Advertisement

Exploring zero-training algorithms for occupancy detection based on smart meter measurements

  • Vincent Becker
  • Wilhelm Kleiminger
Special Issue Paper
  • 328 Downloads

Abstract

Detecting the occupancy in households is becoming increasingly important for enabling context-aware applications in smart homes. For example, smart heating systems, which aim at optimising the heating energy, often use the occupancy to determine when to heat the home. The occupancy schedule of a household can be inferred from the electricity consumption, as its changes indicate the presence or absence of inhabitants. As smart meters become more widespread, the real-time electricity consumption of households is often available in digital form. For such data, supervised classifiers are typically employed as occupancy detection mechanisms. However, these have to be trained on data labelled with the occupancy ground truth. Labelling occupancy data requires a high effort, sometimes it even may be impossible, making it difficult to apply these methods in real-world settings. Alternatively, one could use unsupervised classifiers, which do not require any labelled data for training. In this work, we introduce and explain several unsupervised occupancy detection algorithms. We evaluate these algorithms by applying them to three publicly available datasets with ground truth occupancy data, and compare them to one existing unsupervised classifier and several supervised classifiers. Two unsupervised algorithms perform the best and we find that the unsupervised classifiers outperform the supervised ones we compared to. Interestingly, we achieve a similar classification performance on coarse-grained aggregated datasets and their fine-grained counterparts.

