data science and predictive analytics in virtual …...data science and predictive analytics in...
TRANSCRIPT
![Page 1: Data science and predictive analytics in virtual …...Data science and predictive analytics in virtual power plant environment Piotr Szeląg, PhD Sebastian Dudzik, prof. CUT Częstochowa](https://reader033.vdocuments.us/reader033/viewer/2022060211/5f04d7147e708231d40ff88e/html5/thumbnails/1.jpg)
EMEA USERS CONFERENCE 2017 LONDON #OSISOFTUC ©2017 OSIsoft, LLC
Presented by
Data science and
predictive analytics in
virtual power plant
environment
Piotr Szeląg, PhD
Sebastian Dudzik, prof. CUT
Częstochowa University of Technology
![Page 2: Data science and predictive analytics in virtual …...Data science and predictive analytics in virtual power plant environment Piotr Szeląg, PhD Sebastian Dudzik, prof. CUT Częstochowa](https://reader033.vdocuments.us/reader033/viewer/2022060211/5f04d7147e708231d40ff88e/html5/thumbnails/2.jpg)
EMEA USERS CONFERENCE 2017 LONDON #OSISOFTUC ©2017 OSIsoft, LLC
Presentation Agenda
• Virtual Power Plant at Faculty of Electrical Engineering
– Idea
– Assets
– PI System in VPP
• Data science and predictive analytics
• Methodology of data analysis
• Results of data analysis
• Conclusion and next steps
2
![Page 3: Data science and predictive analytics in virtual …...Data science and predictive analytics in virtual power plant environment Piotr Szeląg, PhD Sebastian Dudzik, prof. CUT Częstochowa](https://reader033.vdocuments.us/reader033/viewer/2022060211/5f04d7147e708231d40ff88e/html5/thumbnails/3.jpg)
EMEA USERS CONFERENCE 2017 LONDON #OSISOFTUC ©2017 OSIsoft, LLC
Vitrual Power Plant - Idea
• A group of producers, consumers
• Control and monitoring system (PI
System)
• Predicting demand/production of
electric energy
• Balancing inside group
• Connecting with electric network
3
![Page 4: Data science and predictive analytics in virtual …...Data science and predictive analytics in virtual power plant environment Piotr Szeląg, PhD Sebastian Dudzik, prof. CUT Częstochowa](https://reader033.vdocuments.us/reader033/viewer/2022060211/5f04d7147e708231d40ff88e/html5/thumbnails/4.jpg)
EMEA USERS CONFERENCE 2017 LONDON #OSISOFTUC ©2017 OSIsoft, LLC
VPP in Czestochowa - assets
photovoltaic panels
4
wind turbines
energy storages
smart meters
weather station
air quality sensors
![Page 5: Data science and predictive analytics in virtual …...Data science and predictive analytics in virtual power plant environment Piotr Szeląg, PhD Sebastian Dudzik, prof. CUT Częstochowa](https://reader033.vdocuments.us/reader033/viewer/2022060211/5f04d7147e708231d40ff88e/html5/thumbnails/5.jpg)
EMEA USERS CONFERENCE 2017 LONDON #OSISOFTUC ©2017 OSIsoft, LLC
VPP in Czestochowa – real time computer system
5
OPC
UFL
VP
P A
SS
ET
S
Matlab
![Page 6: Data science and predictive analytics in virtual …...Data science and predictive analytics in virtual power plant environment Piotr Szeląg, PhD Sebastian Dudzik, prof. CUT Częstochowa](https://reader033.vdocuments.us/reader033/viewer/2022060211/5f04d7147e708231d40ff88e/html5/thumbnails/6.jpg)
EMEA USERS CONFERENCE 2017 LONDON #OSISOFTUC ©2017 OSIsoft, LLC
PI System in VPP
6
![Page 7: Data science and predictive analytics in virtual …...Data science and predictive analytics in virtual power plant environment Piotr Szeląg, PhD Sebastian Dudzik, prof. CUT Częstochowa](https://reader033.vdocuments.us/reader033/viewer/2022060211/5f04d7147e708231d40ff88e/html5/thumbnails/7.jpg)
