Advertisement

Multi-step Ahead Time Series Forecasting Based on the Improved Process Neural Networks

  • Haijian Shao
  • Chunlong Hu
  • Xing DengEmail author
  • Dengbiao Jiang
Conference paper
  • 4 Downloads
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1143)

Abstract

This paper proposes a multi-step ahead time series forecasting based on the improved process neural network. The intelligent algorithm particle swarm optimization (PSO) is used to overcome the potential disadvantages of the neural network, such as slow convergence speed and derivative local minima. Firstly, the theoretical analysis of the PSO is given to optimize the multilayer perceptron (MLP) neural network architecture. Secondly, the theoretical analysis and processing flow about the MLP architecture optimization is given. Thirdly, the performance criteria are applied to verify the performance of the proposed approach. Finally, the experimental evaluation based on a typically chaotic time series with rich spectrum information is utilized to demonstrate that the proposed approach has comparative results and superior on forecasting accuracy comparing to the traditional methods.

Keywords

Time series analysis Multilayer perceptron Particle swarm optimization 

Notes

Acknowledgements

This project is supported by the National Natural Science Foundation of China (NSFC) (No. 61806087, 61902158), Natural science youth fund of Jiangsu Province (No. BK20150471), Jiangsu Province Natural Science Research Projects (No.17KJB470002) and Jiangsu University of Science and Technology Youth Science and Technology Polytechnic Innovation Project (No. 1132931804).

References

  1. 1.
    Shao, H., Deng, X.: AdaBoosting neural network for short-term wind speed forecasting based on seasonal characteristics analysis and lag space estimation. Comput. Model. Eng. Sci. 114(3), 277–293 (2018)Google Scholar
  2. 2.
    Shao, H., Wei, H., Deng, X., Xing, S.: Short-term wind speed forecasting using wavelet transformation and AdaBoosting neural networks in Yunnan wind farm. IET Renew. Power Gener. 11(4), 374–381 (2016)CrossRefGoogle Scholar
  3. 3.
    Rusen, S.: Modeling and analysis of global and diffuse solar irradiation components using the satellite estimation method of HELIOSAT. Comput. Model. Eng. Sci. 115(3), 327–343 (2018)Google Scholar
  4. 4.
    Sharma, S., Kalamkar, V.: Numerical investigation of convective heat transfer and friction in solar air heater with thin ribs. Comput. Model. Eng. Sci. 114(3), 295–319 (2018)Google Scholar
  5. 5.
    Li, S.: A deep learning based computational algorithm for identifying damage load condition: A machine learning inverse problem solver for failure analysis. Comput. Model. Eng. Sci. 287–307 (2018)Google Scholar
  6. 6.
    Shao, H., Deng, X., Jiang, Y.: A novel deep learning approach for short-term wind power forecasting based on infinite feature selection and recurrent neural network. J. Renew. Sustain. Energy 10(4), 043303-1–043303-13 (2018)Google Scholar
  7. 7.
    Ren, S., Chen, G., Li, T., Chen, Q., Li, S., Jones, R., Chan, Y.: A deep learning-based computational algorithm for identifying damage load condition: an artificial intelligence inverse problem solution for failure analysis. Comput. Model. Eng. Sci. 117(3), 287–307 (2018)Google Scholar
  8. 8.
    Casdagli, M.: Nonlinear prediction of chaotic time series. Phys. D: Nonlinear Phenom. 35(3), 335–356 (1989)MathSciNetCrossRefGoogle Scholar
  9. 9.
    Poli, R., Kennedy, J., Blackwell, T.: Particle swarm optimization. Swarm Intell. 1(1), 33–57 (2007)CrossRefGoogle Scholar
  10. 10.
    Bonyadi, M., Zbigniew, M.: Particle swarm optimization for single objective continuous space problems: a review, pp. 1–54. MIT Press, Cambridge (2017)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2021

Authors and Affiliations

  • Haijian Shao
    • 1
    • 2
  • Chunlong Hu
    • 1
  • Xing Deng
    • 1
    • 2
    Email author
  • Dengbiao Jiang
    • 1
  1. 1.School of Computer Science and EngineeringJiangsu University of Science and TechnologyJiangsu, ZhenjiangChina
  2. 2.Key Laboratory of Measurement and Control for CSE, School of AutomationMinistry of Education, Southeast UniversityNanjingChina

Personalised recommendations