Class Syllabus:

Graduate level class on using data science tools in power systems. This course explores how data is generated in power systems and how are new technologies impacting the amount and quality of datasets, understanding popular data processing and analytic techniques, implementing existing packages to solve problems, using machine learning methods to answer questions about power system operations, and choosing appropriate methods based on objectives and datasets. See syllabus.
Acknowledgements: This class draws from a number of sources, including Prof. Yang Weng’s class at ASU, Prof. Hao Zhu’s class at UT Austin, Prof. Ned Mohan’s classes at University of Minnesota.

This website is used for most of the materials posted in this class. The Canvas Site is only used for grading.

Class: Tuesdays, 6pm-8:50pm, ECE Building, room 037.
Instructor: Baosen Zhang, zhangbao@uw.edu, Office: EEB M310, Office Hour: Monday 3:30 to 4:30 or by request
Notebook: The main notebook we use for programming is here. Examples and related course materials can be found here

Note:

  1. You are encouraged to attend lectures in person. They will be recorded and posted to youtube after the lecture.
  2. I will try to respond to emails within 24 hours.
  3. It is very important to do the programming assignments.

Useful Data Sources:

  1. NREL Wind Integration Study, Solar Integration Study
  2. PECAN Street (need to register, free with a .edu email)
  3. ERCOT (Texas) load data
  4. Residential P,Q,V measurements: PQube
  5. WECC Interconnection Models, these require familiarity with power system modeling to use
  6. IEEE PES Subcommittee on Big Data \& Data Analytics

Detailed Topics:

  1. Introduction, review, slide, recorded lecture
  2. Regression 1, slide, recorded lecture
  3. Regression 2, slide, video, slide 2, video
  4. State Estimation, Classification 1, slide, video
  5. Classification 2, slide, video, video 2
  6. Deep Neural Networks, slide, video
  7. Clustering, slide, video
  8. Optimal Operations, slide, video
  9. Project Presentation

Homework and Project:

  1. There are weekly homework assignments.
  2. Final project presentation on the last day of class.

Homework Assignments:

  1. Homework 1, due April 6th at 11:59pm. Submit the answer to the first three questions to CANVAS
  2. Homework 2, the file is here. You may need to run the cells from the beginning of the notebook to get it to display the equations correctly. Solve the problem at the end of notebook, due April 17th at 11:59pm. It will be graded directly in JupyterHub.
  3. Homework 3, the file is here. You may need to run the cells from the beginning of the notebook to get it to display the equations correctly. Solve the problem at the end of notebook, due April 27th at 11:59pm. It will be graded directly in JupyterHub.
  4. Homework 4, the notebook is here. The data you need are found at training data and testing data, they need to be uploaded to the same directory as the notebook. Due May 4th at 11:59pm. It will be graded directly in JupyterHub.
  5. Homework 5, the notebook is here. The data you need are found at training data and testing data, they need to be uploaded to the same directory as the notebook. Due May 11th at 11:59pm. It will be graded directly in JupyterHub.
  6. Homework 6, the notebook is here. The data you need are found at training data, testing data, and bonous question data. They need to be uploaded to the same directory as the notebook. Due May 18th at 11:59pm. It will be graded directly in JupyterHub.
  7. Homework 7. Due May 25th at 11:59pm. Please describe the progress in your project. Create a new file in your directory, named “project_update” and show your data set, any preliminary code and any preliminary results. Only a single member of a team need to do this.