Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.
Stephen Galsworthy, Quby
AI and Machine Learning
for the Connected Home
Session hashtag: #SAISAI4
2004
Home Automation
Europe is founded
2012
Home Automation
Europe partners
with Eneco to create
Toon
2013
Home Automation...
4
Launched in 2016
Launched in 2017
Launched in 2012
Testing phaseOur partners:
SMART THERMOSTAT &
APP
TOON SOLAR BOILER MONITORINGWASTE CHECKER
MONTHLY ENERGY
INSIGHT
WATER INSIGHT
SECURITY
PACKAGE & A...
Z-Wave
Meter adaptor
Boiler adapter
Gas sensor
Philips Hue
Z-Wave
Central heating system
Solar panels
Click data
Smart plu...
100 MB data
per user
collected per
month
Over 350,000 displays
installed
300 types of
sensor and
user
interaction
data
For production grade
algorithms and R&D
For machine learning on
distributed data
- Spark cluster
management
- Collaboratio...
Creating data driven services
Feasibility
ViabilityDesirability
Traditional billing
relationship
Historical energy
insight
Real time
information
Appliance level
diagnostics
<4% 4-6% 8-10...
Energy Waste Checker
“We don’t always notice how much energy we’re
wasting. Toon can now expose the energy
guzzlers in you...
Toon detects inefficient appliances and behaviours
& more coming
soon
Electricity data Appliance signals
Key technology: load disaggregation algorithms
Quby’s disaggregation algorithms
DishwasherWashing
machine
Washing
machine(only night hours shown)
DryerDryer
Patent pendi...
Quby’s disaggregation algorithms
Washing
machine
Dryer DishwasherDryerWashing
machine
Washing
machine
Dryer Dishwasher Dry...
Use case example: Inefficient dishwasher diagnosis
Disaggregation algorithms run on the 10s
electricity meter data
Compare...
Scale of the Waste checker
Each day we detect over
75,000dishwasher
cycles
That’s
13 years
of dishwashers running
continuo...
POP QUIZ
Which is the most
popular day of the week
to do the laundry?
?
It’s Sunday!
5.0
3.7
3.1
3.5
3.3
3.6
4.9
Sunday Monday Tuesday Wednesday Thursday Friday Saturday
with 5.0 million of the ...
It’s Sunday!
k
100k
200k
300k
400k
500k
600k
0 2 4 6 8 10121416182022 0 2 4 6 8 10121416182022 0 2 4 6 8 10121416182022 0 ...
Heating system anomaly detection
Enhancement to our existing Boiler
Monitoring service
1. Boiler and thermostat data are constantly
monitored by Toon
4. Toon user is alerted
2. Toon determines when the
system ...
Heating system anomaly detection
5 things we learned
#1: We love Spark
Machine learning on distributed data is key to all of this working at scale.
An example: Spark’s window ...
#2: We prefer Scala now
Moving from Python to Scala takes effort but it’s worth it.
An example: We define our dataset sche...
#3: We live in the cloud
Rather than taking care of the infrastructure, data engineers can concentrate on how to
make data...
#4: ‘In production’ is not the end
Continuous feedback from hundreds of thousands of users means there’s always
improvemen...
#5: Full-stack data science rocks!
Build and run, from initial concept to end result. Making services that our end users
w...
Stephen Galsworthy
Head of Data Science
+31 (0) 20 462 1680
stephen.galsworthy@quby.com
AI and Machine Learning for the Connected Home with Stephen Galsworthy
AI and Machine Learning for the Connected Home with Stephen Galsworthy
Upcoming SlideShare
Loading in …5
×

