Handwritten Text Recognition for manuscripts and early printed texts
The SmartH2O project: a platform supporting residential water management through smart meters and data intensive modeling
1. a platform supporting residential water
management through smart meters
and data intensive modeling
Andrea Cominola, Rohan Nanda, Matteo Giuliani,
Dario Piga, Andrea Castelletti, Andrea Emilio Rizzoli,
Alexandros Maziotis, Paola Garrone and Julien J. Harou
3. RESIDENTIAL WATER MANAGEMENT
URBAN CONTEXT
2014 2030 2050
66%
54%
urban
population
growth
Source: United Nations. Department of Economic and Social Affairs. Population Division, 2010
4. RESIDENTIAL WATER MANAGEMENT
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
5. AN EXAMPLE: LONDON
UK_WATER SUPPLY UTILITY
15 million customers
2.6 Gl/day drinking water
3 billion $ revenue (2013-14)
6. HOW TO FILL THE GAP?
UK_WATER SUPPLY UTILITY
15 million customers
2.6 Gl/day drinking water
3 billion $ revenue (2013-14)
water demand
available resource
2010 2040
7. HOW TO FILL THE GAP?
UK_WATER SUPPLY UTILITY
15 million customers
2.6 Gl/day drinking water
3 billion $ revenue (2013-14)
water demand
CAPACITY EXPANSION
2010 2040
8. HOW TO FILL THE GAP?
UK_WATER SUPPLY UTILITY
15 million customers
2.6 Gl/day drinking water
3 billion $ revenue (2013-14)
DEMAND MANAGEMENT
CAPACITY EXPANSION
2010 2040
9. THE PROJECT
high resolution water
consumption data
interaction with customers
for socio-psychographic
data gathering
management strategies:
dynamic pricing
rewards
INNOVATIVE WATER
DEMAND MANAGEMENT
13. CUSTOMERS’ BEHAVIOR MODELING
smart meters
and end use
analysis
behavioral modeling
water
consumption
drivers
identification
water
consumption
level forecast at
the customer
scale gamified bill
online and
board game
14. MANAGEMENT AND CONTROL
smart meters
and end use
analysis
gamified bill
online and
board game
behavioral modeling
water
consumption
drivers
identification
water
consumption
level forecast at
the customer
scale
administrator
dashboard
dynamic water pricing
tailored feedbacks
prescriptive norms
gamified bill
Response to
WDMS
15. What is there behind the platform?
Some technological insights
16. MANAGEMENT AND CONTROL
administrator
dashboard
gamified bill
online and
board game
behavioral modeling
water
consumption
drivers
identification
water
consumption
level forecast at
the customer
scale
dynamic water pricing
tailored feedbacks
prescriptive norms
gamified bill
Response to
WDMS
smart meters
and end use
analysis
17. WATER CONSUMPTION DISAGGREGATION INTO END USES
Toilet
Shower
Dishwasher
Washing machine
Garden
Swimming pool
ONE MEASURE MANY END USES
Need for fully automated
disaggregation algorithms
overlapping,
simultaneous water
end uses
human-dependent
vs
automatic fixtures
Source: Nguyen et al., 2013
18. A NEW END USE CHARACTERIZATION ALGORITHM
MODEL FEATURES
Factorial Hidden Markov Model
Iterative Subsequence Dynamic Time Warping
MODEL PERFORMANCE
ABLE TO CHARACTERIZE UP TO 4-5 SIMULTANEOUSLY WORKING FIXTURES
Source: Batra et al., 2014, Muller, 2007, Gharahmani, 1997
19. A NEW END USE CHARACTERIZATION ALGORITHM
ACCURACY
ON EVENT
DETECTION
ACCURACY
ON
TRAJECTORIES
20. Finally, how can the platform support
the management of the resource?