Abstract

The ability to predict water consumption benefits in terms of future temporal water patterns, operational reasons in distribution and decision making related to the development of water supply systems. Although, there have been numerous research work on time series forecasting, the methodology may still need further development in the context of non-linear modeling and analysis. There is many unpredictability that results in complex temporal dependence with traditional time series approaches. But now, artificial neural networks are available to help resolve these issues can improve model prediction. Therefore, this paper presents an experimental study to perform univariate water consumption for time series prediction processes using Deep Learning in Neural Network (DLNN). DLNN has abilities to learn the algorithm from previous data. It also able to process an explosion of data with a nonlinear approach, which the univariate water consumption time series prediction problem was modelled into artificial neural networks. The vast majority of learning algorithms along with DLNN are used in this study called Multilayer Perceptron (DLNN-MLP), Convolutional Neural Networks (DLNN-CNN) and Long Short-Term Memory (DLNN-LSTM) for the model prediction to generate prediction with the lowest error. Dataset from the residential water usage in SIBU Division was chosen for the experiments of this study. The performance of the DLNNs’ models is measured using RMSE and state-of-the-art algorithms. The value of RMSE for a problem relates to the calculation of the lowest error. Based on the experiments result indicates that the DLNN-LSTM (RMSE:0.051) can make decent predictions for water consumption time series despite being inferior to SARIMA (RMSE:0.183). Hence, this finding implies that DLNN-LSTM can be implemented on a univariate water consumption time series prediction problem given that the problem is modelled as supervised learning.

Keyword

Water consumption, Deep neural network, Deep learning, Model prediction.

Cite this article

Said NM, Zin ZM, Ismail MN, Bakar TA

Refference

[1][1]Cutore P, Campisano A, Kapelan Z, Modica C, Savic D. Probabilistic prediction of urban water consumption using the SCEM-UA algorithm. Urban Water Journal. 2008; 5(2):125-32.

[2][2]Shuangli W, Mou L, Shen D, Jianjun W, Hui X. Classification calculation on water consumption of urban water supply network based on clustering analysis. In world automation congress 2012 (pp. 1-4). IEEE.

[3][3]Liang B. Urban annual water consumption prediction using artificial neural network. In Applied Mechanics and Materials. 2013:1008-11.

[4][4]Wang ZH, Xuan CG, Fu Q. Urban water consumption forecasting based on projection pursuit. In Advanced Materials Research 2012:1334-8.

[5][5]Yang T, Shi P, Yu Z, Li Z, Wang X, Zhou X. Probabilistic modeling and uncertainty estimation of urban water consumption under an incompletely informational circumstance. Stochastic Environmental Research and Risk Assessment. 2016; 30:725-36.

[6][6]Donkor EA, Mazzuchi TA, Soyer R, Alan Roberson J. Urban water demand forecasting: review of methods and models. Journal of Water Resources Planning and Management. 2014; 140(2):146-59.

[7][7]Altunkaynak A, Özger M, Çakmakci M. Water consumption prediction of Istanbul city by using fuzzy logic approach. Water Resources Management. 2005; 19(5):641-54.

[8][8]Altunkaynak A, Nigussie TA. Monthly water consumption prediction using season algorithm and wavelet transform–based models. Journal of Water Resources Planning and Management. 2017; 143(6).

[9][9]Bibri SE. The IoT for smart sustainable cities of the future: an analytical framework for sensor-based big data applications for environmental sustainability. Sustainable Cities and Society. 2018; 38:230-53.

[10][10]Benítez R, Ortiz-Caraballo C, Preciado JC, Conejero JM, Sánchez Figueroa F, Rubio-Largo A. A short-term data based water consumption prediction approach. Energies. 2019; 12(12):1-24.

[11][11]Shah S, Hosseini M, Miled ZB, Shafer R, Berube S. A water demand prediction model for central indiana. In proceedings of the AAAI conference on artificial intelligence 2018 (pp.7819-24).

[12][12]Velasco LC, Granados AR, Ortega JM, Pagtalunan KV. Medium-term water consumption forecasting using artificial neural networks. In conference of the science council of Asia, national research council of the Philippines 2017(pp.1-8).

[13][13]Aly AH, Wanakule N. Short-term forecasting for urban water consumption. Journal of Water Resources Planning and Management. 2004; 130(5):405-10.

[14][14]Candelieri A, Soldi D, Archetti F. Short-term forecasting of hourly water consumption by using automatic metering readers data. Procedia Engineering. 2015; 119:844-53.

