Skip to content
Licensed Unlicensed Requires Authentication Published by Oldenbourg Wissenschaftsverlag October 16, 2018

Measurement system and dataset for in-depth analysis of appliance energy consumption in industrial environment

Messaufbau und Datensatz zur detaillierten Verbraucheranalyse in industrieller Umgebung
  • Matthias Kahl

    Matthias Kahl received the Dipl.-Inf.(FH) degree in Computer Science at the University of Applied Science Schmalkalden with the specialization of intelligent information systems in 2010. Since 2015 he is working on his Ph.D at TUM in the main topic of Energy Informatics, Energy Information Retrieval and Non-Intrusive Appliance Recognition.

    ORCID logo EMAIL logo
    , Veronika Krause

    Veronika Krause received the M.Eng. degree in Electromobility and Power Networks in 2014 from the Ostbayerische Technische Hochschule (OTH) Regensburg. From 2014 to 2017 she was a research assistant at OTH Regensburg. Since 2017 she is a technical employee there.

    , Rudolph Hackenberg , Anwar Ul Haq

    Anwar Ul Haq received his B.Sc (2008) from University of AJK, Pakistan and M.Sc. (2012) from Hanyang University, South Korea both in Electrical Engineering with focus on communication networks and energy. Currently he is working as a Ph.D candidate in the Energy Informatics research group at the chair of Application and Middleware Systems, TUM.

    , Anton Horn

    Prof. Dr. Anton Horn is with the Faculty of Electrical Engineering and Information Technology at OTH Regensburg (University of Applied Sciences) since 2009.

    , Hans-Arno Jacobsen

    Prof. Dr. Hans-Arno Jacobsen’s pioneering research lies at the interface between computer science, computer engineering and information systems. After being awarded the prestigious Alexander von Humboldt-Professorship, he joined TUM in October 2011.

    , Thomas Kriechbaumer

    Thomas Kriechbaumer received his B.Sc. and M.Sc. in Computer Science with a specialization in Robotics and Pervasive Computing from Graz University of Technology, Austria, in 2013 and 2015, with a research focus on non-intrusive meter-less power monitoring. He is currently pursuing his Ph.D. at Technical University Munich, Germany, working on smart meter data acquisition architectures in the context of information extraction from energy consumption data.

    , Michael Petzenhauser , Mikhail Shamonin

    Since 2002, Dr. rer. nat. Mikhail Shamonin is Professor of Sensor Technology at Ostbayerische Technische Hochschule Regensburg.

    and Anton Udalzow

    Anton Udalzow received M.Eng. degree in Electrical and Microsystems Engineering from the Ostbayerische Technische Hochschule (OTH) Regensburg in 2017. From 2016 to 2017 he worked as an engineer at OTH Regensburg.

From the journal tm - Technisches Messen

Abstract

To support a rational and efficient use of electrical energy in residential and industrial environments, Non-Intrusive Load Monitoring (NILM) provides several techniques to identify state and power consumption profiles of connected appliances. Design requirements for such systems include a low hardware and installations costs for residential, reliability and high-availability for industrial purposes, while keeping invasive interventions into the electrical infrastructure to a minimum. This work introduces a reference hardware setup that allows an in depth analysis of electrical energy consumption in industrial environments. To identify appliances and their consumption profile, appropriate identification algorithms are developed by the NILM community. To enable an evaluation of these algorithms on industrial appliances, we introduce the Laboratory-measured IndustriaL Appliance Characteristics (LILAC) dataset: 1302 measurements from one, two, and three concurrently running appliances of 15 appliance types, measured with the introduced testbed. To allow in-depth appliance consumption analysis, measurements were carried out with a sampling rate of 50 kHz and 16-bit amplitude resolution for voltage and current signals. We show in experiments that signal signatures, contained in the measurement data, allows one to distinguish the single measured electrical appliances with a baseline machine learning approach of nearly 100 % accuracy.

