Supero: A Sensor System for Unsupervised Residential Power Usage - - PowerPoint PPT Presentation

supero
SMART_READER_LITE
LIVE PREVIEW

Supero: A Sensor System for Unsupervised Residential Power Usage - - PowerPoint PPT Presentation

Supero: A Sensor System for Unsupervised Residential Power Usage Monitoring Dennis E. Phillips 1 , Rui Tan 2 ; Mohammad-Mahdi Moazzami 1 ; Guoliang Xing 1 ; Jinzhu Chen 1 ; David K. Y. Yau 2,3 1 Michigan State University, USA 2 Advanced


slide-1
SLIDE 1

A Sensor System for Unsupervised Residential Power Usage Monitoring

Supero:

Dennis E. Phillips1, Rui Tan2; Mohammad-Mahdi Moazzami1; Guoliang Xing1; Jinzhu Chen1; David K. Y. Yau2,3

1Michigan State University, USA 2Advanced Digital Sciences Center, Singapore 3Purdue University, USA

1 / 23

slide-2
SLIDE 2

Outline

  • Motivation & Approach
  • Light Sensing
  • Acoustic Sensing
  • Implementation & Experiments
  • Implementation & Experiments

2 / 23

slide-3
SLIDE 3

Residential Electricity in U.S.

  • Residential electricity

– Largest sector

  • Rising cost

Industrial 25.5% Residential 36.7% Commercial 34.2% Others

  • Rising cost

– Increase by 75% in 10 years

  • Understanding usage

– Real-time power readings – Fine-grained usage info

Electricity retail sales in U.S. 2011 [US EIA-861, EIA-923]

Appl. Joul % When? Bed light 5% 7pm-11pm Fridge 8% Every 1h Space heater 30% Jan 1 … …. …. ….

3 / 23

slide-4
SLIDE 4

Related Work

  • Direct sensing

– ACme [IPSN’09] Per-appliance inline meter, intrusive

[Jiang IPSN’09]

4 / 23

slide-5
SLIDE 5

Related Work

  • Direct sensing

– ACme [IPSN’09] Per-appliance inline meter, intrusive

  • Indirect sensing

[Jiang IPSN’09]

  • Indirect sensing

– At-the-flick [UbiComp’07] High-rate ADC, in-situ training

5 / 23

slide-6
SLIDE 6

Related Work

  • Direct sensing

– ACme [IPSN’09] Per-appliance inline meter, intrusive

  • Indirect sensing

[Jiang IPSN’09]

  • Indirect sensing

– At-the-flick [UbiComp’07] High-rate ADC, in-situ training – ViridiScope [UbiComp’09] Labor-intensive sensor installation

6 / 23

[Kim UbiComp’09]

slide-7
SLIDE 7

Objective & Challenge

  • Fine-grained usage monitoring

– Accurate energy disaggregation – Inexpensive and easy-to-install sensors – Training-free, ad hoc system deployment (“place sensor on shelf facing light to be monitored”) sensor on shelf facing light to be monitored”)

7 / 23

slide-8
SLIDE 8

Objective & Challenge

  • Fine-grained usage monitoring

– Accurate energy disaggregation – Inexpensive and easy-to-install sensors – Training-free, ad hoc system deployment (“place sensor on shelf facing light to be monitored”) sensor on shelf facing light to be monitored”)

  • High-degree sensing uncertainty

– Noises from environment and human activities – Source appliance identification

  • A sensor can sense multiple appliances
  • An appliance can be sensed by multiple sensors

8 / 23

slide-9
SLIDE 9

Supero

Smart meter Base station Light and acoustic sensors 9 / 23 Light + acoustic captures 90% power consumption

slide-10
SLIDE 10

Supero

Smart meter Base station

100W ‘+1’

Light and acoustic sensors

Event Correlation (remove false alarm) Light/acoustic event Power reading

10 / 23 Light + acoustic captures 90% power consumption

slide-11
SLIDE 11

Supero

Smart meter Base station

100W ‘+1’

Light and acoustic sensors

Event Correlation (remove false alarm)

