# A Bayesian Approach to Unsupervised, Non-Intrusive Load Disaggregation

^{*}

## Abstract

**:**

## 1. Introduction

## 2. Method

#### 2.1. Base Load Calculation

#### 2.2. Thermal Load Calculation

#### 2.3. Calculation of the Thermal Load Prior

Algorithm 1: ABC rejection algorithm for thermal load prior computation |

#### 2.4. Disaggregation

## 3. Experimental Setup

#### 3.1. AMPds Dataset

#### 3.2. Evaluation Metrics

## 4. Results

## 5. Discussion

## 6. Conclusions

## Author Contributions

## Funding

## Institutional Review Board Statement

## Informed Consent Statement

## Data Availability Statement

## Conflicts of Interest

## References

- Tang, R.; Wang, S. Model predictive control for thermal energy storage and thermal comfort optimization of building demand response in smart grids. Appl. Energy
**2019**, 242, 873–882. [Google Scholar] [CrossRef] - Qi, N.; Cheng, L.; Xu, H.; Wu, K.; Li, X.; Wang, Y.; Liu, R. Smart meter data-driven evaluation of operational demand response potential of residential air conditioning loads. Appl. Energy
**2020**, 279, 115708. [Google Scholar] [CrossRef] - Albadi, M.H.; El-Saadany, E.F. A summary of demand response in electricity markets. Electr. Power Syst. Res.
**2008**, 78, 1989–1996. [Google Scholar] [CrossRef] - Gils, H.C. Assessment of the theoretical demand response potential in Europe. Energy
**2014**, 67, 1–18. [Google Scholar] [CrossRef] - Commission, E. Commission Delegated Regulation (EU) 2019/826 of 4 March 2019 Amending Annexes VIII and IX to Directive 2012/27/EU of the European Parliament and of the Council on the Contents of Comprehensive Assessments of the Potential for Efficient Heating and Cooling. 2019. Available online: http://data.europa.eu/eli/reg_del/2019/826/oj (accessed on 12 February 2022).
- Kirkerud, J.; Nagel, N.O.; Bolkesjø, T. The role of demand response in the future renewable northern European energy system. Energy
**2021**, 235, 121336. [Google Scholar] [CrossRef] - Kwac, J.; Rajagopal, R. Data-driven targeting of customers for demand response. IEEE Trans. Smart Grid
**2015**, 7, 2199–2207. [Google Scholar] [CrossRef] - Adika, C.O.; Wang, L. Demand-side bidding strategy for residential energy management in a smart grid environment. IEEE Trans. Smart Grid
**2014**, 5, 1724–1733. [Google Scholar] [CrossRef] - Wang, F.; Zhou, L.; Ren, H.; Liu, X.; Talari, S.; Shafie-khah, M.; Catalao, J.P. Multi-objective optimization model of source–load–storage synergetic dispatch for a building energy management system based on TOU price demand response. IEEE Trans. Ind. Appl.
**2017**, 54, 1017–1028. [Google Scholar] [CrossRef] - O’Connell, N.; Pinson, P.; Madsen, H.; O’Malley, M. Benefits and challenges of electrical demand response: A critical review. Renew. Sustain. Energy Rev.
**2014**, 39, 686–699. [Google Scholar] [CrossRef] - Eskander, M.M.; Silva, C.A. A complementary unsupervised load disaggregation method for residential loads at very low sampling rate data. Sustain. Energy Technol. Assess.
**2021**, 43, 100921. [Google Scholar] [CrossRef] - Moradzadeh, A.; Sadeghian, O.; Pourhossein, K.; Mohammadi-Ivatloo, B.; Anvari-Moghaddam, A. Improving residential load disaggregation for sustainable development of energy via principal component analysis. Sustainability
**2020**, 12, 3158. [Google Scholar] [CrossRef] [Green Version] - Aiad, M.; Lee, P.H. Unsupervised approach for load disaggregation with devices interactions. Energy Build.
**2016**, 116, 96–103. [Google Scholar] [CrossRef] - Zeinal-Kheiri, S.; Shotorbani, A.M.; Mohammadi-Ivatloo, B. Residential load disaggregation considering state transitions. IEEE Trans. Ind. Inform.
**2019**, 16, 743–753. [Google Scholar] [CrossRef] - Hart, G.W. Nonintrusive appliance load monitoring. Proc. IEEE
**1992**, 80, 1870–1891. [Google Scholar] [CrossRef] - Faustine, A.; Mvungi, N.H.; Kaijage, S.; Michael, K. A survey on non-intrusive load monitoring methodies and techniques for energy disaggregation problem. arXiv
**2017**, arXiv:1703.00785. [Google Scholar] - Kelly, J.; Knottenbelt, W. 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, Seoul, Korea, 4–5 November 2015; pp. 55–64. [Google Scholar]
- Athanasiadis, C.; Doukas, D.; Papadopoulos, T.; Chrysopoulos, A. A scalable real-time non-intrusive load monitoring system for the estimation of household appliance power consumption. Energies
**2021**, 14, 767. [Google Scholar] [CrossRef] - Zou, M.; Zhu, S.; Gu, J.; Korunovic, L.M.; Djokic, S.Z. Heating and Lighting Load Disaggregation Using Frequency Components and Convolutional Bidirectional Long Short-Term Memory Method. Energies
**2021**, 14, 4831. [Google Scholar] [CrossRef] - Huber, P.; Calatroni, A.; Rumsch, A.; Paice, A. Review on deep neural networks applied to low-frequency nilm. Energies
**2021**, 14, 2390. [Google Scholar] [CrossRef] - Massidda, L.; Marrocu, M.; Manca, S. Non-intrusive load disaggregation by convolutional neural network and multilabel classification. Appl. Sci.
**2020**, 10, 1454. [Google Scholar] [CrossRef] [Green Version] - Bonfigli, R.; Squartini, S.; Fagiani, M.; Piazza, F. Unsupervised algorithms for non-intrusive load monitoring: An up-to-date overview. In Proceedings of the 2015 IEEE 15th International Conference on Environment and Electrical Engineering (EEEIC), Rome, Italy, 10–13 June 2015; pp. 1175–1180. [Google Scholar]
- Zoha, A.; Gluhak, A.; Nati, M.; Imran, M.A. Low-power appliance monitoring using factorial hidden markov models. In Proceedings of the 2013 IEEE Eighth International Conference on Intelligent Sensors, Sensor Networks and Information Processing, Melbourne, VIC, Australia, 2–5 April 2013; pp. 527–532. [Google Scholar]
