引用本文: | 胡宇晗,朱利鹏,李佳勇,等.融合深度误差反馈学习和注意力机制的短期风电功率预测[J].电力系统保护与控制,2024,52(4):100-108.[点击复制] |
HU Yuhan,ZHU Lipeng,LI Jiayong,et al.Short-term wind power forecasting with the integration of a deep error feedbacklearning and attention mechanism[J].Power System Protection and Control,2024,52(4):100-108[点击复制] |
|
摘要: |
为提高风电功率预测精度,提出了一种有机融合深度反馈学习与注意力机制的短期风电功率预测方法。首先,以风电场数值天气预报(numerical weather prediction, NWP)为原始输入,基于双层长短期记忆网络(long short-term memory, LSTM)模型对风电功率进行初步预测。其次,利用极端梯度提升(eXtreme gradient boosting, XGBoost)算法构建误差估计模型,以便在给定未来一段时间内NWP数据的情况下对初步预测误差进行快速估计。然后,利用自适应白噪声完备集成经验模态分解法(complete ensemble empirical mode decomposition with adaptive noise, CEEMDAN)将初步预测误差分解为不同频段的误差序列,并将其作为附加性反馈输入,对风电功率进行二次预测。进一步在二次预测模型中引入注意力机制,为风电功率预测序列与误差序列动态分配权重,由此引导预测模型在学习过程中充分挖掘学习与误差相关的关键特征。最后,仿真结果表明所提方法可显著提高短期风电功率预测的可靠性。 |
关键词: 风电功率预测 深度学习 反馈学习 长短时记忆单元 注意力机制 |
DOI:10.19783/j.cnki.pspc.230914 |
投稿时间:2023-07-17修订日期:2023-12-25 |
基金项目:国家自然科学基金项目资助(52207094,52377095)
博士后创新型人才计划项目资助(BX20220100) |
|
Short-term wind power forecasting with the integration of a deep error feedbacklearning and attention mechanism |
HU Yuhan,ZHU Lipeng,LI Jiayong,LI Yang,ZENG Yang,ZHENG Limengqian,SHUAI Zhikang |
(College of Electrical and Information Engineering, Hunan University, Changsha 410082, China) |
Abstract: |
To enhance the accuracy of wind power forecasting, a short-term wind power forecasting method is proposed, one that synergistically integrates deep feedback learning with attention mechanisms. First, the historical data of numerical weather prediction (NWP) from the wind farm is taken as the original input. A dual-layer long short-term memory (LSTM)-based learning model is used for the preliminary prediction of wind power. Next, an error estimation model is established based on an extreme gradient boosting (XGBoost) algorithm. This enables fast estimation of the initial prediction errors given the future NWP data. Then, complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) is used to decompose the initial prediction errors into error sequences of different frequency bands. These serve as an additional feedback input for the secondary prediction of wind power. Also, an attention mechanism is introduced into the secondary prediction model to dynamically allocate weights to the wind power forecasting and error sequences and thereby instructing the prediction model to fully mine and learn the key features related to the prediction errors during the learning process. Finally, the simulation results indicate that the proposed method can remarkably enhance the reliability of short-term wind power forecasting. |
Key words: wind power forecasting deep learning feedback learning LSTM attention mechanism |