Convolutional Graph Autoencoder: A Generative Deep Neural Network for Probabilistic Spatio-Temporal Solar Irradiance Forecasting

Machine learning on graphs is an important and omnipresent task for a vast variety of applications including anomaly detection and dynamic network analysis. In this paper, a deep generative model is introduced to capture continuous probability densities corresponding to the nodes of an arbitrary gra...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on sustainable energy Jg. 11; H. 2; S. 571 - 583
Hauptverfasser: Khodayar, Mahdi, Mohammadi, Saeed, Khodayar, Mohammad E., Wang, Jianhui, Liu, Guangyi
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Piscataway IEEE 01.04.2020
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
Algorithms
Anomalies
Artificial neural networks
Bayesian analysis
Computational modeling
Data models
Deep learning
Deep neural network
Forecasting
Geographical distribution
Graph neural networks
Irradiance
Learning algorithms
Machine learning
Mathematical analysis
Mathematical model
Neural networks
Nodes
Optimization
Pattern recognition
Predictive models
probabilistic forecasting
Probabilistic logic
Radiation
Radiation measurement
Solar radiation
spatio-temporal forecasting
spectral graph convolutions
Statistical analysis
Statistical inference
variational Bayesian inference
ISSN:1949-3029, 1949-3037
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Machine learning on graphs is an important and omnipresent task for a vast variety of applications including anomaly detection and dynamic network analysis. In this paper, a deep generative model is introduced to capture continuous probability densities corresponding to the nodes of an arbitrary graph. In contrast to all learning formulations in the area of discriminative pattern recognition, we propose a scalable generative optimization/algorithm theoretically proved to capture distributions at the nodes of a graph. Our model is able to generate samples from the probability densities learned at each node. This probabilistic data generation model, i.e., convolutional graph autoencoder (CGAE), is devised based on the localized first-order approximation of spectral graph convolutions, deep learning, and the variational Bayesian inference. We apply the CGAE to a new problem, the spatio-temporal probabilistic solar irradiance prediction. Multiple solar radiation measurement sites in a wide area in northern states of the U.S. are modeled as an undirected graph. Using our proposed model, the distribution of future irradiance given historical radiation observations is estimated for every site/node. Numerical results on the national solar radiation database show state-of-the-art performance for probabilistic radiation prediction on geographically distributed irradiance data in terms of reliability, sharpness, and continuous ranked probability score.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1949-3029
1949-3037
DOI:10.1109/TSTE.2019.2897688