Deep Generative Methods for Producing Forecast Trajectories in Power Systems

TL;DR

This paper explores deep generative models like autoregressive networks and normalizing flows to produce realistic power system forecast trajectories, enhancing robustness amid increasing renewable energy variability.

Contribution

It introduces the adaptation of deep learning models for generating power system forecast trajectories, outperforming traditional copula-based statistical methods.

Findings

Deep learning models effectively capture spatiotemporal correlations.

Models outperform traditional copula-based approaches.

Extensive experiments validate the models' accuracy on real data.

Abstract

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.