- Kim, H.; Marwah, M.; Arlitt, M.; Lyon, G.; Han, J. Unsupervised disaggregation of low frequency power measurements. In Proceedings of the 2011 SIAM International Conference on Data Mining; SIAM: Philadelphia, PA, USA, 2011; pp. 747–758. [Google Scholar]
- Ulmeanu, A.P.; Barbu, V.S.; Tanasiev, V.; Badea, A. Hidden Markov Models revealing the household thermal profiling from smart meter data. Energy Build.
**2017**, 154, 127–140. [Google Scholar] [CrossRef] - Liang, H.; Ma, J. Separation of residential space cooling usage from smart meter data. IEEE Trans. Smart Grid
**2020**, 11, 3107–3118. [Google Scholar] [CrossRef] - Albert, A.; Rajagopal, R. Thermal profiling of residential energy use. IEEE Trans. Power Syst.
**2014**, 30, 602–611. [Google Scholar] [CrossRef] - Liang, M.; Meng, Y.; Lu, N.; Lubkeman, D.; Kling, A. HVAC load disaggregation using low-resolution smart meter data. In Proceedings of the 2019 IEEE Power & Energy Society Innovative Smart Grid Technologies Conference (ISGT), Washington, DC, USA, 18–21 February 2019; pp. 1–5. [Google Scholar]
- Zhao, H.x.; Magoulès, F. A review on the prediction of building energy consumption. Renew. Sustain. Energy Rev.
**2012**, 16, 3586–3592. [Google Scholar] [CrossRef] - Birt, B.J.; Newsham, G.R.; Beausoleil-Morrison, I.; Armstrong, M.M.; Saldanha, N.; Rowlands, I.H. Disaggregating categories of electrical energy end-use from whole-house hourly data. Energy Build.
**2012**, 50, 93–102. [Google Scholar] [CrossRef] [Green Version] - Chen, X.; Wang, J.; Xie, J.; Xu, S.; Yu, K.; Gan, L. Demand response potential evaluation for residential air conditioning loads. IET Gener. Transm. Distrib.
**2018**, 12, 4260–4268. [Google Scholar] [CrossRef] - Iyengar, S.; Lee, S.; Irwin, D.; Shenoy, P.; Weil, B. Watthome: A data-driven approach for energy efficiency analytics at city-scale. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, London, UK, 19–23 August 2018; pp. 396–405. [Google Scholar]
- Niu, F.; O’Neill, Z.; O’Neill, C. Data-driven based estimation of HVAC energy consumption using an improved Fourier series decomposition in buildings. Energy Build.
**2018**, 11, 633–645. [Google Scholar] [CrossRef] - Zhao, B.; Stankovic, L.; Stankovic, V. Electricity usage profile disaggregation of hourly smart meter data. In Proceedings of the 4th International Workshop on Non-Intrusive Load Monitoring, Austin, TX, USA, 7–8 March 2018. [Google Scholar]
- Batra, N.; Singh, A.; Whitehouse, K. Gemello: Creating a detailed energy breakdown from just the monthly electricity bill. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, 13–17 August 2016; pp. 431–440. [Google Scholar]
- Culière, F.; Leduc, L.; Belikov, A. Bayesian model of electrical heating disaggregation. In Proceedings of the 5th International Workshop on Non-Intrusive Load Monitoring, Virtual Event, Japan, 18 November 2020; pp. 25–29. [Google Scholar]
- Csilléry, K.; Blum, M.G.; Gaggiotti, O.E.; François, O. Approximate Bayesian computation (ABC) in practice. Trends Ecol. Evol.
**2010**, 25, 410–418. [Google Scholar] [CrossRef] - Sunnåker, M.; Busetto, A.G.; Numminen, E.; Corander, J.; Foll, M.; Dessimoz, C. Approximate bayesian computation. PLoS Comput. Biol.
**2013**, 9, e1002803. [Google Scholar] [CrossRef] [Green Version] - Kullback, S.; Leibler, R.A. On information and sufficiency. Ann. Math. Stat.
**1951**, 22, 79–86. [Google Scholar] [CrossRef] - Makonin, S.; Ellert, B.; Bajić, I.V.; Popowich, F. Electricity, water, and natural gas consumption of a residential house in Canada from 2012 to 2014. Sci. Data
**2016**, 3, 1–12. [Google Scholar] [CrossRef] [Green Version] - Bonfigli, R.; Felicetti, A.; Principi, E.; Fagiani, M.; Squartini, S.; Piazza, F. Denoising autoencoders for non-intrusive load monitoring: Improvements and comparative evaluation. Energy Build.
**2018**, 158, 1461–1474. [Google Scholar] [CrossRef] - Wilks, D.S. Statistical Methods in the Atmospheric Sciences; Academic Press: Cambridge, MA, USA, 2011; Volume 100. [Google Scholar]
- Hersbach, H. Decomposition of the continuous ranked probability score for ensemble prediction systems. Weather Forecast.
**2000**, 15, 559–570. [Google Scholar] [CrossRef] - Valenti, M.; Bonfigli, R.; Principi, E.; Squartini, S. Exploiting the reactive power in deep neural models for non-intrusive load monitoring. In Proceedings of the 2018 International Joint Conference on Neural Networks (IJCNN), Rio de Janeiro, Brazil, 8–13 July 2018; pp. 1–8. [Google Scholar]
- Kaselimi, M.; Protopapadakis, E.; Voulodimos, A.; Doulamis, N.; Doulamis, A. Multi-channel recurrent convolutional neural networks for energy disaggregation. IEEE Access
**2019**, 7, 81047–81056. [Google Scholar] [CrossRef] - Kaselimi, M.; Voulodimos, A.; Protopapadakis, E.; Doulamis, N.; Doulamis, A. Energan: A generative adversarial network for energy disaggregation. In Proceedings of the ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain, 4–8 May 2020; pp. 1578–1582. [Google Scholar]