EMEA USERS CONFERENCE 2017 LONDON #OSISOFTUC ©2017 OSIsoft, LLC
PI System in VPP
7
Examples of analyses
PI Asset Framework
in
![Page 8: Data science and predictive analytics in virtual …...Data science and predictive analytics in virtual power plant environment Piotr Szeląg, PhD Sebastian Dudzik, prof. CUT Częstochowa](https://reader033.vdocuments.us/reader033/viewer/2022060211/5f04d7147e708231d40ff88e/html5/thumbnails/8.jpg)
EMEA USERS CONFERENCE 2017 LONDON #OSISOFTUC ©2017 OSIsoft, LLC
Balancing/veryfication of electricity consumption
8
• Ability to balance logically coherent
items:
o Area
o Building
• Localisation of illegal energy
consumption sources
• Identification of abnormal behaviours
• Detecting change in the profile of
electricity consumption
![Page 9: Data science and predictive analytics in virtual …...Data science and predictive analytics in virtual power plant environment Piotr Szeląg, PhD Sebastian Dudzik, prof. CUT Częstochowa](https://reader033.vdocuments.us/reader033/viewer/2022060211/5f04d7147e708231d40ff88e/html5/thumbnails/9.jpg)
EMEA USERS CONFERENCE 2017 LONDON #OSISOFTUC ©2017 OSIsoft, LLC
Energy balance of a building
9
Cold water aggregate
Floor 5
Floor 4
Floor 3
Floor 2
Floor 1
Garage
Pavilion F The total from the meters is smaller
than the readings from pavillion’s
main meter
Illegal eletcric
energy
consumption?
Consumption between the main
meter and the other meters – the
lift
Cold water aggregate
Floor 5
Floor 4
Floor 3
Floor 2
Floor 1
Garage, floor 1 & 2
Balance [kWh]: 807,88 Pavillion F
![Page 10: Data science and predictive analytics in virtual …...Data science and predictive analytics in virtual power plant environment Piotr Szeląg, PhD Sebastian Dudzik, prof. CUT Częstochowa](https://reader033.vdocuments.us/reader033/viewer/2022060211/5f04d7147e708231d40ff88e/html5/thumbnails/10.jpg)
EMEA USERS CONFERENCE 2017 LONDON #OSISOFTUC ©2017 OSIsoft, LLC
Monitoring - PI Coresight
10
![Page 11: Data science and predictive analytics in virtual …...Data science and predictive analytics in virtual power plant environment Piotr Szeląg, PhD Sebastian Dudzik, prof. CUT Częstochowa](https://reader033.vdocuments.us/reader033/viewer/2022060211/5f04d7147e708231d40ff88e/html5/thumbnails/11.jpg)
EMEA USERS CONFERENCE 2017 LONDON #OSISOFTUC ©2017 OSIsoft, LLC
Optimum tariff choice (customer)
11
Customer’s ability to:
• Plan electricity consumption (e.g. during lectures)
• Choose an optimum tariff
• Use of stored energy
• Forecast production / consumption of electricity
![Page 12: Data science and predictive analytics in virtual …...Data science and predictive analytics in virtual power plant environment Piotr Szeląg, PhD Sebastian Dudzik, prof. CUT Częstochowa](https://reader033.vdocuments.us/reader033/viewer/2022060211/5f04d7147e708231d40ff88e/html5/thumbnails/12.jpg)
EMEA USERS CONFERENCE 2017 LONDON #OSISOFTUC ©2017 OSIsoft, LLC
Data science and predictive analytics
• Computer science
• Math & statistics
• Machine learning
• Domain knowledge
• Predicting the future
12
![Page 13: Data science and predictive analytics in virtual …...Data science and predictive analytics in virtual power plant environment Piotr Szeląg, PhD Sebastian Dudzik, prof. CUT Częstochowa](https://reader033.vdocuments.us/reader033/viewer/2022060211/5f04d7147e708231d40ff88e/html5/thumbnails/13.jpg)