Keywords

Occupancy detection Smart meters Unsupervised classification 

References

  1. 1.
    Akbar A, Nati M, Carrez F, Moessner K (2015) Contextual occupancy detection for smart office by pattern recognition of electricity consumption data. In: 2015 IEEE international conference on communications (ICC), pp 561–566. doi: 10.1109/ICC.2015.7248381
  2. 2.
    Alhamoud A, Xu P, Englert F, Reinhardt A, Scholl P, Boehnstedt D, Steinmetz R (2015) Extracting human behavior patterns from appliance-level power consumption data. In: Proceedings of the 12th European conference on wireless sensor networks, EWSN 2015, Porto, Portugal, pp 52–67. doi: 10.1007/978-3-319-15582-1_4
  3. 3.
    Amayri M, Arora A, Ploix S, Bandhyopadyay S, Ngo QD, Badarla VR (2016) Estimating occupancy in heterogeneous sensor environment. Energy Build 129:46–58. doi: 10.1016/j.enbuild.2016.07.026 CrossRefGoogle Scholar
  4. 4.
    Ardakanian O, Bhattacharya A, Culler D (2016) Non-intrusive techniques for establishing occupancy related energy savings in commercial buildings. In: Proceedings of the 3rd ACM international conference on systems for energy-efficient built environments, buildSys ’16, pp 21–30. doi: 10.1145/2993422.2993574
  5. 5.
    Barbato A, Borsani L, Capone A, Melzi S (2009) Home energy saving through a user profiling system based on wireless sensors. In: Proceedings of the 1st ACM workshop on embedded sensing systems for energy-efficiency in buildings, buildSys ’09. ACM, New York, NY, USA, pp 49–54. doi: 10.1145/1810279.1810291
  6. 6.
    Barker S, Mishra A, Irwin D, Cecchet E, Shenoy P, Albrecht J (2012) Smart*: an open data set and tools for enabling research in sustainable homes. In: Proceedings of the 2012 workshop on data mining applications in sustainability (SustKDD 2012), Beijing, ChinaGoogle Scholar
  7. 7.
    Beckel C, Kleiminger W, Cicchetti R, Staake T, Santini S (2014) The ECO data set and the performance of non-intrusive load monitoring algorithms. In: Proceedings of the 1st ACM conference on embedded systems for energy-efficient buildings, buildsys ’14. ACM, New York, NY, USA, pp 80–89. doi: 10.1145/2674061.2674064
  8. 8.
    Boait PJ, Rylatt RM (2010) A method for fully automatic operation of domestic heating. Energy Build 42(1):11–16. doi: 10.1016/j.enbuild.2009.07.005 CrossRefGoogle Scholar
  9. 9.
    Brackney LJ, Florita AR, Swindler AC, Polese LG, Brunemann GA (2012) Design and performance of an image processing occupancy sensor. In: The second international conference on building energy and environment 2012, Boulder, Colorado, USA, pp 987–994Google Scholar
  10. 10.
    Brown R, Ghavami N, Siddiqui HUR, Adjrad M, Ghavami M, Dudley S (2017) Occupancy based household energy disaggregation using ultra wideband radar and electrical signature profiles. Energy Build 141:134–141. doi: 10.1016/j.enbuild.2017.02.004 CrossRefGoogle Scholar
  11. 11.
    Calì D, Matthes P, Huchtemann K, Streblow R, Müller D (2015) \(\text{ CO }_2\) based occupancy detection algorithm: experimental analysis and validation for office and residential buildings. Build Environ 86:39–49. doi: 10.1016/j.buildenv.2014.12.011 CrossRefGoogle Scholar
  12. 12.
    Candanedo LM, Feldheim V (2016) Accurate occupancy detection of an office room from light, temperature, humidity and \(\text{ CO }_2\) measurements using statistical learning models. Energy Build 112:28–39. doi: 10.1016/j.enbuild.2015.11.071 CrossRefGoogle Scholar
  13. 13.
    Chaney J, Owens EH, Peacock AD (2016) An evidence based approach to determining residential occupancy and its role in demand response management. Energy Build 125:254–266. doi: 10.1016/j.enbuild.2016.04.060 CrossRefGoogle Scholar
  14. 14.
    Chen D, Barker S, Subbaswamy A, Irwin D, Shenoy P (2013) Non-intrusive occupancy monitoring using smart meters. In: Proceedings of the 5th ACM workshop on embedded systems for energy-efficient buildings, buildsys’13. ACM, New York, NY, USA, pp 9:1–9:8. doi: 10.1145/2528282.2528294
  15. 15.
    Ebadat A, Bottegal G, Molinari M, Varagnolo D, Wahlberg B, Hjalmarsson H, Johansson KH (2015) Multi-room occupancy estimation through adaptive gray-box models. In: Proceedings of the 4th IEEE conference on decision and control (CDC), pp 3705–3711. doi: 10.1109/CDC.2015.7402794
  16. 16.
    Ebadat A, Bottegal G, Varagnolo D, Wahlberg B, Hjalmarsson H, Johansson KH (2015) Blind identification strategies for room occupancy estimation. In: 2015 European control conference (ECC), pp 1315–1320. doi: 10.1109/ECC.2015.7330720
  17. 17.