Event clustering

Light/acoustic event Power reading

11 / 23 Light + acoustic captures 90% power consumption

slide-12
SLIDE 12

Supero

Smart meter Base station Event-Appliance Association

100W ‘+1’

Light and acoustic sensors

Event Correlation (remove false alarm)

Event clustering Association

Light/acoustic event Power reading

12 / 23 Light + acoustic captures 90% power consumption

slide-13
SLIDE 13

Supero

Smart meter Base station Event-Appliance Association

100W ‘+1’

Light and acoustic sensors

Event Correlation (remove false alarm)

Event clustering Association

Light/acoustic event Power reading

13 / 23 Light + acoustic captures 90% power consumption

slide-14
SLIDE 14

Outline

  • Motivation & Approach
  • Light Sensing
  • Acoustic Sensing
  • Implementation & Experiments
  • Implementation & Experiments

14 / 23

slide-15
SLIDE 15

Event Detection & Correlation

light sensor reading exponential diff

Time (second)

  • Exponential difference filter

– Diff between long-/short-term moving averages

15 / 23

Time (second)

slide-16
SLIDE 16

Event Detection & Correlation

light sensor reading exponential diff

Time (second)

Light on

Report event

Light off

Report event

  • Exponential difference filter

– Diff between long-/short-term moving averages

16 / 23

Time (second)

Light on

slide-17
SLIDE 17

Event Detection & Correlation

light sensor reading exponential diff

Time (second)

Light on

Report event

Light off

Report event

Human movements

  • Exponential difference filter

– Diff between long-/short-term moving averages

17 / 23

Time (second)

Light on movements

slide-18
SLIDE 18

Event Detection & Correlation

light sensor reading exponential diff

Time (second)

Light on

Report event

Light off

Report event

Human movements

  • Exponential difference filter

– Diff between long-/short-term moving averages

  • Event correlation

– Simultaneous events have same source – False alarm if no power reading change

18 / 23

Time (second)

Light on movements

slide-19
SLIDE 19

Light Event Clustering

Light 1 Light 3 Sensor 1 Sensor 2

  • Feature: change of light intensity

Floor plan Clustering on intensity changes

19 / 23

Sensor 1 Light 2

slide-20
SLIDE 20

Light Event Clustering

Cluster A Cluster B Cluster C Light 1 Light 3 Sensor 1 Sensor 2

  • Feature: change of light intensity

Cluster C Floor plan Clustering on intensity changes

20 / 23

Sensor 1 Light 2

slide-21
SLIDE 21

Light Event Clustering

Cluster A Cluster B Cluster C Light 1 Light 3 Sensor 1 Sensor 2

  • Feature: change of light intensity
  • {Cluster A, B, C} ↔ {Light 1, 2, 3}?

Cluster C Floor plan Clustering on intensity changes

21 / 23

Sensor 1 Light 2

slide-22
SLIDE 22

Power Law Decay of Light

log (measurement) (intensity)

measurement = β power d-α

22 / 23

log (distance from light source) lo

slide-23
SLIDE 23

Power Law Decay of Light

log (measurement) (intensity)

measurement = β power d-α

23 / 23

log (distance from light source) lo distance from light source

slide-24
SLIDE 24

Power Law Decay of Light

log (measurement)

α = 3.5

(intensity)

measurement = β power d-α

24 / 23

log (distance from light source) lo Path loss exponent α ∈ [2, 5] distance from light source

slide-25
SLIDE 25

Power Law Decay of Light

log (measurement)

α = 3.5

(intensity)

measurement = β power d-α

25 / 23

log (distance from light source) lo Path loss exponent α ∈ [2, 5] distance from light source Scaling factor

