Embed Size (px)
Citation preview
Stankovic, Lina and Stankovic, Vladimir and Murray, David and Liao,
Jing (2016) Energy feedback enabled by load disaggregation. In: 1st
Energy Feedback Symposium, 2016-07-04 - 2016-07-05, University of
Edinburgh. ,
This version is available at https://strathprints.strath.ac.uk/61936/
Strathprints is designed to allow users to access the research output of the University of
Strathclyde. Unless otherwise explicitly stated on the manuscript, Copyright © and Moral Rights
for the papers on this site are retained by the individual authors and/or other copyright owners.
Please check the manuscript for details of any other licences that may have been applied. You
may not engage in further distribution of the material for any profitmaking activities or any
commercial gain. You may freely distribute both the url (https://strathprints.strath.ac.uk/) and the
content of this paper for research or private study, educational, or not-for-profit purposes without
prior permission or charge.
Any correspondence concerning this service should be sent to the Strathprints administrator:
The Strathprints institutional repository (https://strathprints.strath.ac.uk) is a digital archive of University of Strathclyde research
outputs. It has been developed to disseminate open access research outputs, expose data about those outputs, and enable the
management and persistent access to Strathclyde's intellectual output.
Energy Feedback
enabled by
Load Disaggregation
Lina Stankovic, Vladimir Stankovic, David Murray, Jing Liao
Dept of Electronic & Electrical Engineering, University of Strathclyde
Contact: [email protected]
REFIT: Smart Homes & Energy Demand Reduction
REFIT Energy Feedback & Findings
1. Comparison with
that of the
previous month or
year => 100%
2. Comparison with
other households
=> 50%
3. Monthly
consumption =>
65%
4. Daily or weekly
consumption =>
25%.
5. Appliance-
specific use =>
70%
Kane, T., Cockbill, S., May, A., Mitchell, V., Wilson, C., Dimitriou, V., Liao, J., Murray, D., Stankovic, L., Stankovic, V, Fouchal,
F., Hassan, T.M., & Firth, S.K. (2015) Supporting retrofit decisions using Smart Meter data in a multi-disciplinary
approach., Proc. ECEEE-2015.
Load Disaggregation via Non-intrusive
Appliance Load Monitoring (NILM) for smart-meter aggregate load data
• Supervised NILM methods1,2 — relatively simple, robust,
and require short training periods
• Unsupervised method1,3 —does not require a labelled set
of appliances for training
• Training-less method4 —does not require any prior
knowledge of appliances or a training period
[1] Liao, J., Elafoudi, G., Stankovic, L., & Stankovic, V. (2014). Non-intrusive appliance load monitoring using low-
resolution smart meter data. Proc. IEEE SmartGridComm-2014, 535-540.
[2] Altrabalsi, H., Stankovic, V., Liao, J., & Stankovic, L. (2016). Low-complexity energy disaggregation using appliance load
monitoring. AIMS Energy, 4, 884-905.
[3] Elafoudi, G., Stankovic, L., & Stankovic, V. (2014). Power disaggregation of domestic smart meter readings using
Dynamic Time Warping. Proc. IEEE ISCCSP-2014
[4] Zhao, B., Stankovic, L., & Stankovic, V. (2016). On a training-less solution for non-intrusive appliance load monitoring
using graph signal processing. IEEE Access, 4, 1784-1799
Smart electricity meters and IHDs tell us about real-
time household electricity use, but they don’t tell us which appliances were running, nor what to do about it.
Energy disaggregation tells us when, how long an appliance
was used and how much energy it consumed, but nothing
about why it was used. Beyond NILM
Enhanced feedback on electricity consumption
advice on non-efficient usage of an appliance
inform appliance upgrades
opportunities for (appliance) load shifting
predict appliance electricity demand
relating energy consumption to activities in the home, such
as cooking or laundering
• Kettle: Model inferring the volume of water used purely from disaggregated electricity consumption
• Estimating best usage scenarios to reduce waste
Appliance Modelling & Informing
Energy Savings
House
Months
Recorded
Total
Consumption
(kWh)
Optimal
Volume (mL)
Consumption Above
Optimal (kWh)
Savings per
Year (kWh)
2 20 255.32 825 126.76 15.32
3 20 251.16 550 171.06 28.85
5 21 314.66 825 148.85 17.32
6 19 273.6 550 122.75 16.67
8 18 245.68 550 171.83 23.41
9 18 312.36 550 271.31 73.71
11 12 182.02 500 83.78 29.99
12 15 163.92 825 105.54 20.98
17 15 183.63 550 98.98 16.99
Murray, D.M., Liao, J., Stankovic, L., & Stankovic, V. (2016). Understanding usage patterns of electric kettle and energy
saving potential. Elsevier Applied Energy, 171, 213-242.
Informing Appliance Upgrade Case study of a household upgrading from a standard kettle to
a vacuum kettle
Year Uses Consumption (kWh)
Dec 2013 に Standard 238 17.2
Dec 2014 に Vacuum 217 14.8
• Reduction
in the
number of
re-heats
• ~5%
reduction
per use
• ~14% total
reduction
• Continued
economical
usage style
Murray, D.M., Liao, J., Stankovic, L., & Stankovic, V. (2016). Understanding usage patterns of electric kettle and energy
saving potential. Elsevier Applied Energy, 171, 213-242.
