Comparative analysis of neural network techniques for predicting water consumption time series

Performance Analysis of Artificial Neural Networks Training Algorithms and Transfer Functions for Medium-Term Water Consumption Forecasting

“…4, there were 11 input neurons which represent the month, billed accounts in each category and the water consumed in each category while the number of neurons in the output layer was 5 representing the next month water consumption in each category. A neural network with one hidden layer has the tendency to perform very well [2], [5], [7]. Thus, the researchers used only 1 hidden layer.…”

“…ANN modelling approaches have been embraced enthusiastically by practitioners in water resources, as they are perceived to overcome some of the difficulties associated with traditional statistical approaches [1], [4], [7]. With the changing landscape and climate brought about by weather phenomena and unprecedented human activities, water as a very important environmental resource should be managed scientifically with the use of tools and techniques that will optimize usage management and conservation.…”

“…A major challenge in the www.ijacsa.thesai.org implementation of ANN in water consumption forecasting is the choice of the appropriate ANN model design involving training algorithms and transfer functions that can yield the smallest error from the actual water consumption. Consequential to this challenge is water consumption data preparation through data normalization to ensure the avoidance of slow neural network training [7]- [9]. Data normalization is a process of final data preparation for network training so that the normalized data are shaped to meet the network input layer requirements.…”

Forecasting on China’s Total Water Demand in 2018

“…Currently, there are many researches on water demand. Sen et al (2009) established a fuzzy model for predicting daily drinking water requirement for a person [2] ; Firat et al (2010) found CCNN model performed better than GRNN model and FFNN model by comparing the prediction effect of daily water demand in Izmir, Turkey [3] . Herrera et al (2010) made water demand prediction of a city in southeastern Spain, the results indicated SVM model had the highest prediction accuracy, followed by multivariate adaptive regression spline model, projection pursuit model, random forest model and neural network model [4] ; Nasseri et al (2011) established a genetic algorithm model to predict urban water demand in Tehran [5] ; Ajbar et al (2013) built a neural network model to forecast the monthly and annual water demand for Mecca city, Saudi Arabia [6] .…”

“…These forecasting methods mainly are neural network model (ANNs), fuzzy systems theory model, projection pursuit model and genetic algorithms, or improved model and combined model. However, these models generally do not have high prediction accuracy, whose errors are usually higher than 5%, and are not conducive to analyze how the factors affect the water demand [2][3][4][5][6] .…”