Gated Recurrent Unit (GRU) Based Short Term Forecasting for Wind Energy Estimation

Saini, Vikash Kumar; Bhardwaj, Bhawana; Gupta, Vishu; Kumar, Rajesh; Mathur, Abhishek

doi:10.1109/icpects49113.2020.9336973

Cited by 16 publications

(3 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, three hidden layers are enough for most problems of DNNR architectures [83]. Adam and RMSprop are often employed when selecting optimizers [51]. The value of 0.001 is recommended to be the initial learning rate [8,62].…”

Section: Discussionmentioning

confidence: 99%

“…Moreover, the Adam algorithm has the capability to compute an adaptive learning rate for each parameter, enabling the model to accelerate convergence and minimize fluctuations. The high computational efficiency and low memory storage have positioned the Adam algorithm as one of the most frequently and popularly utilized optimizers [33,51,85,86]. As shown in Figure 3, most studies used the TensorFlow platform to develop work.…”

Section: Selection Of Optimizersmentioning

confidence: 99%

See 1 more Smart Citation

A Study of Optimization in Deep Neural Networks for Regression

et al. 2023

View full text Add to dashboard Cite

Due to rapid development in information technology in both hardware and software, deep neural networks for regression have become widely used in many fields. The optimization of deep neural networks for regression (DNNR), including selections of data preprocessing, network architectures, optimizers, and hyperparameters, greatly influence the performance of regression tasks. Thus, this study aimed to collect and analyze the recent literature surrounding DNNR from the aspect of optimization. In addition, various platforms used for conducting DNNR models were investigated. This study has a number of contributions. First, it provides sections for the optimization of DNNR models. Then, elements of the optimization of each section are listed and analyzed. Furthermore, this study delivers insights and critical issues related to DNNR optimization. Optimizing elements of sections simultaneously instead of individually or sequentially could improve the performance of DNNR models. Finally, possible and potential directions for future study are provided.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Selection Of Optimizersmentioning

confidence: 99%

A Study of Optimization in Deep Neural Networks for Regression

et al. 2023

View full text Add to dashboard Cite

show abstract

“…They have achieved higher forecasting accuracy by addressing the issues of vanishing gradients and exploding gradients (Tian and Chen 2021b). LSTM is suitable for handling long-term dependencies but has a larger number of parameters, while GRU models are easier to train and achieve similar forecasting performance with fewer parameters (Liu et al, 2021;Saini et al, 2020). Therefore, in recent years, there has been an increasing amount of research on topics related to wind power forecasting using the GRU neural network as a basic model.…”

mentioning

confidence: 99%

Short-term wind power forecasting based on dual attention mechanism and gated recurrent unit neural network

Xu,

Liu,

Fan

et al. 2024

Front. Energy Res.

View full text Add to dashboard Cite

Accurate wind power forecasting is essential for both optimal grid scheduling and the massive absorption of wind power into the grid. However, the continuous changes in the contribution of various meteorological features to the forecasting of wind power output under different time or weather conditions, and the overlapping of wind power sequence cycles, make forecasting challenging. To address these problems, a short-term wind power forecasting model is established that integrates a gated recurrent unit (GRU) network with a dual attention mechanism (DAM). To compute the contributions of different features in real time, historical wind power data and meteorological information are first extracted using a feature attention mechanism (FAM). The feature sequences collected by the FAM are then used by the GRU network for preliminary forecasting. Subsequently, one-dimensional convolution employing several distinct convolution kernels is used to filter the GRU outputs. In addition, a multi-head time attention mechanism (MHTAM) is proposed and a Gaussian bias is introduced to assign different weights to different time steps of each modality. The final forecast results are produced by combining the outputs of the MHTAM. The results of the simulation experiment show that for 5-h, 10-h, and 20-h short-term wind power forecasting, the establishedÂ DAM-GRU model performs better than comparative models on the basis of Root Mean Square Error (RMSE), Mean Absolute Error (MAE), R-squared (R2), Square sum error (SSE), Mean absolute percentile error (MAPE), and Relative root mean square error (RRMSE) index.

show abstract