Cluster Computing

, Volume 22, Supplement 5, pp 11129–11141 | Cite as

The power load’s signal analysis and short-term prediction based on wavelet decomposition

  • Huan Wang
  • Min OuyangEmail author
  • Zhibing Wang
  • Ruishi Liang
  • Xin Zhou


The complex signal represented by power load is affected by many factors, so the signal components are very complicated. So that, it is difficult to obtain satisfactory prediction accuracy by using a single model for the complex signal. In this case, wavelet decomposition is used to decompose the power load into a series of sub signals. The low frequency sub signal is remarkably periodic, and the high frequency sub signals can prove to be chaotic signals. Then the signals of different characteristics are predicted by different models. For the low frequency sub signal, the support vector machine (SVM) is adopted. In SVM model, air temperature and week attributes are included in model inputs. Especially the week attribute is represented by a 3-bit binary encoding, which represents Monday to Sunday. For the chaotic high frequency sub signals, the chaotic local prediction (CLP) model is adopted. In CLP model, the embedding dimension and time delay are key parameters, which determines the prediction accuracy. In order to find the optimal parameters, a segmentation validation algorithm is proposed in this paper. The algorithm segments the known power load according to the time sequence. Then, based on the segmentation data, the optimal parameters are chosen based on the prediction accuracy. Compared with a single model, the prediction accuracy of the proposed algorithm is improved obviously, which proves the effectiveness.


Power load Wavelet transform Support vector machine Chaotic local prediction Segmentation validation 



This work was supported by National Natural Science Foundation of China (Grant Nos. 61300095 and 11604094), Natural Science Foundation of Hunan Province, China (Grant No. 2017JJ2068) and the Science Research Foundation of Hunan Provincial Education Department (Grant Nos. 16C0479 and 14A037).


