Advertisement

Short-Term Load Forecasting Based on RBM and NARX Neural Network

  • Xiaoyu Zhang
  • Rui Wang
  • Tao Zhang
  • Ling Wang
  • Yajie Liu
  • Yabing Zha
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10956)

Abstract

In recent years, DBN applied to load forecasting as a hot issue has aroused the concern of many scholars at home and abroad. A new method based on RBM and NARX neural network for short-term load forecasting is brought forward in this paper. In order to test the performance of this model, the historical load data of a town in the UK is used. The obtained results are compared with DBN and NARX neural network based on the same dataset. Experimental results show that the proposed method significantly improves the predication accuracy.

Keywords

Short-term load forecasting Deep belief network Restricted Boltzmann machine NARX neural network 

Notes

Acknowledgement

This work was supported by the National Natural Science Foundation of China (Nos. 61773390, 71571187) and the Distinguished Natural Science Foundation of Hunan Province (No. 2017JJ1001).

References

  1. 1.
    Chen, Y., Luh, P.B., Rourke, S.J.: Short-term load forecasting: similar day-based wavelet neural networks. World Congr. Intell. Control Autom. 25(1), 3353–3358 (2008)Google Scholar
  2. 2.
    Chen, C., Zhou, J.N.: Application of regression analysis in power system load forecasting. Adv. Mater. Res. 960–961, 1516–1522 (2014)CrossRefGoogle Scholar
  3. 3.
    Shankar, R., Chatterjee, K., Chatterjee, T.K.: A very short-term load forecasting using kalman filter for load frequency control with economic load dispatch. J. Eng. Sci. Technol. Rev. 5(1), 97–103 (2012)Google Scholar
  4. 4.
    Wei, L., Zhen-gang, Z.: Based on time sequence of ARIMA model in the application of short-term electricity load forecasting. In: International Conference on Research Challenges in Computer Science, pp. 11–14 (2009)Google Scholar
  5. 5.
    Vähäkyla, P., Hakonen, E., Léman, P.: Short-term forecasting of grid load using Box-Jenkins techniques. Int. J. Electr. Power Energy Syst. 2(1), 29–34 (1980)CrossRefGoogle Scholar
  6. 6.
    Li, X., Chen, H., Gao, S.: Electric power system load forecast model based on State Space time-varying parameter theory. In: IEEE International Conference on Power System Technology, pp. 1–4 (2010)Google Scholar
  7. 7.
    Christiaanse, W.R.: Short-term load forecasting using general exponential smoothing. IEEE Trans. Power Appar. Syst. PAS-90, 900–911(2007)CrossRefGoogle Scholar
  8. 8.
    Koo, B.G., Kim, M.S., Kim, K.H.: Short-term electric load forecasting using data mining technique. In: International Conference on Intelligent Systems and Control, pp. 153–157. IEEE (2013)Google Scholar
  9. 9.
    Lee, K.Y., Cha, Y.T., Park, J.H.: Short-term load forecasting using artificial neural networks. IEEE Trans. Power Syst. 7(1), 124–132 (2014)CrossRefGoogle Scholar
  10. 10.
    Li, G., Cheng, C.T., Lin, J.Y.: Short-term load forecasting using support vector machine with SCE-UA algorithm. In: International Conference on Natural Computation, pp. 290–294. IEEE (2007)Google Scholar
  11. 11.
    Hinton, G.E., Osindero, S., Teh, Y.W.: A fast learning algorithm for deep belief nets. Neural Comput. 18(7), 1527 (2006)MathSciNetCrossRefGoogle Scholar
  12. 12.
    Sun, S., Liu, F., Liu, J.: Web classification using deep belief networks. In: IEEE International Conference on Computational Science and Engineering, pp. 768–773 (2014)Google Scholar
  13. 13.
    Arsa, D.M.S., Jati, G., Mantau, A.J.: Dimensionality reduction using deep belief network in big data case study: hyperspectral image classification. In: International Workshop on Big Data and Information Security, pp. 71–76. IEEE (2017)Google Scholar
  14. 14.
    Cheng, M.: The cross-field DBN for image recognition. In: IEEE International Conference on Progress in Informatics and Computing, pp. 83–86. IEEE (2016)Google Scholar
  15. 15.
    Zhang, X., Wang, R., Zhang, T.: Short-term load forecasting based on an improved deep belief network. In: International Conference on Smart Grid and Clean Energy Technologies, pp. 339–342 (2016)Google Scholar
  16. 16.
    Zhang, X., Wang, R., Zhang, T., Liu, Y., Zha, Y.: Effect of transfer functions in deep belief network for short-term load forecasting. In: He, C., Mo, H., Pan, L., Zhao, Y. (eds.) BIC-TA 2017. CCIS, vol. 791, pp. 511–522. Springer, Singapore (2017).  https://doi.org/10.1007/978-981-10-7179-9_40CrossRefGoogle Scholar
  17. 17.
    Takens F.: Detecting strange attractors in turbulence. In: Dynamical Systems and Turbulence, Warwick 1980, pp. 366–381. Springer, Heidelberg (1981)Google Scholar
  18. 18.
    Hegger, R., Kantz, H., Schreiber, T.: Practical implementation of nonlinear time series methods: the tisean package. Chaos 9(2), 413–435 (1999)CrossRefGoogle Scholar
  19. 19.
    Nonlinear Time Series Analysis (TISEAN). https://www.mpipks-dresden.mpg.de/~tisean/
  20. 20.
    Wang, R., Purshouse, R.C., Fleming, P.J.: Preference-inspired co-evolutionary algorithms for many-objective optimisation. IEEE Trans. Evol. Comput. 17, 474–494 (2013)CrossRefGoogle Scholar
  21. 21.
    Wang, R., Ishibuchi, H., Zhou, Z., Liao, T., Zhang, T.: Localized weighted sum method for many-objective optimization. IEEE Trans. Evol. Comput. 22, 3–18 (2018)CrossRefGoogle Scholar
  22. 22.
    Wang, R., Zhang, Q., Zhang, T.: Decomposition based algorithms using Pareto adaptive scalarizing methods. IEEE Trans. Evol. Comput. 20, 821–837 (2016)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  • Xiaoyu Zhang
    • 1
  • Rui Wang
    • 1
  • Tao Zhang
    • 1
  • Ling Wang
    • 2
  • Yajie Liu
    • 1
  • Yabing Zha
    • 1
  1. 1.College of System EngineeringNational University of Defense TechnologyChangshaPeople’s Republic of China
  2. 2.Department of AutomationTsinghua UniversityBeijingPeople’s Republic of China

Personalised recommendations