摘要
针对变电站短期负荷预测中非线性适应差、区间估计不准的问题,提出一种自适应扩散核密度估计与长短期记忆网络(ADKDE-LSTM)融合的区间预测方法。融合历史负荷与气象数据,通过ADKDE方法分析误差分布,结合LSTM建模时序特征,构建95%置信水平的预测区间。基于某220 kV变电站数据的实验表明,模型在4个数据集的平均预测区间覆盖率(PICP)达0.914,预测区间宽度(PIAW)较对比模型降低20%~30%。所提方法能精准量化负荷不确定性,为电网规划提供可靠区间预测支撑。
To address the challenges of poor nonlinear adaptability and inaccurate interval estimation in substation short-term load prediction,an interval prediction method integrating adaptive diffusion kernel density estimation(ADKDE)with long short-term memory networks(LSTM)is proposed.Historical load and meteorological data are fused,where ADKDE method analyzes error distributions and LSTM network temporal features to construct prediction intervals at a 95%confidence level.Experimental results based on a 220 kV substation dataset demonstrate that the proposed model achieves an average prediction interval coverage probability(PICP)of 0.914 across four datasets,while reducing the prediction interval average width(PIAW)by 20%-30%compared to the comparison models.The proposed method effectively quantifies load uncertainty,providing reliable interval predictions to support power grid planning.
作者
包育德
邱润韬
许博智
BAO Yude;QIU Runtao;XU Bozhi(Guangzhou Power Supply Bureau of Guangdong Power Grid,Guangzhou 510663,China)
出处
《电器与能效管理技术》
2025年第11期42-50,共9页
Electrical & Energy Management Technology
基金
国家自然科学基金资助项目(52307080)。