EMEA USERS CONFERENCE 2017 LONDON #OSISOFTUC ©2017 OSIsoft, LLC
Typical data science workflow
13
![Page 14: Data science and predictive analytics in virtual …...Data science and predictive analytics in virtual power plant environment Piotr Szeląg, PhD Sebastian Dudzik, prof. CUT Częstochowa](https://reader033.vdocuments.us/reader033/viewer/2022060211/5f04d7147e708231d40ff88e/html5/thumbnails/14.jpg)
EMEA USERS CONFERENCE 2017 LONDON #OSISOFTUC ©2017 OSIsoft, LLC
Methodology of data analysis
• Cleaning data
– Missed time rows
– Missed values (imputation)
• Dividing data into the subsets
• Choice a time ranges meeting
some selected criteria:
– annual time range
– semester time range
– season time range
14
![Page 15: Data science and predictive analytics in virtual …...Data science and predictive analytics in virtual power plant environment Piotr Szeląg, PhD Sebastian Dudzik, prof. CUT Częstochowa](https://reader033.vdocuments.us/reader033/viewer/2022060211/5f04d7147e708231d40ff88e/html5/thumbnails/15.jpg)
EMEA USERS CONFERENCE 2017 LONDON #OSISOFTUC ©2017 OSIsoft, LLC
Methodology of data analysis (continued)
• Applying the ‘mean profile’ method
(‘naïve’) for prediction of the power
consumption profile for a selected
day of the week
• Analysis of prediction accuracy
15
![Page 16: Data science and predictive analytics in virtual …...Data science and predictive analytics in virtual power plant environment Piotr Szeląg, PhD Sebastian Dudzik, prof. CUT Częstochowa](https://reader033.vdocuments.us/reader033/viewer/2022060211/5f04d7147e708231d40ff88e/html5/thumbnails/16.jpg)
EMEA USERS CONFERENCE 2017 LONDON #OSISOFTUC ©2017 OSIsoft, LLC
Results of data analysis
16
Exemplary day profile analysis (annual average: Wednesday 2015, 2016)
2015 2016
![Page 17: Data science and predictive analytics in virtual …...Data science and predictive analytics in virtual power plant environment Piotr Szeląg, PhD Sebastian Dudzik, prof. CUT Częstochowa](https://reader033.vdocuments.us/reader033/viewer/2022060211/5f04d7147e708231d40ff88e/html5/thumbnails/17.jpg)
EMEA USERS CONFERENCE 2017 LONDON #OSISOFTUC ©2017 OSIsoft, LLC
Results of data analysis
17
Exemplary day profile analysis (season average: Friday)
Spring Summer
![Page 18: Data science and predictive analytics in virtual …...Data science and predictive analytics in virtual power plant environment Piotr Szeląg, PhD Sebastian Dudzik, prof. CUT Częstochowa](https://reader033.vdocuments.us/reader033/viewer/2022060211/5f04d7147e708231d40ff88e/html5/thumbnails/18.jpg)
EMEA USERS CONFERENCE 2017 LONDON #OSISOFTUC ©2017 OSIsoft, LLC
Results of data analysis
18
Exemplary day profile analysis (season average: Friday)
Fall Winter
![Page 19: Data science and predictive analytics in virtual …...Data science and predictive analytics in virtual power plant environment Piotr Szeląg, PhD Sebastian Dudzik, prof. CUT Częstochowa](https://reader033.vdocuments.us/reader033/viewer/2022060211/5f04d7147e708231d40ff88e/html5/thumbnails/19.jpg)
EMEA USERS CONFERENCE 2017 LONDON #OSISOFTUC ©2017 OSIsoft, LLC
Results of data analysis
19
Exemplary day profile analysis (season average: spring 2015)
Monday Thursday
