Volume 7, No. 3, May 2018

General Information

  • ISSN: 2278-0149 (Online)
  • Abbreviated Title:  Int. J. Mech. Eng. Robot. Res.  
  • Editor-in-Chief: ​Prof Richard (Chunhui) Yang, Western Sydney University, Australia
  • Associate Editor: Prof. B.V. Appa Rao, Andhra University; Prof. Ian McAndrew, Capitol Technology University, USA
  • Managing Editor: Murali Krishna. B
  • DOI: 10.18178/ijmerr
  • Abstracting/Indexing: Scopus (since 2016), CNKI, Google Scholar, Crossref, etc.
  • E-mail questions to IJMERR Editorial Office.


Please send your full manuscript to:


Useful Documents

Paper Template

Copyright Transfer Agreement

Application For Reviewers

Contact us

International Journal of Mechanical Engineering and Robotics Research
E-mail: ijmerr@vip.163.com

Short-Term Forecasting Models of Wind Speed for Airborne Wind Turbines: A Comparative Study

Natapol Korprasertsak and Thananchai Leephakpreeda
School of Manufacturing Systems and Mechanical Engineering, Sirindhorn International Institute of Technology, Thammasat University, Pathum Thani, Thailand

Abstract— Airborne wind turbine technology is rapidly growing with a purpose to overcome working limitations of wind turbines at low altitude. High-altitude wind is strong for efficient power generation, but wind conditions are variant. Wind-speed forecasting in real time is necessary for power generation or flight stabilization. This study is to investigate three widely-used forecasting models with a single and multistep ahead scheme for short-term wind speed prediction from historical wind measurement data: the persistence model, autoregressive moving average (ARMA) model, and artificial neural network (ANN). In a single step scheme, accuracy of persistence model dramatically decreases as the time horizon increases; nevertheless, the persistence model is the simplest algorithm for implementation. The ARMA model and the ANN yield significant accuracy of wind speed forecasting, compared with the persistence model. The overall mean absolute errors (MAEs) of ARMA and ANN are 19.78% and 22.69% lower than the persistence method, respectively. The lowest errors are found in ANN for most cases of time horizon lengths. Unlike ANN, setup of the ARMA model is systematical. A few time horizons can be recommended for short-term wind speed forecasting for an airborne wind turbine. However, for a long time horizon, the multi-step ahead forecasting scheme is recommended since the overall MAEs from ARMA and ANN are reduced by 4.70% and 11.88% respectively. 
Index Terms—airborne wind turbine, wind forecasting, persistence model, autoregressive moving average model, artificial neural network
Cite: Natapol Korprasertsak and Thananchai Leephakpreeda, "Short-Term Forecasting Models of Wind Speed for Airborne Wind Turbines: A Comparative Study," International Journal of Mechanical Engineering and Robotics Research, Vol. 7, No. 3, pp. 250-256, May 2018. DOI: 10.18178/ijmerr.7.3.250-256