Forecasting Power Grid Frequency Trajectories with Structured State Space Models

Abstract

Improving our ability to model, predict, and understand power system dynamics is becoming increasingly important as we face the challenges of transitioning to a carbon-neutral energy system. The power grid frequency is central to power system control as it is the primary observable for balancing generation and demand on short time scales. By facilitating frequency control actions, accurate prediction of grid frequency can improve system stability. In recent years, promising new deep learning techniques for time series forecasting tasks have emerged. Here, we explore the application of structured state space models (S4) to high-resolution power system frequency time series. S4 models have previously demonstrated good performance for long-term dependence tasks, but how useful are they for high-resolution energy time series?