of

AI and Machine Learning for the Connected Home with Stephen Galsworthy Slide 1 AI and Machine Learning for the Connected Home with Stephen Galsworthy Slide 2 AI and Machine Learning for the Connected Home with Stephen Galsworthy Slide 3 AI and Machine Learning for the Connected Home with Stephen Galsworthy Slide 4 AI and Machine Learning for the Connected Home with Stephen Galsworthy Slide 5 AI and Machine Learning for the Connected Home with Stephen Galsworthy Slide 6 AI and Machine Learning for the Connected Home with Stephen Galsworthy Slide 7 AI and Machine Learning for the Connected Home with Stephen Galsworthy Slide 8 AI and Machine Learning for the Connected Home with Stephen Galsworthy Slide 9 AI and Machine Learning for the Connected Home with Stephen Galsworthy Slide 10 AI and Machine Learning for the Connected Home with Stephen Galsworthy Slide 11 AI and Machine Learning for the Connected Home with Stephen Galsworthy Slide 12 AI and Machine Learning for the Connected Home with Stephen Galsworthy Slide 13 AI and Machine Learning for the Connected Home with Stephen Galsworthy Slide 14 AI and Machine Learning for the Connected Home with Stephen Galsworthy Slide 15 AI and Machine Learning for the Connected Home with Stephen Galsworthy Slide 16 AI and Machine Learning for the Connected Home with Stephen Galsworthy Slide 17 AI and Machine Learning for the Connected Home with Stephen Galsworthy Slide 18 AI and Machine Learning for the Connected Home with Stephen Galsworthy Slide 19 AI and Machine Learning for the Connected Home with Stephen Galsworthy Slide 20 AI and Machine Learning for the Connected Home with Stephen Galsworthy Slide 21 AI and Machine Learning for the Connected Home with Stephen Galsworthy Slide 22 AI and Machine Learning for the Connected Home with Stephen Galsworthy Slide 23 AI and Machine Learning for the Connected Home with Stephen Galsworthy Slide 24 AI and Machine Learning for the Connected Home with Stephen Galsworthy Slide 25 AI and Machine Learning for the Connected Home with Stephen Galsworthy Slide 26 AI and Machine Learning for the Connected Home with Stephen Galsworthy Slide 27 AI and Machine Learning for the Connected Home with Stephen Galsworthy Slide 28 AI and Machine Learning for the Connected Home with Stephen Galsworthy Slide 29 AI and Machine Learning for the Connected Home with Stephen Galsworthy Slide 30 AI and Machine Learning for the Connected Home with Stephen Galsworthy Slide 31 AI and Machine Learning for the Connected Home with Stephen Galsworthy Slide 32
Upcoming SlideShare
What to Upload to SlideShare
Next
Download to read offline and view in fullscreen.

0 Likes

Share

Download to read offline

AI and Machine Learning for the Connected Home with Stephen Galsworthy

Download to read offline

Quby is the creator and provider of Toon, a leading European smart home platform. We enable Toon users to control and monitor their homes using both an in-home display and app. As a data driven company, we use AI and machine learning to generate actionable insights for our end users. Using the data we collect via our IoT devices we have introduced multiple data driven services, including an energy waste checker and a boiler monitoring service. In this talk, Stephen will describe how AI and machine learning are implemented on the Toon platform, and will show multiple AI use cases relating to the connected home. We’ll take a look at how Deep Learning algorithms are used to detect inefficient appliances from electricity meter data and how streaming algorithms allow users to be alerted to anomalies with their heating systems in near real-time. Stephen will share the experiences from the Data Science and Data Engineering teams at Quby with bringing data science algorithms from R&D to production and the lessons learned in offering multiple data driven services to hundreds of thousands of users on a daily basis.