    Ebadat A, Bottegal G, Varagnolo D, Wahlberg B, Johansson KH (2015) Regularized deconvolution-based approaches for estimating room occupancies. IEEE Trans Autom Sci Eng 12(4):1157–1168. doi: 10.1109/TASE.2015.2471305 CrossRefGoogle Scholar
  18. 18.
    European Commission (2014) Cost-benefit analyses & state of play of smart metering deployment in the EU-27. Technical Report 52014SC0189, EU Commission, Brussels. URL: http://eur-lex.europa.eu/legal-content/EN/TXT/?uri=celex%3A52014SC0189
  19. 19.
    Froehlich J, Larson EC, Campbell T, Haggerty C, Fogarty J, Patel SN (2009) Hydrosense: infrastructure-mediated single-point sensing of whole-home water activity. In: Proceedings of the 11th international conference on Ubiquitous computing, UbiComp 2009, Orlando, Florida, USA, pp 235–244. doi: 10.1145/1620545.1620581
  20. 20.
    Gao G, Whitehouse K (2009) The self-programming thermostat: optimizing setback schedules based on home occupancy patterns. In: Proceedings of the 1st ACM workshop on embedded sensing systems for energy-efficiency in buildings, buildSys ’09. ACM, New York, NY, USA, pp 67–72. doi: 10.1145/1810279.1810294
  21. 21.
    Guo X, Tiller D, Henze G, Waters C (2010) The performance of occupancy-based lighting control systems: a review. Light Res Technol 42(4):415–431. doi: 10.1177/1477153510376225 CrossRefGoogle Scholar
  22. 22.
    Gupta M, Intille SS, Larson K (2009) Adding GPS-control to traditional thermostats: an exploration of potential energy savings and design challenges. In: Proceedings of the 7th international conference on pervasive computing, pervasive 2009, Nara, Japan, pp 95–114. doi: 10.1007/978-3-642-01516-8_8
  23. 23.
    Jin M, Bekiaris-Liberis N, Weekly K, Spanos CJ, Bayen A M (2016) Occupancy detection via environmental sensing. IEEE Trans Autom Sci Eng 99:1–13. doi: 10.1109/TASE.2016.2619720 CrossRefGoogle Scholar
  24. 24.
    Jin M, Jia R, Kang Z, Konstantakopoulos IC, Spanos CJ (2014) PresenceSense: zero-training algorithm for individual presence detection based on power monitoring. In: Proceedings of the 1st ACM conference on embedded systems for energy-efficient buildings, buildsys ’14. ACM, New York, NY, USA, pp 1–10. doi: 10.1145/2674061.2674073
  25. 25.
    Kleiminger W (2015) Occupancy sensing and prediction for automated energy savings. Ph.D. thesis, ETH Zurich. doi: 10.3929/ethz-a-010450096
  26. 26.
    Kleiminger W, Beckel C, Dey AK, Santini S (2013) Using unlabeled Wi-Fi scan data to discover occupancy patterns of private households. In: Proceedings of the 11th ACM conference on embedded network sensor systems, sensys ’13, Rome, Italy, pp 47:1–47:2. doi: 10.1145/2517351.2517421
  27. 27.
    Kleiminger W, Beckel C, Santini S (2015) Household occupancy monitoring using electricity meters. In: Proceedings of the 2015 ACM international joint conference on pervasive and Ubiquitous computing, UbiComp ’15, pp 975–986. doi: 10.1145/2750858.2807538
  28. 28.
    Kleiminger W, Beckel C, Staake T, Santini S (2013) Occupancy detection from electricity consumption data. In: Proceedings of the 5th ACM workshop on embedded systems for energy-efficient buildings, buildsys’13. ACM, New York, NY, USA, pp 10:1–10:8. doi: 10.1145/2528282.2528295
  29. 29.
    Kleiminger W, Mattern F, Santini S (2014) Predicting household occupancy for smart heating control: a comparative performance analysis of state-of-the-art approaches. Energy Build 85:493–505. doi: 10.1016/j.enbuild.2014.09.046 CrossRefGoogle Scholar
  30. 30.
    Krumm J, Brush AJB (2011) Learning time-based presence probabilities. In: Proceedings of the 9th international conference on pervasive computing, pervasive 2011, San Francisco, CA, USA, pp 79–96. doi: 10.1007/978-3-642-21726-5_6
  31. 31.
    Lu J, Sookoor T, Srinivasan V, Gao G, Holben B, Stankovic J, Field E, Whitehouse K (2010) The smart thermostat: using occupancy sensors to save energy in homes. In: Proceedings of the 8th ACM conference on embedded networked sensor systems, sensys ’10. ACM, New York, NY, USA, pp 211–224. doi: 10.1145/1869983.1870005
  32. 32.
    Matthews BW (1975) Comparison predicted and observed secondary structure of T4 phage lysozyme. Biochim Biophys Acta 405(2):442–451. doi: 10.1016/0005-2795(75)90109-9 CrossRefGoogle Scholar
  33. 33.
    Mozer M, Vidmar L, Dodier RH (1996) The neurothermostat: predictive optimal control of residential heating systems. In: Advances in neural information processing systems, vol 9, NIPS, Denver, CO, USA, pp 953–959Google Scholar
  34. 34.
    Page E (1954) Continuous inspection schemes. Biometrika 41(1–2):100–115. doi: 10.1093/biomet/41.1-2.100 MathSciNetCrossRefzbMATHGoogle Scholar
  35. 35.
