More Like this

1. Sorta Solving the OPF by Not Solving the OPF: DAE Control Theory and the Price of Realtime Regulation

   https://doi.org/10.1109/OJCSYS.2024.3414221  

   Nadeem, Muhammad; Taha, Ahmad F (January 2024, IEEE Open Journal of Control Systems)
2. DeepOPF-V: Solving AC-OPF Problems Efficiently

   https://doi.org/10.1109/TPWRS.2021.3114092  

   Huang, Wanjun; Pan, Xiang; Chen, Minghua; Low, Steven H. (January 2022, IEEE Transactions on Power Systems)
3. Load Encoding for Learning AC-OPF

   Mak, Terrence W.K.; Fioretto, Ferdinando; Van Hentenryck, Pascal (January 2023, IEEE PES General Meeting (PES))
4. Towards Understanding the Unreasonable Effectiveness of Learning {AC-OPF} Solutions

   Dinh, My H.; Fioretto, Ferdinando; Mohammadian, Mostafa; Baker, Kyri (January 2021, ArXivorg)

   Optimal Power Flow (OPF) is a fundamental problem in power systems. It is computationally challenging and a recent line of research has proposed the use of Deep Neural Networks (DNNs) to find OPF approximations at vastly reduced runtimes when compared to those obtained by classical optimization methods. While these works show encouraging results in terms of accuracy and runtime, little is known on why these models can predict OPF solutions accurately, as well as about their robustness. This paper provides a step forward to address this knowledge gap. The paper connects the volatility of the outputs of the generators to the ability of a learning model to approximate them, it sheds light on the characteristics affecting the DNN models to learn good predictors, and it proposes a new model that exploits the observations made by this paper to produce accurate and robust OPF predictions. 

   more » « less
5. Emulating AC OPF Solvers With Neural Networks

   https://doi.org/10.1109/TPWRS.2022.3195097  

   Baker, Kyri (November 2022, IEEE Transactions on Power Systems)