Privacy Preservation of Data-Driven Models in Smart Grids Using Homomorphic Encryption

<p dir="ltr">Deep learning models have been applied for varied electrical applications in smart grids with a high degree of reliability and accuracy. The development of deep learning models requires the historical data collected from several electric utilities during the training of...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Dabeeruddin Syed (16864260) (author)
مؤلفون آخرون: Shady S. Refaat (16864269) (author), Othmane Bouhali (8252544) (author)
منشور في: 2020
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513515827494912
author Dabeeruddin Syed (16864260)
author2 Shady S. Refaat (16864269)
Othmane Bouhali (8252544)
author2_role author
author
author_facet Dabeeruddin Syed (16864260)
Shady S. Refaat (16864269)
Othmane Bouhali (8252544)
author_role author
dc.creator.none.fl_str_mv Dabeeruddin Syed (16864260)
Shady S. Refaat (16864269)
Othmane Bouhali (8252544)
dc.date.none.fl_str_mv 2020-07-08T03:00:00Z
dc.identifier.none.fl_str_mv 10.3390/info11070357
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Privacy_Preservation_of_Data-Driven_Models_in_Smart_Grids_Using_Homomorphic_Encryption/25835260
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Information and computing sciences
Artificial intelligence
Cybersecurity and privacy
Machine learning
Deep learnings
homomorphic encryption
fault localization
smart grids
deep neural networks
dc.title.none.fl_str_mv Privacy Preservation of Data-Driven Models in Smart Grids Using Homomorphic Encryption
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">Deep learning models have been applied for varied electrical applications in smart grids with a high degree of reliability and accuracy. The development of deep learning models requires the historical data collected from several electric utilities during the training of the models. The lack of historical data for training and testing of developed models, considering security and privacy policy restrictions, is considered one of the greatest challenges to machine learning-based techniques. The paper proposes the use of homomorphic encryption, which enables the possibility of training the deep learning and classical machine learning models whilst preserving the privacy and security of the data. The proposed methodology is tested for applications of fault identification and localization, and load forecasting in smart grids. The results for fault localization show that the classification accuracy of the proposed privacy-preserving deep learning model while using homomorphic encryption is 97–98%, which is close to 98–99% classification accuracy of the model on plain data. Additionally, for load forecasting application, the results show that RMSE using the homomorphic encryption model is 0.0352 MWh while RMSE without application of encryption in modeling is around 0.0248 MWh.</p><h2>Other Information</h2><p dir="ltr">Published in: Information<br>License: <a href="https://creativecommons.org/licenses/by/4.0/" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.3390/info11070357" target="_blank">https://dx.doi.org/10.3390/info11070357</a></p>
eu_rights_str_mv openAccess
id Manara2_85303e713fb0a582e274a6bbb1924a5b
identifier_str_mv 10.3390/info11070357
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/25835260
publishDate 2020
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Privacy Preservation of Data-Driven Models in Smart Grids Using Homomorphic EncryptionDabeeruddin Syed (16864260)Shady S. Refaat (16864269)Othmane Bouhali (8252544)Information and computing sciencesArtificial intelligenceCybersecurity and privacyMachine learningDeep learningshomomorphic encryptionfault localizationsmart gridsdeep neural networks<p dir="ltr">Deep learning models have been applied for varied electrical applications in smart grids with a high degree of reliability and accuracy. The development of deep learning models requires the historical data collected from several electric utilities during the training of the models. The lack of historical data for training and testing of developed models, considering security and privacy policy restrictions, is considered one of the greatest challenges to machine learning-based techniques. The paper proposes the use of homomorphic encryption, which enables the possibility of training the deep learning and classical machine learning models whilst preserving the privacy and security of the data. The proposed methodology is tested for applications of fault identification and localization, and load forecasting in smart grids. The results for fault localization show that the classification accuracy of the proposed privacy-preserving deep learning model while using homomorphic encryption is 97–98%, which is close to 98–99% classification accuracy of the model on plain data. Additionally, for load forecasting application, the results show that RMSE using the homomorphic encryption model is 0.0352 MWh while RMSE without application of encryption in modeling is around 0.0248 MWh.</p><h2>Other Information</h2><p dir="ltr">Published in: Information<br>License: <a href="https://creativecommons.org/licenses/by/4.0/" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.3390/info11070357" target="_blank">https://dx.doi.org/10.3390/info11070357</a></p>2020-07-08T03:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.3390/info11070357https://figshare.com/articles/journal_contribution/Privacy_Preservation_of_Data-Driven_Models_in_Smart_Grids_Using_Homomorphic_Encryption/25835260CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/258352602020-07-08T03:00:00Z
spellingShingle Privacy Preservation of Data-Driven Models in Smart Grids Using Homomorphic Encryption
Dabeeruddin Syed (16864260)
Information and computing sciences
Artificial intelligence
Cybersecurity and privacy
Machine learning
Deep learnings
homomorphic encryption
fault localization
smart grids
deep neural networks
status_str publishedVersion
title Privacy Preservation of Data-Driven Models in Smart Grids Using Homomorphic Encryption
title_full Privacy Preservation of Data-Driven Models in Smart Grids Using Homomorphic Encryption
title_fullStr Privacy Preservation of Data-Driven Models in Smart Grids Using Homomorphic Encryption
title_full_unstemmed Privacy Preservation of Data-Driven Models in Smart Grids Using Homomorphic Encryption
title_short Privacy Preservation of Data-Driven Models in Smart Grids Using Homomorphic Encryption
title_sort Privacy Preservation of Data-Driven Models in Smart Grids Using Homomorphic Encryption
topic Information and computing sciences
Artificial intelligence
Cybersecurity and privacy
Machine learning
Deep learnings
homomorphic encryption
fault localization
smart grids
deep neural networks