Application of Dynamic Time Warping Algorithm in Prototype Selection for the Disaggregation of Domestic Water Flow Data into End Use Events

摘要: The disaggregation of domestic water consumption flow-trace data into end use event categories still remains a complex challenge to be resolved in the field urban management. Domestic studies currently utilise software and analyst experience disaggregate flow events (e.g. faucet, dishwasher, toilet, etc.),which often requires excess two hours per home weeks data. An existing available database for over 200 households located South-east Queensland (SEQ), Australia was utilised purpose this study, which ultimately aims automate trace analysis process. One first research issues addressed develop prototype that encapsulates wide variation pattern characteristics each event, order reduce unnecessary computation memory resource required analyse entire database. To achieve aim, study employed Dynamic Time Warping algorithm. outcome practice is series prototypes representing predominant household shower, clothes washer, etc.). Future work will employ an artificial network model Moreover, validation its accuracy examined through predicting uses new sample smart metered households.