Abstract

Accurately forecasting wind speed on a short-term scale has become essential in the field of wind power energy. In this paper, a multi-variable long short-term memory network model (MV-LSTM) based on Pearson correlation coefficient feature selection is proposed to predict the short-term wind speed. The proposed method utilizes multiple historical meteorological variables, such as wind speed, temperature, humidity, and air pressure, to predict the wind speed in the next hour. Hourly data collected from two ground observation stations in Yanqing and Zhaitang in Beijing were divided into training and test sets. The training sets were used to train the model, and the test sets were used to evaluate the model with the root-mean-square error (RMSE), mean absolute error (MAE), mean bias error (MBE), and mean absolute percentage error (MAPE) metrics. The proposed method is compared with two other forecasting methods (the autoregressive moving average model (ARMA) method and the single-variable long short-term memory network (LSTM) method, which inputs only historical wind speed data) based on the same dataset. The experimental results prove the feasibility of the MV-LSTM method for short-term wind speed forecasting and its superiority to the ARMA method and the single-variable LSTM method.

Highlights

  • Due to the shortage of conventional energy such as fossil fuels and increasingly severe environmental pollution, wind energy, as the most economical and environmentally friendly renewable energy, has attracted wide attention [1]

  • We introduce the advantages of recurrent neural networks (RNNs) compared to traditional neural networks in processing time-series data, and their shortcomings in respect of long-term memory

  • We propose a multi-variable long short-term memory network (LSTM) network model based on Pearson correlation coefficient feature selection for short-term wind speed prediction, which takes the historical data for multiple meteorological elements into account

Read more

Summary

Introduction

Due to the shortage of conventional energy such as fossil fuels and increasingly severe environmental pollution, wind energy, as the most economical and environmentally friendly renewable energy, has attracted wide attention [1]. Statistical methods are used for short-term wind speed forecasting; they include the autoregressive (AR) model, autoregressive moving average (ARMA) model, autoregressive integrated moving average (ARIMA) model, and filtering model [9] These methods have been widely used in wind speed time-series prediction based on a large amount of historical data. Hu et al [2] introduced a differential evolution (DE) algorithm to optimize the number of hidden layers in each LSTM and the neuron count in each hidden layer of the LSTM for the trade-off between learning performance and model complexity These examples show that the LSTM has more advantages in short-term wind speed prediction than traditional machine learning algorithms.

Site Description
Prediction Methods
Evaluation Metrics
Results and Discussion
Method
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call