SEGMENTATION OF THE TIME SERIES OF ENERGY CONSUMPTION PARAMETERS

B.M. Pleskach

Èlektron. model. 2021, 43(2):79-85

ABSTRACT

The importance of introducing into the practice of industrial enterprises means of diagnosing energy efficiency and supporting decision-making in the management of energy consumption is noted. The actual problem of formation of information base of precedent method of diagnosing energy efficiency of technological systems is considered. Such a base should be created at the pace of the technological process and keep the characteristics of cases of efficient use of energy. It is proposed to allocate precedents of energy consumption by segmenting the flow of derivative mode parameters of equipment operation into stationary sections. Segmentation is based on the sequential calculation of the distances between the elements of a series in the space of mode parameters and comparing them with the threshold values. The technique and algorithm of time series segmentation are given.

KEYWORDS

time series segmentation, energy monitoring, precedents of energy consumption.

REFERENCES

  1. Olajire, A.A. (2012), “The brewing industry and environmental challenges”, Journal of Cleaner Production, 256, рр. 1-21. 
    https://doi.org/10.1016/j.jclepro.2012.03.003
  2. Mandal, S. and Madheswaran, S. (2011), “Energy use efficiency of Indian cement companies: a data envelopment analysis”, Energy Efficiency, Vol. 4,  57–73. 
    https://doi.org/10.1007/s12053-010-9081-7
  3. Moss, K. (2006), “Monitoring and Targeting”, Computer Science, available at: https:// doi.org/10.4324/9780203349021. 
  4. Ramasubramanian, S., Avinash, Y., Pragathi Chitra, S., et al. (2009), “An activity based approach to minimize energy usage of service sector infrastructure”, Infrastructure Systems and Services: Developing 21st Century Infrastructure Networks (INFRA), 2009 Second International Conference on IEEE, pp 1–6.
    https://doi.org/10.1109/INFRA.2009.5397878
  5. Prakhovnyk, A.V., Zakladny, O.M. and Zakladny, O.O. (2011), “Functional diagnostics of energy efficiency of electromechanical systems with induction motors”, Electrical and computer systems, Vol. 3, pp. 375-376, available at: http://nbuv.gov.ua/UJRN/etks_2011_ 3_129.
  6. Keogh, E., Chu, S., Hart, D. and Pazzani, M. (200), “Segmenting Time Series: A Survey and Novel Approach”, Data Mining in Time Series Databases, pp. 1-21, available at: https://www.cs.rutgers.edu/~pazzani/Publications/survey.pdf.
    https://doi.org/10.1142/9789812565402_0001
  7. Shumway, R.H. and Stoffer, D.S. (2011), Time Series Analysis and Its Applications: With R Examples, 3rd Edition, Springer, Pittsburgh, PA, USA.
    https://doi.org/10.1007/978-1-4419-7865-3
  8. Vasko, K. and Toivonen, H. (2002), “Estimating the number of segments in time series data using permutation tests”, IEEE International Conference on Data Mining, pp. 466–473.
    https://doi.org/10.1109/ICDM.2002.1183990
  9. Himberg, J., Korpiaho, K., Mannila, H., Tikanmaki, J. and Toivonen, H. (2001), “Time-series segmentation for context recognition in mobile devices”, IEEE International Conference on Data Mining (ICDM01), San Jose, CA, USA, pp. 466–473.
    https://doi.org/10.1109/ICDM.2001.989520

Full text: PDF