Forecasting for the Total Electricity Consumption of Taiwan by Fuzzy Time Series Model

  • Jing-Rong ChangEmail author
  • Zhong-Qi Liu
  • Pei-Yu Yu
Conference paper
Part of the Smart Innovation, Systems and Technologies book series (SIST, volume 110)


Prediction at present no matter in what industry is applicable. It is not only the price, enrollment, etc., and even energy is applicable. In today’s era of so advanced technology, “electricity” is a very important energy source for the public. However, sometimes the generator is powered off due to excessive power consumption of the people, such as: the power outage in Taiwan in August 2017. In this paper, fuzzy time series will be used to explore the total electricity consumption in Taiwan in recent years. And we can also use the results to understand the people’s electricity consumption, and even adjust the power supply when necessary. Among them, in the experimental part, the method of NQDA discrete will be used for data pre-processing, and then the corresponding fuzzy rules will be established. Finally, the fuzzy values will be de-fuzzified and the predicted values will be output. The strength of the method was verified by the total electricity consumption in Taiwan from 1996 to 2017.


Fuzzy time series Electricity consumption 


  1. 1.
    Song, Q., Chissom, B.S.: Fuzzy time series and its models. Int. J. Fuzzy Sets Syst. 54(3), 269–277 (1993)MathSciNetCrossRefGoogle Scholar
  2. 2.
    Huarng, K.: Effective lengths of intervals to improve forecasting in fuzzy time series. Int. J. Fuzzy Sets Syst. 123(3), 387–394 (2001)MathSciNetCrossRefGoogle Scholar
  3. 3.
    Chen, S.M.: Forecasting enrollments based on fuzzy time series. Int. J. Fuzzy Sets Syst. 81(3), 311–319 (1996)CrossRefGoogle Scholar
  4. 4.
    Chang, J.R., Liu, C.C.: A fuzzy time series model based on N-th quantile discretization approach for TAIEX forecasting. In: IEEE 5th International Conference on Knowledge and Smart Technology (KST), pp. 5–10, IEEE (2013)Google Scholar
  5. 5.
    Electricity Consumption Statistics:
  6. 6.
    Song, Q., Chissom, B.S.: Forecasting enrollments with fuzzy time series—Part II. Int. J. Fuzzy Sets Syst. 62(1), 1–8 (1994)CrossRefGoogle Scholar
  7. 7.
    Chang, J.R., Lee, Y.T., Liao, S.Y., Cheng, C.H.: Cardinality-based fuzzy time series for forecasting enrollments. In: Okuno, H.G., Ali, M. (eds.) Industrial, Engineering and Other Applications of Applied Intelligent Systems 2007, LNCS, vol. 4570, pp. 735–744. Springer, Berlin, Heidelberg (2007)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Department of Information ManagementChaoyang University of TechnologyTaichungTaiwan

Personalised recommendations