Registration Link

Instructors

Alexandra “Sascha” von Meier, University of California, Berkeley
Kevin Jones, Dominion Energy
Sean Murphy, PingThings
Laurel Dunn, University of California, Berkeley
Mohini Bariya, University of California, Berkeley
Miles Rusch, University of California, Berkeley

Abstract
This two-part virtual tutorial is geared at training practitioners on how to use AI to analyze PMU (synchrophasor) data. The first session (PMU fundamentals) will provide a foundation for understanding and interpreting PMU measurement data and applications to practitioners at electric utilities. The second session (Intro to AI) will provide an introduction to Artificial Intelligence (AI), and will give attendees hands-on experience using AI to analyze PMU data in Python. The course will discuss opportunities for PMU data analytics to change best-practices in the industry, and participants will become practiced at using tools that can streamline workflows for digesting and visualizing time series data at scale.

Day 2 | October 28, 2020 | Intro to AI
Day 2 will provide an introductory training for practitioners to start using AI in their own work. The course will begin by covering fundamental concepts related to AI and big data, and will motivate the need for practitioners in energy to become well-versed in AI tools. The course will step through interactive coding exercises using the National Infrastructure for AI on the Grid (NI4AI) Python API to access publicly hosted PMU data. NI4AI is built on PingThings’ PredictiveGridTM platform, a state-of-the-art tool optimized to support big data visualization and analysis workflows. Participants are requested to come prepared with a login to ni4ai.org and with Python installed (both are free). Exercises will assume some familiarity with Python, though participants with no programming experience will benefit from exposure to the concepts and tools presented.

Intro to AI (Day 2)

1. Big data analytics and prediction
(Sean Murphy, 20 min)

2. Interfacing with PMU data in Python
(Laurel Dunn, 25 min)
2.1. Accessing the NI4AI API
2.2. Phasor visualization
2.3. “Unwrapping” phase angle

3. Use cases for PMU data
3.1. Detecting voltage sags
(Mohini Bariya, 30 min)
3.2. Analyzing frequency
(Miles Rusch, 30 min)

4. Closing remarks and outlook for AI on the grid
(Sean Murphy, 15 min)