基于iTransformer-BiGRU优化的超短期光伏功率预测
Ultra-short-term photovoltaic power prediction based on iTransformer-BiGRU optimization
准确预测光伏发电功率预测对于可再生能源的利用至关重要。现有很多模型难以有效捕捉目标变量和协变量之间的复杂关系，且对时间动态和多变量数据之间的相互作用捕捉不精准。因此，提出一种新的模型架构，利用iTransformer和双向门控循环单元从中提取特征，对于模型的融合输出，通过整合多头注意力机制和柯尔莫哥洛夫-阿诺德网络映射来增强表征能力。利用公开数据集对模型的有效性进行验证，结果表明该模型能有效捕捉光伏发电的变化，其中春季指标的提升效果最优，相较iTransformer模型预测结果的平均绝对误差下降了36.8%，均方根误差下降了29.8%。
发电、发电厂电工基础理论自动化技术、自动化技术设备计算技术、计算机技术电气测量技术、电气测量仪器
光伏功率预测iTransformer多头注意力深度学习时间序列建模双向门控循环单元
董慧,刘清惓,谷祥宇,徐杰.基于iTransformer-BiGRU优化的超短期光伏功率预测[EB/OL].(2025-10-31)[2025-11-02].http://www.paper.edu.cn/releasepaper/content/202510-37.点此复制
Accurate prediction of photovoltaic (PV) power forecasting is critical for renewable energy utilization. Many existing models are difficult to effectively capture the complex relationships between target variables and covariates, and are imprecise in capturing temporal dynamics and interactions between multivariate data. Therefore, a new model architecture is proposed that utilizes iTransformer and bi-directional gated recurrent units to extract features from them, and for the fused output of the model, the characterization is enhanced by integrating the multi-head attention mechanism and Kolmogorov-Arnold network mapping. The model\'s effectiveness was validated using publicly available datasets. The results demonstrate that the proposed model effectively captures variations in photovoltaic (PV) power generation, with the most significant performance improvement observed in spring. Compared to the iTransformer model\'s predictions, the mean absolute error (MAE) was reduced by 36.8% and the root mean square error (RMSE) by 29.8%.
photovoltaic power predictioniTransformer multi-head attentiondeep learningtime series modelingBiGRU
展开英文信息
评论