This document discusses indirect water end use sensing to provide consumption disaggregation and feedback. It describes a single, screw-on sensor that senses pressure in real time to identify water use events from pressure waves. Early work identified end uses but not in real time. Current research collects data from over 9 homes to predict volume and classify fixtures into categories like kitchen sink or toilet. Visualizations of hot/cold breakdowns and 5-week usage datasets are shown. Future work aims to provide three levels of usage granularity and incorporate multiple sensors for improved accuracy.
3. hydrosense
• single, screw-on sensor
• senses pressure in real time
Froehlich et al., UbiComp2009; Larson et al., PMC2010, Larson and Froehlich et al. Pervasive 2011
4. water tower
water
tower
pressure regulator
incoming cold
water from
supply line
utility water pressure
meter regulator
5. water tower
water
tower
pressure regulator
incoming cold
water from
supply line
utility water pressure
meter regulator
6. water tower
water tower
plumbing layout
incoming cold
water from
supply line
utility water pressure
meter regulator
7. water tower
water tower
bathroom 1
hose
spigot
kitchen
incoming cold
water from
dishwasher
supply line
thermal
expansion
utility water pressure
tank
meter regulator
hot
water
heater laundry
bathroom 2
8. water tower
water tower
toilet flushed
bathroom 1
hose
toilet spigot
kitchen
incoming cold
water from
dishwasher
supply line
thermal
expansion
utility water pressure
tank
meter regulator
hot
water
heater laundry
bathroom 2
9. water tower
water tower
toilet
bathroom 1
hose
kitchen sink cold
spigot kitchen sink
cold open
kitchen
incoming cold
water from
dishwasher
supply line
thermal
expansion
utility water pressure
tank
meter regulator
hot
water
heater laundry
bathroom 2
10. water tower
water tower
toilet
kitchen sink cold bathroom 1
hose
kitchen sink spigot
hot kitchen sink
hot open
kitchen
incoming cold
water from
dishwasher
supply line
thermal
expansion
utility water pressure
tank
meter regulator
hot
water
heater laundry
bathroom 2
11. water tower
water tower
bathroom 1
hose
spigot kitchen sink
hot open
kitchen
incoming cold
water from
dishwasher
supply line
thermal
expansion
utility water pressure
tank
meter regulator
hot
water
heater laundry
bathroom 2
12. water tower
water tower
bathroom 1
hose
spigot
kitchen
incoming cold
water from
dishwasher
supply line
utility water pressure
meter regulator
hot
water
heater laundry
bathroom 2
13. 2 years ago…
•End Use: 10 homes, staged
•Water flow: 7 fixtures, max flow
•Not in real time: no feedback
Where are we now?
16. water tower
water tower
bathroom 1
hose
spigot
kitchen
incoming cold
water from
dishwasher
supply line
thermal
expansion
utility water pressure
tank
meter regulator
hot
water
heater laundry
bathroom 2
17. 80
bathroom sink pressure signal
70
psi
60
50
Cold Line
Pressure…
open close
40
0 4.5 9
time (s)
18. 80
bathroom sink pressure signal
70
psi
60
flow volume
50
Cold Line
Pressure…
open close
40
0 4.5 9
time (s)
26. hydrosense
example pressure waves
upstairs toilet flushbath open
kitchen sink
kitchen sink
hot open open
dishwasher open
cold
downstairs shower toilet
downstairs
open flush
27. natural water use
toilet
70 kitchen sink kitchen sink
bathroom sink
pressure (psi)
50
30
28. data collection
water tower
bathroom 1
hose
spigot
kitchen
incoming cold
water from
dishwasher
supply line
thermal
expansion
utility water pressure
tank
meter regulator
hot
water
heater laundry
bathroom 2
Larson and Froehlich, et al., Pervasive 2011
42. Key Questions
1 What are the key gaps in water usage
understanding?
2
What aspects of disaggregated data are potential
users interested in and what sort of reactions do the
visualizations provoke?
3
How might these visualizations impact behavior?
