Back to Search
Start Over
Spatio-temporal graph neural networks for multi-site PV power forecasting
- Source :
- 2022 IEEE Power & Energy Society General Meeting (PESGM).
- Publication Year :
- 2022
- Publisher :
- IEEE, 2022.
-
Abstract
- Accurate forecasting of solar power generation with fine temporal and spatial resolution is vital for the operation of the power grid. However, state-of-the-art approaches that combine machine learning with numerical weather predictions (NWP) have coarse resolution. In this paper, we take a graph signal processing perspective and model multi-site photovoltaic (PV) production time series as signals on a graph to capture their spatio-temporal dependencies and achieve higher spatial and temporal resolution forecasts. We present two novel graph neural network models for deterministic multi-site PV forecasting dubbed the graph-convolutional long short term memory (GCLSTM) and the graph-convolutional transformer (GCTrafo) models. These methods rely solely on production data and exploit the intuition that PV systems provide a dense network of virtual weather stations. The proposed methods were evaluated in two data sets for an entire year: 1) production data from 304 real PV systems, and 2) simulated production of 1000 PV systems, both distributed over Switzerland. The proposed models outperform state-of-the-art multi-site forecasting methods for prediction horizons of six hours ahead. Furthermore, the proposed models outperform state-of-the-art single-site methods with NWP as inputs on horizons up to four hours ahead.<br />10 pages, 7 figures, accepted for publication in IEEE Transactions on Sustainable Energy
- Subjects :
- Signal Processing (eess.SP)
FOS: Computer and information sciences
Computer Science - Machine Learning
Exploit
Computer science
Real-time computing
forecasting
Machine Learning (cs.LG)
FOS: Electrical engineering, electronic engineering, information engineering
convolution
weather forecasting
Electrical Engineering and Systems Science - Signal Processing
Image resolution
Solar power
Transformer (machine learning model)
Renewable Energy, Sustainability and the Environment
business.industry
Photovoltaic system
Perspective (graphical)
graph neural networks
predictive models
data models
machine learning
Temporal resolution
correlation
photovoltaic systems
Graph (abstract data type)
production
business
graph signal processing
Subjects
Details
- Database :
- OpenAIRE
- Journal :
- 2022 IEEE Power & Energy Society General Meeting (PESGM)
- Accession number :
- edsair.doi.dedup.....9404d5641b1cfc676fbcd03882cf8fab