Security and Privacy Issues in Smart Grid by Applying Deep Learning Techniques (SI-gridl)

Smart Grid is the next generation of the electrical-grid, which is envisioned to revolutionize the way electricity is generated, distributed and monitored. It is strongly believed that it will make the life of our next generations and us a lot safer and more sustainable. Therefore, many countries have already taken major steps towards its adoption so that benefits provided by Smart Grid can be reached to its citizens. However, there are a number of issues which needs to be addressed before this dream can be fully realized. Among the most pressing issues security and privacy are the most serious. Smart grid is exposed to a wide array of threats, including data theft, false data injection, denial of service, and insider attack. On the other hand, advancements in cryptography, differential privacy and secure multi-party computation have much promised. However, there is still much to be desired from these approaches. The integration of the cloud-fog-based computing model has also provided great prospects in moving towards the goals of Smart Grid, but we are still far behind achieving the desired goals.

Machine learning-based approaches have also been adopted to address the security and privacy issues of smart grid. However, the cutting edge deep learning-based approaches have not been studied for addressing the security and privacy problems in smart grid. This special section will focus on these issues in the context of machine learning/deep learning models.

Authors are invited to submit outstanding and original unpublished research manuscripts focused on the latest findings in security and privacy issues in smart grid by applying deep learning techniques. The topics of interest are:

1. Robustness, fault-tolerance in smart grid using deep learning models
2. Fault data injection attacks detection using deep learning models.
3. Privacy preserving data aggregation and protection using deep learning models
4. Privacy preserving using fully homomorphic encryption schemes in smart grids.
5. Differential privacy and deep learning for smart grid communication.
6. Fault prediction, diagnosis and avoidance using deep learning models.
7. Deep learning empowered forensics techniques for smart grid.
8. Deep learning empowered secure logging/provenance techniques for smart grid.
9. Machine learning and deep learning for resilient and efficient smart grid working.
10. Intelligent data collection and inspection models using deep learning
11. Security and Privacy issues in Fog-enabled model for smart grid
12. Fully homomorphic encryption based fault-tolerance in Fog-enabled model for smart grid.
13. Secure Multiparty computation based fault-tolerance in Fog-enabled model for smart grid

Submission of manuscripts:

Research articles must not have been published or submitted for publication elsewhere. All articles will be peer reviewed and accepted based on quality, originality, novelty, and relevance to the theme of the special section. Before submission, authors should carefully read over the journal’s Author Guidelines, which is available at http://www.elsevier.com/wps/find/journaldescription.cws_home/367/authorinstructions.

Authors should submit their papers through the journal’s web submission tool at evise.com/profile/#/COMPELECENG/login by selecting “SI-gridl” from the “Issues” pull-down menu during the submission process. For additional questions, please contact the guest editors.

Schedule:

Manuscript due: July 31, 2020

Acceptance/rejection notification: September 30, 2020

2nd-round check: November 30, 2020

Final manuscript due: January 31, 2021

Publication: April 2021

Note: The decision on paper acceptance will be made as a cluster, not by individual papers, according to the above schedule.

Guest Editors:

Dr. Gwanggil Jeon, Incheon National University, Korea (Managing Guest Editor)
Email: gjeon@inu.ac.kr

Dr. Abdellah Chehri, Université du Québec à Chicoutimi, Canada
Email: Abdellah_Chehri@uqac.ca

Guest Editors’ shot bios:

Gwanggil Jeon received his B.S., M.S., and Ph.D. degrees from Hanyang University, Korea, in 2003, 2005, and 2008, respectively. From 2009 to 2011, he was a postdoctoral fellow at the University of Ottawa, Canada, and from 2011 to 2012, he was an assistant professor at Niigata University, Japan. He is a professor in Xidian University, China and Incheon National University, Korea. His research interests fall under the umbrella of image processing, deep learning, artificial intelligence, smart grid.

Abdellah Chehri received his M.A.Sc. Degrees in Signal and Digital Communication from the University Sophia-Antipolis at Nice-France. In Sept. 2004, he joined the Department of Electrical and Computer Engineering of Laval University, Quebec, Canada, where he was a member of the Radiocommunications and Signal Processing Laboratory (LRTS). He received his PhD in Electrical Engineering in June 2009 under the supervision of Pr Paul Fortier and Dr Pierre Martin Tardif. From 2007 to 2009, he worked as a project member at the Bell-Aliant Research Laboratory, Quebec, Canada. During this period, he also served as a lecturer in the Information Technologies Graduate Program of UQAT. He joined the University of Ottawa in July 2009 as a post-doc fellow. He is working as an assistant professor at Université du Québec à Chicoutimi.