The aim of residential water end-use studies is to disaggregate water consumption into different water end-use categories (i.e., shower, toilet, etc.). The authors previously developed a beta application software (i.e., Autoflow v2.1) that provides an intelligent platform to autonomously categorize residential water consumption data and generate management analysis reports. However, the Autoflow v2.1 software water end use event recognition accuracy achieved was between 75 to 90%, which leaves room for improvement. In the present study, a new module augmented to the existing procedure improved flow disaggregation accuracy, which resulted in Autoflow v3.1. The new module applied self-organizing maps (SOM) and K-means clustering algorithms for undertaking an initial pre-grouping of water end-use events before the existing pattern recognition procedures were applied (i.e., ANN, HMM, etc.) For validation, a dataset consisting of over 100,000 events from 252 homes in Australia were employed to verify accuracy improvements derived from augmenting the new hybrid SOM and K-means algorithm techniques into the existing Autoflow v2.1 software. The water end use event categorization accuracy ranged from 86 to 94.2% for the enhanced model (Autoflow v3.1), which was a 1.7 to 9% improvement on event categorization.

The smart water meter collected data has made a great progress for the categorization of residential water end use events, the efficiency and accuracy still need to be improved. In this paper, an advanced algorithm is proposed for clustering the end-use category of a mechanical appliance. For this study, the database of end use events was collected using smart meters from over 200 households located in South-east Queensland (SEQ), Australia. Firstly, the raw data is pre-processed and physical characteristics (e.g., volume, duration, max flowrate, etc.) are extracted. Due to the type of the dataset is water end used flow data, which based on time series, a K-Medoids clustering algorithm based on the Dynamic Time Warping algorithm is used for clustering. In addition, a swarm intelligence which is named Artificial Bee Colony algorithm brings the whole system into equilibrium. Numerical experiments are based on toilet flushing events. Results indicate that the hybrid technique improves the clustering accuracy from 82.85% to 95.71%, and it can be implemented to other mechanical water end use events such as clothes washers and dish washers.