Prediction of future demand for water distribution systems

Abstract

This project focuses on the prediction of future water demand for distribution systems specifically targeting the Namayingo water supply system in Namayingo Town council, Uganda. The growing population and climate variability have led to increasing pressure on water resources, making accurate forecasting crucial for optimizing distribution, ensuring sustainable water supply, and improving infrastructure planning. This research aims to develop a predictive model using Artificial Neural Networks (ANNs) to forecast water demand by integrating real-time data such as weather conditions, population growth, and economic factors. The model will enable water utilities to proactively manage demand fluctuations, reduce inefficiencies, and ensure a consistent water supply. By validating the model through error metrics such as RMSE, MAE, and R², this project will offer a reliable decision-support tool for water resource management. The results of this study will contribute to meeting Uganda's water demand challenges and align with global sustainable development goals related to clean water and sustainable cities.