Forecasting monthly urban water demand using Extended Kalman Filter and Genetic Programming

Research highlights? We implemented GP for developing suitable functional forms for water demand forecasting. ? These formula have been evaluated by mathematical sensitivity analysis and the best one has been chosen. ? Then, EKF as a nonlinear data assimilator has been used for increasing accuracy of the best model result. In this paper, a hybrid model which combines Extended Kalman Filter (EKF) and Genetic Programming (GP) for forecasting of water demand in Tehran is developed. The initial goal of the current work is forecasting monthly water demand using GP for achieving an explicit optimum formula. In the proposed model, the EKF is applied to infer latent variables in order to make a forecasting based on GP results of water demand. The available dataset includes monthly water consumption of Tehran, the capital of Iran, from 1992 to 2002. Five best formulas based on GP results on this dataset are presented. In these models, the first five to three lags of observed water demand are used as probable and independent inputs. For each model, sensitivity of the results for each input is measured mathematically. A model with the most compatibility of the computed versus the observed water demand is used for filtering based on EKF method. Results of GP and hybrid models of EKFGP demonstrate the visible effect of observation precision on water demand prediction. These results can help decision makers of water resources to reduce their risks of online water demand forecasting and optimal operation of urban water systems.

[1]  Mohsen Nasseri,et al.  Optimized scenario for rainfall forecasting using genetic algorithm coupled with artificial neural network , 2008, Expert Syst. Appl..

[2]  T. McMahon,et al.  Forecasting operational demand for an urban water supply zone , 2002 .

[3]  Vladan Babovic,et al.  The evolution of equations from hydraulic data Part II: Applications , 1997 .

[4]  Nitin Muttil,et al.  Genetic programming for analysis and real-time prediction of coastal algal blooms , 2005 .

[5]  Arthur Gelb,et al.  Applied Optimal Estimation , 1974 .

[6]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[7]  David R. Maidment,et al.  Time patterns of water use in six Texas cities , 1984 .

[8]  R. E. Kalman,et al.  A New Approach to Linear Filtering and Prediction Problems , 2002 .

[9]  David R. Maidment,et al.  Cascade Model of Monthly Municipal Water Use , 1984 .

[10]  Massoud Tabesh,et al.  FUZZY AND NEURO-FUZZY MODELS FOR SHORT-TERM WATER DEMAND FORECASTING IN TEHRAN , 2009 .

[11]  Hubert H. G. Savenije,et al.  FORECAST OF WATER DEMAND IN WEINAN CITY IN CHINA USING WDF-ANN MODEL , 2003 .

[12]  Robert A. Young,et al.  Price elasticity of demand for municipal water: A case study of Tucson, Arizona , 1973 .

[13]  S. T. Wong,et al.  A Model on Municipal Water Demand: A Case Study of Northeastern Illinois , 1997 .

[14]  Vladan Babovic,et al.  Velocity predictions in compound channels with vegetated floodplains using genetic programming , 2003 .

[15]  Luc Boullart,et al.  Genetic programming: principles and applications , 2001 .

[16]  J. L. Steiner,et al.  Influence of season to season variability in weather on irrigation scheduling of wheat: A simulation study , 1985, Irrigation Science.

[17]  John R. Koza,et al.  Genetic programming: a paradigm for genetically breeding populations of computer programs to solve problems , 1990 .

[18]  Peter A. Whigham,et al.  Modelling rainfall-runoff using genetic programming , 2001 .

[19]  C N Joo,et al.  Application of short-term water demand prediction model to Seoul. , 2002, Water science and technology : a journal of the International Association on Water Pollution Research.

[20]  Holger R. Maier,et al.  Input determination for neural network models in water resources applications. Part 1—background and methodology , 2005 .

[21]  R. Bruce Billings,et al.  STATE-SPACE VERSUS MULTIPLE REGRESSION FOR FORECASTING URBAN WATER DEMAND , 1998 .

[22]  Vladan Babovic,et al.  Declarative and Preferential Bias in GP-based Scientific Discovery , 2002, Genetic Programming and Evolvable Machines.

[23]  M. Keijzer,et al.  Genetic programming as a model induction engine , 2000 .

[24]  Todd H. Skaggs,et al.  Sensitivity Methods for Time‐Continuous, Spatially Discrete Groundwater Contaminant Transport Models , 1996 .

[25]  N. Jayasuriya,et al.  Temperature and rainfall thresholds for base use urban water demand modelling , 2007 .

[26]  Asoke K. Nandi,et al.  Fault detection using genetic programming , 2005 .

[27]  Vladan Babovic,et al.  GENETIC PROGRAMMING AND ITS APPLICATION IN REAL‐TIME RUNOFF FORECASTING 1 , 2001 .

[28]  Dong Gyu Lee,et al.  Genetic programming model for long-term forecasting of electric power demand , 1997 .

[29]  C. Sivapragasam,et al.  Genetic programming model for forecast of short and noisy data , 2007 .

[30]  Ashraf F. Ashour,et al.  Empirical modelling of shear strength of RC deep beams by genetic programming , 2003 .

[31]  Roger H. Willsie,et al.  Water Use Relationships and Projection Corresponding with Regional Growth, Seattle Region , 1974 .

[32]  Vladan Babovic,et al.  The evolution of equations from hydraulic data. Part I: Theory , 1997 .

[33]  Zekai Sen,et al.  Sediment Concentration and Its Prediction by Perceptron Kalman Filtering Procedure , 2004 .

[34]  Vladan Babovic,et al.  Rainfall‐Runoff Modeling Based on Genetic Programming , 2006 .

[35]  T. McMahon,et al.  Forecasting daily urban water demand: a case study of Melbourne , 2000 .