Wind Park Power Prediction: Attention-Based Graph Networks and Deep Learning to Capture Wake Losses

01/10/2022
by   Lars Ødegaard Bentsen, et al.
0

With the increased penetration of wind energy into the power grid, it has become increasingly important to be able to predict the expected power production for larger wind farms. Deep learning (DL) models can learn complex patterns in the data and have found wide success in predicting wake losses and expected power production. This paper proposes a modular framework for attention-based graph neural networks (GNN), where attention can be applied to any desired component of a graph block. The results show that the model significantly outperforms a multilayer perceptron (MLP) and a bidirectional LSTM (BLSTM) model, while delivering performance on-par with a vanilla GNN model. Moreover, we argue that the proposed graph attention architecture can easily adapt to different applications by offering flexibility into the desired attention operations to be used, which might depend on the specific application. Through analysis of the attention weights, it was showed that employing attention-based GNNs can provide insights into what the models learn. In particular, the attention networks seemed to realise turbine dependencies that aligned with some physical intuition about wake losses.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/04/2023

Towards Deep Attention in Graph Neural Networks: Problems and Remedies

Graph neural networks (GNNs) learn the representation of graph-structure...
research
03/06/2023

Wind Turbine Gearbox Fault Detection Based on Sparse Filtering and Graph Neural Networks

The wind energy industry has been experiencing tremendous growth and con...
research
06/15/2020

Fast Graph Attention Networks Using Effective Resistance Based Graph Sparsification

The attention mechanism has demonstrated superior performance for infere...
research
05/25/2023

Demystifying Oversmoothing in Attention-Based Graph Neural Networks

Oversmoothing in Graph Neural Networks (GNNs) refers to the phenomenon w...
research
06/11/2023

Between-Sample Relationship in Learning Tabular Data Using Graph and Attention Networks

Traditional machine learning assumes samples in tabular data to be indep...
research
07/31/2018

Deep Belief Networks Based Feature Generation and Regression for Predicting Wind Power

Wind energy forecasting helps to manage power production, and hence, red...
research
01/23/2022

Investigating Expressiveness of Transformer in Spectral Domain for Graphs

Transformers have been proven to be inadequate for graph representation ...

Please sign up or login with your details

Forgot password? Click here to reset