Data-driven power flow analysis and power grid topology identification

Add to your list(s) Download to your calendar using vCal

• Prof Ning Zhang, Tsinghua University
• Friday 06 December 2019, 11:00-12:00
• 1109B (CAP seminar room) .

If you have a question about this talk, please contact Fei Teng.

Power system is a typical system that well follows the physical law. Therefore, power system has long been studied using model-driven method. However, in some special circumstances, the model-driven method might not work well or the parameters of the model might not be available. At the same time, the big data technologies Has made great progress in recent years. This talk will present two examples in data-driven power system analysis. The first is data-driven power flow calculation. We propose a linearized PF model through a data-driven approach, including the approach that uses P, Q to calculate V and theta and the one that uses V and theta to calculate P,Q. Partial least squares (PLS)- and Bayesian linear regression (BLR)-based algorithms are designed to address data collinearity and avoid overfitting.

We also propose a numerical method to identify the topology and estimate line parameter without the information of voltage angles. A two-step framework is proposed, the first step applies a data-driven regression method to provide preliminary estimation on the topology and line parameter. Then, the second step utilizes a joint data-and-model-driven method, i.e. a specialized Newton- Raphson iteration and power flow equation, to calculate line parameter and recover voltage angle and further correct the topology.

Bio: Ning Zhang is an associate professor in the Department of Electrical Engineering, Tsinghua University. He got his B.Sc. degree from Tsinghua University, Beijing, China in 2007. He got his Ph.D in electrical engineering from Tsinghua University in 2012. He was a research associate in The University of Manchester from Oct. 2010 to Jul. 2011 and a research assistant in Harvard University from Dec. 2013 to Mar 2014. He is an IEEE Senior Member and Cigre Member. His research interests include multiple energy system, power system planning and operation with renewable energy (wind power photovoltaic, concentrated solar power) and data-driven analytic of power system. He has published more than 100 papers, including more than 50 papers in IEEE Transactions and Applied Energy. He has 13 invention patents and 8 computer software copyrights. His papers have over 2500 citations with an H index of 28 on Google Scholar.

This talk is part of the Control and Power Seminars series.

This talk is included in these lists:

• 1109B (CAP seminar room)
• Andrea Picciau's list
• Control and Power Seminars

Note that ex-directory lists are not shown.