Advertisement

Time-Series Based Ensemble Forecasting Algorithm for Out-Limit Detection on Stable Section of Power Network

  • Haizhu WangEmail author
  • Chao Hu
  • Yue Chen
  • Bo Zhou
  • Zhangguo Chen
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 905)

Abstract

With the development of power company network technology, out-limit forecast of grid stable section is an important point of grid operation and control. However, due to the large amount of grid stable section data in power grid, traditional single classic forecasting algorithms are difficult to predict efficiently and accurately. In order to solve this problem, we proposed a time-series based ensemble forecasting algorithm (TSEFA) for out-limit detection on grid stable section which integrates multiple classification forecasting algorithms to classify and predict the collected grid stable section data, and then to realize the forecasting of the out-limit quantity with comprehensive optimal accuracy. Compared with the other four single-model algorithms (i.e. SWAF, RA, ANN, SVM), our TSEFA algorithm achieves the effect of efficient and accurate forecasting, and enhances the security and stability of the grid stable section analysis platform.

Keywords

Time-series Out-limit detection Ensemble forecasting Grid stable section 

Notes

Acknowledgement

This work is supported by Science and Technology Project of Guangdong Power Grid Co., Ltd. “New Generation Grid Dispatch Operation Data Storage and Analysis Service Based on Big Data” (No. 036000KK52160030).

References

  1. 1.
    Dong, Y., Zhang, J., Garibaldi, J.M.: Neural networks and AdaBoost algorithm based ensemble models for enhanced forecasting of nonlinear time series. In: International Joint Conference on Neural Networks, pp. 149–156. IEEE (2014)Google Scholar
  2. 2.
    Kapoor, P., Bedi, S.S.: Weather forecasting using sliding window algorithm. ISRN Sig. Process. 3(1), 1–5 (2013)Google Scholar
  3. 3.
    Punzo, P.D., Robust, M.: Clustering in regression analysis via the contaminated gaussian cluster-weighted model. J. Classif. 34(1), 1–45 (2017)MathSciNetCrossRefGoogle Scholar
  4. 4.
    Park, D.C., El-Sharkawi, M.A., Marks, R.J.I., Atlas, L.E., Damborg, M.J.: Electric load forecasting using an artificial neural network. IEEE Trans. Power Syst. 6(2), 442–449 (1991)CrossRefGoogle Scholar
  5. 5.
    Percival, D.B., Walden, A.T.: Wavelet Methods for Time Series Analysis, vol. 6, no. 1, pp. 13–20. China Machine Press, Beijing (2004)Google Scholar
  6. 6.
    Wan, C.H., Yang-Ping, O.U.: Deformation data of dam monitoring based on wavelet analysis method. Beijing Surveying & Mapping, pp. 2–5 (2010)Google Scholar
  7. 7.
    Song, C., Zhang, Q.: Sliding-window algorithm for asynchronous cooperative sensing in wireless cognitive networks. In: IEEE International Conference on Communications, pp. 3432–3436. IEEE (2008)Google Scholar
  8. 8.
    Walker, E.: Applied regression analysis and other multivariable methods. Technometrics 31(1), 117–118 (2008)CrossRefGoogle Scholar
  9. 9.
    Ostad-Ali-Askari, K., Shayannejad, M., Ghorbanizadeh-Kharazi, H.: Artificial neural network for modeling nitrate pollution of groundwater in marginal area of Zayandeh-rood River, Isfahan, Iran. KSCE J. Civil Eng. 21(1), 1–7 (2016)Google Scholar
  10. 10.
    Chen, N., Lu, W., Yang, J.: Support Vector Machine, pp. 24–52. Springer, London (2016)Google Scholar
  11. 11.
    Janacek, G.: Time series analysis forecasting and control. J. Time 31(4), 303 (2012)Google Scholar
  12. 12.
    Alberg, D., Last, M.: Short-term load forecasting in smart meters with sliding window-based ARIMA algorithms. In: Nguyen, N.T., Tojo, S., Nguyen, L.M., Trawiński, B. (eds.) ACIIDS 2017. LNCS (LNAI), vol. 10192, pp. 299–307. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-54430-4_29CrossRefGoogle Scholar
  13. 13.
    Zhang, H., Wang, P., Sun, J.: Regression analysis of interval-censored failure time data with possibly crossing hazards. Stat. Med. 37(5), 497 (2018)MathSciNetCrossRefGoogle Scholar
  14. 14.
    Folkes, S.R., Lahav, O., Maddox, S.J.: An artificial neural network approach to the classification of galaxy spectra. Mon. Not. R. Astron. Soc. 283(2), 651–665 (2018)CrossRefGoogle Scholar
  15. 15.
    Yuan, Y.: Canonical duality solution for alternating support vector machine. J. Ind. Manag. Optim. 8(3), 611–621 (2017)MathSciNetzbMATHCrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Haizhu Wang
    • 1
    Email author
  • Chao Hu
    • 2
  • Yue Chen
    • 2
  • Bo Zhou
    • 2
  • Zhangguo Chen
    • 1
  1. 1.Electric Power Dispatching and Control Center of Guangdong Power Grid Co., Ltd.GuangzhouChina
  2. 2.NARI Information & Communication Technology Co., Ltd.NanjingChina

Personalised recommendations