Machine Intelligence for Secure and Resilient Power and Energy SystemsSpeaker: Charalambos Konstantinou – Tallahassee, FL, United States
Topic(s): Hardware, Power and Energy
AbstractIn recent years, the advances in machine learning have led to the adoption of such algorithms in a multitude of power and energy systems applications, ranging from customer analytics to load dispatching and energy management systems. Despite the performance benefits of data-driven solutions compared with conventional approaches, there still exist many challenges in regard to the security and robustness as well as the communication efficiency of machine learning algorithms. In light of the recent advancements in adversarial learning, this talk presents methods to certify the attack resiliency and enhance the robustness of learning models used for power and energy systems. Examples are provided for false data injection attack detection in state estimation routines of energy management systems.
About this LectureNumber of Slides: 50
Duration: 45 - 60 minutes
Languages Available: English
Request this Lecture
To request this particular lecture, please complete this online form.
Request a Tour
To request a tour with this speaker, please complete this online form.
All requests will be sent to ACM headquarters for review.