The authors have recently developed an intelligent application, Autoflow©, which is a powerful tool to autonomously categorise residential water consumption data into a registry of single and combined events. This tool was developed using data collected in several cities in Australia, and when applied on standalone properties, the achieved accuracy ranged from 86% and 96% in terms of number of correctly classified events. Taking advantage of the analysis results from Autoflow©, the aim of this study is to propose a short-term water demand forecasting model that not only allows water utilities to predict the overall and peak water demand of up to 24-hour ahead, but also obtain the disaggregated forecast volume of each end-use category. Based on the periodic pattern of the water consumption data, a state-space approach has been adopted whose components including trend, seasonal and external effect from temperature were all modelled as stochastic processes. In this model, Dynamic Harmonic Regression, Kalman Filter and Fixed Interval Smooth algorithms were employed for the estimation of all above-mentioned components. The model has been tested against datasets collected at different time of the year to estimate its efficiency as well as the impact of temperature on water consumption. The verification process has showed that the achieved R2 for all testings are above 0.9 when undertaking forecast of up to 24-hour ahead, whilst the obtained Mean Absolute Percentage Error (MAPE) of the disaggregated forecast volume of each category most of the time lie below 5%. Further model testing is planned to be applied on 1200 new apartment buildings in the Commonwealth Games Village located in Gold Coast Australia to validate its efficiency. Once finished, the overall Autoflow© application will have significant impact in practice that allows the water utility to have detailed plan in moderating water demand along the day, or assist in optimising the pumping activities at the least required energy. Most importantly, the ability to determine and approximate the peak demand will allow utilities to have flexible solutions to solve the over-capacity problem, especially at old metropolitans where the demand far exceeds the supply capacity of the old existing distribution network.