Рет қаралды 20
Smart meter deployments are increasing rapidly due to their ability to provide fine-granular, real-time energy consumption data, which can be utilized for a wide range of applications in smart grids, such as demand response, energy management, and grid optimization. However, regulations such as the General Data Protection Regulation (GDPR) limit the use of smart meter data, as it can reveal personally identifying information. In this presentation, individual smart meter load forecasting is investigated while considering privacy constraints. Privacy-preserving data-driven algorithms, such as federated learning, are explored for this purpose.
The presentation begins with a general overview of data-sharing concerns in smart grids, followed by a discussion of privacy issues related to smart meter data and relevant regulations. Next, general approaches to individual smart meter load forecasting are examined. Finally, privacy-preserving data-driven algorithms are investigated for their applicability to individual smart meter load forecasting.
About the presenter:
Mert Kesici received the B.Sc. degree in electrical engineering from Kocaeli University, Kocaeli, Turkey, in 2016, and the M.Sc. degree in electrical engineering from Istanbul Technical University, Istanbul, in 2019. He is currently a Marie Skłodowska-Curie Early-Stage Researcher and a PhD candidate at Imperial College London. His research interests include the cyber security of smart grids and the application of privacy-preserving machine learning algorithms to smart grids.
_____
InnoCyPES Summer School 2024: Exploring the Cyber-Physical Evolution of Offshore Wind and Distribution Grids.
The programme focused on innovative and key topics for the future of power systems: IoT-Edge Networks, Cybersecurity, Data Management, Power Quality, and Grid-Forming Inverter-Based Resources and Stability.
The event was hosted at the Università del Salento in Lecce, Italy, from September 9th to 13th, 2024.
Innovative Tools for Cyber-Physical Energy Systems (InnoCyPES) is a doctoral network part of the Marie Skłodowska-Curie Actions programme, funded by the European Union under the Horizon Europe Research and Innovation Programme.
Website: innocypes.eu