ISBN-13: 9783639304558 / Angielski / Miękka / 2010 / 96 str.
Prediction of future water demand is critical to economies, communities, ecosystems, cost-effective, sustainable management and expansion of urban water supply infrastructure. Its importance increases when water must be allocated among competing users in the rapidly growing cities. This study compares Time series analysis and Artificial Neural Networks (ANNs) as techniques for water demand prediction for a case study city. The effects of meterological factors on domestic water demand prediction were taken in consideration in order to find the best model. Multilayer Perceptron(MLP), Cascade correlation (CCNN) and General Regression Neural Network (GRNN) were applied. The combination between Time Series and ANN techniques was also studied.
Prediction of future water demand is critical to economies, communities, ecosystems, cost-effective, sustainable management and expansion of urban water supply infrastructure. Its importance increases when water must be allocated among competing users in the rapidly growing cities. This study compares Time series analysis and Artificial Neural Networks (ANNs) as techniques for water demand prediction for a case study city. The effects of meterological factors on domestic water demand prediction were taken in consideration in order to find the best model. Multilayer Perceptron(MLP), Cascade correlation (CCNN) and General Regression Neural Network (GRNN) were applied. The combination between Time Series and ANN techniques was also studied.