File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/TII.2021.3098259
- Scopus: eid_2-s2.0-85112608816
- WOS: WOS:000739636900018
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Privacy-preserving Spatiotemporal Scenario Generation of Renewable Energies: A Federated Deep Generative Learning Approach
Title | Privacy-preserving Spatiotemporal Scenario Generation of Renewable Energies: A Federated Deep Generative Learning Approach |
---|---|
Authors | |
Keywords | Scenario generation Renewable energy Uncertainty modeling Least square generative adversarial networks Federated learning Deep generative models |
Issue Date | 2021 |
Citation | IEEE Transactions on Industrial Informatics, 2021 How to Cite? |
Abstract | Scenario generation is a fundamental and crucial tool for decision-making in power systems with high-penetration renewables. Based on big historical data, a novel federated deep generative learning framework, called Fed-LSGAN, is proposed by integrating federated learning and least square generative adversarial networks (LSGANs) for renewable scenario generation. Specifically, federated learning learns a shared global model in a central server from renewable sites at network edges, which enables the Fed-LSGAN to generate scenarios in a privacy-preserving manner without sacrificing the generation quality by transferring model parameters, rather than all data. Meanwhile, the LSGANs-based deep generative model generates scenarios that conform to the distribution of historical data through fully capturing the spatial-temporal characteristics of renewable powers, which leverages the least squares loss function to improve the training stability and generation quality. The simulation results demonstrate that the proposal manages to generate high-quality renewable scenarios and outperforms the state-of-the-art centralized methods. Besides, an experiment with different federated learning settings is designed and conducted to verify the robustness of our method. |
Persistent Identifier | http://hdl.handle.net/10722/308877 |
ISSN | 2023 Impact Factor: 11.7 2023 SCImago Journal Rankings: 4.420 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Li, Yang | - |
dc.contributor.author | Li, Jiazheng | - |
dc.contributor.author | Wang, Yi | - |
dc.date.accessioned | 2021-12-08T07:50:19Z | - |
dc.date.available | 2021-12-08T07:50:19Z | - |
dc.date.issued | 2021 | - |
dc.identifier.citation | IEEE Transactions on Industrial Informatics, 2021 | - |
dc.identifier.issn | 1551-3203 | - |
dc.identifier.uri | http://hdl.handle.net/10722/308877 | - |
dc.description.abstract | Scenario generation is a fundamental and crucial tool for decision-making in power systems with high-penetration renewables. Based on big historical data, a novel federated deep generative learning framework, called Fed-LSGAN, is proposed by integrating federated learning and least square generative adversarial networks (LSGANs) for renewable scenario generation. Specifically, federated learning learns a shared global model in a central server from renewable sites at network edges, which enables the Fed-LSGAN to generate scenarios in a privacy-preserving manner without sacrificing the generation quality by transferring model parameters, rather than all data. Meanwhile, the LSGANs-based deep generative model generates scenarios that conform to the distribution of historical data through fully capturing the spatial-temporal characteristics of renewable powers, which leverages the least squares loss function to improve the training stability and generation quality. The simulation results demonstrate that the proposal manages to generate high-quality renewable scenarios and outperforms the state-of-the-art centralized methods. Besides, an experiment with different federated learning settings is designed and conducted to verify the robustness of our method. | - |
dc.language | eng | - |
dc.relation.ispartof | IEEE Transactions on Industrial Informatics | - |
dc.subject | Scenario generation | - |
dc.subject | Renewable energy | - |
dc.subject | Uncertainty modeling | - |
dc.subject | Least square generative adversarial networks | - |
dc.subject | Federated learning | - |
dc.subject | Deep generative models | - |
dc.title | Privacy-preserving Spatiotemporal Scenario Generation of Renewable Energies: A Federated Deep Generative Learning Approach | - |
dc.type | Article | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/TII.2021.3098259 | - |
dc.identifier.scopus | eid_2-s2.0-85112608816 | - |
dc.identifier.eissn | 1941-0050 | - |
dc.identifier.isi | WOS:000739636900018 | - |