Generating Contextual Load Profiles Using a Conditional Variational Autoencoder
This addresses data insufficiency for power system planning and security assessment, but is incremental as it applies an existing method to a specific domain.
The paper tackled generating realistic load profiles for industrial and commercial customers using a conditional variational autoencoder, demonstrating that the model captures temporal features and produces data with good univariate distributions and multivariate dependencies.
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.