ABSTRACT
Among renewable energy generation technologies, wind energy has become one of the most outstanding issues, especially in the last decade. Wind speed is the most critical parameter influencing the power obtained from a wind turbine. The unstable structure of the wind causes an impossibility to receive a direct theoretical relation between wind power and speed. Accordingly, obtaining a simulation of the generated turbine power concerning the approaching wind speed has become vitally essential, nowadays. In the current study, generated wind turbine power (P) has been predicted using three forecasting methods. The computer was trained using wind speed (V) and the turbine rotor rotational speed (ṅ) as the inputs of the forecasting methods. The methods used for this purpose were to include adaptive neuro-fuzzy inference system (ANFIS), Elmanneural network (ENN), and feed-forward neural network (FNN) approaches. In the training of the programs, among the cumulative of 43,800 wind speed, turbine rotor rotational speed, and wind power data, 80% and 20% of the total data were used for training and testing stages of the algorithms, respectively. The statistical results of the computations demonstrated that among three methods, ANFIS gave better outcomes when compared to ENN and FNN, in both the training and testing stages of the algorithms. The proposed models of the current study have revealed low and acceptable mean absolute error (MAE) and root mean square error (RMSE) statistical error results of ANFIS tool; corresponding to 52.448 kW and 87.204 kW error, respectively, were obtained at the training stage, whereas 48.675 kW and 78.453 kW error, respectively, were obtained at the testing stage. For the estimation of wind power, while the coefficient of determination (R2) was detected as R2 = 0.9948 and 0.9961 in training and testing stages, respectively, with ANFIS model, it was found out as R2 = 0.9942 and 0.9957 with ENN model and R2 = 0.9943 and 0.9956 with FNN model. Namely, it has been reported that ANFIS tool can be successfully applied in wind output power estimations, as long as wind speed and turbine rotor rotational speed values are provided without the need for numerous experimental measurements, which induces additional time, labor, and measurement expenses.
Disclosure statement
No potential conflict of interest was reported by the author(s).
Authorship contribution statement
Sergen Tumse: Investigation, Methodology, Writing, Review, Software and Editing Akin Ilhan: Investigation, Methodology, Writing, Review and Editing Mehmet Bilgili: Investigation, Methodology, Software and Supervision Besir Sahin: Investigation, Methodology, Supervision and Editing
Nomenclature
ANN Artificial neural network
ANFIS Adaptive neuro-fuzzy inference system
ENN Elman neural network
FNN Feed-forward neural network
ARMA Autoregressive moving average
MLP Multilayer perception
LSTM Long short-term memory
LSTMN Long short-term memory networks
EMD Empirical mode decomposition
ARIMA Autoregressive integrated moving average
RNN Recurrent neural network
DNN Deep neural network
VMD Variational mode decomposition
ESN Echo state network
EEMD Ensemble empirical mode decomposition
GPR Gaussian process regression
ELM Extreme learning machine
SVM Support vector machine
NLR Nonlinear logistic regression
WRF Weather research and forecast
SVR Support vector regression
RMSE Root mean square error
MAE Mean absolute error
R2 Coefficient of determination
P Wind power (kW)
V Wind speed (m/s)
ṅ Turbine rotational speed (rpm)
x Variable
xn Normalized value of x variable
xmin Minimum value of x variable
xmax Maximum value of x variable
F Forecasted value
a Bias to layer 2
h Neurons number in hidden layer
vj Layer weight
k Number of input parameters
wij Weight of input layer
bj Bias to layer 1
xi Input variable
σ Width of curve
c Center location of curve
A Actual value
n Total observation number