File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/TPWRS.2022.3175252
- WOS: WOS:000965924700001
Supplementary
-
Citations:
- Web of Science: 0
- Appears in Collections:
Article: Robust Load Forecasting towards Adversarial Attacks via Bayesian Learning
Title | Robust Load Forecasting towards Adversarial Attacks via Bayesian Learning |
---|---|
Authors | |
Issue Date | 2022 |
Publisher | IEEE. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=59 |
Citation | IEEE Transactions on Power Systems , How to Cite? |
Abstract | Electric load forecasting is an essential problem for the power industry, which has a significant impact on power system operation. Currently, deep learning is proved to be an effective tool for load forecasting. However, those learning-based models are vulnerable towards adversarial attacks, which raises concerns about the robustness of load forecasting models. In this study, we propose a Bayesian training method to enhance the robustness of deep learning based load forecasting models towards adversarial attacks. We theoretically prove that the proposed method can improve the load forecasting robustness against various attacking objectives without compromising the prediction performance. An approximated training scheme is proposed to accelerate the training process so as to make the method better applied in practice. The experimental results show that such an approximation still yields higher robustness compared to four recently proposed benchmark robust forecasting methods while maintaining the prediction performance under no attack. |
Persistent Identifier | http://hdl.handle.net/10722/322525 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Zhou, Y | - |
dc.contributor.author | Ding, Z | - |
dc.contributor.author | Wen, Q | - |
dc.contributor.author | Wang, Y | - |
dc.date.accessioned | 2022-11-14T08:25:41Z | - |
dc.date.available | 2022-11-14T08:25:41Z | - |
dc.date.issued | 2022 | - |
dc.identifier.citation | IEEE Transactions on Power Systems , | - |
dc.identifier.uri | http://hdl.handle.net/10722/322525 | - |
dc.description.abstract | Electric load forecasting is an essential problem for the power industry, which has a significant impact on power system operation. Currently, deep learning is proved to be an effective tool for load forecasting. However, those learning-based models are vulnerable towards adversarial attacks, which raises concerns about the robustness of load forecasting models. In this study, we propose a Bayesian training method to enhance the robustness of deep learning based load forecasting models towards adversarial attacks. We theoretically prove that the proposed method can improve the load forecasting robustness against various attacking objectives without compromising the prediction performance. An approximated training scheme is proposed to accelerate the training process so as to make the method better applied in practice. The experimental results show that such an approximation still yields higher robustness compared to four recently proposed benchmark robust forecasting methods while maintaining the prediction performance under no attack. | - |
dc.language | eng | - |
dc.publisher | IEEE. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=59 | - |
dc.relation.ispartof | IEEE Transactions on Power Systems | - |
dc.rights | IEEE Transactions on Power Systems . Copyright © IEEE. | - |
dc.rights | ©20xx IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. | - |
dc.title | Robust Load Forecasting towards Adversarial Attacks via Bayesian Learning | - |
dc.type | Article | - |
dc.identifier.email | Wang, Y: yiwang@eee.hku.hk | - |
dc.identifier.authority | Wang, Y=rp02900 | - |
dc.identifier.doi | 10.1109/TPWRS.2022.3175252 | - |
dc.identifier.hkuros | 342380 | - |
dc.identifier.isi | WOS:000965924700001 | - |