Back to Search
Start Over
Forecasting of Wind Speed by Using Three Different Techniques of Prediction Models
- Source :
- Annals of Data Science. 10:679-711
- Publication Year :
- 2021
- Publisher :
- Springer Science and Business Media LLC, 2021.
-
Abstract
- Wind energy plays a major role in meeting the world’s growing power demand, due to which wind speed forecasting is essential for power system management, energy trading and maintaining the balance between consumption and generation for a stable electricity market. In this article, three different types of predicting techniques have been implemented for estimating wind speed by means of different meteorological parameters. Group method of data handling (GMDH), multi linear regression (MLR) and artificial neural network (ANN) models have been developed. For these models, data sets of 05 years (12 datasets from each year) were collected from the National Renewable Energy Laboratory (NREL). Five different types of input variables, which are ambient temperature (Ta), atmospheric pressure (Pr), wind direction (WD), relative humidity (RH) and precipitation (Pc) were selected as independent variables in all models. The collected wind speed (Wv) is selected as output or dependent variable. In this study, 48 sets of data were picked for training process and 12 datasets were selected for testing. The performances of models were examined using statistical parameters such as RMSE, MAPE and R2. MLR, GMDH and ANN techniques accurately performed with values of correlation coefficient (R) being obtained as 0.90552, 0.95542 and 0.97617 respectively. Comparative study of all models reveals that out of these three techniques, ANN performs the best. In the ANN model, the values of RMSE, MAE and R2 obtained were 0.17476, 0.12984 and 0.95210 respectively, which are optimal results when compared to those of other models. After ANN, GMDH performed better than MLR. Above analysis reveals that the wind speed was predicted with the highest accuracy by the neural technique.
- Subjects :
- Wind power
Variables
Correlation coefficient
Group method of data handling
business.industry
020209 energy
media_common.quotation_subject
02 engineering and technology
Wind direction
01 natural sciences
Wind speed
Computer Science Applications
010104 statistics & probability
Electric power system
Artificial Intelligence
Linear regression
Statistics
0202 electrical engineering, electronic engineering, information engineering
Business, Management and Accounting (miscellaneous)
0101 mathematics
Statistics, Probability and Uncertainty
business
media_common
Mathematics
Subjects
Details
- ISSN :
- 21985812 and 21985804
- Volume :
- 10
- Database :
- OpenAIRE
- Journal :
- Annals of Data Science
- Accession number :
- edsair.doi...........79c4a2405ac98dcbaa11e59d14c78dea