slide-26
SLIDE 26

Cluster-Light Association

  • Error of associating cluster m and light j

∈ − −

⋅ ⋅ =

m

R i m i j i m j m

d P e

, , ,

µ β

α

26 / 23

Discrepancy between model prediction and observation for sensor i

slide-27
SLIDE 27

Cluster-Light Association

  • Error of associating cluster m and light j

∈ − −

⋅ ⋅ =

m

R i m i j i m j m

d P e

, , ,

µ β

α

  • bserved intensity

change of sensor i in cluster m

27 / 23

Discrepancy between model prediction and observation for sensor i

slide-28
SLIDE 28

Cluster-Light Association

  • Error of associating cluster m and light j

∈ − −

⋅ ⋅ =

m

R i m i j i m j m

d P e

, , ,

µ β

α

  • bserved intensity

change of sensor i in cluster m model-predicted intensity change of sensor i

28 / 23

Discrepancy between model prediction and observation for sensor i

slide-29
SLIDE 29

Cluster-Light Association

  • Error of associating cluster m and light j

∈ − −

⋅ ⋅ =

m

R i m i j i m j m

d P e

, , ,

µ β

α

  • bserved intensity

change of sensor i in cluster m model-predicted intensity change of sensor i sensors that can detect event in cluster m

29 / 23

Discrepancy between model prediction and observation for sensor i

slide-30
SLIDE 30

Cluster-Light Association

  • Error of associating cluster m and light j

∈ − −

⋅ ⋅ =

m

R i m i j i m j m

d P e

, , ,

µ β

α

  • bserved intensity

change of sensor i in cluster m model-predicted intensity change of sensor i sensors that can detect event in cluster m

30 / 23

Discrepancy between model prediction and observation for sensor i Light 1 (50W) Light 2 (50W) Sensor 1

slide-31
SLIDE 31

Cluster-Light Association

  • Error of associating cluster m and light j

∈ − −

⋅ ⋅ =

m

R i m i j i m j m

d P e

, , ,

µ β

α

  • bserved intensity

change of sensor i in cluster m model-predicted intensity change of sensor i sensors that can detect event in cluster m

31 / 23

Discrepancy between model prediction and observation for sensor i Light 1 (50W) Light 2 (50W)

Intensity change

  • f sensor 1

Sensor 1 Cluster 1 Cluster 2 P1 = 49W P2 = 52W

slide-32
SLIDE 32

Cluster-Light Association

  • Error of associating cluster m and light j

∈ − −

⋅ ⋅ =

m

R i m i j i m j m

d P e

, , ,

µ β

α

  • bserved intensity

change of sensor i in cluster m model-predicted intensity change of sensor i sensors that can detect event in cluster m

32 / 23

Discrepancy between model prediction and observation for sensor i Light 1 (50W) Light 2 (50W)

Intensity change

  • f sensor 1

Sensor 1 Cluster 1 Cluster 2 P1 = 49W P2 = 52W

em,j

Light 1 Light 2 Cluster 1 3000 100 Cluster 2 110 4000

slide-33
SLIDE 33

Cluster-Light Association

  • Error of associating cluster m and light j

∈ − −

⋅ ⋅ =

m

R i m i j i m j m

d P e

, , ,

µ β

α

  • bserved intensity

change of sensor i in cluster m model-predicted intensity change of sensor i sensors that can detect event in cluster m

33 / 23

Discrepancy between model prediction and observation for sensor i Light 1 (50W) Light 2 (50W)

Intensity change

  • f sensor 1

Sensor 1 Cluster 1 Cluster 2 P1 = 49W P2 = 52W

em,j

Light 1 Light 2 Cluster 1 3000 100 Cluster 2 110 4000

slide-34
SLIDE 34

Cluster-Light Association (cont’d)

  • For given light decay model, find a binary matrix [am,j]

∑ ∑ ∑

∀ ∀

⋅ =

j m j m j m

e a E ) , ( min

, , ,

β α

am,j=1: cluster m is associated with light j

34 / 42

∑ ∑

∀ ∀

= =

j j m m j m

a a 1 , 1 s.t.

, ,

slide-35
SLIDE 35

Cluster-Light Association (cont’d)

  • For given light decay model, find a binary matrix [am,j]

∑ ∑ ∑

∀ ∀

⋅ =

j m j m j m

e a E ) , ( min

, , ,

β α

Total association error

am,j=1: cluster m is associated with light j

35 / 42

∑ ∑

∀ ∀

= =

j j m m j m

a a 1 , 1 s.t.

, ,

slide-36
SLIDE 36

Cluster-Light Association (cont’d)

  • For given light decay model, find a binary matrix [am,j]

∑ ∑ ∑

∀ ∀

⋅ =

j m j m j m

e a E ) , ( min

, , ,

β α

Total association error

am,j=1: cluster m is associated with light j

36 / 42

∑ ∑

∀ ∀

= =

j j m m j m

a a 1 , 1 s.t.

