摘要
针对负荷数据随机性、非平稳性对电力系统安全运行带来的挑战,为提高短期电力负荷预测的精度,提出基于变分模态分解(VMD)和改进的白鲸优化算法(TLBWO)优化组合模型的短期电力负荷预测方法。利用VMD将原始负荷序列分解为不同频率的子模态及残余量;分别构建卷积神经网络(CNN)和双向长短期记忆(BiLSTM)网络组合的电力负荷预测模型,并利用TLBWO算法优化网络参数;将每个分解的结果进行叠加。以中国南方某地区的负荷数据为例进行预测分析,结果表明,上述模型的决定系数达到了0.985,预测精度高于对比模型,验证了所提模型的有效性。
For the challenges brought by randomness and non-stationarity of load data to the safe operation of power system,in order to solve the problem of power load forecasting accuracy,a combined model short-term load forecasting method based on Variational Mode Decomposition(VMD)and TLBWO optimization is proposed.VMD was used to decompose the original time series load data into sub-modes and residuals of different frequencies.The combined power load forecasting model of CNN and BiLSTM is constructed respectively,and the TLBWO algorithm is used to optimize the network parameters.The component results are superimposed.The load data of a region in the south of China is taken as an 2 example to forecast.The results show that the R of the proposed model reaches 0.985,the prediction accuracy is higher than that of the comparison model,which verifies the availability of the model.
作者
陈曦
张玲华
CHEN Xi;ZHANG Linghua(School of Communication and Information Engineering,Nanjing University of Posts and Telecommunications,Nanjing 210003,China;Jiangsu Communication and Network Technology Engineering Research Center,Nanjing 210003,China)
出处
《电子设计工程》
2025年第5期8-12,17,共6页
Electronic Design Engineering
基金
国家自然科学基金资助项目(62371253)。
关键词
负荷预测
变分模态分解
卷积神经网络
长短期记忆网络
白鲸优化
load forecasting
Variational Mode Decomposition
Convolutional Neural Network
Long Short-Term Memory network
Beluga Whale Optimization
