buildsys15

If you can measure it, can you improve it? Exploring the value of energy disaggregation

Transcript

1. Nipun Batra, Amarjeet Singh, Kamin Whitehouse Buildsys 2015 If You Measure It, Can You Improve It? Exploring The Value of Energy Disaggregation through actionable feedback 1
2. General eco feedback vs Actionable Feedback Eco feedback Misc. 22% Light 10% Fridge 11% HVAC 56%
3. General eco feedback vs Actionable Feedback Eco feedback Misc. 22% Light 10% Fridge 11% HVAC 56%
4. General eco feedback vs Actionable Feedback Eco feedback Misc. 22% Light 10% Fridge 11% HVAC 56% Power (W) 0 175 350 525 700 Power (W) 0 175 350 525 700 Home 1 Home 2 Actionable feedback Fridge consumption over 24 hours Misc. 22% Light 10% Fridge 11% HVAC 56%
5. General eco feedback vs Actionable Feedback Eco feedback Misc. 22% Light 10% Fridge 11% HVAC 56% Power (W) 0 175 350 525 700 Power (W) 0 175 350 525 700 Home 1 Home 2 Actionable feedback Fridge consumption over 24 hours Misc. 22% Light 10% Fridge 11% HVAC 56% High power state
6. General eco feedback vs Actionable Feedback Eco feedback Misc. 22% Light 10% Fridge 11% HVAC 56% Power (W) 0 175 350 525 700 Power (W) 0 175 350 525 700 Home 1 Home 2 Actionable feedback Fridge consumption over 24 hours Misc. 22% Light 10% Fridge 11% HVAC 56% High power state High power state
7. General eco feedback vs Actionable Feedback Eco feedback Misc. 22% Light 10% Fridge 11% HVAC 56% Power (W) 0 175 350 525 700 Home 2 Actionable feedback Fridge consumption over 24 hours Your fridge defrosts too much, wasting 30% energy Misc. 22% Light 10% Fridge 11% HVAC 56%
8. Approach overview- How to give feedback Power (W) 0 175 350 525 700 Specific features of trace to infer why energy usage is high Length of duty cycles
9. Approach overview- How to give feedback Power (W) 0 175 350 525 700 Specific features of trace to infer why energy usage is high Actual power value
10. Feedback methods on Fridge and HVAC Both appliances commonly found across homes Others 38% Fridge 8% HVAC 54%
11. Evaluation overview Submetered traces Power (W) 0 350 700 Submeter sensor
12. Can we give such feedback? Disaggregated traces Power (W) 0 350 700 NILM Household aggregate Submetered traces Power (W) 0 350 700 Submeter sensor 0 2000 4000 0 2000 4000 Smart meter
13. Do disaggregated traces provide features needed for providing feedback? Disaggregated traces Power (W) 0 350 700 NILM Household aggregate Submetered traces Power (W) 0 350 700 Submeter sensor 0 2000 4000 0 2000 4000 Smart meter
14. 0 125 250 375 500 Fridge is a duty cycle based appliance; compressor turns ON and OFF periodically
15. Defrost cycles occurs periodically and consume high amount of power 0 125 250 375 500
16. 0 125 250 375 500 Defrost introduces heat increasing ON duration of next cycles
17. Fridge usage increases compressor ON durations (and reduce compressor OFF durations) 0 125 250 375 500
18. Night hours typically have “baseline” usage 0 175 350 525 700 Baseline duty % = Median duty % in the night
19. Defrost energy 0 175 350 525 700 Defrost energy = Energy consumed in defrost state + Extra energy consumed in next few compressor cycles
20. Defrost energy 0 175 350 525 700 Defrost energy = Energy consumed in defrost state + Extra energy consumed in next few compressor cycles
21. Usage energy 0 175 350 525 700 Usage energy = Extra energy consumed over baseline
22. Experimental setup Wiki Energy data set 1. 97 fridges 2. 58 HVAC
23. 13 out of 95 homes can be given feedback based on usage energy saving upto 23% fridge energy
24. 13 out of 95 homes can be given feedback based on usage energy saving upto 23% fridge energy NILM algorithms show poor accuracy in identifying homes which can be given feedback based on usage energy
25. 17 out of 95 homes can be given feedback on excess defrost saving upto 25% fridge energy
26. Such feedback can’t be given with disaggregated traces, since these techniques fare poorly on defrost detection.
27. Benchmark NILM algorithms on our data set give accuracy comparable or better than state-of-the-art Kolter 2012 Parson 2012 Parson 2014 Batra 2014 CO FHMM Hart Error Energy % 0 17.5 35 52.5 70
28. 0 125 250 375 500 “Average” error in energy would be low even if NILM predicted this
29. But, we wanted to predict.. 0 125 250 375 500
30. It’s the details that we care about 0 125 250 375 500
31. Like fridge, HVAC duty cycles to maintain the set temperature 0 1000 2000 3000 4000
32. As temperature increases during the day, more energy required to cool the home 0 1000 2000 3000 4000
33. 0 1000 2000 3000 4000 People typically turn up the temperatures when they leave home
34. Recommended Min. Temp (F) 77 79 81 83 85 2 4 6 8 10 12 14 16 18 20 22 24 EnergyStar.gov recommended HVAC setpoint schedule Sleep Morning Work Evening
35. Recommended Min. Temp (F) 77 79 81 83 85 2 4 6 8 10 12 14 16 18 20 22 24 Setpoint schedule score Sleep Morning Work Evening
36. Recommended Min. Temp (F) 77 79 81 83 85 2 4 6 8 10 12 14 16 18 20 22 24 Setpoint schedule score Sleep Sleep score = 1 if sleep temp. > 82, (82-temp.)/4 if 78<sleep temp. <82 0 otherwise
37. Learning HVAC setpoint 0 1000 2000 3000 4000 77 85 5 1015 20 HVAC trace Weather Learnt setpoint
38. Giving feedback 77 85 5 1015 20 Features from HVAC trace 69 75 5 10 15 20 0 1000 2000 3000 4000 77 85 5 10 15 20 Learnt setpoint Don’t need feedback Need feedback
39. 84% accuracy on giving feedback using submetered traces 39
40. NILM methods give 15-30% worse accuracy for feedback 40
41. Benchmark NILM algorithms on our data set give accuracy comparable or better than state-of-the-art Batra 2014 CO FHMM Hart Error Energy % 0 7.5 15 22.5 30
42. Error in prediction of minutes of HVAC usage (%) 0 6 12 18 24 Hart FHMM CO Night Morning Morning hours which have lesser NILM accuracy are important for HVAC feedback
43. Conclusions Appliance level data does enable actionable energy saving feedback
44. Conclusions Appliance level data does enable actionable energy saving feedback BUT Results show that we need to revisit the metrics by which we measures progress