Summary of Short-term Wind Speed Forecasting Model Based on An Attention-gated Recurrent Neural Network and Error Correction Strategy, by Haojian Huang
Short-term wind speed forecasting model based on an attention-gated recurrent neural network and error correction strategy
by Haojian Huang
First submitted to arxiv on: 17 Apr 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Atmospheric and Oceanic Physics (physics.ao-ph)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This dissertation proposes an improved short-term wind speed forecast pattern using an attention-based gated recurrent neural network (AtGRU) with error correction. The AtGRU model serves as a preliminary predictor, while a GRU model is used to correct errors. To reduce noise in historical wind speed series, singular spectrum analysis (SSA) is employed. The prediction process can introduce certain errors, which are processed using variational modal decomposition (VMD) to train the error corrector. The final forecast result is the sum of the predictor’s forecast and the error corrector’s output. The proposed SSA-AtGRU-VMD-GRU model outperforms compared models in three case studies on Woodburn, St. Thomas, and Santa Cruz. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps predict wind speeds more accurately. This is important because it can help make sure power grids are safe and reliable when using wind power. The challenge is that wind speed data is hard to predict because it’s not linear or stationary. To solve this problem, the researchers developed a new model called SSA-AtGRU-VMD-GRU. This model uses attention-based recurrent neural networks and error correction to improve predictions. The results show that this model works better than other methods in predicting wind speeds. |
Keywords
» Artificial intelligence » Attention » Neural network
