摘要
针对短期电力负荷预测模型其预测结果精度不佳的问题,本文提出了一种利用变分模态分解技术(VMD)获取短期负荷数据深层特征,后使用麻雀搜索算法(SSA)针对随机森林(RF)负荷预测模型中的超参数进行优化的短期电力负荷预测模型。首先在数据处理部分使用VMD将负荷数据分解获得多个模态分量,对分解后的模态分量进行分析并将受噪声影响严重以致波形浮动过大的模态分量进行合并以减少模型计算量。然后利用麻雀搜索算法对随机森林预测模型进行超参数优化,对经过VMD分解后所得的多个模态分量分别构建优化预测模型进行预测,重构其结果获得最终预测结果。通过算例分析,验证了本文所提模型较同类智能模型在短期负荷预测方面有更加优秀的表现。
In response to the problem of poor accuracy in short-term electricity load forecasting models,this paper proposes a Short-term power load forecasting model that utilizes the variational mode decomposition(VMD)technique to extract deep features from short-term load data,followed by optimizing the hyperparameters of the Random Forest(RF)load forecasting model using the sparrow search algorithm(SSA).Firstly,in the data processing part,VMD is used to decompose the load data to obtain multiple modal components,and the decomposed modal components are analyzed,and the modal components that are seriously affected by noise and cause excessive waveform fluctuation are merged to reduce the calculation cost of the model.Then,the sparrow search algorithm is used to optimize the hyperparameters of the random forest prediction model.The optimal prediction model is constructed for the multiple modal components obtained after VMD decomposition,and their results are reconstructed to obtain the final prediction outcomes.Through the analysis of examples,it is verified that the proposed prediction model has higher prediction accuracy than the commonly used intelligent prediction model.
作者
张羽姗
周亚同
ZHANG Yushan;ZHOU Yatong(School of Electronics and Information Engineering,Hebei University of Technology,Tianjin 300401,China)
出处
《电工电能新技术》
CSCD
北大核心
2024年第12期30-39,共10页
Advanced Technology of Electrical Engineering and Energy
基金
京津冀基础研究合作专项(J210008、21JCZXJC00170、H2021202008)
内蒙古自治区纪检监察大数据实验室开放课题(IMDBD202105)。
