| 引用本文: | 文 斌,章学勤,付文龙,等.基于二次模态分解重构及BiTCN-BiGRU模型的光伏短期发电功率预测[J].电力系统保护与控制,2025,53(18):74-87.[点击复制] |
| WEN Bin,ZHANG Xueqin,FU Wenlong,et al.Short-term PV power generation forecasting based on quadratic mode decomposition reconstruction and BiTCN-BiGRU model[J].Power System Protection and Control,2025,53(18):74-87[点击复制] |
|
| 摘要: |
| 针对光伏功率序列具有非平稳性和波动性的特点导致预测模型预测精度偏低的问题，提出一种基于二次模态分解重构、双向时序卷积网络(bidirectional temporal convolutional network, BiTCN)-双向门控循环单元(bidirectional gated recirculation unit, BiGRU)组合模型及与多策略改进沙猫群优化算法(multi-strategy improved sand cat swarm algorithm, MSCSO)相结合的光伏短期发电功率预测方法。首先，利用Spearman相关系数选取气象特征作为模型输入，并采用模糊C均值聚类方法进行相似日分类。其次，采用改进完全集合经验模态分解、变分模态分解对光伏功率序列进行分解并采用样本熵对分量进行重构。最后，建立BiTCN-BiGRU组合预测模型进行预测并通过MSCSO优化模型参数，将各分量预测结果叠加得到最终光伏功率预测值。通过与多种预测模型在不同天气条件和不同地区的对比分析，验证了所提模型具有更高的预测精度和良好的适应性。 |
| 关键词: 二次模态分解重构 沙猫群算法 双向时序卷积网络 双向门控循环单元 光伏功率预测 |
| DOI：10.19783/j.cnki.pspc.241500 |
| 投稿时间：2024-03-31修订日期：2025-02-20 |
| 基金项目:国家自然科学基金项目资助(62273200)；湖北省输电线路工程技术研究中心研究基金项目资助(2022KXL03)；湖北省自然科学基金联合基金项目资助(2024AFD409) |
|
| Short-term PV power generation forecasting based on quadratic mode decomposition reconstruction and BiTCN-BiGRU model |
| WEN Bin1,2,ZHANG Xueqin1,FU Wenlong1,2,DING Yifu3,FENG Xuanyu1 |
| (1. College of Electrical Engineering and New Energy, China Three Gorges University, Yichang 443002, China;
2. Hubei Provincial Key Laboratory for Operation and Control of Cascaded Hydropower Station
(China Three Gorges University), Yichang 443002, China; 3. Nanchuan Power Supply Branch,
State Grid Chongqing Electric Power Company, Chongqing 408400, China) |
| Abstract: |
| To address the issue of low prediction accuracy caused by the unstable and fluctuating characteristics of photovoltaic (PV) power generation, a short-term PV power forecasting method is proposed. The method integrates quadratic mode decomposition reconstruction (QMDR), a bidirectional temporal convolutional network (BiTCN) and bidirectional gated recirculation unit (BiGRU) combined model, and a multi-strategy improved sand cat swarm optimization algorithm (MSCSO). First, meteorological features are selected as model inputs using the Spearman correlation coefficient, and fuzzy C-mean clustering method is applied for similar-day classification. Next, the PV power series are decomposed by improved complete ensemble empirical modal decomposition and variational modal decomposition, and the components are reconstructed by sample entropy. Finally, a combined prediction model of BiTCN-BiGRU is established, with the parameters of the model optimized by MSCSO. The final PV power prediction is obtained by superimposing the forecasts of each constructed component. Comparative analyses under different weather conditions and across different regions verify that the proposed model has higher prediction accuracy and better adaptability than existing approaches. |
| Key words: quadratic modal decomposition reconstruction sand cat swarm optimization bidirectional temporal convolutional networks bidirectional gated recirculation unit PV power prediction |
