4.8 Article

End-to-end wind turbine wake modelling with deep graph representation learning

Related references

Note: Only part of the references are listed.
Article Thermodynamics

Wind farm wake modeling based on deep convolutional conditional generative adversarial network

Jincheng Zhang et al.

Summary: A novel wind farm wake modeling method is proposed in this study, based on a deep learning framework, which can accurately and efficiently predict wind turbine wake flow. Validation and parametric studies show that the model has good generalization ability, and performs well in a wind farm case study.

ENERGY (2022)

Article Green & Sustainable Science & Technology

Robust validation of a generalised actuator disk CFD model for tidal turbine analysis using the FloWave ocean energy research facility

Charles E. Badoe et al.

Summary: This study evaluates the effectiveness of a generalized actuator disk-computational fluid dynamics (GAD-CFD) approach in capturing the fluid-machine interaction for tidal energy converters. Through physical testing in a unique large-scale experimental facility and extensive validation with numerical simulations, the GAD-CFD approach is shown to perform well in simulating real-world conditions.

RENEWABLE ENERGY (2022)

Article Thermodynamics

Dynamic wind farm wake modeling based on a Bilateral Convolutional Neural Network and high-fidelity LES data

Rui Li et al.

Summary: In this study, a deep learning method called Bilateral Convolutional Neural Network (BiCNN) is proposed to accurately model the wake interactions in a wind farm. The results show that the developed BiCNN model can predict the dynamic wind farm wakes in real time, with an overall prediction error of 3.7% with respect to the freestream wind speed.

ENERGY (2022)

Review Computer Science, Artificial Intelligence

Graph neural network for traffic forecasting: A survey

Weiwei Jiang et al.

Summary: Traffic forecasting is crucial for intelligent transportation systems. Graph neural networks have been widely used to model spatial and temporal dependencies in traffic forecasting problems, achieving state-of-the-art performance. This survey reviews the research on different graph neural networks in various traffic forecasting problems and provides a comprehensive list of open data and source codes for each problem, as well as identifies future research directions.

EXPERT SYSTEMS WITH APPLICATIONS (2022)

Article Computer Science, Artificial Intelligence

Molecular contrastive learning of representations via graph neural networks

Yuyang Wang et al.

Summary: Molecular machine learning shows promise in efficient molecular property prediction and drug discovery. MoICLR is a self-supervised learning framework that utilizes large unlabelled data to improve the performance of graph-neural-network encoders on molecular property benchmarks. It achieves state of the art results and learns representations that can distinguish chemically reasonable molecular similarities.

NATURE MACHINE INTELLIGENCE (2022)

Article Water Resources

Deep residual U-net convolution neural networks with autoregressive strategy for fluid flow predictions in large-scale geosystems

Zhihao Jiang et al.

Summary: In this study, a deep learning surrogate model was developed to predict time-dependent multiphase flow in a 2D geological system, achieving accurate results with less training data. By combining residual U-net and autoregressive strategy, the surrogate model showed improved prediction performance, providing effective measures for uncertainty analysis in subsurface systems.

ADVANCES IN WATER RESOURCES (2021)

Article Engineering, Aerospace

Deep Learning Methods for Reynolds-Averaged Navier-Stokes Simulations of Airfoil Flows

Nils Thuerey et al.

AIAA JOURNAL (2020)

Article Energy & Fuels

Wake modeling of wind turbines using machine learning

Zilong Ti et al.

APPLIED ENERGY (2020)

Article Energy & Fuels

Full rotor modelling and generalized actuator disc for wind turbine wake investigation

H. Daaou Nedjari et al.

ENERGY REPORTS (2020)

Article Chemistry, Physical

Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals

Chi Chen et al.

CHEMISTRY OF MATERIALS (2019)

Article Green & Sustainable Science & Technology

Analysis of control-oriented wake modeling tools using lidar field results

Jennifer Annoni et al.

WIND ENERGY SCIENCE (2018)

Editorial Material Engineering, Electrical & Electronic

Geometric Deep Learning Going beyond Euclidean data

Michael M. Bronstein et al.

IEEE SIGNAL PROCESSING MAGAZINE (2017)

Article Green & Sustainable Science & Technology

An enhanced disk averaged CFD model for the simulation of horizontal axis tidal turbines

M. Edmunds et al.

RENEWABLE ENERGY (2017)

Article Green & Sustainable Science & Technology

Implementation of a generalized actuator disk wind turbine model into the weather research and forecasting model for large-eddy simulation applications

J. D. Mirocha et al.

JOURNAL OF RENEWABLE AND SUSTAINABLE ENERGY (2014)

Article Green & Sustainable Science & Technology

A new analytical model for wind-turbine wakes

Majid Bastankhah et al.

RENEWABLE ENERGY (2014)

Article Green & Sustainable Science & Technology

Experimental study of the turbulence intensity effects on marine current turbines behaviour. Part I: One single turbine

Paul Mycek et al.

RENEWABLE ENERGY (2014)

Article Green & Sustainable Science & Technology

Blind test calculations of the performance and wake development for a model wind turbine

Per-Age Krogstad et al.

RENEWABLE ENERGY (2013)