Advertisement

Non-intrusive Load Monitoring on the Edge of the Network: A Smart Measurement Node

  • Hugo Wöhrl
  • Davide BrunelliEmail author
Conference paper
  • 12 Downloads
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 627)

Abstract

To efficiently reduce energy usage in buildings, it is necessary to understand how energy is consumed today. Non-intrusive load monitoring (NILM) is a promising approach where appliance level load profiles can be extracted from an agglomerated single-point measurement using statistical or machine-learning methodology. Moving NILM to the edge of the network holds many advantages like reduced operation cost and decreased power consumption while minimizing privacy concerns. In this paper, we present a NILM hardware that can apply real-time NILM on the edge of the network on an ultra-low power AI-optimized microcontroller.

Keywords

Non-intrusive load monitoring Smart meter Power efficiency Energy disaggregation Blind source separation problem 

References

  1. 1.
    Armel KC, Gupta A, Shrimali G, Albert A (2013) Is disaggregation the holy grail of energy efficiency? The case of electricity. Energy Policy 52:213–234CrossRefGoogle Scholar
  2. 2.
    Rossi M, Rizzon L, Fait M, Passerone R, Brunelli D (2014) Energy neutral wireless sensing for server farms monitoring. IEEE J Emerg Sel Top Circ and Syst 4(3):324–334CrossRefGoogle Scholar
  3. 3.
    Nardello M, Rossi M, Brunelli D (2017) A low-cost smart sensor for non intrusive load monitoring applications. In: 2017 IEEE 26th international symposium on industrial electronics (ISIE), Edinburgh, pp 1362–1368Google Scholar
  4. 4.
    Nardello M, Rossi M, Brunelli D (2017) An innovative cost-effective smart meter with embedded non intrusive load monitoring. In: 2017 IEEE PES innovative smart grid technologies conference Europe (ISGT-Europe), Torino, pp 1–6Google Scholar
  5. 5.
    Hart GW (1992) Nonintrusive appliance load monitoring. Proc IEEE 80(12):1870–1891CrossRefGoogle Scholar
  6. 6.
    Kelly J, Knottenbelt W (2015) Neural NILM: deep neural networks applied to energy disaggregation. In: Proceedings of the 2nd ACM international conference on embedded systems for energy-efficient built environments, pp 55–64Google Scholar
  7. 7.
    Gupta S, Reynolds MS, Patel SN (2010) ElectriSense: single-point sensing using EMI for electrical event detection and classification in the home. In: Proceedings of the 12th ACM international conference on ubiquitous computing, pp 139–148Google Scholar
  8. 8.
    Kelly D (2016) Disaggregation of domestic smart meter energy dataGoogle Scholar
  9. 9.
    Bernard T Non-intrusive load monitoring (NILM): combining multiple distinct electrical features and unsupervised machine learning techniquesGoogle Scholar
  10. 10.
    Porcarelli D, Brunelli D, Benini L (2014) Clamp-and-Forget: a self-sustainable non-invasive wireless sensor node for smart metering applications. Microelectron J 45(12):1671–1678CrossRefGoogle Scholar
  11. 11.
    Balsamo D, Porcarelli D, Benini L, Davide B (2013) A new non-invasive voltage measurement method for wireless analysis of electrical parameters and power quality. In: SENSORS, IEEE, Baltimore, MD, pp 1–4Google Scholar
  12. 12.
    Porcarelli D, Brunelli D, Benini L (2012) Characterization of lithium-ion capacitors for low-power energy neutral wireless sensor networks. In: 2012 ninth international conference on networked sensing (INSS), Antwerp, pp 1–4Google Scholar
  13. 13.
    Brunelli D, Caione C (2015) Sparse recovery optimization in wireless sensor networks with a sub-nyquist sampling rate. Sensors (Switzerland) 15 (7):16654–16673Google Scholar
  14. 14.
    Negri L, Sami M, Macii D, Terranegra A (2004) FSM-based power modeling of wireless protocols: the case of Bluetooth. In: Proceedings of the 2004 international symposium on low power electronics and design (IEEE Cat. No.04TH8758), Newport Beach, CA, USA, pp 369–374Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Department of Electronics and Computer ScienceTechnical University of BerlinBerlinGermany
  2. 2.Department of Industrial EngineeringUniversity of TrentoTrentoItaly

Personalised recommendations