Deep Concatenated Residual Network With Bidirectional LSTM for One-Hour-Ahead Wind Power Forecasting
- Authors
- Minseung Ko; Lee, K (Lee, Kwangsuk); Kim, JK (Kim, Jae-Kyeong); Changwoo Hong; Dong, ZY (Dong, Zhao Yang); Kyeon Hur
- Issue Date
- Apr-2021
- Publisher
- IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
- Keywords
- Forecasting; Wind power generation; Logic gates; Predictive models; Residual neural networks; Wind forecasting; Statistical analysis; Activation function; bidirectional learning; deep learning; long short-term memory; residual networks; wind power forecasting
- Citation
- IEEE TRANSACTIONS ON SUSTAINABLE ENERGY, v.12, no.2, pp 1,321 - 1,335
- Journal Title
- IEEE TRANSACTIONS ON SUSTAINABLE ENERGY
- Volume
- 12
- Number
- 2
- Start Page
- 1,321
- End Page
- 1,335
- URI
- https://yscholarhub.yonsei.ac.kr/handle/2021.sw.yonsei/6352
- DOI
- 10.1109/TSTE.2020.3043884
- ISSN
- 1949-3029
- Abstract
- This paper presents a deep residual network for improving time-series forecasting models, indispensable to reliable and economical power grid operations, especially with high shares of renewable energy sources. Motivated by the potential performance degradation due to the overfitting of the prevailing stacked bidirectional long short-term memory (Bi-LSTM) layers associated with its linear stacking, we propose a concatenated residual learning by connecting the multi-level residual network (MRN) and DenseNet. This method further integrates long and short Bi-LSTM networks, ReLU, and SeLU for its activating function. Rigorous studies present superior prediction accuracy and parameter efficiency for the widely used temperature dataset as well as the actual wind power dataset. The peak value forecasting and generalization capability, along with the credible confidence range, demonstrate that the proposed model offers essential features of a time-series forecasting, enabling a general forecasting framework in grid operations. The source code of this paper can be found in https://github.com/MinseungKo/DRNet.git.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - College of Engineering > Electrical and Electronic Engineering > 1. Journal Articles
Items in Scholar Hub are protected by copyright, with all rights reserved, unless otherwise indicated.