Albert Akhriev, Jakub Marecek, et al.
AAAI 2020
Many steady-state problems in power systems, including rectangular power-voltage formulations of optimal power flows in the alternating-current model, can be cast as polynomial optimization problems (POP). For a POP, one can derive strong convex relaxations, or rather hierarchies of increasingly strong, but increasingly computationally challenging convex relaxations. We study means of switching from solving a convex relaxation to Newton's method working on a non-convex (augmented) Lagrangian of the POP.
Albert Akhriev, Jakub Marecek, et al.
AAAI 2020
Mikhail Krechetov, Jakub Marecek, et al.
IJCAI 2019
Philipp Hähnel, Jakub Marecek, et al.
Journal of Computational Physics
Amira Abbas, Andris Ambainis, et al.
Nature Reviews Physics