Comparative between cost prediction using statistical methods and neural networks

Prediction of total cost of water helps the Isfahan municipality to optimize the water usage in its 14 urban zone. The total cost of water, basically, depends on different parameters. Generally, the analytically prediction of the total cost is very difficult if not impossible. Thus, applying intelligent systems such as neural network models can be a good alternative. In this paper, using multi-layer perceptron neural network and error back propagation algorithm, the total cost of municipal water in the Isfahan municipality is calculated based on parameters such as per capita population and area of each urban zone. In this paper, a model for simulation and prediction of the annual total cost of water in Isfahan municipality is developed. The simulation model is developed using the regression and the neural network model is built using data from 2004 to 2009. Finally, the neural network method is selected as the main simulation method for forecasting the total cost of water in the 14 urban zones of Isfahan.