A Machine Learning Initializer for Newton-Raphson AC Power Flow Convergence

Okhuegbe, Samuel N.; Ademola, Adedasola A.; Liu, Yilu

doi:10.1109/tpec60005.2024.10472261

A Machine Learning Initializer for Newton-Raphson AC Power Flow Convergence

Conference · Mon Feb 12 04:00:00 EST 2024 · 2024 IEEE Texas Power and Energy Conference (TPEC)

DOI:https://doi.org/10.1109/tpec60005.2024.10472261· OSTI ID:2447266

Okhuegbe, Samuel N. ^[1]; Ademola, Adedasola A. ^[2]; Liu, Yilu ^[3]

Univ. of Tennessee, Knoxville, TN (United States)
Univ. of Tennessee, Knoxville, TN (United States); Dominion Energy, Glen Allen, VA (United States)
Univ. of Tennessee, Knoxville, TN (United States); Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)

Power flow computations are fundamental to many power system studies. Obtaining a converged power flow case is not a trivial task especially in large power grids due to the non-linear nature of the power flow equations. One key challenge is that the widely used Newton based power flow methods are sensitive to the initial voltage magnitude and angle estimates, and a bad initial estimate would lead to non-convergence. This paper addresses this challenge by developing a random-forest (RF) machine learning model to provide better initial voltage magnitude and angle estimates towards achieving power flow convergence. This method was implemented on a real ERCOT 6102 bus system under various operating conditions. By providing better Newton-Raphson initialization, the RF model precipitated the solution of 2,106 cases out of 3,899 non-converging dispatches. These cases could not be solved from flat start or by initialization with the voltage solution of a reference case. Finally, results obtained from the RF initializer performed better when compared with DC power flow initialization, Linear regression, and Decision Trees.

Research Organization:: Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)

Sponsoring Organization:: USDOE

DOE Contract Number:: AC05-00OR22725

OSTI ID:: 2447266

Conference Information:: Journal Name: 2024 IEEE Texas Power and Energy Conference (TPEC)

Country of Publication:: United States

Language:: English

References (10)

Automated Tool to Create Chronological AC Power Flow Cases for Large Interconnected Systems Vyakaranam, Bharat; Nguyen, Quan H.; Nguyen, Tony B. IEEE Open Access Journal of Power and Energy, Vol. 8 https://doi.org/10.1109/oajpe.2021.3075659	journal	January 2021
A Physics-Informed Graph Attention-based Approach for Power Flow Analysis Jeddi, Ashkan B.; Shafieezadeh, Abdollah 2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA) https://doi.org/10.1109/icmla52953.2021.00261	conference	December 2021
The initial guess estimation newton method for power flow in distribution systems Sun, Qiuye; Liu, Ling; Ma, Dazhong IEEE/CAA Journal of Automatica Sinica, Vol. 4, Issue 2 https://doi.org/10.1109/jas.2017.7510514	journal	April 2017
Physics-Guided Deep Neural Networks for Power Flow Analysis Hu, Xinyue; Hu, Haoji; Verma, Saurabh IEEE Transactions on Power Systems, Vol. 36, Issue 3 https://doi.org/10.1109/tpwrs.2020.3029557	journal	May 2021
Power Flow Convergence and Reactive Power Planning in the Creation of Large Synthetic Grids Birchfield, Adam B.; Xu, Ti; Overbye, Thomas J. IEEE Transactions on Power Systems, Vol. 33, Issue 6 https://doi.org/10.1109/tpwrs.2018.2813525	journal	November 2018
Physics-Guided Residual Learning for Probabilistic Power Flow Analysis Chen, Kejun; Zhang, Yu IEEE Access, Vol. 11 https://doi.org/10.1109/ACCESS.2023.3308067	journal	January 2023
On Extending and Comparing Newton–Raphson Variants for Solving Power-Flow Equations Dutto, Simone; Masetti, Giulio; Chiaradonna, Silvano IEEE Transactions on Power Systems, Vol. 34, Issue 4 https://doi.org/10.1109/tpwrs.2019.2897640	journal	July 2019
Applications of Physics-Informed Neural Networks in Power Systems - A Review Huang, Bin; Wang, Jianhui IEEE Transactions on Power Systems, Vol. 38, Issue 1 https://doi.org/10.1109/tpwrs.2022.3162473	journal	January 2023
AC vs. DC distribution: Maximum transfer capability Starke, Michael; Tolbert, Leon M. 2008 IEEE Power and Energy Society General Meeting - Conversion and Delivery of Electrical Energy in the 21st Century https://doi.org/10.1109/PES.2008.4596730	conference	July 2008
Learning Warm-Start Points For Ac Optimal Power Flow Baker, Kyri 2019 IEEE 29th International Workshop on Machine Learning for Signal Processing (MLSP) https://doi.org/10.1109/MLSP.2019.8918690	conference	October 2019

Similar Records

Loadflow solution by applying hybrid algorithm to the Newton-Raphson method

Conference · Sun Dec 31 23:00:00 EST 1989 · Proceedings of the American Power Conference; (United States) · OSTI ID:6174457

Application of the fast Newton-Raphson economic dispatch and reactive power/voltage dispatch by sensitivity factors to optimal power flow

Journal Article · Thu Jun 01 00:00:00 EDT 1995 · IEEE Transactions on Energy Conversion · OSTI ID:94110

A direct Newton-Raphson economic dispatch

Journal Article · Sat Aug 01 00:00:00 EDT 1992 · IEEE Transactions on Power Systems (Institute of Electrical and Electronics Engineers); (United States) · OSTI ID:7102354

Related Subjects

random forest
Newton Raphson
machine learning
power flow convergence
power flow initialization

A Machine Learning Initializer for Newton-Raphson AC Power Flow Convergence

Citation Formats

References (10)

Similar Records

Related Subjects