Feedforward Error Learning Deep Neural Networks for Multivariate Deterministic Power Forecasting
- Authors
- Ko, Min-Seung; Lee, Kwangsuk; Hur, Kyeon
- Issue Date
- Sep-2022
- Publisher
- IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
- Keywords
- Predictive models; Forecasting; Computational modeling; Data models; Task analysis; Convolutional neural networks; Load modeling; Compound scaling; convolutional neural networks (CNN); deterministic power forecasting; error learning; feature selection; multivariate forecasting
- Citation
- IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, v.18, no.9, pp 6214 - 6223
- Pages
- 10
- Journal Title
- IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
- Volume
- 18
- Number
- 9
- Start Page
- 6214
- End Page
- 6223
- URI
- https://yscholarhub.yonsei.ac.kr/handle/2021.sw.yonsei/6561
- DOI
- 10.1109/TII.2022.3160628
- ISSN
- 1551-3203
1941-0050
- Abstract
- This article proposes a deep neural network (DNN) framework for multivariate deterministic power forecasting in the context of the high penetration of variable and uncertain renewable energy sources. The deep learning model is organized based on the 1-D convolutional neural network to lessen the computational burden, typical of recurrent neural network based models, and combines WaveNet and EfficientNet to improve the forecasting accuracy. Motivated by the inefficiency that all the models conduct the same tasks in the popular ensemble approach, we also designed a feedforward error learning DNN, which computes the error of the basic model separately. We further incorporated embedded and filter methods for feature selection to enhance the model visibility and the utility of the framework. Comprehensive studies on the public load and PV datasets demonstrate that the proposed framework outperforms the conventional methods in applicability, computational efficiency, and forecasting accuracy.
- 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.