Zusammenfassung

Um elektrische Verbraucher in privaten sowie industriellen Anlagen effizient und kostensparend betreiben zu können, bieten Non-Intrusive Load Monitoring (NILM) Algorithmen die Möglichkeit, Verbraucher zu identifizieren und deren Zustand sowie Verbrauchsprofile zu ermitteln. Ein solches System sollte geringe Material- und Aufwandskosten beim Einsatz im privaten Sektor und hohe Zuverlässigkeit im industriellen Sektor aufweisen. Zudem muss die Installation, ohne aufwendig in die elektrische Infrastruktur eines Gebäudes eingreifen zu müssen, durchführbar sein. Das vorgestellte System ist ein Referenzaufbau, der eine tiefgehende Verbrauchsanalyse industrieller Anlagen erlaubt. Um Verbraucher im aggregierten Messsignal identifizieren zu können, bedarf es effizienter Algorithmen zur Geräteerkennung aus dem NILM-Forschungsgebiet. Um die Evaluation dieser Algorithmen anhand industrieller Verbraucher für die Forschungsgemeinschaft ermöglichen zu können, veröffentlichen wir den Laboratory-measured IndustriaL Appliance Characteristics (LILAC) Datensatz: 1302 Messungen von ein, zwei und drei Geräten gleichzeitig, aus 15 verschiedenen Gerätetypen stammend und mit dem vorgestellten Messsystem aufgezeichnet. Um aktuellste Algorithmen aus NILM anwenden zu können, wurden die Aufnahmen mit einer hohen Abtastrate und Amplitudenauflösung (50 kHz, 16 bit) von Spannungs- und Stromsignalen aufgenommen. Wir zeigen anhand von Experimenten, dass die Messungen dazu geeignet sind um mit einem einfachen Klassifikationssystem eine nahezu 100-prozentige Geräteerkennung zu ermöglichen.

Award Identifier / Grant number: 16KN033622

Funding statement: This research was partially funded by the Alexander von Humboldt Foundation established by the government of the Federal Republic of Germany and was supported by the Federal Ministry for Economic Affairs and Energy under the project number 16KN033622 on the basis of a decision by the German Bundestag.

About the authors

Matthias Kahl

Matthias Kahl received the Dipl.-Inf.(FH) degree in Computer Science at the University of Applied Science Schmalkalden with the specialization of intelligent information systems in 2010. Since 2015 he is working on his Ph.D at TUM in the main topic of Energy Informatics, Energy Information Retrieval and Non-Intrusive Appliance Recognition.

Veronika Krause

Veronika Krause received the M.Eng. degree in Electromobility and Power Networks in 2014 from the Ostbayerische Technische Hochschule (OTH) Regensburg. From 2014 to 2017 she was a research assistant at OTH Regensburg. Since 2017 she is a technical employee there.

Anwar Ul Haq

Anwar Ul Haq received his B.Sc (2008) from University of AJK, Pakistan and M.Sc. (2012) from Hanyang University, South Korea both in Electrical Engineering with focus on communication networks and energy. Currently he is working as a Ph.D candidate in the Energy Informatics research group at the chair of Application and Middleware Systems, TUM.

Anton Horn

Prof. Dr. Anton Horn is with the Faculty of Electrical Engineering and Information Technology at OTH Regensburg (University of Applied Sciences) since 2009.

Hans-Arno Jacobsen

Prof. Dr. Hans-Arno Jacobsen’s pioneering research lies at the interface between computer science, computer engineering and information systems. After being awarded the prestigious Alexander von Humboldt-Professorship, he joined TUM in October 2011.

Thomas Kriechbaumer

Thomas Kriechbaumer received his B.Sc. and M.Sc. in Computer Science with a specialization in Robotics and Pervasive Computing from Graz University of Technology, Austria, in 2013 and 2015, with a research focus on non-intrusive meter-less power monitoring. He is currently pursuing his Ph.D. at Technical University Munich, Germany, working on smart meter data acquisition architectures in the context of information extraction from energy consumption data.

Mikhail Shamonin

Since 2002, Dr. rer. nat. Mikhail Shamonin is Professor of Sensor Technology at Ostbayerische Technische Hochschule Regensburg.

Anton Udalzow

Anton Udalzow received M.Eng. degree in Electrical and Microsystems Engineering from the Ostbayerische Technische Hochschule (OTH) Regensburg in 2017. From 2016 to 2017 he worked as an engineer at OTH Regensburg.

Acknowledgment

The authors from OTH Regensburg thank Tobias Probst for valuable assistance in the realization of the electrical cabinet.

