SmartH2O an integrated platform coupling smart water meters with - - PowerPoint PPT Presentation

SmartH2O an integrated platform coupling smart water meters with ICT and data intensive modeling to support residential water management

Andrea Cominola, the SmartH2O Consortium

URBAN WATER MANAGEMENT

2

URBAN CONTEXT

2014 2030 2050 66% 54%

urban population growth

41 megacities worldwide

Source: United Nations. Department of Economic and Social Affairs. Population Division, 2010

URBAN WATER MANAGEMENT

3

URBAN CONTEXT

URBAN WATER DEMAND MANAGEMENT

4

URBAN CONTEXT

DEMAND MANAGEMENT

URBAN WATER DEMAND MANAGEMENT

5

city scale user level customized management tailored WDMS strategic level planning

THE PROJECT_GOAL

6

MAIN GOAL Understanding, modelling and modifying consumers behavior to achieve quantifiable water savings in the residential sector

THE PROJECT_CONCEPT

7

KEY ELEMENTS

• High-resolution water consumption data
• Interaction with customers for information sharing and socio-

psychographic data gathering

• Gamification techniques for users engagement

LEVERAGES FOR WATER DEMAND MANAGEMENT

• Customized feedbacks to water consumers – RECOMMENDATIONS
• Rewards (and dynamic pricing) – BEHAVIOURAL ECONOMICS

THE PROJECT_USE CASES

8

THE PROJECT_PLATFORM

9

smart meters and end use analysis gamified bill

• nline and

board game behavioral modeling water consumption drivers identification water consumption level forecast at the customer scale administrator dashboard

tailored feedbacks prescriptive norms gamified bill price schemes

Response to WDMS

platform

Technological insights

DATA GATHERING

1 1

SM SMART MET ETER ERS

1-hour sampling resolution data 400 new smart meters installed in the Swiss case

DATA GATHERING

12

ONLINE SURVEYS YS

• nline surveys are rolled out with the SmartH2O users, in order

to collect us users’ psych cho-so sociographic da data (e.g., house characteristics, water consumption devices) and at attitudes (water saving and consumption attitudes and water price preferences)

• surveys are also developed to get feedbacks from the users on

the usability of the SmartH2O platform

END_USE CHARACTERIZATION

13

A new algorithm to perform household energy and water consumption TR TRACE DISAGGREGATI TION into end-uses (e.g., washing machine, toilet, tap, etc…) has been developed, with the purpose of profiling users’ consumption.

Preliminary experiment: 1 household (New Zealand) Piecewise constant trajectories on 1 min resolution built from 10s resolution sampling

HSID ¡algorithm

USER BEHAVIOURAL MODELING

14

Single user’s BEHAVIORAL MODELING through CLUSTERING and CLASSIFICATION techniques.

Hour of day

2 4 6 8 10 12 14 16 18 20 22 24

Average daily consumption [Liters]

20 40 60 80 100 120 140 160 180 200

0.5 1 1.5 2 2.5 3

11 % 52 % 37 %

Hour the day

5 10 15 20 25

Normalized household consumption

0.05 0.1 0.15

High consumers Medium consumers Low consumers

USER BEHAVIOURAL MODELING

15

A first prototype of AGENT-BASED MODEL for multi-user modelling

CUSTOMERS WEB PORTAL

16

CUSTOMERS ENGAGEMENT and GAMIFICATION

17

next steps

1 9

SMART SENSORS

2

SMART MODELLING SENSORS

2 1

SMART MODELLING USERS’ SENSORS ENGAGEMENT

2 2

SMART MODELLING USERS’ SENSORS ENGAGEMENT Closing the loop with the design and implementation of customized water demand management strategies Water savings monitoring

The consortium

thank you

http://www.smarth2o-fp7.eu/

@smartH2Oproject #SmartH2O @AndreaCominola @NRMPolimi

Andrea Cominola, PhD candidate andrea.cominola@polimi.it

Politecnico di Milano

Department of Electronics, Information and Bioengineering