Wind Speed Prediction in Non-Monitored Areas Based on Topographic Radial Basis Neural Network (T-RBNN)

2018 4th International Conference on Renewable Energy Technologies

Muhammad Lawan, Salisu^1 ; Azlan Wan Zainal Abidin, Wan^1 ; Abubakar, U.^1

Universiti Malaysia Sarawak, Malaysia^1

关键词: Developed model;    MATLAB /simulink;    Meteorological input;    Radial basis neural networks;    Root Mean Square;    Statistical measures;    Wind monitoring;    Wind speed prediction;   

Others  :  https://iopscience.iop.org/article/10.1088/1755-1315/168/1/012012/pdf
DOI  :  10.1088/1755-1315/168/1/012012

来源: IOP

【 摘 要 】

This paper shows an improved method for the prediction of wind speed in the areas where wind monitoring station is not available. The model has nine meteorological inputs, and one output, which is wind speed. The model was developed using Matlab/Simulink (R2016). The model was trained, tested and validated for accuracy purposes. The overall performance of the model was judged using statistical measures. It was realized that the developed model is capable of reproducing wind speed in the areas not covered by measurements. The root mean square and covariance of the developed model was 7.18 % and 0.0098 respectively.