Denoising diffusion probabilistic models for probabilistic energy forecasting

TL;DR

This paper introduces the application of denoising diffusion probabilistic models to probabilistic energy forecasting, demonstrating their effectiveness in generating high-quality renewable energy time series data.

Contribution

It is the first to adapt diffusion models for energy forecasting, showing competitive performance against existing deep generative models.

Findings

Diffusion models produce high-quality energy load, PV, and wind power samples.

The approach is competitive with GANs, VAEs, and normalizing flows.

Open data from GEFCom 2014 used for validation.

Abstract

Scenario-based probabilistic forecasts have become vital for decision-makers in handling intermittent renewable energies. This paper presents a recent promising deep learning generative approach called denoising diffusion probabilistic models. It is a class of latent variable models which have recently demonstrated impressive results in the computer vision community. However, to our knowledge, there has yet to be a demonstration that they can generate high-quality samples of load, PV, or wind power time series, crucial elements to face the new challenges in power systems applications. Thus, we propose the first implementation of this model for energy forecasting using the open data of the Global Energy Forecasting Competition 2014. The results demonstrate this approach is competitive with other state-of-the-art deep learning generative models, including generative adversarial networks, variational autoencoders, and normalizing flows.