| 引用本文: | 潘 超,王 超,孙 惠,孟 涛.基于超参数优化和误差修正的STAGN超短期风电功率预测[J].电力系统保护与控制,2025,53(8):117-129.[点击复制] |
| PAN Chao,WANG Chao,SUN Hui,MENG Tao.STAGN ultra-short-term wind power forecasting based on hyperparameter optimization and error correction[J].Power System Protection and Control,2025,53(8):117-129[点击复制] |
|
| 摘要: |
| 针对风电功率预测模型的数据关联性与误差修正适应性问题，提出基于超参数优化和误差修正单元切换的超短期风电功率预测方法。首先，构建时空注意力门控网络预测模型，利用改进开普勒算法进行超参数优化。然后，考虑风电场数据与预测误差之间的非线性关联，构建误差修正自适应单元。同时挖掘风速时序变化特征，构建深度学习单元。在此基础上，提出基于风速矩阵梯度的误差修正单元切换策略。最后，将模型应用于实际风场的功率预测并与其他模型对比分析。结果表明，所提方法在预测精度上优于其他方法，且在风速复杂多变的风场仍具有较高预测精度，验证了所提方法的准确性和适用性。 |
| 关键词: 超短期风电功率预测 改进开普勒算法 误差修正 风速矩阵梯度 |
| DOI：10.19783/j.cnki.pspc.240939 |
| 投稿时间：2024-07-22修订日期：2024-08-25 |
| 基金项目:国家重点研发计划项目资助(2022YFB2404000) |
|
| STAGN ultra-short-term wind power forecasting based on hyperparameter optimization and error correction |
| PAN Chao1,WANG Chao1,SUN Hui1,MENG Tao1,2 |
| (1. Key Laboratory of Modern Power System Simulation and Control & Renewable Energy Technology
(Northeast Electric Power University), Ministry of Education, Jilin 132012, China; 2. State Grid
Jilin Electric Power Research Institute Co., Ltd., Changchun 130021, China) |
| Abstract: |
| To address the issues of data correlation and error correction adaptability in wind power forecasting models, an ultra-short-term wind power prediction method based on hyperparameter optimization and error correction unit switching mechanism is proposed. First, a spatiotemporal attention gated network (STAGN) forecasting model is developed, and hyperparameter optimization is carried out using the improved Kepler optimization algorithm. Second, an error correction adaptive unit is constructed by considering the nonlinear correlation between wind farm data and forecasting errors. Meanwhile, the temporal variation characteristics of wind speed are explored to construct a deep learning unit. On this basis, the error correction unit switching strategy based on the wind speed matrix gradient is proposed. Finally, the model is applied to power forecasting in an actual wind farm and compared with other models. The results show that the proposed method outperforms others in terms of forecasting accuracy and maintains high forecasting accuracy in wind farms with highly variable wind speeds, verifying its accuracy and applicability. |
| Key words: ultra-short-term wind power prediction improved Kepler optimization algorithm error correction wind speed matrix gradient |
