Predictive Analysis of NARX, NLIO, and RNN Networks for Short-Term Wind Power Forecasting

  • Tushar SrivastavaEmail author
  • M. M. Tripathi
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 612)


The power utilities now a day’s focusing on the use of renewable energy at massive level due to increasing awareness about environment and depleting natural resources. Wind power is one of the main renewable forms of energy but due to the intermittent nature of wind speed, it becomes important to have a precise prediction of speed of wind and wind turbine power before it can be used as primary source of electricity. In this paper, three artificial intelligence methods NARX, NLIO, and RNN Networks are used for short-term wind power forecasting using the data of Kolkata region of India. The simulation results suggest that RNN is able to forecast the wind power better than NARX and NLIO network.


Bayesian regularization Recurrent neural network Mean absolute percentage error Nonlinear auto-regressive exogenous network Nonlinear input–output 


  1. 1.
    Huang C-M, Kuo C-J, Huang Y-C (2017) Short-term wind power forecasting and uncertainty analysis using a hybrid intelligent method. IET Renew Power Gener 11(5):678–687CrossRefGoogle Scholar
  2. 2.
    Shilpa GN, Dr. Sheshadri GS (2017) Short-term load forecasting using ARIMA model for Karnataka state electrical load. Int J Eng Res Development 13(7):75–79Google Scholar
  3. 3.
    Elgarhy SM, Othman MM, Taha A, Hasanien HM (2017) Short term load forecasting using ANN technique. In: International Middle East power system conference (MEPCON), Egypt, pp 1385–1394Google Scholar
  4. 4.
    Buitrago J, Asfour S (2017) Short-term forecasting of electric loads using nonlinear autoregressive artificial neural networks with exogenous vector inputs. In: Energies (MDPI), Miami, pp. 10–40, Jan 2017Google Scholar
  5. 5.
    Philip OO, Adeleke BT (2017) Predictive and comparative analysis of NARX and NIO timeSeies prediction. Am J Eng Res (AJER). ISSN: 2320-0936Google Scholar
  6. 6.
    Olaofe ZO, Folly KA (2012) Wind power estimation using recurrent neural network technique. IEEE, July 2012Google Scholar
  7. 7.
    Kaur H, Salaria DS (2013) Bayesian regularization based neural network tool for software effort estimation. Global J Comput Sci Technol Neural Artif Intell. ISSN: 0975-4350Google Scholar
  8. 8.
    Bâral A, Căruţaşu G, Botezatu C, Pîrjan A (2016) Comparative analysis between wind and solar forecasting methods using artificial neural networks. In: 16th IEEE international symposium on computational intelligence and informatics (CINTI 2015), BudapestGoogle Scholar
  9. 9.
    Kayri M (2016) Predictive abilities of Bayesian regularization and Levenberg–Marquardt algorithms in artificial neural networks: a comparative empirical study on social data. In: Mathematical and computational applications (MDPI), pp 1–11, May 2016MathSciNetCrossRefGoogle Scholar
  10. 10.
    Tripathi MM, Singh SN, Upadhyay KG (2009) Price forecasting in competitive electricity markets: an analysis. In: Proceedings of international conference on energy engineering (ICEE 2009), Puducherry, pp 7–9Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  1. 1.Delhi Technological UniversityNew DelhiIndia

Personalised recommendations