Wind Speed Prediction Using Artificial Neural Networks Based on Multiple Local Measurements in Eskisehir


BAŞARAN FİLİK Ü., FİLİK T.

3rd International Conference on Energy and Environment Research (ICEER), Barcelona, Spain, 7 - 11 September 2016, vol.107, pp.264-269 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Volume: 107
  • Doi Number: 10.1016/j.egypro.2016.12.147
  • City: Barcelona
  • Country: Spain
  • Page Numbers: pp.264-269
  • Keywords: Wind energy, wind speed prediction, artificial neural network, POWER-GENERATION, MODELS
  • Anadolu University Affiliated: Yes

Abstract

In this study, artificial neural network (ANN) based models, which differently uses multiple local meteorological measurements together such as wind speed, temperature and pressure values, are proposed and it shown ANN based multivariable model's wind speed predictions can be improved for various cases. A data monitoring system are used which can sensitively measures in milliseconds time interval and records the values of weather temperature, wind speed, wind direction and weather pressure in this study. The proposed ANN based multivariable model's root mean square error (RMSE) and mean absolute error (MAE) performances are presented and compared for various cases. The effect of using multiple local variables instead of wind speed only are analyzed and compared with persistence method for benchmark. (C) 2016 The Authors. Published by Elsevier Ltd.