EnergyDiff: Universal Time-Series Energy Data Generation using Diffusion Models

TL;DR

EnergyDiff is a novel diffusion-based framework that generates high-resolution synthetic energy time series data, preserving complex temporal dependencies and distributions, useful for privacy-preserving energy system analysis.

Contribution

The paper introduces EnergyDiff, a universal diffusion model for energy time series data, with a new denoising network and marginal calibration, improving synthetic data quality across diverse energy domains.

Findings

Outperforms baselines in capturing temporal dependencies

Effective across multiple energy domains and resolutions

Maintains realistic marginal distributions in generated data

Abstract

High-resolution time series data are crucial for the operation and planning of energy systems such as electrical power systems and heating systems. Such data often cannot be shared due to privacy concerns, necessitating the use of synthetic data. However, high-resolution time series data is difficult to model due to its inherent high dimensionality and complex temporal dependencies. Leveraging the recent development of generative AI, especially diffusion models, we propose EnergyDiff, a universal data generation framework for energy time series data. EnergyDiff builds on state-of-the-art denoising diffusion probabilistic models, utilizing a proposed denoising network dedicated to high-resolution time series data and introducing a novel Marginal Calibration technique. Our extensive experimental results demonstrate that EnergyDiff achieves significant improvement in capturing the temporal dependencies and marginal distributions compared to baselines, particularly at the 1-minute resolution. EnergyDiff's universality is validated across diverse energy domains (e.g., electricity demand, heat pump, PV, multiple time resolutions (1 minute, 15 minutes, 30 minutes and 1 hour), and at both customer and transformer levels.