, ,

One-to-one mapping

slide-37
SLIDE 37

Cluster-Light Association (cont’d)

  • For given light decay model, find a binary matrix [am,j]

∑ ∑ ∑

∀ ∀

⋅ =

j m j m j m

e a E ) , ( min

, , ,

β α

Total association error

am,j=1: cluster m is associated with light j

– Hungarian algorithm

37 / 42

∑ ∑

∀ ∀

= =

j j m m j m

a a 1 , 1 s.t.

, ,

One-to-one mapping

slide-38
SLIDE 38

Cluster-Light Association (cont’d)

  • For given light decay model, find a binary matrix [am,j]

∑ ∑ ∑

∀ ∀

⋅ =

j m j m j m

e a E ) , ( min

, , ,

β α

Total association error

am,j=1: cluster m is associated with light j

– Hungarian algorithm

  • Iterate α and β to further minimize E(α, β)

– Adaptively calibrate environment-dependent α and β

38 / 42

∑ ∑

∀ ∀

= =

j j m m j m

a a 1 , 1 s.t.

, ,

One-to-one mapping

slide-39
SLIDE 39

Outline

  • Motivation & Approach
  • Light Sensing
  • Acoustic Sensing
  • Implementation & Experiments
  • Implementation & Experiments

39 / 23

slide-40
SLIDE 40

Adaptive Acoustic Sampling

Signal energy

Slow sampling (1 KHz)

Signal energy > T1 Signal energy

Signal energy # zero crossings

base station

Fast sampling (12 KHz)

Signal energy < T2

40 / 23

Low pass Band pass High pass

slide-41
SLIDE 41

Clustering-based Event Detection

  • Multiple phases (fan, microwave)

– Unknown and unpredictable

  • K-means clustering

– Automatically identify K

scatter cluster within scatter cluster between max

41 / 23

slide-42
SLIDE 42

Clustering-based Event Detection

  • Multiple phases (fan, microwave)

– Unknown and unpredictable

  • K-means clustering

– Automatically identify K

scatter cluster within scatter cluster between max

Detect the phase changes of 3-speed fan

42 / 23

Acoustic feature

slide-43
SLIDE 43

Clustering-based Event Detection

  • Multiple phases (fan, microwave)

– Unknown and unpredictable

  • K-means clustering

– Automatically identify K

scatter cluster within scatter cluster between max

Detect the phase changes of 3-speed fan

43 / 23

Acoustic feature metric

slide-44
SLIDE 44

Clustering-based Event Detection

  • Multiple phases (fan, microwave)

– Unknown and unpredictable

  • K-means clustering

– Automatically identify K

scatter cluster within scatter cluster between max

Detect the phase changes of 3-speed fan

44 / 23

Acoustic feature metric K=3

slide-45
SLIDE 45

Outline

  • Motivation & Approach
  • Light Sensing
  • Acoustic Sensing
  • Implementation & Experiments
  • Implementation & Experiments

45 / 23

slide-46
SLIDE 46

Implementation & Deployments

TelosB (light) Iris (acoustic) Kill-A-Watt Apartment-1 deployment

  • System

– TelosB/Iris + TED5000 + KAW ground truth meters

  • Five deployments

– Three apartments (40~150 m2), two houses – 9 ~ 22 sensors

Iris (acoustic) Kill-A-Watt Apartment-1 deployment

46 / 23

slide-47
SLIDE 47

Supero in Action

  • Video demonstrating installation and setup

47 / 23

slide-48
SLIDE 48

Evaluation

  • 10 days experiment in Apartment-1
  • Impact of sensor deployment in Apartment-2
  • Compare with ViridiScope [UbiComp’09]

(Regression on appliance states + power readings)

– Oracle: ground truth appliance states – Oracle: ground truth appliance states – Baseline: closest appliance is source

