Learning to Solve the AC-OPF Using Sensitivity-Informed Deep Neural Networks
- 11 November 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Power Systems
- Vol. 37 (4) , 2833-2846
Abstract
To shift the computational burden from real-time to offline in delay-critical power systems applications, recent works entertain the idea of using a deep neural network (DNN) to predict the solutions of the AC optimal power flow (AC-OPF) once presented load demands. As network topologies may change, training this DNN in a sample-efficient manner becomes a necessity. To improve data efficiency, this work utilizes the fact OPF data are not simple training labels, but constitute the solutions of a parametric optimization problem. We thus advocate training a sensitivity-informed DNN (SI-DNN) to match not only the OPF optimizers, but also their partial derivatives with respect to the OPF parameters (loads). It is shown that the required Jacobian matrices do exist under mild conditions, and can be readily computed from the related primal/dual solutions. The proposed SI-DNN is compatible with a broad range of OPF solvers, including a non-convex quadratically constrained quadratic program (QCQP), its semidefinite program (SDP) relaxation, and MATPOWER; while SI-DNN can be seamlessly integrated in other learning-to-OPF schemes. Numerical tests on three benchmark power systems corroborate the advanced generalization and constraint satisfaction capabilities for the OPF solutions predicted by an SI-DNN over a conventionally trained DNN, especially in low-data setups.Keywords
All Related Versions
Funding Information
- National Science Foundation (2034137)
- National Science Foundation (1901134, 2126052, 2128593)
This publication has 33 references indexed in Scilit:
- Quadratically Constrained Quadratic Programs on Acyclic Graphs With Application to Power FlowIEEE Transactions on Control of Network Systems, 2015
- Convex Relaxation for Optimal Power Flow Problem: Mesh NetworksIEEE Transactions on Power Systems, 2014
- Convex Relaxation of Optimal Power Flow—Part II: ExactnessIEEE Transactions on Control of Network Systems, 2014
- Semidefinite programming for optimal power flow problemsInternational Journal of Electrical Power & Energy Systems, 2008
- Perturbation Approach to Sensitivity Analysis in Mathematical ProgrammingJournal of Optimization Theory and Applications, 2006
- Geometric Algorithm for Multiparametric Linear ProgrammingJournal of Optimization Theory and Applications, 2003
- Optimal power flow solutions under variable load conditionsIEEE Transactions on Power Systems, 2000
- Optimal continuation power flowElectric Power Systems Research, 1995
- A general parametric optimal power flowIEEE Transactions on Power Systems, 1994
- Sensitivity analysis for nonlinear programming using penalty methodsMathematical Programming, 1976