References

1. Jack Kelly and William Knottenbelt. Does disaggregated electricity feedback reduce domestic electricity consumption? A systematic review of the literature. CoRR, 2016.Search in Google Scholar

2. Kathleen Carrie Armel, Abhay Gupta, Gireesh Shrimali, and Adrian Albert. Is disaggregation the holy grail of energy efficiency? The case of electricity. Energy Policy, 52:213–234, jan 2013. 10.1016/j.enpol.2012.08.062.Search in Google Scholar

3. G.W. Hart, E.C. Kern, and F.C. Schweppe. Non-intrusive appliance monitor apparatus, August 1989. URL https://www.google.com/patents/US4858141. US Patent 4,858,141.Search in Google Scholar

4. George William Hart. Nonintrusive Appliance Load Monitoring. Proceedings of the IEEE, 80(12):1870–1891, 1992.10.1109/5.192069Search in Google Scholar

5. F Sultanem. Using appliance signatures for monitoring residential loads at meter panel level. IEEE Transactions on Power Delivery, 6(4):1380–1385, 1991. 10.1109/61.97667.Search in Google Scholar

6. Steven B. Leeb, Steven R. Shaw, and James L. Kirtley. Transient Event Detection in Spectral Envelope Estimates for Nonintrusive Load Monitoring. IEEE Transactions on Power Delivery, 10(3):1200–1210, jul 1995. 10.1109/61.400897.Search in Google Scholar

7. Anwar Ul Haq and Hans-Arno Jacobsen. Prospects of appliance-level load monitoring in off-the-shelf energy monitors: A technical review. Energies, 11(1):2018. ISSN 1996-1073. 10.3390/en11010189.Search in Google Scholar

8. A. U. Haq, T. Kriechbaumer, M. Kahl, and H. A. Jacobsen. CLEAR - A Circuit Level Electric Appliance Radar for the Electric Cabinet. In IEEE International Conference on Industrial Technology (ICIT), pages 1130–1135, March 2017. 10.1109/ICIT.2017.7915521.Search in Google Scholar

9. Thomas Kriechbaumer, Anwar Ul Haq, Matthias Kahl, and Hans-Arno Jacobsen. MEDAL: A Cost-Effective High-Frequency Energy Data Acquisition System for Electrical Appliances. In Proceedings of the 8thInternational Conference on Future Energy Systems, e-Energy ’17. ACM, 2017.10.1145/3077839.3077844Search in Google Scholar

10. Jack Kelly and William Knottenbelt. The UK-DALE Dataset, Domestic Appliance-Level Electricity Demand and Whole-House Demand from Five UK Homes. Scientific Data, 2:150007, 2015. 10.1038/sdata.2015.7. URL http://www.doc.ic.ac.uk/~dk3810/data/.Search in Google Scholar PubMed PubMed Central

11. Jeremy Zico Kolter and Matthew J Johnson. REDD: A Public Data Set for Energy Disaggregation Research. In Workshop on Data Mining Applications in Sustainability (SIGKDD), volume 25, pages 59–62. ACM, 2011.Search in Google Scholar

12. JG Roos, IE Lane, EC Botha, and Gerhard P Hancke. Using Neural Networks for Non-intrusive Monitoring of Industrial Electrical Loads. In Instrumentation and Measurement Technology Conference, pages 1115–1118. IEEE, 1994. 10.1109/imtc.1994.351862.Search in Google Scholar

13. K. D. Lee, S. B. Leeb, L. K. Norford, P. R. Armstrong, J. Holloway, and S. R. Shaw. Estimation of variable-speed-drive power consumption from harmonic content. IEEE Transactions on Energy Conversion, 20(3):566–574, September 2005. ISSN 0885-8969. 10.1109/TEC.2005.852963.Search in Google Scholar

14. S. R. Shaw, C. B. Abler, R. F. Lepard, D. Luo, S. B. Leeb, and L. K. Norford. Instrumentation for High Performance Nonintrusive Electrical Load Monitoring. ASME, 120(3):224, 1998. 10.1115/1.2888073.Search in Google Scholar

15. Shwetak N Patel, Thomas Robertson, Julie A Kientz, Matthew S Reynolds, and Gregory D Abowd. At the Flick of a Switch: Detecting and Classifying Unique Electrical Events on the Residential Power Line. Lecture Notes in Computer Science, 4717:271–288, 2007.10.1007/978-3-540-74853-3_16Search in Google Scholar