48 / 23

slide-49
SLIDE 49

10-day Results

Appliance Supero Oracle Baseline kWh Error (%) kWh Error (%) kWh Error (%) Light 1 4.17 0.5 4.11 0.9 4.11 0.9 Light 2 4.96 0.1 4.92 0.8 4.92 0.8 Light 3 6.24 1.4 6.25 1.7 6.25 1.7 Light 4 1.45 0.1 1.45 0.1 1.48 1.7 Light 5 0.39 0.2 0.39 0.7 0.41 5.5 Water boiler 0.48 0.5 0.48 0.5 100 Tower fan 0.21 50 0.17 17.9 0.24 66.2

  • Supero

– All 146 light events detected, no false alarm, no miss 49 / 23

Rice cooker 0.98 2.2 1.01 1.2 1.01 0.8 Hair dryer 0.07 19.2 0.09 0.4 0.02 73.2 Fridge 11.8 3.7 11.8 3.2 11.8 3.2 Bath fan 0.12 N/A 0.17 N/A N/A Router 2.03 4.3 3.04 43.3 3.04 43.3 Average error 7.5 6.5 27.0

slide-50
SLIDE 50

10-day Results

Appliance Supero Oracle Baseline kWh Error (%) kWh Error (%) kWh Error (%) Light 1 4.17 0.5 4.11 0.9 4.11 0.9 Light 2 4.96 0.1 4.92 0.8 4.92 0.8 Light 3 6.24 1.4 6.25 1.7 6.25 1.7 Light 4 1.45 0.1 1.45 0.1 1.48 1.7 Light 5 0.39 0.2 0.39 0.7 0.41 5.5 Water boiler 0.48 0.5 0.48 0.5 100 Tower fan 0.21 50 0.17 17.9 0.24 66.2

  • Supero

– All 146 light events detected, no false alarm, no miss – Comparable to Oracle 50 / 23

Rice cooker 0.98 2.2 1.01 1.2 1.01 0.8 Hair dryer 0.07 19.2 0.09 0.4 0.02 73.2 Fridge 11.8 3.7 11.8 3.2 11.8 3.2 Bath fan 0.12 N/A 0.17 N/A N/A Router 2.03 4.3 3.04 43.3 3.04 43.3 Average error 7.5 6.5 27.0

slide-51
SLIDE 51

10-day Results

Appliance Supero Oracle Baseline kWh Error (%) kWh Error (%) kWh Error (%) Light 1 4.17 0.5 4.11 0.9 4.11 0.9 Light 2 4.96 0.1 4.92 0.8 4.92 0.8 Light 3 6.24 1.4 6.25 1.7 6.25 1.7 Light 4 1.45 0.1 1.45 0.1 1.48 1.7 Light 5 0.39 0.2 0.39 0.7 0.41 5.5 Water boiler 0.48 0.5 0.48 0.5 100 Tower fan 0.21 50 0.17 17.9 0.24 66.2

  • Supero

– All 146 light events detected, no false alarm, no miss – Comparable to Oracle

  • Baseline: False alarms caused by hair dryer and bath fan

51 / 23

Rice cooker 0.98 2.2 1.01 1.2 1.01 0.8 Hair dryer 0.07 19.2 0.09 0.4 0.02 73.2 Fridge 11.8 3.7 11.8 3.2 11.8 3.2 Bath fan 0.12 N/A 0.17 N/A N/A Router 2.03 4.3 3.04 43.3 3.04 43.3 Average error 7.5 6.5 27.0

slide-52
SLIDE 52

Impact of Sensor Placement

52 / 23

6 lights, exhaust fan, waste disposer dish washer, vacuum cleaner 6 TelosB, 11 Iris

slide-53
SLIDE 53

Impact of Sensor Placement

Deployment Sensor # result Red 6

  • Green

6

  • Blue

4

  • Yellow

4

  • Black

3

  • Light sensing

Black 3

  • 53 / 23

6 lights, exhaust fan, waste disposer dish washer, vacuum cleaner 6 TelosB, 11 Iris

slide-54
SLIDE 54

Impact of Sensor Placement

Deployment Sensor # result Red 6

  • Green

6

  • Blue

4

  • Yellow

4

  • Black

3

  • Light sensing

Black 3

  • 54 / 23

6 lights, exhaust fan, waste disposer dish washer, vacuum cleaner 6 TelosB, 11 Iris

