Prediction model based on influencing factors of water consumption
Wang Pu1,2, Wang Yizhi1,2, Zhang Jin3, Wang Ying1,2
1.Key Laboratory of Three Gorges Reservoir Region′s Eco-Environment, Ministry of Education, Chongqing University, Chongqing 400045, China; 2.National Centre for International Research of Low-carbon and Green Buildings, Chongqing University, Chongqing 400045, China; 3. Institute of Urban Water Management, Technische Universität Dresden, Dresden 01062, Germany
Abstract：Urban water consumption prediction is full of complexity due to the different influencing factors and the uncertainty of the statistics database. A comprehensive water consumption prediction model was developed to slove this problem. Multiple approaches were integrated into this model. Specifically, the significant influencing factors of water consumption were selected by principal component analysis: then, the selected influencing factors were further classified by gray cluster analysis and gray relational analysis. Based on the evaluation of the significant influencing factors, a multilayer perceptron network was established by SPSS software, GRNN and BP neural networks were established by Matlab software. IOWA operator was also applied to the water prediction model. Consequently, a MLP-GRNN-BP comprehensive water demand consumption prediction model was developed based on the IOWA operator. The evaluation system,using the sum of squares error(SSE), the mean square error(MSE), mean absolute error(MAE), mean absolute percentage error(MAPE), mean square percentage error(MSPE)and Theil coefficient(μ), was established to evaluate the performance of the predictive models. The proposed models were applied to the city of Chongqing for the municipal water consumption prediction to verify the feasibility of these methods. The results show that the number of significant influencing factors for water consumption in Chongqing city can be reduced from 31 to 12, and the 12 significant influencing factors can be further classified into four clusters, and four kinds of the influencing factors can be analyzed and ranked respectively. MAPE, MSPE and Theil coefficient values are within 5%, when the BP, MLP, GRNN and MLP-GRNN-BP model are used in the case study, indication a good prediction.
王圃,, 王以知,, 张晋, 王颖,. 基于用水量驱动因子的水量预测模型[J]. 排灌机械工程学报, 2014, 32(12): 1051-1056.
Wang Pu,, Wang Yizhi,, Zhang Jin, Wang Ying,. Prediction model based on influencing factors of water consumption. Journal of Drainage and Irrigation Machinery Engin, 2014, 32(12): 1051-1056.
[1]崔慧珊,邓逸群. 居民用水量的影响因素研究评述[J]. 水资源保护,2009(1):83-85. Cui Huishan,Deng Yiqun. Factors influencing residential water consumption[J]. Water Resource Protection, 2009(1):83-85.(in Chinese)[2]尹学康,韩德宏.城市需水量预测[M].北京:中国建筑工业出版社,2005.[3]冯琨,张永丽. 基于因子分析的BP神经网络对成都市需水量预测研究[J]. 水资源研究, 2011, 32(2): 8-11. Feng Kun, Zhang Yongli. Chengdu water demand prediction factor analysis based on BP neural network [J]. Journal of Water Resources Research, 2011, 32(2): 8-11.(in Chinese)[4]晁增福,邢小宁. 基于BP神经网络模型的阿克苏市城市需水量预测[J]. 能源与环境, 2011(4): 24-25. Chao Zengfu, Xing Xiaoning. Aksu city water demand prediction based on BP neural network model[J]. Energy and Environment,2011(4):24-25.(in Chinese)[5]严岩,王辰星,张亚君,等. 基于灰色模型的农村生活用水影响因子分析[J]. 水资源与水工程学报,2013,24(5):50-53,58. Yan Yan, Wang Chenxing, Zhang Yajun, et al. Analysis of impact factor of domestic water in rural area based on gray model[J]. Journal of Water Resources and Water Engineering, 2013,24(5):50-53,58.(in Chinese)[6]龙训建,钱鞠,梁川. 基于主成分分析的BP神经网络及其在需水预测中的应用[J]. 成都理工大学学报: 自然科学版, 2010, 37(2): 206-210. Long Xunjian, Qian Ju, Liang Chuan. Water demand forecast model of BP networks based on principle component analysis[J]. Journal of Chengdu University of Technology:Science & Technology Edition,2010,37(2): 206-210.(in Chinese)[7]陈友华.基于IOWA算子的组合预测方法[J].预测,2003,22(6):61-65. Chen Youhua. A kind of combination forecasting method based on induced ordered weighted averaging(IOWA)operators[J]. Forecasting,2003,22(6):61-65.(in Chinese)[8]Schefter J E, David E L. Estimating residential water demand under multi-part tariffs using aggregate data[J]. Land Economics, 1985,61(3): 272-280.[9]Martinez Espineira R. Residential water demand in the northwest of Spain[J]. Environmental and Resource Economics, 2002, 21(2): 161-187.[10]Nieswiadomy M L. Estimating urban residential water demand: Effects of price structure, conservation, and education[J]. Water Resources Research, 1992, 28(3): 609-615.[11]Renwick M E, Green R D. Do residential water demand side management policies measure up & an analysis of eight California water agencies[J]. Journal of Environmental Economics and Management, 2000, 40(1): 37-55.[12]Gato S, Jayasuriya N, Roberts P. Temperature and rainfall thresholds for base use urban water demand modelling[J]. Journal of Hydrology, 2007, 337(3): 364-376.[13]Firat M, Yurdusev M A, Turan M E. Evaluation of artificial neural network techniques for municipal water consumption modeling[J]. Water Resources Management, 2009, 23(4): 617-632.[14]Day D, Howe C. Forecasting peak demand:What do we need to know [J]. Water Supply, 2003, 3(3): 177-184.[15]Panagopoulos G P. Assessing the impacts of socio-economic and hydrological factors on urban water demand: A multivariate statistical approach[J]. Journal of Hydrology, 2014,518:42-48.[16]Peng Z, Lei Z. Quantitative study on the urban fresh water consumption since Chinese rapid urbanization[J]. Ecological Economy, 2009(5):195-204.[17]李萍,魏晓妹. 变化环境下农业需水量演变趋势及驱动力[J]. 排灌机械工程学报, 2013, 31(9): 822-828. Li Ping,Wei Xiaomei. Evolutionary tendency of agriculture water requirement and its driving force under changing environment[J]. Journal of Drainage and Irrigation Machinery Engineering, 2013, 31(9): 822-828.(in Chinese)[18]张琴, 汪雄海, 朱庆建. 基于联合时序的混沌时用水量短期预测调度[J]. 排灌机械工程学报,2011,29(4):352-358. Zhang Qin,Wang Xionghai,Zhu Qingjian. Short-term prediction of chaotic hourly water consumption based on united time series[J].Journal of Drainage and Irrigation Machinery Engineering,2011,29(4):352-358.(in Chinese)[19]刘思峰,党耀国,方志耕,等.灰色系统理论及应用[M]. 北京:科学出版社,2010.[20]王亚丽,冯利华,赵丹丹,等. 金华市区居民用水量影响因素的关联分析[J]. 水资源与水工程学报, 2011, 22(3): 51-54. Wang Yali, Feng Lihua, Zhao Dandan,et al. Relational analysis of influence factors on residential water consumption in Jinhua city[J]. Journal of Water Resources and Water Engineering, 2011, 22(3): 51-54.(in Chinese)[21]成晋松,吕惠进,刘玲. 太原市用水量影响因素的灰色关联分析[J]. 水资源与水工程学报, 2012,23(2):109-115. Cheng Jinsong, Lü Huijin,Liu Ling. Grey relational analysis of influence factors on water consumption in Taiyuan city[J]. Journal of Water Resources and Water Engineering,2012,23(2):109-115.(in Chinese)