16. Sidhant Gupta, Matthew S Reynolds, and Shwetak N Patel. ElectriSense: Single-Point Sensing Using EMI for Electrical Event Detection and Classification in the Home. In Proceedings of the 12thACM international conference on Ubiquitous computing, pages 139–148. ACM, ACM Press, 2010. 10.1145/1864349.1864375.Search in Google Scholar

17. Jian Liang, Simon KK Ng, Gail Kendall, and John WM Cheng. Load Signature Study–Part I: Basic Concept, Structure, and Methodology. IEEE Transactions on Power Delivery, 25(2):551–560, 2010. 10.1109/tpwrd.2009.2033799.Search in Google Scholar

18. Karim Said Barsim, Lukas Mauch, and Bin Yang. Neural Network Ensembles to Real-time Identification of Plug-level Appliance Measurements. Signature, 2:11, 2016.Search in Google Scholar

19. Jingkun Gao, Suman Giri, Emre Can Kara, and Mario Bergés. PLAID: A Public Dataset of High-Resolution Electrical Appliance Measurements for Load Identification Research. In Proceedings of the 1stACM Conference on Embedded Systems for Energy-Efficient Buildings, pages 198–199. ACM, Association for Computing Machinery (ACM), 2014. 10.1145/2674061.2675032.Search in Google Scholar

20. Thomas Kriechbaumer and Hans-Arno Jacobsen. BLOND, a building-level office environment dataset of typical electrical appliances. Scientific Data, 5(180048), 2018. 10.1038/sdata.2018.48.Search in Google Scholar PubMed PubMed Central

21. Jack Kelly and William Knottenbelt. Neural NILM: Deep Neural Networks Applied to Energy Disaggregation. In Proceedings of the 2ndACM International Conference on Embedded Systems for Energy-Efficient Built Environments, pages 55–64. ACM, Association for Computing Machinery (ACM), 2015. 10.1145/2821650.2821672.Search in Google Scholar

22. Leen De Baets, Joeri Ruyssinck, Chris Develder, Tom Dhaene, and Dirk Deschrijver. Appliance classification using vi trajectories and convolutional neural networks. Energy and Buildings, 158(Supplement C):32–36, 2018. ISSN 0378-7788. 10.1016/j.enbuild.2017.09.087. URL http://www.sciencedirect.com/science/article/pii/S0378778817312690.Search in Google Scholar

23. Kien Nguyen Trung, Olivier Zammit, Eric Dekneuvel, Benjamin Nicolle, Cuong Nguyen Van, and Gilles Jacquemod. An Innovative Non-Intrusive Load Monitoring System for Commercial and Industrial Application. In International Conference on Advanced Technologies for Communications (ATC), pages 23–27. IEEE, Institute of Electrical and Electronics Engineers (IEEE), October 2012. 10.1109/atc.2012.6404221.Search in Google Scholar

24. Matthias Kahl, Anwar Ul Haq, Thomas Kriechbaumer, and Hans-Arno Jacobsen. A comprehensive feature study for appliance recognition on high frequency energy data. In Proceedings of the 2017 ACM 8thInternational Conference on Future Energy Systems, e-Energy ’17, New York, NY, USA, 5 2017. ACM. ISBN 978-1-4503-5036-5/17/05. 10.1145/3077839.3077845.Search in Google Scholar

25. Nipun Batra, Jack Kelly, Oliver Parson, Haimonti Dutta, William Knottenbelt, Alex Rogers, Amarjeet Singh, and Mani Srivastava. NILMTK: An Open Source Toolkit for Non-intrusive Load Monitoring. In Proceedings of the 5thInternational Conference on Future Energy Systems, pages 265–276, New York, NY, USA, 2014. ACM. 10.1145/2602044.2602051.Search in Google Scholar

26. Thomas A Runkler. Data Analytics. Springer, 2012. ISBN 978-3-658-14074-8.10.1007/978-3-8348-2589-6Search in Google Scholar

Received: 2018-04-10
Accepted: 2018-09-24
Published Online: 2018-10-16
Published in Print: 2019-01-28

© 2019 Walter de Gruyter GmbH, Berlin/Boston

Downloaded on 26.2.2024 from https://www.degruyter.com/document/doi/10.1515/teme-2018-0038/html
Scroll to top button