Load Shifting
65% of REFIT households would consider
adjusting the timing of their appliance use to
benefit from a better tariff.
dishwasher, washing machine and tumble
dryer, hobbies, charging devices, bread-maker,
computing, and charging their car.
Non Off-Peak uses: 344
Total load that can be shifted: 99.77 kWh
Day Price: £13.05
Night Price: £7.54
Possible Savings: ~ £5.10
Murray, D.M., Liao, J., Stankovic, L., Stankovic, V., Hauxwell-Baldwin, R., Wilson, C., Coleman, M., Kane, T., & Firth, S.
(2015). A data management platform for personalised real-time energy feedback. Proc. EEDAL-2015
Temporal Patterns of Appliance Use
House 12 (Working) House 11 (Retired)
Murray, D.M., Liao, J., Stankovic, L., & Stankovic, V. (2015) How to make efficient use of kettles: Understanding usage
patterns, Proc. EEDAL-2015.
Kettle Demand Prediction
Deeper understanding and more accurate prediction of
appliances will enable more accurate load simulation
Murray, D.M., Liao, J., Stankovic, L., & Stankovic, V. (2016). Understanding usage patterns of electric kettle and energy
saving potential. Elsevier Applied Energy, 171, 213-242.
Meaningful & salient feedback
Moving away from ‘energy-
centric’ approach in which information feedback
directly concerns energy
consumption
To an ‘activity-centric’ approach, where the
emphasis shifts from energy
use to households’ lived experience, i.e., routines,
habits and activities that
constitute the majority of life
at home.
FWWSH;Iﾆ ｷゲ ｷﾏヮﾗヴデ;ﾐデ さin making energy more visible and more
amenable to understanding and controlざく
Understanding the linkages between
appliance use and common activities in the
house by integrating quantitative smart
home data with qualitative household
ethnography to identify activities at home
Develop, test, and validate a multi-step
methodology for making robust activity-
based inferences in households
Demonstrate how smart energy meter data
can be used to feed back information to
households on the time profile of everyday
activities in the home and their energy-
using consequences
Stankovic, L., Stankovic, V., Liao, J., Wilson, C., Hauxwell-Baldwin, R., & Coleman, M. (2015). Understanding domestic
appliance use through their linkages to common activities. Proc. EEDAL-2015
Linkages between Time-use
(Activities) and Energy
Wilson, C., Stankovic, L., Stankovic, V., Liao, J., Coleman, M., Hauxwell-Baldwin, R., Kane, T., Firth, S., & Hassan, T. (2015).
Identifying the time profile of everyday activities in the home using smart meter data. Proc. ECEEE-2015
0%
10%
20%
30%
40%
50%
60%
70%
80%
90%
100%
0:00
-1:0
0
1:00
-2:0
0
2:00
-3:0
0
3:00
-4:0
0
4:00
-5:0
0
5:00
-6:0
0
6:00
-7:0
0
7:00
-8:0
0
8:00
-9:0
0
9:00
-10:
00
10:0
0-11
:00
11:0
0-12
:00
12:0
0-13
:00
13:0
0-14
:00
14:0
0-15
:00
15:0
0-16
:00
16:0
0-17
:00
17:0
0-18
:00
18:0
0-19
:00
19:0
0-20
:00
20:0
0-21
:00
21:0
0-22
:00
22:0
0-23
:00
23:0
0-00
:00
%o
fto
tale
lect
rici
tyu
se
Electricityusebyac vityoverthecourseofaday:
averageweekday(Oct2014),%oftotalelectricityuse
residual
ligh ng
baseload
electricheater
coldappliances
hobbies
compu ng
games
radio
tv
cleaning
laundering
washing
cooking
explained
but not
linked to
activities
Cooking
Laundering
Cleaning
Watching TV
Computing
Hobbies
Baseload
Cold appliances
Unknown
Other
In this household, detected activities can account for almost 50% of the monthly total electricity consumption, with cooking and laundering playing a significant part.
Understanding Energy Demand
through Activities
Stankovic, L., Stankovic, V., Liao, J., Wilson, C., Hauxwell-Baldwin, R., & Coleman, M. (2015). Understanding domestic
appliance use through their linkages to common activities. Proc. EEDAL-2015
Fridge
1%
freezer
5%
Tumble dryer
1%
Washing
machine
3% Toaster
0%
PC
2%
TV
1% Microwave
1% Kettle
3%
Dishwasher
4%
Monitor
standby
1%
vivo
2% Electrical shower
6%
Oven
7% Vacuum cleaner
1% Iron
1% breadmaker
2% Immersion
0%
Underfloor
heating
1%
hair dryer
0%
electrical hob
1%
electrical
sander
1%
Base load
15%
unknown
41%
cold appliance
6%
cooking
16%
laundry
5% TV
2%
cleaning
1% washing
6%
computing
4%
electrical heater
4%
base load
15%
unknown
41%
• The total electricity use explained by activity inferences is 33%. The rest is accounted
for by lighting, cold appliances, base load, and heating.
Monthly electricity breakdown
Using disaggregated information about the when, duration
and energy consumption of each appliance use:
Time use statistics to quantify, predict and inform
(efficient) appliance use and upgrade
Identify opportunities for load shifting of particular
appliances & quantify energy savings due to shifting
appliance use
Understanding electricity demand through the lens of
activities by integrating quantitative smart home data
with qualitative household ethnography to identify
activities at home
15
NILM-facilitated Energy Feedback
