A Meta-Learning Approach to the Optimal Power Flow Problem Under Topology Reconfigurations
This work provides an incremental improvement for power system operators by reducing the computational burden of retraining OPF predictors when system topologies are reconfigured.
This paper addresses the challenge of retraining deep neural networks for optimal power flow (OPF) problems when power system topologies change. The authors propose a meta-learning approach that finds a common initialization vector, enabling fast training for new topologies with few gradient steps and data samples while maintaining high prediction accuracy.
Recently, there has been a surge of interest in adopting deep neural networks (DNNs) for solving the optimal power flow (OPF) problem in power systems. Computing optimal generation dispatch decisions using a trained DNN takes significantly less time when compared to using conventional optimization solvers. However, a major drawback of existing work is that the machine learning models are trained for a specific system topology. Hence, the DNN predictions are only useful as long as the system topology remains unchanged. Changes to the system topology (initiated by the system operator) would require retraining the DNN, which incurs significant training overhead and requires an extensive amount of training data (corresponding to the new system topology). To overcome this drawback, we propose a DNN-based OPF predictor that is trained using a meta-learning (MTL) approach. The key idea behind this approach is to find a common initialization vector that enables fast training for any system topology. The developed OPF-predictor is validated through simulations using benchmark IEEE bus systems. The results show that the MTL approach achieves significant training speeds-ups and requires only a few gradient steps with a few data samples to achieve high OPF prediction accuracy.