Prediction of Wind Speed Using Artificial Neural Networks and ANFIS Methods (Observation Buoy Example)

TL;DR

This study compares artificial neural networks and ANFIS methods for wind speed prediction using buoy data, demonstrating that ANFIS achieves higher accuracy with lower error and higher correlation.

Contribution

The paper introduces a combined approach using NARX neural networks and ANFIS for wind speed estimation from buoy data, highlighting the superior performance of ANFIS.

Findings

ANFIS achieved 0.31634 MSE and 0.99 R in prediction.

ANN achieved 2.19 MSE and 0.897 R in training.

Both methods effectively estimate wind speed from buoy data.

Abstract

Estimation of the wind speed plays an important role in many issues such as route determination of ships, efficient use of wind roses, and correct planning of agricultural activities. In this study, wind velocity estimation is calculated using artificial neural networks (ANN) and adaptive artificial neural fuzzy inference system (ANFIS) methods. The data required for estimation was obtained from the float named E1M3A, which is a float inside the POSEIDON float system. The proposed ANN is a Nonlinear Auto Regressive with External Input (NARX) type of artificial neural network with 3 layers, 50 neurons, 6 inputs and 1 output. The ANFIS system introduced is a fuzzy inference system with 6 inputs, 1 output, and 3 membership functions (MF) per input. The proposed systems were trained to make wind speed estimates after 3 hours and the data obtained were obtained and the successes of the systems were revealed by comparing the obtained values with real measurements. Mean Squarred Error (MSE) and the regression between the predictions and expected values (R) were used to evaluate the success of the estimation values obtained from the systems. According to estimation results, ANN achieved 2.19 MSE and 0.897 R values in training, 2.88 MSE and 0.866 R values in validation, and 2.93 MSE and 0.857 R values in testing. ANFIS method has obtained 0.31634 MSE and 0.99 R values