Generating Contextual Load Profiles Using a Conditional Variational Autoencoder

TL;DR

This paper introduces a conditional variational autoencoder model to generate realistic industrial and commercial load profiles, conditioned on time and grid exchange, aiding system planning and security assessment with limited data.

Contribution

The paper presents a novel CVAE-based generative model specifically designed for complex, variable power load profiles, capturing temporal features and dependencies.

Findings

Generated profiles match historical data distributions

Model captures temporal and dependency features

Produces realistic, diverse load profiles

Abstract

Generating power system states that have similar distribution and dependency to the historical ones is essential for the tasks of system planning and security assessment, especially when the historical data is insufficient. In this paper, we described a generative model for load profiles of industrial and commercial customers, based on the conditional variational autoencoder (CVAE) neural network architecture, which is challenging due to the highly variable nature of such profiles. Generated contextual load profiles were conditioned on the month of the year and typical power exchange with the grid. Moreover, the quality of generations was both visually and statistically evaluated. The experimental results demonstrate our proposed CVAE model can capture temporal features of historical load profiles and generate `realistic' data with satisfying univariate distributions and multivariate dependencies.