Abstract
Water consumptions and demands by persons vary from time to time and from location to location depending on countless factors, notably, population, socio-economic and climatic variables. Today, studies which create models on water consumption of persons, using numerous methods including artificial neural networks and regression models in this regard and ensure that projections are made are ongoing. In this study; parameters affecting water consumption were examined within the scope of the study area, and the parameter reduction was realized with the help of the Factor Analysis. Then, as a new method, the Band Similarity method was used together with the Artificial Bee Colony optimization algorithm, and urban water demand models were produced and the temporal dependence of the relevant variables was examined. As a result of the study, it was seen that the Band Similarity method improved the results obtained with the optimization algorithm and helped to understand the temporal dependencies of the variables. The fact that the Band Similarity method, which was put forward for the first time in its field, worked successfully and produced results, can be said to be the main contribution of this study to the knowledge.
The use of band similarity in urban water demand forecasting as a new method