slide-55
SLIDE 55

Impact of Sensor Placement

Deployment Sensor # result Red 6

  • Green

6

  • Blue

4

  • Yellow

4

  • Black

3

  • Light sensing

Black 3

  • 55 / 23

6 lights, exhaust fan, waste disposer dish washer, vacuum cleaner 6 TelosB, 11 Iris

slide-56
SLIDE 56

Impact of Sensor Placement

Deployment Sensor # result Red 6

  • Green

6

  • Blue

4

  • Yellow

4

  • Black

3

  • Light sensing

Black 3

  • 56 / 23

6 lights, exhaust fan, waste disposer dish washer, vacuum cleaner 6 TelosB, 11 Iris

slide-57
SLIDE 57

Impact of Sensor Placement

Deployment Sensor # result Red 6

  • Green

6

  • Blue

4

  • Yellow

4

  • Black

3

  • Light sensing

Black 3

  • 57 / 23

6 lights, exhaust fan, waste disposer dish washer, vacuum cleaner 6 TelosB, 11 Iris

slide-58
SLIDE 58

Impact of Sensor Placement

Deployment Sensor # result Red 6

  • Green

6

  • Blue

4

  • Yellow

4

  • Black

3

  • Light sensing

Black 3

  • 58 / 23

6 lights, exhaust fan, waste disposer dish washer, vacuum cleaner 6 TelosB, 11 Iris

slide-59
SLIDE 59

Impact of Sensor Placement

Deployment Sensor # result Red 6

  • Green

6

  • Blue

4

  • Yellow

4

  • Black

3

  • Light sensing

Black 3

  • 59 / 23

6 lights, exhaust fan, waste disposer dish washer, vacuum cleaner 6 TelosB, 11 Iris Deployment Sensor # result Red 11

  • Green

7

  • Blue

4

  • Black

2

  • Acoustic sensing
slide-60
SLIDE 60

Impact of Sensor Placement

Deployment Sensor # result Red 6

  • Green

6

  • Blue

4

  • Yellow

4

  • Black

3

  • Light sensing

Black 3

  • 60 / 23

6 lights, exhaust fan, waste disposer dish washer, vacuum cleaner 6 TelosB, 11 Iris Deployment Sensor # result Red 11

  • Green

7

  • Blue

4

  • Black

2

  • Acoustic sensing
slide-61
SLIDE 61

Impact of Sensor Placement

Deployment Sensor # result Red 6

  • Green

6

  • Blue

4

  • Yellow

4

  • Black

3

  • Light sensing

Black 3

  • 61 / 23

6 lights, exhaust fan, waste disposer dish washer, vacuum cleaner 6 TelosB, 11 Iris Deployment Sensor # result Red 11

  • Green

7

  • Blue

4

  • Black

2

  • Acoustic sensing
slide-62
SLIDE 62

Impact of Sensor Placement

Deployment Sensor # result Red 6

  • Green

6

  • Blue

4

  • Yellow

4

  • Black

3

  • Light sensing

Black 3

  • 62 / 23

6 lights, exhaust fan, waste disposer dish washer, vacuum cleaner 6 TelosB, 11 Iris Deployment Sensor # result Red 11

  • Green

7

  • Blue

4

  • Black

2

  • Acoustic sensing
slide-63
SLIDE 63

Impact of Sensor Placement

Deployment Sensor # result Red 6

  • Green

6

  • Blue

4

  • Yellow

4

  • Black

3

  • Light sensing

Black 3

  • 63 / 23

6 lights, exhaust fan, waste disposer dish washer, vacuum cleaner 6 TelosB, 11 Iris Deployment Sensor # result Red 11

  • Green

7

  • Blue

4

  • Black

2

  • Acoustic sensing
slide-64
SLIDE 64

Conclusion

  • Supero

– Multi-sensor fusion – Unsupervised event clustering – Autonomous appliance association

  • Easy to install

– Considerable flexibility in sensor placement

  • Real Implementation/Evaluation

– 5 environments (3 apartments, 2 houses) – Accurate, 7.5% average error

64 / 23

slide-65
SLIDE 65

Q & A

65 / 23