首页|基于注意力机制的IWOA-BiGRU超短期风电功率预测

基于注意力机制的IWOA-BiGRU超短期风电功率预测

扫码查看
超短期风电功率预测对电力系统调度及大规模风电并网具有重要作用.为得到准确可靠的风电功率预测结果,针对风电功率数据非线性和时序性的特点,提出一种基于IWOA-AT-BiGRU的超短期风电功率预测方法.首先,提出改进鲸鱼优化算法(improved whale optimization algorithm,IWOA)来优化风电功率预测模型的超参数,加速模型收敛,提高预测准确度;然后,在BiGRU中加入注意力机制(AT),AT用来加强重要信息对风功率的影响,BiGRU同时考虑数据的正反向信息,充分挖掘数据的时序特征;最后,通过某风电场实测数据进行实验,结果表明提出的方法预测准确度均高于其他对比模型,具有良好的预测性能.
Ultra-short-term Wind Power Forecasting Model of IWOA-BiGRU Based on Attention Mechanism
Ultra-short-term wind power forecasting plays an important role in power system dispatch and large-scale wind power grid connection.In order to obtain accurate and reliable wind power prediction results,we proposed an ul-tra-short-term wind power forecasting method based on IWOA-AT-BiGRU according to the nonlinearity and timing char-acteristics of wind power data.Firstly,we proposed an improved whale optimization algorithm(IWOA)to optimize the hyperparameters of the wind power forecasting model,accelerate the convergence of the model,and improve the accura-cy.Then,we added an attention mechanism to the BiGRU,which is used to enhance the influence of important infor-mation on wind power.And BiGRU considers the forward and negative information of the data at the same time to fully explore the timing characteristics of the data.Finally,the experiment is carried out through the measured data of a wind farm,the results show that the forecasting accuracy of the proposed method is higher than that of other comparable mod-els and has good forecasting performance.

wind powerultra-short-term forecastingattention mechanismimproved whale optimization algorithmbidirectional gated recurrent unit

向玲、金子皓、李林春

展开 >

华北电力大学能源动力与机械工程学院,河北保定 071003

风电功率 超短期预测 注意力机制 改进鲸鱼优化算法 双向门控循环单元

国家自然科学基金资助项目国家自然科学基金资助项目

5207517052175092

2024

华北电力大学学报(自然科学版)
华北电力大学

华北电力大学学报(自然科学版)

CSTPCD北大核心
影响因子:0.868
ISSN:1007-2691
年,卷(期):2024.51(4)