  1. 1.
    Hu, D.G., Shu, H., Hu, H.D.: Spatiotemporal regression Kriging to predict precipitation using time-series MODIS data. Cluster Comput. 20(1), 347–357 (2017). SIGoogle Scholar
  2. 2.
    Zhang, G.W., Xu, L.Y., Xue, Y.L.: Model and forecast stock market behavior integrating investor sentiment analysis and transaction data. Cluster Comput. 20(1), 789–803 (2017)Google Scholar
  3. 3.
    Hirata, Y., Aihara, K.: Improving time series prediction of solar irradiance after sunrise: comparison among three methods for time series prediction. Solar Energy 149, 294–301 (2017)Google Scholar
  4. 4.
    Yang, G.L., Cao, S.Q., Wu, Y.: Recent advancements in signal processing and machine learning. Math. Probl. Eng. 2014 Article ID 549024 (2014)Google Scholar
  5. 5.
    Moreau, F., Gibert, D., Holschneider, M., et al.: Identification of sources of potential fields with the continuous wavelet transform: basic theory. J. Geophys. Res. 104(B3), 5003–5013 (1999)Google Scholar
  6. 6.
    Mallat, S.: A Wavelet Tour of Signal Processing: The Sparse Way, vol. 3. Elsevier, Amsterdam (2009)zbMATHGoogle Scholar
  7. 7.
    Kumari, G.S., Kumar, S.k.: Electrocardio graphic signal analysis using wavelet transforms. In: 2015 International Conference on Electrical, Electronics, Signals, Communication and Optimization (EESCO), pp. 1–6 (2015)Google Scholar
  8. 8.
    Rosenstein, M.T., Collins, J.J., Luca, C.J.D.: A practical method for calculating largest Lyapunov exponents from small data sets. Phys. D 65(1–2), 117–134 (1993)MathSciNetzbMATHGoogle Scholar
  9. 9.
    Yong, Z.: New prediction of chaotic time series based on local Lyapunov exponent. Chin. Phys. Lett. 22(5) Article ID 020503 (2013)Google Scholar
  10. 10.
    Corts, C., Vapnik, V.: Support vector networks. Mach. Learn. 20(3), 273–297 (1995)zbMATHGoogle Scholar
  11. 11.
    Petra, V., Anna, B.E., Viera, R., Slavomír, Š., et al.: Smart grid load forecasting using online support vector regression. Comput. Electr. Eng. 000, 1–16 (2017)Google Scholar
  12. 12.
    Su, L.Y., Li, C.L.: Local prediction of chaotic time series based on polynomial coefficient autoregressive model. Math. Probl. Eng. 2015, Article ID 901807Google Scholar
  13. 13.
    Qu, J.L., Wang, X.F., Qiao, Y.C, et al.: An improved local weighted linear prediction model for chaotic time series. Chin. Phys. Lett. 31(2) Article ID 020503 (2014)Google Scholar
  14. 14.
    Frandes, M., Timar, B., Timar, R., Lungeanu, D.: Chaotic time series prediction for glucose dynamics in type 1 diabetes mellitus using regime-switching models. Sci. Rep. 7 Article ID 6232 (2017)Google Scholar
  15. 15.
    Livi, L., Sadeghian, A.: Granular computing, computational intelligence, and the analysis of non-geometric input spaces. Granul. Comput. 1(1), 13–20 (2016)Google Scholar
  16. 16.
    Antonelli, M., Ducange, P., Lazzerini, B., Marcelloni, F.: Multi-objective evolutionary design of granular rule-based classifiers. Granul. Comput. 1(1), 37–58 (2016)Google Scholar
  17. 17.
    Lingras, P., Haider, F., Triff, M.: Granular meta-clustering based on hierarchical, network, and temporal connections. Granul. Comput. 1(1), 71–92 (2016)Google Scholar
  18. 18.
    Skowron, A., Jankowski, A., Dutta, S.: Interactive granular computing. Granul. Comput. 1(2), 95–113 (2016)MathSciNetzbMATHGoogle Scholar
  19. 19.
    Dubois, D., Prade, H.: Bridging gaps between several forms of granular computing. Granul. Comput. 1(2), 115–126 (2016)Google Scholar
  20. 20.
    Yao, Y.: A triarchic theory of granular computing. Granul. Comput. 1(2), 145–157 (2016)Google Scholar
  21. 21.
    Ciucci, D.: Orthopairs and granular computing. Granul. Comput. 1(3), 159–170 (2016)MathSciNetGoogle Scholar
  22. 22.
    Mallat, S.: Multi-resolution approximations and wavelet orthogonal bases of l2(r). Trans. Am. Math. Soc. 315, 67–87 (1989)Google Scholar
  23. 23.
    Smola, A., Scholkopf, B.: A Tutorial on Support Vector Regression. Royal Holloway College, London (1998)zbMATHGoogle Scholar
  24. 24.
    Zhang, H.R., Han, Z.Z.: An improved sequential minimal optimization learning algorithm for regression support vector machine. J. Softw. 12(3), 2006–2013 (2003)MathSciNetzbMATHGoogle Scholar
  25. 25.
    Takens, F.: Detecting Strange Attractors in Fluid Turbulence. Springer, Berlin (1981)zbMATHGoogle Scholar
  26. 26.
    Gautama, T., Mandic, D.P., Van Hulle, M.M.: A differential entropy based method for determining the optimal embedding parameters of a signal. In: 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing. Hong Kong, China: IEEE, pp. 29–32 (2003)Google Scholar
  27. 27.
    Kohavi, R.: A study of cross-validation and bootstrap for accuracy estimation and model selection. Int. Joint Conf. Artif. Intell. 14, 1137–1143 (1995)Google Scholar
  28. 28.
    Rao, C.R., Wu, Y.: Linear model selection by cross-validation. J. Stat. Plan. Inference 128(1), 231–240 (2005)MathSciNetzbMATHGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2017

Authors and Affiliations

  • Huan Wang
    • 1
    • 2
  • Min Ouyang
    • 2
    • 3
    Email author
  • Zhibing Wang
    • 2
    • 3
  • Ruishi Liang
    • 4
  • Xin Zhou
    • 2
    • 5
  1. 1.School of Electron and Information EngineeringUniversity of Electronic Science and Technology of China, Zhongshan InstituteZhongshanChina
  2. 2.Key Laboratory of Intelligent Information Perception and Processing Technology (Hunan Province)ZhuzhouChina
  3. 3.School of ComputerHunan University of TechnologyZhuzhouChina
  4. 4.School of Computer EngineeringUniversity of Electronic Science and Technology of China, Zhongshan InstituteZhongshanChina
  5. 5.School of SciencesHunan University of TechnologyZhuzhouChina

Personalised recommendations