Wind Park Power Prediction: Attention-Based Graph Networks and Deep Learning to Capture Wake Losses
This work addresses the problem of accurate power production forecasting for wind farms, which is crucial for grid integration, but it is incremental as it builds on existing GNN methods with added attention mechanisms.
The paper tackled wind farm power prediction by proposing an attention-based graph neural network framework to capture wake losses, achieving performance significantly better than MLP and BLSTM models and on-par with a vanilla GNN.
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.