Compact Optimization Learning for AC Optimal Power Flow
Seonho Park, Wenbo Chen, Terrence W. K. Mak, Pascal Van Hentenryck
Abstract
This article reconsiders end-to-end learning approaches to the Optimal Power Flow (OPF). Existing methods, which learn the input/output mapping of the OPF, suffer from scalability issues due to the high dimensionality of the output space. This article first shows that the space of optimal solutions can be significantly compressed using principal component analysis (PCA). It then proposes <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Compact Learning</small> , a new method that learns in a subspace of the principal components and translates the vectors into the original output space. This compression reduces the number of trainable parameters substantially, improving scalability and effectiveness. <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Compact Learning</small> is evaluated on a variety of test cases from the PGLib and a realistic French transmission system having renewable energy changes with up to 30,000 buses. The article also shows that the output of <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Compact Learning</small> can be used to warm-start an exact AC solver to restore feasibility, while bringing significant speed-ups.