The potential of topographical feedforward neural network (T-FFNN) technique in monthly wind speed and direction prediction

In this paper, the time series, and a parametric feedforward neural network model were designed. A methodology for wind speed prediction in the regions where wind speed is not available by measurement based on the T-FFNN is proposed in this work according to the meteorological, topographical and geo...

Full description

Saved in:
Bibliographic Details
Main Authors: Lawan, S. M., Abidin, W. A. W. Z., Lawan, A. M., Bichi, S. L., Abba, I.
Format: Conference Proceeding
Language:English
Subjects:
Atmospheric modeling
Mathematical model
neural network
prediction
Training
wind
Wind energy
Wind forecasting
wind mapping
Wind speed
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, the time series, and a parametric feedforward neural network model were designed. A methodology for wind speed prediction in the regions where wind speed is not available by measurement based on the T-FFNN is proposed in this work according to the meteorological, topographical and geographical parameters for long-term prediction. Typical wind speed and direction are respectively predicted by the optimum 9-152-1 T-FFNN. Then the prediction results are analyzed. The results show that the suggested approach is powerful and can be used effectively to predict the wind speed and direction. The observed and modeled data were used in developing the energy map using ArcGIS 9.3 which shows the distribution of wind speed and power density across the studied area.
ISSN:2155-6830
DOI:10.1109/ICEEI.2017.8312407