首页|基于DBO-LSTM-attention模型的风电功率预测模型

基于DBO-LSTM-attention模型的风电功率预测模型

扫码查看
针对传统风电功率预测精度不高的问题,提出一种基于蜣螂优化算法(DBO)优化的长短期记忆网络(LSTM)结合注意力机制的风电功率预测模型.该模型利用LSTM建模风电相关特征序列,选用DBO算法优化LSTM的超参数,并引入注意力机制提高模型对重要时间序列特征的关注度.实验结果表明,所提出的模型相较于传统的风电功率预测模型具有更好的预测性能.
Wind Power Prediction Model Based on DBO-LSTM-Attention Modeling
A wind power prediction model based on the dung beetle optimization algorithm(Dung Beetle Optimization Algorithm)optimized long and short-term memory network(LSTMN)combined with the attention mechanism is proposed to address the problem of low accuracy of traditional wind power prediction.The model makes use of modeling wind power related feature sequences,selects the hyperparameters optimized by the algorithm,and introduces the attention mechanism to improve the model's attention to important time series features.The experimental results show that the proposed model has better prediction performance than the traditional wind power prediction model.

wind power predictionlong and short-term memory networkdung beetle optimization algorithmattention mechanism

应润宇、王玉林

展开 >

辽宁工程技术大学电气与控制工程学院,辽宁 葫芦岛 125105

风电功率预测 长短期记忆网络 蜣螂优化算法 注意力机制

2024

现代工业经济和信息化

现代工业经济和信息化

影响因子:0.485
ISSN:
年,卷(期):2024.14(11)