**Figure 1.**Ridgeline plot of average daily total, base, and thermal load distribution as a function of mean outdoor temperature.

**Figure 2.**Ridgeline plot of average daily load distribution for heat pump, furnace, and unmonitored loads as a function of mean outdoor temperature.

**Figure 3.**Ridgeline plot of distribution of the measured base hourly load, and of its prior and posterior distributions, grouped by the hour of the day.

**Figure 4.**Ridgeline plot of distribution of the measured thermal hourly load, and of its prior and posterior distributions, grouped by the hour of the day, when the average outside temperature is in the range [5–7 °C].

**Figure 5.**Load disaggregation examples for different periods in a year, with different values of the outdoor mean temperature.

Base Load | Thermal Load | |||
---|---|---|---|---|

Prior | Posterior | Prior | Posterior | |

MAEh (W) | 162.39 | 107.95 | 215.07 | 107.95 |

rMAEh (%) | 18.88 | 12.55 | 25.00 | 12.55 |

Precision (%) | 88.93 | 93.19 | 88.93 | 93.19 |

Recall (%) | 86.83 | 90.68 | 86.83 | 90.68 |

F1 score (%) | 87.86 | 91.92 | 87.86 | 91.92 |

CRPSh (W) | 121.96 | 87.81 | 163.80 | 87.81 |

MAEd (W) | 85.30 | 52.24 | 86.91 | 52.24 |

rMAEd (%) | 9.92 | 6.07 | 10.10 | 6.07 |

MAEm (W) | 25.44 | 23.13 | 40.14 | 23.13 |

rMAEm (%) | 2.96 | 2.69 | 4.67 | 2.69 |

Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |

© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Massidda, L.; Marrocu, M.
A Bayesian Approach to Unsupervised, Non-Intrusive Load Disaggregation. *Sensors* **2022**, *22*, 4481.
https://doi.org/10.3390/s22124481

**AMA Style**

Massidda L, Marrocu M.
A Bayesian Approach to Unsupervised, Non-Intrusive Load Disaggregation. *Sensors*. 2022; 22(12):4481.
https://doi.org/10.3390/s22124481

**Chicago/Turabian Style**

Massidda, Luca, and Marino Marrocu.
2022. "A Bayesian Approach to Unsupervised, Non-Intrusive Load Disaggregation" *Sensors* 22, no. 12: 4481.
https://doi.org/10.3390/s22124481