Revisiting Deep AC-OPF
This work addresses the need for rigorous benchmarking in power systems optimization, highlighting incremental improvements by showing that linear methods can match ML performance, which is crucial for researchers and practitioners in energy and ML.
The paper tackled the problem of evaluating machine learning models as fast surrogates for AC optimal power flow (AC-OPF), finding that while their transformer-based model OPFormer-V improves over the state-of-the-art DeepOPF-V, simple linear baselines achieve comparable performance, with relative gains of ML approaches being less pronounced than expected.
Recent work has proposed machine learning (ML) approaches as fast surrogates for solving AC optimal power flow (AC-OPF), with claims of significant speed-ups and high accuracy. In this paper, we revisit these claims through a systematic evaluation of ML models against a set of simple yet carefully designed linear baselines. We introduce OPFormer-V, a transformer-based model for predicting bus voltages, and compare it to both the state-of-the-art DeepOPF-V model and simple linear methods. Our findings reveal that, while OPFormer-V improves over DeepOPF-V, the relative gains of the ML approaches considered are less pronounced than expected. Simple linear baselines can achieve comparable performance. These results highlight the importance of including strong linear baselines in future evaluations.