Short-Term Canyon Wind Speed Prediction Based on CNN—GRU Transfer Learning

Abstract

Due to the particularity of the site selection of hydropower stations, the canyon wind with large fluctuations often occurs during the construction of the hydropower station, which will seriously affect the safety of construction personnel. Especially in the early stage of the construction of the hydropower station, the historical data and information on the canyon wind are scarce. Short-term forecasting of canyon wind speed has become extremely important. The main innovation of this paper is to propose a time series prediction method based on transfer learning. This method can achieve short-term prediction when there are few wind speed sample data, and the model is relatively simple while ensuring the accuracy of prediction. Considering the temporal and nonlinear characteristics of canyon wind speed data, a hybrid transfer learning model based on a convolutional neural network (CNN) and gated recurrent neural network (GRU) is proposed to predict short-term canyon wind speed with fewer observation data. In this method, the time sliding window is used to extract time series from historical wind speed data and temperature data of adjacent cities as the input of the neural network. Next, CNN is used to extract the feature vector from the input, and the feature vector can form time series. Then, the GRU network is used for short-term wind speed prediction by the time series. Experimental results show that the proposed method improves MAE and RMSE by nearly 20%, which will provide new ideas for the application of wind speed forecasting in canyons under complex terrain. The research contents of this paper contribute to the actual construction of hydropower stations.

An overview of deterministic and probabilistic forecasting methods of wind energy

“…For example, Ji et al. (2022) 186 established a CNN-gate recurrent unit (GRU) model for wind speed prediction, where CNN was used to extract characteristic input vectors.

Figure 7 The structures and schemes of five categories of deep learning technologies (A) Structure of the traditional AE, (B) Structure of DBN, (C) Structure of DNN with n hidden layers, (D) Scheme of TL and (E) Basic structure of CNN.

…”

“…TL is a novel machine learning approach for tackling issues in domains with distinct but relevant tasks, 186 thus enabling wind prediction based on forecasts of nearby locations. Machine learning techniques (especially DNNs) are generally adopted as predictors.…”

Comparison of RNN, LSTM, and GRU Methods on Forecasting Website Visitors

“…The results obtained are very helpful in preparation for controlling the pandemic. Ji et al (Ji et al 2022) considered the temporal and nonlinear characteristics of canyon wind speed data, a hybrid transfer learning model based on CNN and GRU, to predict short-term canyon wind speed with less observational data. Then, Li (Li et al, 2021) discussed the GRU for performing useful remaining-of-life prediction tasks.…”

Review of AI-Based Wind Prediction within Recent Three Years: 2021–2023

“…Many methods have been proposed for WSP/WPP, which can be classified into several groups according to different classification criteria [9], as shown in Figure 2. According to the time scale [10], they are divided into ultra-short-term (a few seconds to 30 min ahead), short-term (30 min to 6 h ahead), medium-term (6 h to 1 day ahead) and long-term (1 day to 1 week or more ahead) models [11][12][13]. This classification reflects a focus on the time span of predictions and provides more specific time frameworks for different application scenarios.…”