8-10. (in Chinese)
[4] 唐纪, 王景. 组合预测方法评述[J]. 预测, 1999(2): 42-43. TANG Ji, WANG Jing. Review of combined prediction methods. Forecasting, 1999(2): 42-43. (in Chinese)
[5] ZHANG, G. P. Time series forecasting using a hybrid ARMA and neural network model. Neurocom Puting, 2003(50): 159-175. [Google Scholar] [CrossRef] 
[6] TANG, X. W., ZHOU, Z. F. and SHI, Y. The error bounds of combined forecasting. Mathematical and Computer Modelling, 2002, 36(9): 997-1005. [Google Scholar] [CrossRef] 
[7] 侯建中, 张福林. 用最优加权组合法预测深圳市人口发展趋势[J]. 数理医药学杂志, 1998, 11(3): 203-205. HOU Jianzhong, ZHANG Fulin. Using optimal weighted combination method to forecast the population development trend of Shenzhen City. Journal of Mathematical Medicine, 1998, 11(3): 203-205. (in Chinese)
[8] 深圳市统计局. 深圳统计年鉴[M]. 北京: 中国统计出版社, 2018. Shenzhen Municipal Bureau of Statistics. Shenzhen statistical yearbook. Beijing: China Statistics Press, 2018. (in Chinese)
[9] 陈守煜, 郭瑜, 王大刚. 智能预报模式与水文中长期智能预报方法[J]. 中国工程科学, 2006, 8(7): 30-35. CHEN Shouyu, GUO Yu, WANG Dagang. Intelligent forecasting mode and approach of mid and long term intelligent hydrological forecasting. Engineering Science, 2006, 8(7): 30-35. (in Chinese)
[10] GUO, Y., LAI, X.-Q. Use of partial supervised model of fuzzy clustering iteration to mid- and long-term hydrological forecasting. Fuzzy Information & Engineering and Operations Research & Management, Advances in Intelligent Systems and Computing, 2014, 211, 287-293.[CrossRef] 
[11] 赵磊, 李媛媛, 李金超, 等. 基于数据挖掘技术的电力日负荷优选组合预测[J]. 华北电力大学学报, 2005, 32(3): 19-22. ZHAO Lei, LI Yuanyuan, LI Jinchao, et al. Optimum combined forecasting of power daily load based sedon data mining technology. Journal of North China Electric Power University, 2005, 32(3): 19-22. (in Chinese)
[12] 郭瑜. 半监督迭代模糊聚类模型及其在中长期水文预报中的应用[J]. 东南大学学报(自然科学版), 2013, 43(s1): 59-62. GUO Yu. Partial supervision model of fuzzy clustering iteration and its application in mid- and long-term hydrological forecasting. Journal of Southeast University (Natural Science Edition), 2013, 43(S1): 59-62. (in Chinese)
[13] 厉红梅, 李适宇, 林高松, 等. 深圳市供水量的最优组合预测[J]. 数理统计与管理, 2005, 25(4): 18-22. LI Hongmei, LI Shiyu, LIN Gaosong, et al. Optimal combination forecasting of water supply quantity of Shenzhen City. Mathematical Statistics and Management, 2005, 25(4): 18-22. (in Chinese)