Generative Modeling and Data Augmentation for Power System Production Simulation
This work addresses the problem of small sample sizes in power system load forecasting, offering an incremental improvement through enhanced data augmentation.
The paper tackles load forecasting in power systems with limited training data by using a diffusion-based generative model for data augmentation, which reduces forecasting errors significantly and outperforms generative adversarial models by achieving about 200 times smaller errors.
As a key component of power system production simulation, load forecasting is critical for the stable operation of power systems. Machine learning methods prevail in this field. However, the limited training data can be a challenge. This paper proposes a generative model-assisted approach for load forecasting under small sample scenarios, consisting of two steps: expanding the dataset using a diffusion-based generative model and then training various machine learning regressors on the augmented dataset to identify the best performer. The expanded dataset significantly reduces forecasting errors compared to the original dataset, and the diffusion model outperforms the generative adversarial model by achieving about 200 times smaller errors and better alignment in latent data distributions.