Deep Generative Methods for Producing Forecast Trajectories in Power Systems
This work addresses the need for robust forecasting to ensure power grid security for Transport System Operators, but it is incremental as it adapts existing deep learning methods to a specific domain.
The paper tackled the problem of generating forecast trajectories for energy production and load in power systems to address increased variability from renewables, and demonstrated that deep learning models like autoregressive networks and normalizing flows outperform current copula-based statistical methods on French TSO wind forecast data.
With the expansion of renewables in the electricity mix, power grid variability will increase, hence a need to robustify the system to guarantee its security. Therefore, Transport System Operators (TSOs) must conduct analyses to simulate the future functioning of power systems. Then, these simulations are used as inputs in decision-making processes. In this context, we investigate using deep learning models to generate energy production and load forecast trajectories. To capture the spatiotemporal correlations in these multivariate time series, we adapt autoregressive networks and normalizing flows, demonstrating their effectiveness against the current copula-based statistical approach. We conduct extensive experiments on the French TSO RTE wind forecast data and compare the different models with \textit{ad hoc} evaluation metrics for time series generation.