Froehlich, et al., CHI2012
43. DESIGN SET 1: ISOLATING DESIGN DIMENSIONS
Design Dimensions
Data
Explored
Granularity
Individual Fixture Fixture Category Activity Hot and Cold
Time
Granularity
So Far Today So Far This So Far This
Week Month
Comparison
Self Comparison To Others To A Goal Social/Self
Measuremen
t
Unit In Gallons In Dollars Dollars / Gallons Including
44. DESIGN SET 2: DESIGN PROBES
Design Probes Explored
Time- Aquatic
Series Eco-system
Spatial Rainflow
Per- Other
Occupant
45. DESIGN SET 2: DESIGN PROBES
Aquatic Ecosystem View
New water
Water “Frank” the
savings goal
savings goal fish meets his
water
savings met
met mate
tracker
display is
“Frank” also
the fish interactive so
Frank and fish respond
his mate to touch
have
and so on… children
46. DESIGN SET 2: DESIGN PROBES
Other Design Probes
Geographic Comparisons Dashboards
Metaphorical Unit Designs Recommendations
Froehlich, et al., CHI2012
52. save
process (local)
update
save to disk/cloud
keep diary (sparse)
infer activity later
install for two weeks
stream to cloud
update global models
53. Indirect Water End Use Sensing:
Consumption, Disaggregation, and Feedback
Sensing and Architecture Behavior Change Product Development
Eric Larson Jon Froehlich Kevin Ashton
eclarson@uw.edu jonf@cs.umd.edu Kevin.Ashton@belkin.com
@ec_larson @jonfroehlich @kevin_ashton
eclarson.com cs.umd.edu/~jonf
UNIVERSITY of
WASHINGTON
Notas do Editor
hydrosense is a single screw on sensor that identifies water usage down to the fixture leveland provides estimates of water flow from each fixture
Cold water enters the home through a service line, typically at 40-100 pounds per square inch (psi) depending on such factors as the elevation and proximity to a water tower or pumping station.Pressure is important to the proper functioning of HydroSense because it’s a pressure-based sensing solution.------The pound per square inch or, more accurately, pound-force per square inch (symbol: psi or lbf/in² or lbf/in²) is a unit of pressure or of stress based on avoirdupois units. It is the pressure resulting from a force of one pound-force applied to an area of one square inch:1 psi (6.894757 kPa) : pascal (Pa) is the SI unit of pressure.40 psi is 275.79 kilopascals100 psi is 689.47 kilopascals
Many homes have a pressure regulator that stabilizes the water pressure and also reduces the incoming water pressure to a safe level for household fixtures.From the regulator, most homes contain a combination of series plumbed and branched piping.
The cold water supply branches to the individual water fixtures (e.g., toilets/sinks/showers) and into the water heater.
The plumbing system forms a closed loop pressure system with water held at a relatively stable pressure throughout the piping. This is why, when you open a faucet, water immediately flows out.
The cold water supply branches to the individual water fixtures (e.g., toilets/sinks/showers) and into the water heater.The plumbing system forms a closed loop pressure system with water held at a relatively stable pressure throughout the piping. This is why, when you open a faucet, water immediately flows out.
The cold water supply branches to the individual water fixtures (e.g., toilets/sinks/showers) and into the water heater.The plumbing system forms a closed loop pressure system with water held at a relatively stable pressure throughout the piping. This is why, when you open a faucet, water immediately flows out.
The cold water supply branches to the individual water fixtures (e.g., toilets/sinks/showers) and into the water heater.The plumbing system forms a closed loop pressure system with water held at a relatively stable pressure throughout the piping. This is why, when you open a faucet, water immediately flows out.
The cold water supply branches to the individual water fixtures (e.g., toilets/sinks/showers) and into the water heater.The plumbing system forms a closed loop pressure system with water held at a relatively stable pressure throughout the piping. This is why, when you open a faucet, water immediately flows out.
The cold water supply branches to the individual water fixtures (e.g., toilets/sinks/showers) and into the water heater.The plumbing system forms a closed loop pressure system with water held at a relatively stable pressure throughout the piping. This is why, when you open a faucet, water immediately flows out.
The plumbing system forms a closed loop pressure system with water held at a relatively stable pressure throughout the piping. This is why, when you open a faucet, water immediately flows out.
bath tubs, showers, kitchen sinks and bathroom sinks10 – 20 samples from each fixturevaried flow rate and temperature for each sample taken
To show how these rates compare I will show versus the graph. The black line is the curve associated with the water meter. The red line shows the volume error for the E-kNN within Fixture model, the green lines show the error for the minimal calibration and the yellow bars show the error for typical flow rate analysis. The flow trace meter typically adds a +/- 1% error to the error associated with the inline meter. The Within model is comparable to the flow trace error while the minimal calibration is larger but still within 5% for flow rates greater then 0.5gpm.
