Panel Session: Data Analytics and Machine Learning for Power System Monitoring and Operation: An Industrial Perspective (slides)
C. Mishra, T. Hong
-
PES
IEEE Members: $10.00
Non-members: $20.00Pages/Slides: 44
With the increasing deployment of advanced sensors, power system operators have been collecting significant amounts of data. These multi-domain multi-resolution data (PMUs, SCADA, Weather, GIS, etc.) provide an opportunity to level up the intelligence of the modern power system. Advanced data analytics and machine learning enable health status predictions, prompt anomaly detections, and autonomous decision-making in a distributed or decentralized fashion. These capabilities are essential for accommodating more intermittent renewable and facilitating grid decarbonization.
Nowadays, machine learning frameworks and their applications have been extensively studied by power system academia. However, the challenges in real-world scenarios and the pathway to field deployment are still not clear. In this panel session, we present a series of successful stories, R&D efforts, pilot projects, and visions from broader industrial members, including utilities, electric research institutes, and national labs, about the applications of data analytics and machine learning for distributed and decentralized decisions and control. Our ultimate goal of this panel session is to connect cutting-edge data analytics and machine learning theories to real-world problems and show the pathway for artificial intelligence-based technology landing to address challenges in the process of grid decarbonization.
Presentations and Panelists:
• “Data Driven Grid Dynamics Discovery and Analysis” by C. Mishra, Dominion Energy
• “Data-Driven Optimization for Voltage Control of Networked Microgrids” by T. Hong, ANL
Nowadays, machine learning frameworks and their applications have been extensively studied by power system academia. However, the challenges in real-world scenarios and the pathway to field deployment are still not clear. In this panel session, we present a series of successful stories, R&D efforts, pilot projects, and visions from broader industrial members, including utilities, electric research institutes, and national labs, about the applications of data analytics and machine learning for distributed and decentralized decisions and control. Our ultimate goal of this panel session is to connect cutting-edge data analytics and machine learning theories to real-world problems and show the pathway for artificial intelligence-based technology landing to address challenges in the process of grid decarbonization.
Presentations and Panelists:
• “Data Driven Grid Dynamics Discovery and Analysis” by C. Mishra, Dominion Energy
• “Data-Driven Optimization for Voltage Control of Networked Microgrids” by T. Hong, ANL
Chairs:
Yichen Zhang, Tianqi Hong