Modified Particle Swarm Optimization with Attention-Based LSTM for Wind Power Prediction
The accuracy of wind power prediction is crucial for the economic operation of a wind power dispatching management system. Wind power generation is closely related to the meteorological conditions around wind plants; a small variation in wind speed could lead to a large fluctuation in the extracted...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-06-01
|
Series: | Energies |
Subjects: | |
Online Access: | https://www.mdpi.com/1996-1073/15/12/4334 |
_version_ | 1797487835957166080 |
---|---|
author | Yiyang Sun Xiangwen Wang Junjie Yang |
author_facet | Yiyang Sun Xiangwen Wang Junjie Yang |
author_sort | Yiyang Sun |
collection | DOAJ |
description | The accuracy of wind power prediction is crucial for the economic operation of a wind power dispatching management system. Wind power generation is closely related to the meteorological conditions around wind plants; a small variation in wind speed could lead to a large fluctuation in the extracted power and is difficult to predict accurately, causing difficulties in grid connection and generating large economic losses. In this study, a wind power prediction model based on a long short-term memory network with a two-stage attention mechanism is established. An attention mechanism is used to measure the input data characteristics and trend characteristics of the wind power and reduce the initial data preparation process. The model effectively alleviates the intermittence and fluctuation of meteorological conditions and improves prediction accuracy significantly. In addition, the modified particle swarm optimization algorithm is introduced to optimize the hyperparameters of the LSTM network, which speeds up the convergence of the model dramatically and avoids falling into local optima, reducing the influence of man-made random selection of LSTM network hyperparameters on the prediction results. The simulation results on the real wind power data show that the modified model has increased prediction accuracy compared with the previous machine learning methods. The monitoring and data collecting system for wind farms reveals that the accuracy of the model is around 95.82%. |
first_indexed | 2024-03-09T23:53:29Z |
format | Article |
id | doaj.art-4eda2e4964d049e9935da72c05a7f689 |
institution | Directory Open Access Journal |
issn | 1996-1073 |
language | English |
last_indexed | 2024-03-09T23:53:29Z |
publishDate | 2022-06-01 |
publisher | MDPI AG |
record_format | Article |
series | Energies |
spelling | doaj.art-4eda2e4964d049e9935da72c05a7f6892023-11-23T16:29:26ZengMDPI AGEnergies1996-10732022-06-011512433410.3390/en15124334Modified Particle Swarm Optimization with Attention-Based LSTM for Wind Power PredictionYiyang Sun0Xiangwen Wang1Junjie Yang2College of Electronics and Information Engineering, Shanghai University of Electric Power, No. 185, Hucheng Ring Road, Pudong New Area District, Shanghai 201306, ChinaCollege of Electronics and Information Engineering, Shanghai University of Electric Power, No. 2103, Pingliang Road, Yangpu District, Shanghai 200090, ChinaSchool of Electronic Information Engineering, Shanghai Dianji University, No. 300, Shuihua Road, Pudong New Area District, Shanghai 201306, ChinaThe accuracy of wind power prediction is crucial for the economic operation of a wind power dispatching management system. Wind power generation is closely related to the meteorological conditions around wind plants; a small variation in wind speed could lead to a large fluctuation in the extracted power and is difficult to predict accurately, causing difficulties in grid connection and generating large economic losses. In this study, a wind power prediction model based on a long short-term memory network with a two-stage attention mechanism is established. An attention mechanism is used to measure the input data characteristics and trend characteristics of the wind power and reduce the initial data preparation process. The model effectively alleviates the intermittence and fluctuation of meteorological conditions and improves prediction accuracy significantly. In addition, the modified particle swarm optimization algorithm is introduced to optimize the hyperparameters of the LSTM network, which speeds up the convergence of the model dramatically and avoids falling into local optima, reducing the influence of man-made random selection of LSTM network hyperparameters on the prediction results. The simulation results on the real wind power data show that the modified model has increased prediction accuracy compared with the previous machine learning methods. The monitoring and data collecting system for wind farms reveals that the accuracy of the model is around 95.82%.https://www.mdpi.com/1996-1073/15/12/4334wind power predictionmodify particle swarm optimization algorithm (MPSO)attention mechanismLSTM neural network |
spellingShingle | Yiyang Sun Xiangwen Wang Junjie Yang Modified Particle Swarm Optimization with Attention-Based LSTM for Wind Power Prediction Energies wind power prediction modify particle swarm optimization algorithm (MPSO) attention mechanism LSTM neural network |
title | Modified Particle Swarm Optimization with Attention-Based LSTM for Wind Power Prediction |
title_full | Modified Particle Swarm Optimization with Attention-Based LSTM for Wind Power Prediction |
title_fullStr | Modified Particle Swarm Optimization with Attention-Based LSTM for Wind Power Prediction |
title_full_unstemmed | Modified Particle Swarm Optimization with Attention-Based LSTM for Wind Power Prediction |
title_short | Modified Particle Swarm Optimization with Attention-Based LSTM for Wind Power Prediction |
title_sort | modified particle swarm optimization with attention based lstm for wind power prediction |
topic | wind power prediction modify particle swarm optimization algorithm (MPSO) attention mechanism LSTM neural network |
url | https://www.mdpi.com/1996-1073/15/12/4334 |
work_keys_str_mv | AT yiyangsun modifiedparticleswarmoptimizationwithattentionbasedlstmforwindpowerprediction AT xiangwenwang modifiedparticleswarmoptimizationwithattentionbasedlstmforwindpowerprediction AT junjieyang modifiedparticleswarmoptimizationwithattentionbasedlstmforwindpowerprediction |