Intelligent Scene-Adaptive Desensitization: A Machine Learning Approach for Dynamic Data Privacy in Virtual Power Plants
In the context of virtual power plants (VPPs), the one-size-fits-all approach of traditional static desensitization methods proves inadequate due to the diverse and dynamic operational scenarios encountered. These methods fail to provide the necessary flexibility for varying data privacy requirement...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-03-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/13/6/1051 |
| _version_ | 1797241383776419840 |
|---|---|
| author | Ruxia Yang Hongchao Gao Fangyuan Si Jun Wang |
| author_facet | Ruxia Yang Hongchao Gao Fangyuan Si Jun Wang |
| author_sort | Ruxia Yang |
| collection | DOAJ |
| description | In the context of virtual power plants (VPPs), the one-size-fits-all approach of traditional static desensitization methods proves inadequate due to the diverse and dynamic operational scenarios encountered. These methods fail to provide the necessary flexibility for varying data privacy requirements across different scenarios. To address this shortcoming, our research introduces a dynamic desensitization method specifically designed for VPPs. Leveraging machine learning for adaptive scene recognition, the method adjusts data privacy levels intelligently according to each unique scenario. A novel similarity utility function and a Gaussian processes-based differential privacy algorithm ensure tailored and efficient privacy protection. Experimental results highlight an 87.5% accuracy in scene recognition, validating our method’s capability to adapt to diverse scenarios effectively. This study contributes to the field by providing a nuanced approach to data protection, effectively addressing the specific needs of complex VPP environments. |
| first_indexed | 2024-04-24T18:22:28Z |
| format | Article |
| id | doaj.art-7cf9cda0609549758b36d68c70852dc2 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-04-24T18:22:28Z |
| publishDate | 2024-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-7cf9cda0609549758b36d68c70852dc22024-03-27T13:34:51ZengMDPI AGElectronics2079-92922024-03-01136105110.3390/electronics13061051Intelligent Scene-Adaptive Desensitization: A Machine Learning Approach for Dynamic Data Privacy in Virtual Power PlantsRuxia Yang0Hongchao Gao1Fangyuan Si2Jun Wang3State Grid Smart Grid Research Institute Co., Ltd., Nanjing 210003, ChinaState Key Laboratory of Power System, Department of Electrical Engineering, Tsinghua University, Beijing 100000, ChinaState Key Laboratory of Power System, Department of Electrical Engineering, Tsinghua University, Beijing 100000, ChinaState Grid Shanghai Municipal Electric Power Company, Shanghai 201507, ChinaIn the context of virtual power plants (VPPs), the one-size-fits-all approach of traditional static desensitization methods proves inadequate due to the diverse and dynamic operational scenarios encountered. These methods fail to provide the necessary flexibility for varying data privacy requirements across different scenarios. To address this shortcoming, our research introduces a dynamic desensitization method specifically designed for VPPs. Leveraging machine learning for adaptive scene recognition, the method adjusts data privacy levels intelligently according to each unique scenario. A novel similarity utility function and a Gaussian processes-based differential privacy algorithm ensure tailored and efficient privacy protection. Experimental results highlight an 87.5% accuracy in scene recognition, validating our method’s capability to adapt to diverse scenarios effectively. This study contributes to the field by providing a nuanced approach to data protection, effectively addressing the specific needs of complex VPP environments.https://www.mdpi.com/2079-9292/13/6/1051virtual power plantload identificationsupport vector machinedifferential privacydynamic desensitization |
| spellingShingle | Ruxia Yang Hongchao Gao Fangyuan Si Jun Wang Intelligent Scene-Adaptive Desensitization: A Machine Learning Approach for Dynamic Data Privacy in Virtual Power Plants Electronics virtual power plant load identification support vector machine differential privacy dynamic desensitization |
| title | Intelligent Scene-Adaptive Desensitization: A Machine Learning Approach for Dynamic Data Privacy in Virtual Power Plants |
| title_full | Intelligent Scene-Adaptive Desensitization: A Machine Learning Approach for Dynamic Data Privacy in Virtual Power Plants |
| title_fullStr | Intelligent Scene-Adaptive Desensitization: A Machine Learning Approach for Dynamic Data Privacy in Virtual Power Plants |
| title_full_unstemmed | Intelligent Scene-Adaptive Desensitization: A Machine Learning Approach for Dynamic Data Privacy in Virtual Power Plants |
| title_short | Intelligent Scene-Adaptive Desensitization: A Machine Learning Approach for Dynamic Data Privacy in Virtual Power Plants |
| title_sort | intelligent scene adaptive desensitization a machine learning approach for dynamic data privacy in virtual power plants |
| topic | virtual power plant load identification support vector machine differential privacy dynamic desensitization |
| url | https://www.mdpi.com/2079-9292/13/6/1051 |
| work_keys_str_mv | AT ruxiayang intelligentsceneadaptivedesensitizationamachinelearningapproachfordynamicdataprivacyinvirtualpowerplants AT hongchaogao intelligentsceneadaptivedesensitizationamachinelearningapproachfordynamicdataprivacyinvirtualpowerplants AT fangyuansi intelligentsceneadaptivedesensitizationamachinelearningapproachfordynamicdataprivacyinvirtualpowerplants AT junwang intelligentsceneadaptivedesensitizationamachinelearningapproachfordynamicdataprivacyinvirtualpowerplants |