Committee Machines for Hourly Water Demand Forecasting in Water Supply Systems

Prediction models have become essential for the improvement of decision-making processes in public management and, particularly, for water supply utilities. Accurate estimation often needs to solve multimeasurement, mixed-mode, and space-time problems, typical of many engineering applications. As a result, accurate estimation of real world variables is still one of the major problems in mathematical approximation. Several individual techniques have shown very good estimation abilities. However, none of them are free from drawbacks. This paper faces the challenge of creating accurate water demand predictive models at urban scale by using so-called committee machines, which are ensemble frameworks of single machine learning models. The proposal is able to combine models of varied nature. Specifically, this paper analyzes combinations of such techniques as multilayer perceptrons, support vector machines, extreme learning machines, random forests, adaptive neural fuzzy inference systems, and the group method for data handling. Analyses are checked on two water demand datasets from Franca (Brazil). As an ensemble tool, the combined response of a committee machine outperforms any single constituent model.

[1]  T. Mazzuchi,et al.  Urban Water Demand Forecasting: Review of Methods and Models , 2014 .

[2]  Huicheng Zhou,et al.  Application of a Combination Model Based on Wavelet Transform and KPLS-ARMA for Urban Annual Water Demand Forecasting , 2014 .

[3]  G. Pask,et al.  Heuristic Self-Organization in Problems of Engineering Cybernetics , 2003 .

[4]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[5]  A. Atiya,et al.  Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond , 2005, IEEE Transactions on Neural Networks.

[6]  Davy Geysen,et al.  Operational Demand Forecasting In District Heating Systems Using Ensembles Of Online Machine Learning Algorithms , 2017 .

[7]  Luuk C. Rietveld,et al.  Improving the Performance of Water Demand Forecasting Models by Using Weather Input , 2014 .

[8]  J. Adamowski.  Peak Daily Water Demand Forecast Modeling Using Artificial Neural Networks , 2008 .

[9]  Rahman Khatibi,et al.  Groundwater vulnerability indices conditioned by Supervised Intelligence Committee Machine (SICM). , 2017, The Science of the total environment.

[10]  Phalguni Gupta,et al.  Face Classification Using Gabor Wavelets and Random Forest , 2009, 2009 Canadian Conference on Computer and Robot Vision.

[11]  Patrick P. K. Chan,et al.  Random forest based ensemble system for short term load forecasting , 2012, 2012 International Conference on Machine Learning and Cybernetics.

[12]  R. Polikar,et al.  Ensemble based systems in decision making , 2006, IEEE Circuits and Systems Magazine.

[13]  Simon Haykin,et al.  Neural Networks and Learning Machines , 2010 .

[14]  Shuming Liu,et al.  Short-Term Water Demand Forecast Based on Deep Learning Method , 2018, Journal of Water Resources Planning and Management.

[15]  C.A.M. Lima,et al.  Ensembles of support vector machines for regression problems , 2002, Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290).

[16]  Zhi-Hua Zhou,et al.  Ensemble Methods: Foundations and Algorithms , 2012 .

[17]  B. Wujek,et al.  Automated Hyperparameter Tuning for Effective Machine Learning , 2017 .

[18]  David Zimbra,et al.  Urban Water Demand Forecasting with a Dynamic Artificial Neural Network Model , 2008 .

[19]  Rahim Barzegar,et al.  Combining the advantages of neural networks using the concept of committee machine in the groundwater salinity prediction , 2016, Modeling Earth Systems and Environment.

[20]  Mohammad Najafzadeh,et al.  Prediction of pipeline scour depth in clear-water and live-bed conditions using group method of data handling , 2012, Neural Computing and Applications.

[21]  Idel Montalvo,et al.  Improved performance of PSO with self-adaptive parameters for computing the optimal design of Water Supply Systems , 2010, Eng. Appl. Artif. Intell..

[22]  Sarah Praskievicz,et al.  Identifying the Relationships Between Urban Water Consumption and Weather Variables in Seoul, Korea , 2009 .

[23]  R. J. Sassi,et al.  Study on Daily Demand Forecasting Orders using Artificial Neural Network , 2016, IEEE Latin America Transactions.

[24]  Kamil Kamiński,et al.  Application of Artificial Neural Networks to the Technical Condition Assessment of Water Supply Systems , 2017 .

[25]  Guang-Bin Huang,et al.  Trends in extreme learning machines: A review , 2015, Neural Networks.

[26]  Amadou Ba,et al.  Tailoring Seasonal Time Series Models to Forecast Short-Term Water Demand , 2016 .

[27]  Mariette Awad,et al.  An ordinal kernel trick for a computationally efficient support vector machine , 2014, 2014 International Joint Conference on Neural Networks (IJCNN).

[28]  Manuel Herrera,et al.  Correlation analysis of water demand and predictive variables for short-term forecasting models , 2017 .

[29]  Bernhard Schölkopf,et al.  An Introduction to Support Vector Machines , 2003 .

[30]  Joaquín Izquierdo,et al.  Hybrid regression model for near real-time urban water demand forecasting , 2017, J. Comput. Appl. Math..

[31]  Joaquín Izquierdo,et al.  Municipal Water Demand Forecasting: Tools for Intervention Time Series , 2011 .

[32]  R. Clemen.  Combining forecasts: A review and annotated bibliography , 1989 .

[33]  Niranjan Nayak,et al.  Solar power forecasting using a hybrid EMD-ELM method , 2017, 2017 International Conference on Circuit ,Power and Computing Technologies (ICCPCT).

[34]  Antonio Candelieri.  Clustering and Support Vector Regression for Water Demand Forecasting and Anomaly Detection , 2017 .

[35]  G. Saulo.  Administração da produção e operações , 2008 .

[36]  T. Asefa,et al.  Improving Short-Term Urban Water Demand Forecasts with Reforecast Analog Ensembles , 2016 .

[37]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[38]  Jyh-Shing Roger Jang,et al.  ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..

[39]  Dianhui Wang,et al.  Extreme learning machines: a survey , 2011, Int. J. Mach. Learn. Cybern..