    Patel SN, Reynolds MS, Abowd GD (2008) Detecting human movement by differential air pressure sensing in HVAC system ductwork: an exploration in infrastructure mediated sensing. In: Proceedings of the 6th international conference on pervasive computing, pervasive ’08, pp 1–18. doi: 10.1007/978-3-540-79576-6_1
  36. 36.
    Patel SN, Robertson T, Kientz JA, Reynolds MS, Abowd GD (2007) At the flick of a switch: detecting and classifying unique electrical events on the residential power line. In: Proceedings of the 9th international conference on Ubiquitous computing, UbiComp ’07, Innsbruck, Austria, pp 271–288. doi: 10.1007/978-3-540-74853-3_16
  37. 37.
    Pedersen TH, Nielsen KU, Petersen S (2017) Method for room occupancy detection based on trajectory of indoor climate sensor data. Build Environ 115:147–156. doi: 10.1016/j.buildenv.2017.01.023 CrossRefGoogle Scholar
  38. 38.
    Rabiner L, Juang B (1986) An introduction to hidden Markov models. IEEE ASSP Mag. doi: 10.1109/MASSP.1986.1165342 zbMATHGoogle Scholar
  39. 39.
    Scott J, Bernheim Brush A, Krumm J, Meyers B, Hazas M, Hodges S, Villar N (2011) Preheat: controlling home heating using occupancy prediction. In: Proceedings of the 13th international conference on Ubiquitous computing, UbiComp ’11. ACM, New York, NY, USA, pp 281–290. doi: 10.1145/2030112.2030151
  40. 40.
    Smith JR, Fishkin KP, Jiang B, Mamishev A, Philipose M, Rea AD, Roy S, Sundara-Rajan K (2005) RFID-based techniques for human-activity detection. Commun ACM 48(9):39–44. doi: 10.1145/1081992.1082018 CrossRefGoogle Scholar
  41. 41.
    Soltanaghaei E, Whitehouse K (2016) Walksense: classifying home occupancy states using walkway sensing. In: Proceedings of the 3rd ACM international conference on systems for energy-efficient built environments, buildsys ’16, pp 167–176. doi: 10.1145/2993422.2993576
  42. 42.
    Szczurek A, Maciejewska M (2016) Detection of occupancy events from indoor air monitoring data. In: 3rd international conference on mathematics and computers in sciences and in industry (MCSI), pp 229–234. doi: 10.1109/MCSI.2016.050
  43. 43.
    Tang G, Wu K, Lei J, Xiao W (2015) The meter tells you are at home! Non-intrusive occupancy detection via load curve data. In: 2015 IEEE international conference on smart grid communications (Smartgridcomm), Miami, FL, USA, pp 897–902. doi: 10.1109/SmartGridComm.2015.7436415
  44. 44.
    Tapia EM, Intille SS, Larson K (2004) Activity recognition in the home using simple and ubiquitous sensors. In: Proceedings of the 2nd international conference on pervasive computing, pervasive ’04, Vienna, Austria, pp 158–175. doi: 10.1007/978-3-540-24646-6_10
  45. 45.
    Teixeira T, Savvides A (2008) Lightweight people counting and localizing for easily deployable indoors WSNs. J Sel Top Signal Process 2(4):493–502. doi: 10.1109/JSTSP.2008.2001426 CrossRefGoogle Scholar
  46. 46.
    Telkonet. Telkonet products. URL: http://www.telkonet.com [cited 18.05.2017]
  47. 47.
    van Kasteren T, Noulas AK, Englebienne G, Kröse BJA (2008) Accurate activity recognition in a home setting. In: Proceedings of the 10th international conference on Ubiquitous computing, UbiComp 2008, Seoul, Korea, pp 1–9. doi: 10.1145/1409635.1409637
  48. 48.
    Viterbi AJ (1967) Error bounds for convolutional codes and an asymptotically optimum decoding algorithm. IEEE Trans Inf Theory 13(2):260–269. doi: 10.1109/TIT.1967.1054010 CrossRefzbMATHGoogle Scholar
  49. 49.
    Wang S (1989) \(\text{ CO }_2\)-based occupancy detection for on-line outdoor air flow. Indoor Built Environ 7(3):165–181. doi: 10.1177/1420326X9800700305 CrossRefGoogle Scholar
  50. 50.
    Woodstock TK, Radke RJ, Sanderson AC (2016) Sensor fusion for occupancy detection and activity recognition using time-of-flight sensors. In: Proceedings of the 19th international conference on information fusion (FUSION), pp 1695–1701Google Scholar
  51. 51.
    Yang L, Ting K, Srivastava MB (2014) Inferring occupancy from opportunistically available sensor data. In: Proceedings of the IEEE international conference on pervasive computing and communications, PerCom 2014, Los Alamitos, CA, USA, pp 60–68. doi: 10.1109/PerCom.2014.6813945
  52. 52.
    Zikos S, Tsolakis A, Meskos D, Tryferidis A, Tzovaras D (2016) Conditional random fields—based approach for real-time building occupancy estimation with multi-sensory networks. Autom Constr 68:128–145. doi: 10.1016/j.autcon.2016.05.005 CrossRefGoogle Scholar

Copyright information

© Springer-Verlag GmbH Germany 2017

Authors and Affiliations

  1. 1.Department of Computer ScienceETH ZurichZurichSwitzerland

Personalised recommendations