![Page 20: Data science and predictive analytics in virtual …...Data science and predictive analytics in virtual power plant environment Piotr Szeląg, PhD Sebastian Dudzik, prof. CUT Częstochowa](https://reader033.vdocuments.us/reader033/viewer/2022060211/5f04d7147e708231d40ff88e/html5/thumbnails/20.jpg)
EMEA USERS CONFERENCE 2017 LONDON #OSISOFTUC ©2017 OSIsoft, LLC
Results of data analysis
20
Exemplary week profile analysis (season average: 2015)
![Page 21: Data science and predictive analytics in virtual …...Data science and predictive analytics in virtual power plant environment Piotr Szeląg, PhD Sebastian Dudzik, prof. CUT Częstochowa](https://reader033.vdocuments.us/reader033/viewer/2022060211/5f04d7147e708231d40ff88e/html5/thumbnails/21.jpg)
EMEA USERS CONFERENCE 2017 LONDON #OSISOFTUC ©2017 OSIsoft, LLC
Conclusions
• Profile analysis has shown that even the naive method
gives good results
• This is due to the stability of the electricity consumption of
the analyzed object during the considered time periods
• Further research is needed including other prediction and
validation models (cross validation, etc.).
21
![Page 22: Data science and predictive analytics in virtual …...Data science and predictive analytics in virtual power plant environment Piotr Szeląg, PhD Sebastian Dudzik, prof. CUT Częstochowa](https://reader033.vdocuments.us/reader033/viewer/2022060211/5f04d7147e708231d40ff88e/html5/thumbnails/22.jpg)
EMEA USERS CONFERENCE 2017 LONDON #OSISOFTUC ©2017 OSIsoft, LLC
Next steps
• Challenge: Incorporation of renewable energy sources and
existing energy storage (the analysis covered years where
renewables and storage were not included in VPP)
• Challenge: Transfer of analytical algorithms from Matlab to
PI Analytics
• Implementation of anomaly detection algorithms (too big or
too small consumption) - PI Analytics and PI Notifications
22
![Page 23: Data science and predictive analytics in virtual …...Data science and predictive analytics in virtual power plant environment Piotr Szeląg, PhD Sebastian Dudzik, prof. CUT Częstochowa](https://reader033.vdocuments.us/reader033/viewer/2022060211/5f04d7147e708231d40ff88e/html5/thumbnails/23.jpg)
EMEA USERS CONFERENCE 2017 LONDON #OSISOFTUC ©2017 OSIsoft, LLC
Piotr Szeląg, PhD [email protected]
Vice-Dean for Students Affairs
Czestochowa University of Technology
Faculty of Electrical Engineering
Sebastian Dudzik, prof. CUT [email protected]
Director of the Institute of Optoelectronics and Measurement Systems
Czestochowa University of Technology
Faculty of Electrical Engineering
23
![Page 24: Data science and predictive analytics in virtual …...Data science and predictive analytics in virtual power plant environment Piotr Szeląg, PhD Sebastian Dudzik, prof. CUT Częstochowa](https://reader033.vdocuments.us/reader033/viewer/2022060211/5f04d7147e708231d40ff88e/html5/thumbnails/24.jpg)
EMEA USERS CONFERENCE 2017 LONDON #OSISOFTUC ©2017 OSIsoft, LLC
24
Questions
Please wait for the
microphone before asking
your questions
Please remember to…
Complete the Online Survey
for this session
State your
name & company
![Page 25: Data science and predictive analytics in virtual …...Data science and predictive analytics in virtual power plant environment Piotr Szeląg, PhD Sebastian Dudzik, prof. CUT Częstochowa](https://reader033.vdocuments.us/reader033/viewer/2022060211/5f04d7147e708231d40ff88e/html5/thumbnails/25.jpg)
EMEA USERS CONFERENCE 2017 LONDON #OSISOFTUC ©2017 OSIsoft, LLC
Thank You
Dziękuję