Wind Power Scenario Generation Using Graph Convolutional Generative Adversarial Network

TL;DR

This paper introduces a novel graph convolutional GAN for generating realistic wind power scenarios, capturing spatial and temporal correlations efficiently, and outperforming existing methods in realism and computational efficiency.

Contribution

The paper presents a GCGAN that embeds spatial and temporal features using graph filters and 1D convolutions, reducing model complexity and improving scenario realism.

Findings

Generated scenarios show more realistic spatial and temporal statistics.

The approach reduces training and computational complexity.

Outperforms existing GAN-based wind power data generation methods.

Abstract

Generating wind power scenarios is very important for studying the impacts of multiple wind farms that are interconnected to the grid. We develop a graph convolutional generative adversarial network (GCGAN) approach by leveraging GAN's capability in generating large number of realistic scenarios without using statistical modeling. Unlike existing GAN-based wind power data generation approaches, we design GAN's hidden layers to match the underlying spatial and temporal characteristics. We advocate the use of graph filters to embed the spatial correlation among multiple wind farms, and a one-dimensional (1D) convolutional layer to represent the temporal feature filters. The proposed graph and feature filter design significantly reduce the GAN model complexity, leading to improvements in training efficiency and computation complexity. Numerical results using real wind power data from Australia demonstrate that the scenarios generated by the proposed GCGAN exhibit more realistic spatial and temporal statistics than other GAN-based outputs.