Indoor Air Quality Monitoring System for Smart Buildings Yu Zheng Microsoft Research
Apr 01, 2015
Indoor Air Quality Monitoring System for Smart Buildings
Yu ZhengMicrosoft Research
Outdoor Air QualityAir quality monitor station
S1
S2
S4
S5
S8
S3
S6S7
S6
S9S10
S12
S11
S13 S14
S22S15
S16
S16
S17
S18
S19
S20
S21
50kmx40km
Indoor Air Quality• PM2.5 has NOT been monitored and dealt with• PM2.5 is NOT considered as a factor by HVAC
Problems!
HVAC: Heating, Ventilation, and Air Conditioning
PM2.5: Particulate matter with a diameter < 2.5
What We Do
• Monitor indoor PM2.5 and PM10– In 5 Microsoft Campuses in China– Deploy sensors on different floor of a building
What We Do
• Cloud + Client system
Indoor Air Quality
Data Receiver
Web Service
Cloud
Mobile Apps WebsitesSensors
5 : 0 2 5 : 0 5 5 : 0 8 5 : 1 1 5 : 1 4 5 : 1 7 5 : 2 00
2 5 0 05 0 0 07 5 0 0
1 0 0 0 0
Cou
nt
T i m e
P M 2 . 5
Client• Check air quality anytime• Inform people’s decision making
Urban Air
45
Suggestion to HVAC
• Purification Time (PT)
5:00 5:20 5:40 6:00 6:20 --20
30
40
50
60
70
80
t1
t0
Ind
oo
r P
M2
.5 c
on
ce
ntr
ati
on
(g
/m3 )
Scenario 1 Scenario 2
Time
t2
𝑃𝑇=𝑡1 −𝑡 0
8am7am
0.5h
1.5h
6:30am
• Depends on many factors– Outdoor/indoor air
quality– Meteorological data
80~120min40~80min
0~40min
Indoor/Outdoor
Temperature
Humidity
Pressure
Wind Speed
Suggestion to HVAC
• Learn the purification time from historical data– hourly outdoor air quality data– Hourly meteorological data
Indoor Air Quality
Data Receiver
Web Service
Cloud
Mobile Apps WebsitesSensors
Web Crawler Outdoor
Air quality MeteorologyKnowledge
Mining HVAC
Filters
Suggestion to HVAC
• Predict the purification time based on ANN
PTI
Outdoor AQI
Indoor AQI
Temperature
Humidity
Pressure
Wind Speed
w11
wij
w'11
w'jk
b1
b16
b'1
b'12
C
Suggestion to HVAC
• Replace HVAC’s filter sheet• Gap between the inferred and real PTs
1/17/2014 2/12/2014 2/21/2014 3/6/20140
20
40
60
80
Tim
e o
f p
uri
fic
ati
on
(m
inu
tes
)
Date
Real time PTI
Evaluation
• Data– A real dataset of 150 workdays from 12/23/2013 to 5/9/2014
generated in Beijing campus• Indoor air quality (every 10 minutes)• Hourly outdoor air quality from a monitoring station• Hourly meteorological data
• Baseline – Default: Historical longest time– Average– Linear Regression– ANN: without considering the meteorological data
Data is publicly available
Evaluation
• Results
0.0
0.2
0.4
0.6
0.8
1.0
0.81
1.00
0.55
0.72
Acc
ura
cy
0.87
0.0
0.5
1.0
1.5
2.02.00
0.33 0.33
0.14
Pu
rifi
cati
on
tim
e (H
ou
rs)
PTI ANN Regression Average Deault
0.15
Conclusion
• Deployed a real system in 5 MS campuses• Cloud + Client system– Inform people’s decision making– Suggestion to the operation of HVAC systems
Data, models and mobile client are publicly available ! Yu Zheng
Microsoft [email protected] Air