Skip to main content

LSTM-Based Reinforcement Q Learning Model for Non Intrusive Load Monitoring

  • 397 Accesses

Part of the Lecture Notes in Networks and Systems book series (LNNS,volume 451)

Abstract

Smart meters have been widely used in smart homes to provide efficient monitoring and billing to consumers. While providing customers with usage information at the device level can lead to energy savings, modern smart meters can only provide useful data for the whole house with low accuracy. Therefore, machine learning applied to the problem of energy disaggregation has gained wide attention. In this paper, an intelligent and optimized recurrent Long Short-Term Memory (LSTM) reinforcement Q-learning technique was evaluated on a large-scale household energy use dataset for Non-Intrusive Load Monitoring (NILM). Our proposed model can maximize energy disaggregation performance and is able to predict new observations from previous ones. The design of such a deep learning model for energy disaggregation is examined in the universal REDD smart meter dataset and compared to reference model. The experimental results demonstrate that the accuracy of the energy prediction in terms of accuracy was significantly improved in 99% of cases after using LSTM-based reinforcement Q learning, compared to the deep learning approach TFIDF-DAE [1] with an accuracy of 85%.

This is a preview of subscription content, access via your institution.

Buying options

Chapter
USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-3-030-99619-2_1
  • Chapter length: 13 pages
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
eBook
USD   219.00
Price excludes VAT (USA)
  • ISBN: 978-3-030-99619-2
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
Softcover Book
USD   279.99
Price excludes VAT (USA)
Fig. 1.
Fig. 2.
Fig. 3.
Fig. 4.

References

  1. Siddiqui, A., Sibal, A.: Energy disaggregation in smart home appliances: a deep learning approach. Energy (2020, in press). Elsevier. hal-02954362

    Google Scholar 

  2. Jaradat, A., Lutfiyya, H., Haque, A.: Smart home energy visualizer: a fusion of data analytics and information visualization. IEEE Can. J. Electr. Comput. Eng. 45(1), 77–87 (2022)

    CrossRef  Google Scholar 

  3. Siddiqui, S.A., Ahmad, M.O., Ahmed, J.: Smart home for efficient energy management. In: Agarwal, P., Mittal, M., Ahmed, J., Idrees, S.M. (eds.) Smart Technologies for Energy and Environmental Sustainability. GET, pp. 97–103. Springer, Cham (2022). https://doi.org/10.1007/978-3-030-80702-3_6

    CrossRef  Google Scholar 

  4. Kim, H., Choi, H., et al.: A systematic review of the smart energy conservation system: from smart homes to sustainable smart cities. Renew. Sustain. Energy Rev. 140, 110755 (2021)

    Google Scholar 

  5. Pinto, G., Wang, Z., Roy, A., Hong, T., Capozzoli, A.: Transfer learning for smart buildings: a critical review of algorithms, applications, and future perspectives. Adv. Appl. Energy 5, 100084 (2022)

    Google Scholar 

  6. Popa, D., Pop, F., Serbanescu, C., Castiglione, A.: Deep learning model for home automation and energy reduction in a smart home environment platform. Neural Comput. Appl. 31(5), 1317–1337 (2018). https://doi.org/10.1007/s00521-018-3724-6

    CrossRef  Google Scholar 

  7. Mathew, A., Roy, A., Mathew, J., et al.: Intelligent residential energy management system using deep reinforcement learning. IEEE Syst. J. 14(4), 5362–5372 (2020)

    Google Scholar 

  8. Ruelens, F., Claessens, B.J., Vrancx, P., et al.: Direct load control of thermostatically controlled loads based on sparse observations using deep reinforcement learning. CSEE J. Power Energy Syst. 5(4), 423–432 (2019)

    Google Scholar 

  9. Arroyo, J., Manna, C., Spiessens, F., et al.: Reinforced model predictive control (RL-MPC) for building energy management. Appl. Energy J. 309, 118346 (2022)

    Google Scholar 

  10. Dargazany, A.: DRL: deep reinforcement learning for intelligent robot control-concept. literature and future. arXiv preprint arXiv:2105.13806 (2021)

  11. Ren, M., Liu, X., Yang, Z., et al.: A novel forecasting based scheduling method for household energy management system based on deep reinforcement learning. Sustain. Urban Areas 76, 103207 (2022)

    Google Scholar 

  12. Claessens, B.J., Vrancx, P., Ruelens, F.: Convolutional neural networks for automatic state-time feature extraction in reinforcement learning applied to residential load control. IEEE Trans. Smart Grid 9(4), 3259–3269 (2016)

    Google Scholar 

  13. Huang, Q., Huang, R., Hao, W., et al.: Adaptive power system emergency control using deep reinforcement learning. IEEE Trans. Smart Grid 11(2), 1171–1182 (2019)

    Google Scholar 

  14. Bucci, G., Ciancetta, F., Fiorucci, E., et al.: State of art overview of non-intrusive load monitoring applications in smart grids. Sensors 18, 100145 (2021)

    Google Scholar 

  15. Deshpande, R., Hire, S., Mohammed, Z.A.: Smart energy management system using non-intrusive load monitoring. SN Comput. Sci. 3(2), 1–11 (2022)

    Google Scholar 

  16. Figueiredo, M., De Almeida, A., Ribeiro, B.: Home electrical signal disaggregation for non-intrusive load monitoring (NILM) systems. Neurocomputing 96, 66–73 (2012)

    CrossRef  Google Scholar 

  17. Bonfigli, R., Principi, E., et al.: Non-intrusive load monitoring by using active and reactive power in additive Factorial Hidden Markov Models. Appl. Energy 208, 1590–1607 (2017)

    CrossRef  Google Scholar 

  18. Guo, L., Wang, S., Chen, H., et al.: A load identification method based on active deep learning and discrete wavelet transform. IEEE Access 8, 113932–113942 (2020)

    Google Scholar 

  19. Nalmpantis, C., Gkalinikis, V., et al.: Neural Fourier energy disaggregation. Sensors 22(2), 473 (2022)

    Google Scholar 

  20. Gomes, E., Pereira, L.: PB-NILM: pinball guided deep non-intrusive load monitoring. IEEE Access 8, 48386–48398 (2020)

    Google Scholar 

  21. Pereira, L., Nunes, N.: Performance evaluation in non-intrusive load monitoring: datasets, metrics, and tools - a review. Wiley Interdisc. Rev. Data Min. Knowl. Discov. 8(6), 1265 (2018)

    Google Scholar 

  22. Khodayar, M.: Learning deep architectures for power systems operation and analysis. Electrical Engineering Theses and Dissertations. 41 (2020)

    Google Scholar 

  23. Li, H.: A Non-intrusive home load identification method based on adaptive reinforcement learning algorithm. IOP Conf. Ser. Mater. Sci. Eng. 853(1), 012030 (2020)

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Kalthoum Zaouali .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Verify currency and authenticity via CrossMark

Cite this paper

Zaouali, K., Ammari, M.L., Bouallegue, R. (2022). LSTM-Based Reinforcement Q Learning Model for Non Intrusive Load Monitoring. In: Barolli, L., Hussain, F., Enokido, T. (eds) Advanced Information Networking and Applications. AINA 2022. Lecture Notes in Networks and Systems, vol 451. Springer, Cham. https://doi.org/10.1007/978-3-030-99619-2_1

Download citation