Wind power forecasting considering data privacy protection: a federated deep reinforcement learning approach
| dc.contributor.author | Li, Yang | |
| dc.contributor.author | Wang, Ruinong | |
| dc.contributor.author | Li, Yuanzheng | |
| dc.contributor.author | Zhang, Meng | |
| dc.contributor.author | Long, Chao | |
| dc.date.accessioned | 2022-11-23T13:53:42Z | |
| dc.date.available | 2022-11-23T13:53:42Z | |
| dc.date.issued | 2022-11-16 | |
| dc.description.abstract | In a modern power system with an increasing proportion of renewable energy, wind power prediction is crucial to the arrangement of power grid dispatching plans due to the volatility of wind power. However, traditional centralized forecasting methods raise concerns regarding data privacy-preserving and data islands problem. To handle the data privacy and openness, we propose a forecasting scheme that combines federated learning and deep reinforcement learning (DRL) for ultra-short-term wind power forecasting, called federated deep reinforcement learning (FedDRL). Firstly, this paper uses the deep deterministic policy gradient (DDPG) algorithm as the basic forecasting model to improve prediction accuracy. Secondly, we integrate the DDPG forecasting model into the framework of federated learning. The designed FedDRL can obtain an accurate prediction model in a decentralized way by sharing model parameters instead of sharing private data which can avoid sensitive privacy issues. The simulation results show that the proposed FedDRL outperforms the traditional prediction methods in terms of forecasting accuracy. More importantly, while ensuring the forecasting performance, FedDRL can effectively protect the data privacy and relieve the communication pressure compared with the traditional centralized forecasting method. In addition, a simulation with different federated learning parameters is conducted to confirm the robustness of the proposed scheme. | en_UK |
| dc.identifier.citation | Li Y, Wang R, Li Y, et al., (2023) Wind power forecasting considering data privacy protection: a federated deep reinforcement learning approach, Applied Energy, Volume 329, January 2023, Article number 120291 | en_UK |
| dc.identifier.eissn | 1872-9118 | |
| dc.identifier.issn | 0306-2619 | |
| dc.identifier.uri | https://doi.org/10.1016/j.apenergy.2022.120291 | |
| dc.identifier.uri | https://dspace.lib.cranfield.ac.uk/handle/1826/18727 | |
| dc.language.iso | en | en_UK |
| dc.publisher | Elsevier | en_UK |
| dc.rights | Attribution-NonCommercial-NoDerivatives 4.0 International | * |
| dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/4.0/ | * |
| dc.subject | Wind power forecasting | en_UK |
| dc.subject | Data openness and sharing | en_UK |
| dc.subject | Privacy protection | en_UK |
| dc.subject | Deep reinforcement learning | en_UK |
| dc.subject | Federated learning | en_UK |
| dc.subject | Uncertainty modeling | en_UK |
| dc.title | Wind power forecasting considering data privacy protection: a federated deep reinforcement learning approach | en_UK |
| dc.type | Article | en_UK |