To show how these rates compare I will show versus the graph. The black line is the curve associated with the water meter. The red line shows the volume error for the E-kNN within Fixture model, the green lines show the error for the minimal calibration and the yellow bars show the error for typical flow rate analysis. The flow trace meter typically adds a +/- 1% error to the error associated with the inline meter. The Within model is comparable to the flow trace error while the minimal calibration is larger but still within 5% for flow rates greater then 0.5gpm.
To motivate these transformations, we need to return to the plumbing system. When we activate a fixture in the plumbing system, the entire system responds instantaneously, like letting the air out of a balloon. Depending on where we activate the water in the system, different resonances will be excited – so it will be important which resonances are activated and, as you can see from these examples, how quickly those resonances die out over time.
how to know ground truth?
so in addition installing the hydrosense system, we need to install a wireless network of sensors at every fixture that uses water in the home so we can label the water usage we see from the hydrosense system.
and in the end the deployment sites looked like this, here is a subset of the sinks we instrumented
toilets
and showers. Notice that we also had to instrument the diverter valve to know whether the bath or shower was running, in addition to secondary shower handles.
here is a clothes washer. We also tied a thermistor on the drain valve of the washer in order to know whether the homeowner used a hot/cold or cold/cold cycle.
and even instrumenting things like the refidgerator water dispenser.
and at the end of the labeling process we ended up with 156 days of water use spread out among 5 deployment sites and almost 15000 water usage labels to evaluate our hydrosense system. One thing that was quite surpirsing was that 22% off all the pressure waves we collected were compound events, that is, more than one water source was on at the same time.
and at the end of the labeling process we ended up with 156 days of water use spread out among 5 deployment sites and almost 15000 water usage labels to evaluate our hydrosense system. One thing that was quite surpirsing was that 22% off all the pressure waves we collected were compound events, that is, more than one water source was on at the same time.
but we can break the results down by granularity of the sensing. we can talk about results at the valve level, so knowing the exact bathroom sink hot valve that was activated.or at the fixture level, so knowing that the bathroom faucet was activated, but we don’t care about the temperature state. If you do activity inference, this might be your main interest because it gives you location.and finally we can talk about the fixture category level – so knowing only that a faucet was activated, but not where. For sustainability you might be interested in one or all of these levels of accuracy.
here are the results shown only for using all terms. Recall that we installed two pressure sensors
The addition of a second sensor resulted in a marginal to medium (but significant) increase in classification accuracies across the board, surpassing 80% at the valve level all the way up to almost 98% at the category level.But lastly let’s delve a little further into the 90% accuracy at the fixture level.
The design space is huge—how does one structure the design process to effectively design for this data?
One key insight that we had while performing this work is to realize that eco-feedback displays do not just visualize consumption, they document household activitiesConsequently, designers have to account for how their designs expose otherwise latent household routines and how this may affect underlying social dynamics in a household. Our findings suggest that these issues could affect whether a display will be accepted into the home.
As you’ve noticed, we used the same visual representation—bar graphs—to isolate the affect of each dimension on the designs
We explored six design probes
The aquatic ecosystem uses fish and plant life to depict water usage information in an artistic and ambient manner.The display is intended to be attractive and appealing to children and adults who prefer a less ‘data-centric’ design. Unlike our other designs, which focus on tracking consumption, this display focuses on water savings and reaching water savings goals for different fixtures in the home
Finally, we had other design probes including geographic-based comparisons, dashboard designs, metaphorical unit designs and recommendation systems. These are beyond the scope of this talk.
One key insight that we had while performing this work is to realize that eco-feedback displays do not just visualize consumption, they document household activitiesConsequently, designers have to account for how their designs expose otherwise latent household routines and how this may affect underlying social dynamics in a household. Our findings suggest that these issues could affect whether a display will be accepted into the home.
One key insight that we had while performing this work is to realize that eco-feedback displays do not just visualize consumption, they document household activitiesConsequently, designers have to account for how their designs expose otherwise latent household routines and how this may affect underlying social dynamics in a household. Our findings suggest that these issues could affect whether a display will be accepted into the home.
