Wind Power Scenario Generation Using Graph Convolutional Generative Adversarial Network
Preprint
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 to use graph filters to embed the spatial correlation among multiple wind farms, and a one-dimensional (1D) convolutional layer for representing the temporal feature filters. The proposed graph and feature filter designs significantly reduce the GAN model complexity, leading to improvements on the 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.Keywords
All Related Versions
This publication has 8 references indexed in Scilit:
- Topology-Aware Graph Neural Networks for Learning Feasible and Adaptive AC-OPF SolutionsIEEE Transactions on Power Systems, 2022
- An approach for day-ahead interval forecasting of photovoltaic power: A novel DCGAN and LSTM based quantile regression modeling methodEnergy Reports, 2022
- GCNs-Net: A Graph Convolutional Neural Network Approach for Decoding Time-Resolved EEG Motor Imagery SignalsIEEE Transactions on Neural Networks and Learning Systems, 2022
- Sequence Generative Adversarial Networks for Wind Power Scenario GenerationIEEE Journal on Selected Areas in Communications, 2019
- Fault Location in Power Distribution Systems via Deep Graph Convolutional NetworksIEEE Journal on Selected Areas in Communications, 2019
- A Review on Hybrid Empirical Mode Decomposition Models for Wind Speed and Wind Power PredictionEnergies, 2019
- Model-Free Renewable Scenario Generation Using Generative Adversarial NetworksIEEE Transactions on Power Systems, 2018
- Handling renewable energy variability and uncertainty in power systems operationWires Energy and Environment, 2013