Smart thermometer-niek

Preview:

Citation preview

Making your own smart ‘machine learning’ thermostat

Data Donderdag – 19 november 2015 – Niek Temme

Arduino +

XBee

RaspPI +

XBee

AWS HBase Spark

Boiler

Quirky needs your Wink Hub back after a botched security update - CNET -

18 – 50 billion connected devices by 2020 - Gartner, IDC, Cisco -

device hub cloud

Arduino +

XBee

RaspPI +

XBee

AWS HBase Spark

Boiler

Quirky needs your Wink Hub back after a botched security update - CNET -

18 – 50 billion connected devices by 2020 - Gartner, IDC, Cisco -

device hub cloud

Device Connection Cloud

- Storage

- Analitics

How Smart, Connected Products Are Transforming Companies Michael E. Porter James E. Heppelmann

oktober2015

The device

2

3

4

1

2

3

4

1 A01_1933 A01_1933 A01_1982 A01_1982 A01_1933 A01_1884 A01_1933 A01_1982 A01_1933

40b5af00_rx000A01_8574094222_9670832 column=fd:cd, timestamp=1425905812807, value=1933 40b5af00_rx000A01_8574094222_9796804 column=fd:cd, timestamp=1425905812807, value=1933 40b5af00_rx000A01_8574094222_9919598 column=fd:cd, timestamp=1425905812807, value=1982 40b5af00_rx000A01_8574094223_9043289 column=fd:cd, timestamp=1425905812807, value=1982 40b5af00_rx000A01_8574094223_9166720 column=fd:cd, timestamp=1425905812807, value=1933 40b5af00_rx000A01_8574094223_9294077 column=fd:cd, timestamp=1425905812807, value=1884 40b5af00_rx000A01_8574094223_9416375 column=fd:cd, timestamp=1425905812807, value=1933 40b5af00_rx000A01_8574094223_9540631 column=fd:cd, timestamp=1425905812807, value=1982 40b5af00_rx000A01_8574094223_9669088 column=fd:cd, timestamp=1425905812807, value=1933

Connection & Storage

3sensors1000valuesperscecond

Inoneyear31bilionrows+/-800GB

? Analytics

increase maintain

6 1 2 3 4 5 1 2 3 4 5 6

Smart Temp - Sensor value - 2015-03-19

8

10

12

14

16

18

20

0 10 20 30 40 50 60

Tempe

rature°C

Minutes

Acttemp

Settemp

Making it smart

00:00 00:10 00:30 00:20 00:40 00:50 01:00

6 min 5 min 4 min 3 min 2 min 2 min

Making it smart

Score score =

( [number of times boiler goes on] * 10 * 60 ) + ( [total minutes boiler is on] * 2 ) + ( absolute( [maximum reached temperature] – [set temperature] ) ) + ( if([overshoot]=true ) then 3600 else 0 )

00:00 00:10 00:30 00:20 00:40 00:50 01:00

4 min 4 min 4 min 3 min 3 min 2 min

00:00 00:10 00:30 00:20 00:40 00:50 01:00

2 min 2 min 2 min off off off

scenario tempdif: 7 ℃ outempdif: 8 ℃

initial

improved

k-meansclustering

Thank you

questions or feedback? http://niektemme.com/2015/08/09/smart-thermostat/ niektemme@gmail.com @niektemme linkedin.com/in/niektemme

EXTRA SLIDES

•  1000 values per second

•  Why 1000?

•  Solved with in-memory database

Arduino +

XBee

RaspPI +

XBee

AWS HBase Spark

Boiler

2 3 4

5 6 7

Arduino +

XBee

RaspPI +

XBee

AWS HBase Spark

Boiler

Quirky needs your Wink Hub back after a botched security update - CNET -

18 – 50 billion connected devices by 2020 - Gartner, IDC, Cisco -

Arduino +

XBee

RaspPI +

XBee

AWS HBase Spark

Boiler

2 3 4

5 6 7

I II III

Making your own smart ‘machine learning’ thermostat using

Arduino, AWS, HBase, Spark, Raspberry PI and XBee

niektemme.com/2015/08/09/smart-thermostat

Arduino +

XBee

RaspPI +

XBee

AWS HBase Spark

Boiler

2 3 4

5 6 7

I II III

Arduino +

XBee

RaspPI +

XBee

AWS HBase Spark

Boiler

2 3 4

5 6 7

I II III

Start with ‘IoT’

Used scenario •  Scenario = pattern of six 10 minute intervals

For example 5 4 3 2 2 2

•  The tempdif = (set – inside) temperature

•  The outtempdif = (set – outside) temperature

•  Raspberry PI selects (given a tempdif and outtempdiff) –  50% of the time: best temperature scenario –  50% of the time: alternative scenario

•  Used scenario and tempdif and outtempdiff used to select this scenario are uploaded to the server.

Making it smart

Minutesperrun–maintainroomtemperature Minutesperrun–maintainroomtemperature(alternaKve)

Two step process

A. Score each used scenario

B. Cluster and rank scenarios in each cluster

B. Cluster and select

Making it smart

8

10

12

14

16

18

20

0 10 20 30 40 50 60

Tempe

rature°C

Minutes

Acttemp

Settemp

8

10

12

14

16

18

20

0 10 20 30 40 50 60

Tempe

rature°C

Minutes

Acttemp

Settemp

Arduino +

XBee

RaspPI +

XBee

AWS HBase Spark

Boiler

2 3 4

5 6 7

I II III

00:00 00:10 00:30 00:20 00:40 00:50 01:00

6 min 5 min 4 min 3 min 2 min 2 min

6 1 2 3 4 5 1 2 3 4 5 6

increase maintain

8

10

12

14

16

18

20

0 10 20 30 40 50 60

Tempe

rature°C

Minutes

Acttemp

Settemp

Making it smart

00:00 00:10 00:30 00:20 00:40 00:50 01:00

6 min 6 min 6 min 2 min off 2 min

Arduino +

XBee

RaspPI +

XBee

AWS HBase Spark

Boiler

Device Connection Cloud

- Storage

- Analitics

How Smart, Connected Product Are Transforming Companies Michael E. Porter James E. Heppelmann

oktober2015

Personal journey

Recommended