Designing effective urban water demand management strategies at the household level does require a deep understanding of the determinants of users' consumption. Low resolution data on residential water consumption, as traditionally metered, can only be used to model consumers' behavior at an aggregate level whereas end uses breakdown and the motivations and individual attitudes of consumers are hidden. The recent advent of smart meters allows gathering high frequency consumption data that can be used both to provide instantaneous information to water utilities on the state of the network and continuously inform the users on their consumption and savings. Smart metered data also allow for the characterization of water end uses: this information, coupled with users' psychographic variables, constitutes the knowledge basis for developing individual and multi users models, through which water utilities can test the impact of different management strategies. SmartH2O is an EU funded project which aims at creating an ICT platform able to (i) capture and store quasi real time, high resolution residential water usage data measured with smart meters, (ii) infer the main determinants of residential water end uses and build customers' behavioral models and (iii) predict how the customer behavior can be influenced by various water demand management strategies, spanning from dynamic water pricing schemes to social awareness campaigns. The project exploits a social computing approach for raising users' awareness about water consumption and pursuing water savings in the residential sector. In this work, we first present the SmartH2O platform and data collection, storage and analysis components. We then introduce some preliminary models and results on total water consumption disaggregation into end uses and single user behaviors using innovative fully automated algorithms and overcoming the need of invasive metering campaigns at the fixture level.
The SmartH2O project: a platform supporting residential water management through smart meters and data intensive modeling
COMINOLA, ANDREA;GIULIANI, MATTEO;CASTELLETTI, ANDREA FRANCESCO;GARRONE, PAOLA MARIA;
2014-01-01
Abstract
Designing effective urban water demand management strategies at the household level does require a deep understanding of the determinants of users' consumption. Low resolution data on residential water consumption, as traditionally metered, can only be used to model consumers' behavior at an aggregate level whereas end uses breakdown and the motivations and individual attitudes of consumers are hidden. The recent advent of smart meters allows gathering high frequency consumption data that can be used both to provide instantaneous information to water utilities on the state of the network and continuously inform the users on their consumption and savings. Smart metered data also allow for the characterization of water end uses: this information, coupled with users' psychographic variables, constitutes the knowledge basis for developing individual and multi users models, through which water utilities can test the impact of different management strategies. SmartH2O is an EU funded project which aims at creating an ICT platform able to (i) capture and store quasi real time, high resolution residential water usage data measured with smart meters, (ii) infer the main determinants of residential water end uses and build customers' behavioral models and (iii) predict how the customer behavior can be influenced by various water demand management strategies, spanning from dynamic water pricing schemes to social awareness campaigns. The project exploits a social computing approach for raising users' awareness about water consumption and pursuing water savings in the residential sector. In this work, we first present the SmartH2O platform and data collection, storage and analysis components. We then introduce some preliminary models and results on total water consumption disaggregation into end uses and single user behaviors using innovative fully automated algorithms and overcoming the need of invasive metering campaigns at the fixture level.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