  • Be the first to like this

AI and Machine Learning for the Connected Home with Stephen Galsworthy

  1. 1. Stephen Galsworthy, Quby AI and Machine Learning for the Connected Home Session hashtag: #SAISAI4
  2. 2. 2004 Home Automation Europe is founded 2012 Home Automation Europe partners with Eneco to create Toon 2013 Home Automation Europe becomes Quby Our history in milestones 2018 launch security service ThuisWacht with Interpolis 2018 Launch Toon2 2006 Home control alternatives are prototyped
  3. 3. 4 Launched in 2016 Launched in 2017 Launched in 2012 Testing phaseOur partners:
  4. 4. SMART THERMOSTAT & APP TOON SOLAR BOILER MONITORINGWASTE CHECKER MONTHLY ENERGY INSIGHT WATER INSIGHT SECURITY PACKAGE & APP SMART METER DONGLE & APP ENERGY INSIGHTS APP DATA SERVICES
  5. 5. Z-Wave Meter adaptor Boiler adapter Gas sensor Philips Hue Z-Wave Central heating system Solar panels Click data Smart plugs & smoke detectors Electricity sensor
  6. 6. 100 MB data per user collected per month Over 350,000 displays installed 300 types of sensor and user interaction data
  7. 7. For production grade algorithms and R&D For machine learning on distributed data - Spark cluster management - Collaboration using shared notebooks - Scheduling complex workflows - Dashboards API management Big data storage and processing Our Data Science platform
  8. 8. Creating data driven services
  9. 9. Feasibility ViabilityDesirability
  10. 10. Traditional billing relationship Historical energy insight Real time information Appliance level diagnostics <4% 4-6% 8-10% 20%+ Maximizing energy savings and customer engagement 1Armel et. al., Stanford University (2011) Increasingengagementbetween customerandutility Increasing energy savings potential1
  11. 11. Energy Waste Checker “We don’t always notice how much energy we’re wasting. Toon can now expose the energy guzzlers in your home.” Launched in December 2017 to all Eneco Toon users
  12. 12. Toon detects inefficient appliances and behaviours & more coming soon
  13. 13. Electricity data Appliance signals Key technology: load disaggregation algorithms
  14. 14. Quby’s disaggregation algorithms DishwasherWashing machine Washing machine(only night hours shown) DryerDryer Patent pending algorithms can detect appliances from 10 second resolution electricity meter data
  15. 15. Quby’s disaggregation algorithms Washing machine Dryer DishwasherDryerWashing machine Washing machine Dryer Dishwasher Dryer But users try to make it complicated for us…
  16. 16. Use case example: Inefficient dishwasher diagnosis Disaggregation algorithms run on the 10s electricity meter data Compared with industry energy consumption standards and peers Translated to personalised advice for the end user Toon determines the “fingerprint” of the appliance through features
  17. 17. Scale of the Waste checker Each day we detect over 75,000dishwasher cycles That’s 13 years of dishwashers running continuously and over 25% are used inefficiently
  18. 18. POP QUIZ Which is the most popular day of the week to do the laundry? ?
  19. 19. It’s Sunday! 5.0 3.7 3.1 3.5 3.3 3.6 4.9 Sunday Monday Tuesday Wednesday Thursday Friday Saturday with 5.0 million of the 27 million washing machine detections we’ve made in 2018 so far
  20. 20. It’s Sunday! k 100k 200k 300k 400k 500k 600k 0 2 4 6 8 10121416182022 0 2 4 6 8 10121416182022 0 2 4 6 8 10121416182022 0 2 4 6 8 10121416182022 0 2 4 6 8 10121416182022 0 2 4 6 8 10121416182022 0 2 4 6 8 10121416182022 Sunday Monday Tuesday Wednesday Thursday Friday Saturday with 5.0 million of the 27 million washing machine detections we’ve made in 2018 so far
  21. 21. Heating system anomaly detection Enhancement to our existing Boiler Monitoring service
  22. 22. 1. Boiler and thermostat data are constantly monitored by Toon 4. Toon user is alerted 2. Toon determines when the system leaves its normal operating range Heating system anomaly detection 3. Severity and user preferences taken into account
  23. 23. Heating system anomaly detection
  24. 24. 5 things we learned
  25. 25. #1: We love Spark Machine learning on distributed data is key to all of this working at scale. An example: Spark’s window functions work great for time series data.
  26. 26. #2: We prefer Scala now Moving from Python to Scala takes effort but it’s worth it. An example: We define our dataset schemas statically. Static typing and type inference in Scala helps enforce these schemas.
  27. 27. #3: We live in the cloud Rather than taking care of the infrastructure, data engineers can concentrate on how to make data available to the business. The Databricks platform gives us cluster timeouts, autoscaling, spot instances… ….all without the need for additional FTEs.
  28. 28. #4: ‘In production’ is not the end Continuous feedback from hundreds of thousands of users means there’s always improvements to make. An example: Our users told us that they wanted more information about their efficient appliances, such as heat pump dryers. We productionized a deep learning model to give them this info.
  29. 29. #5: Full-stack data science rocks! Build and run, from initial concept to end result. Making services that our end users will love. Working together we deliver state-of-the-art algorithms operating at scale in production.
  30. 30. Stephen Galsworthy Head of Data Science +31 (0) 20 462 1680 stephen.galsworthy@quby.com

Quby is the creator and provider of Toon, a leading European smart home platform. We enable Toon users to control and monitor their homes using both an in-home display and app. As a data driven company, we use AI and machine learning to generate actionable insights for our end users. Using the data we collect via our IoT devices we have introduced multiple data driven services, including an energy waste checker and a boiler monitoring service. In this talk, Stephen will describe how AI and machine learning are implemented on the Toon platform, and will show multiple AI use cases relating to the connected home. We’ll take a look at how Deep Learning algorithms are used to detect inefficient appliances from electricity meter data and how streaming algorithms allow users to be alerted to anomalies with their heating systems in near real-time. Stephen will share the experiences from the Data Science and Data Engineering teams at Quby with bringing data science algorithms from R&D to production and the lessons learned in offering multiple data driven services to hundreds of thousands of users on a daily basis.

Views

Total views

690

On Slideshare

0

From embeds

0

Number of embeds

2

Actions

Downloads

28

Shares

0

Comments

0

Likes

0

×