Machine Learning for AC Optimal Power Flow
This work addresses power grid optimization for energy systems, but it appears incremental as it applies existing ML methods to a known domain without claiming major breakthroughs.
The paper tackles the AC Optimal Power Flow problem by formulating it as two machine learning tasks: end-to-end prediction of optimal generator settings and prediction of active constraints, and validates these approaches on two benchmark grids.
We explore machine learning methods for AC Optimal Powerflow (ACOPF) - the task of optimizing power generation in a transmission network according while respecting physical and engineering constraints. We present two formulations of ACOPF as a machine learning problem: 1) an end-to-end prediction task where we directly predict the optimal generator settings, and 2) a constraint prediction task where we predict the set of active constraints in the optimal solution. We validate these approaches on two benchmark grids.