Spatial Network Decomposition for Fast and Scalable AC-OPF Learning
This addresses the scalability and training time challenges in power system optimization for grid operators, though it is incremental as it builds on existing machine-learning approaches with a novel decomposition strategy.
The paper tackles the slow training of machine learning models for predicting AC optimal power flow (AC-OPF) solutions by proposing a two-stage spatial decomposition method, achieving high-fidelity predictions with minor constraint violations and reducing running times significantly, such as seeding a load flow optimization to within 0.03% of the AC-OPF objective.
This paper proposes a novel machine-learning approach for predicting AC-OPF solutions that features a fast and scalable training. It is motivated by the two critical considerations: (1) the fact that topology optimization and the stochasticity induced by renewable energy sources may lead to fundamentally different AC-OPF instances; and (2) the significant training time needed by existing machine-learning approaches for predicting AC-OPF. The proposed approach is a 2-stage methodology that exploits a spatial decomposition of the power network that is viewed as a set of regions. The first stage learns to predict the flows and voltages on the buses and lines coupling the regions, and the second stage trains, in parallel, the machine-learning models for each region. Experimental results on the French transmission system (up to 6,700 buses and 9,000 lines) demonstrate the potential of the approach. Within a short training time, the approach predicts AC-OPF solutions with very high fidelity and minor constraint violations, producing significant improvements over the state-of-the-art. The results also show that the predictions can seed a load flow optimization to return a feasible solution within 0.03% of the AC-OPF objective, while reducing running times significantly.