A joint missing power data recovery method based on the spatiotemporal correlation of multiple wind farms
Open Access
- 1 January 2024
- journal article
- research article
- Published by AIP Publishing in Journal of Renewable and Sustainable Energy
- Vol. 16 (1)
Abstract
In reality, wind power data are often accompanied by data losses, which can affect the accurate prediction of wind power and subsequently impact the real-time scheduling of the power system. Existing methods for recovering missing data primarily consider the environmental conditions of individual wind farms, thereby overlooking the spatiotemporal correlations between neighboring wind farms, which significantly compromise their recovery effectiveness. In this paper, a joint missing data recovery model based on power data from adjacent wind farms is proposed. At first, a spatial–temporal module (STM) is designed using a combination of graph convolution network and recurrent neural networks to learn spatiotemporal dependencies and similarities. Subsequently, to provide a solid computational foundation for the STM, a Euclidean-directed graph based on Granger causality is constructed to reflect the hidden spatiotemporal information in the data. Finally, comprehensive tests on data recovery for both missing completely at random and short-term continuous missing are conducted on a real-world dataset. The results demonstrate that the proposed model exhibits a significant advantage in missing data recovery compared to baseline models.Keywords
Funding Information
- Natural Science Foundation of Shanxi Province (No. 202203021221153)
This publication has 20 references indexed in Scilit:
- Missing data in wind farm time series: Properties and effect on forecastsElectric Power Systems Research, 2020
- A passive islanding detection method based on K-means clustering and EMD of reactive power signalSustainable Energy, Grids and Networks, 2020
- Missing data imputation with adversarially-trained graph convolutional networksNeural Networks, 2020
- SolarGAN: Multivariate Solar Data Imputation Using Generative Adversarial NetworkIEEE Transactions on Sustainable Energy, 2020
- Variable-Lag Granger Causality for Time Series Analysis2019
- Wind Power Curve Modeling With Asymmetric Error DistributionIEEE Transactions on Sustainable Energy, 2019
- Vertically Correlated Echelon Model for the Interpolation of Missing Wind Speed DataIEEE Transactions on Sustainable Energy, 2014
- Calibration of a Wind Farm Wind Speed Model With Incomplete Wind DataIEEE Transactions on Sustainable Energy, 2013
- The Graph Neural Network ModelIEEE Transactions on Neural Networks, 2008
- Long Short-Term MemoryNeural Computation, 1997