Power system state estimation (PSSE) aims at finding the voltage magnitudes and angles at all generation and load buses, using meter readings and other available information. PSSE is often formulated as a nonconvex and nonlinear least-squares (NLS) cost function, which is traditionally solved by the Gauss-Newton method. However, Gauss-Newton iterations for minimizing nonconvex problems are sensitive to the initialization, and they can diverge. In this context, we advocate a deep neural network (DNN) based "trainable regularizer"to incorporate prior information for accurate and reliable state estimation. The resulting regularized NLS does not admit a neat closed form solution. To handle this, a novel end-to-end DNN is constructed subsequently by unrolling a Gauss-Newton-type solver which alternates between least-squares loss and the regularization term. Our DNN architecture can further offer a suite of advantages, e.g., accommodating network topology via graph neural networks based prior. Numerical tests using real load data on the IEEE 118-bus benchmark system showcase the improved estimation performance of the proposed scheme compared with state-of-the-art alternatives. Interestingly, our results suggest that a simple feed forward network based prior implicitly exploits the topology information hidden in data.
|Original language||English (US)|
|Title of host publication||2020 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids, SmartGridComm 2020|
|Publisher||Institute of Electrical and Electronics Engineers Inc.|
|State||Published - Nov 11 2020|
|Event||2020 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids, SmartGridComm 2020 - Tempe, United States|
Duration: Nov 11 2020 → Nov 13 2020
|Name||2020 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids, SmartGridComm 2020|
|Conference||2020 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids, SmartGridComm 2020|
|Period||11/11/20 → 11/13/20|
Bibliographical noteFunding Information:
The work of Q. Yang, G. Wang, and J. Sun was supported in part by the National Natural Science Foundation of China under Grants 61522303, 61720106011, 61621063, and U1613225. Q. Yang was also supported by the China Scholarship Council. The work of A. Sadeghi and G. B. Giannakis was supported in part by the National Science Foundation under Grants 1711471 and 1901134.
© 2020 IEEE.
- Gauss-Newton unrolled neural networks
- Regularized state estimation
- Trainable priors