[15][15]Bigui W, Hongwei Z. Traversal grey model for water consumption prediction. In international symposium on geomatics for integrated water resource management 2012 (pp. 1-4). IEEE.

[16][16]Wang W, Jiang J, Fu M. An enhanced differential evolution based grey model for forecasting urban water consumption. In proceedings of the Chinese control conference 2014 (pp. 7643-8). IEEE.

[17][17]Liu BZ, Wang DW. Grey regressive prediction method of urban life water consumption. In the Chinese control and decision conference 2014 (pp. 2913-8). IEEE.

[18][18]Zhou H, Huang J, Yuan Y, Tang B. Prediction of water consumption in hospitals based on a modified grey GM (0, 1∣ sin) model of oscillation sequence: the example of Wuhan City. Journal of Applied Mathematics. 2014:1-7.

[19][19]Froelich W, Magiera E. Forecasting domestic water consumption using bayesian model. In intelligent decision technologies 2016 (pp. 337-46). Springer, Cham.

[20][20]Ren Y, Xing T, Chen X, Xu E, Zhao Y. Based on process neural network learning algorithm for prediction of urban water consumption. In international conference on computing, control and industrial engineering 2010 (pp. 34-7). IEEE.

[21][21]Wang L. Improving artificial neural network models for predicting hourly water consumption (Master thesis, University of Waterloo). 2018.

[22][22]Chen G, Long T, Xiong J, Bai Y. Multiple random forests modelling for urban water consumption forecasting. Water Resources Management. 2017; 31:4715-29.

[23][23]Farah E, Abdallah A, Shahrour I. Prediction of water consumption using artificial neural networks modelling. In MATEC web of conferences 2019 (pp. 1-5). EDP Sciences.

[24][24]Zhang W, Bai Y. Prediction of water consumption using NARX neural network based on grey relational analysis. In international conference on sensing, diagnostics, prognostics, and control 2018 (pp. 471-5). IEEE.

[25][25]Pesantez JE, Berglund EZ, Kaza N. Smart meters data for modeling and forecasting water demand at the user-level. Environmental Modelling & Software. 2020.

[26][26]Tu C, He X, Shuai Z, Jiang F. Big data issues in smart grid–a review. Renewable and Sustainable Energy Reviews. 2017; 79:1099-107.

[27][27]Xenochristou M. Water demand forecasting using machine learning on weather and smart metering data. Doctoral Theses, University of Exeter. 2019.

[28][28]Wen L, Zhou K, Yang S. Load demand forecasting of residential buildings using a deep learning model. Electric Power Systems Research. 2020.

[29][29]Pham T, Tran T, Phung D, Venkatesh S. Predicting healthcare trajectories from medical records:a deep learning approach. Journal of Biomedical Informatics. 2017; 69:218-29.

[30][30]Fooshee D, Mood A, Gutman E, Tavakoli M, Urban G, Liu F, et al. Deep learning for chemical reaction prediction. Molecular Systems Design & Engineering. 2018; 3(3):442-52.

[31][31]Kubat M. An introduction to machine learning. Springer International Publishing AG; 2017.

[32][32]Graves A. Long short-term memory. In supervised sequence labelling with recurrent neural networks 2012 (pp. 37-45). Springer, Berlin, Heidelberg.

[33][33]https://www.packtpub.com/product/python-deep-learning-second-edition/9781789348460. Accessed 26 October 2020.

[34][34]Kwiatkowski D, Phillips PC, Schmidt P, Shin Y. Testing the null hypothesis of stationarity against the alternative of a unit root: how sure are we that economic time series have a unit root? Journal of Econometrics. 1992; 54(1-3):159-78.

[35][35]Said NM, Zin ZM, Ismail MN, Bakar TA. Comparative analysis of missing data imputation methods for continuous variables in water consumption data. International Journal of Advanced Trends in Computer Science and Engineering. 2019; 8(1.6):471-8.

[36][36]Tyralis H, Papacharalampous G. Variable selection in time series forecasting using random forests. Algorithms. 2017; 10(4):1-25.

[37][37]Firat M, Turan ME, Yurdusev MA. Comparative analysis of neural network techniques for predicting water consumption time series. Journal of Hydrology. 2010; 384(1-2):46-51.

[38][38]Koller D, Sahami M. Toward optimal feature selection. Stanford InfoLab; 1996:1-15.

[39][39]Kumar V, Minz S. Feature selection: a literature review. SmartCR. 2014; 4(3):211-29.