基于VMD-CNN-LSTM的农业大棚园区用电负荷短期预测OA北大核心CSTPCD
The Short-term Forecasting of Power Load in Agricultural Greenhouses Based on VMD-CNN-LSTM
针对农业大棚用电负荷受农村供电能力、气象因素等的影响,具有强波动性和高非线性的问题,综合大棚短期负荷的气象特征和时序特征,提出 了 一种基于变分 模态分解(variational mode decomposition,VMD)的长短期记忆(long short-term memor-y,LSTM)网络与卷积神经网络(convolutional neural network,CNN)相融合的VMD-CNN-LSTM的短期负荷预测模型架构.首先,基于VMD方法分解负荷序列,降低负荷波动性;其次,采用CNN方法提取负荷的气象特征,采用LSTM方法提取负荷时序特征,进行负荷分量预测,并将模态分量的预测结果重构;最后,以山东省寿光市农业大棚负荷数据为基础开展仿真实验.结果表明,VMD-CNN-LSTM模型与传统神经网络模型相比,可有效提高农业大棚短期负荷预测的精度.
Based on the meteorological and temporal characteristics of short-term load in greenhouses,an integrated short-term load prediction architecture based on the fusion of variational mode decompo-sition(VMD),convolutional neural network(CNN),and long short-term memory(LSTM)is proposed to solve the problem that the electricity load of agricultural greenhouses is affected by ru-ral power supply capacity and meteorological factors,which have strong fluctuation and high non-linear characteristics.First,the load sequence is decomposed using the VMD method to reduce load volatility.Second,the meteorological characteristics of the load are extracted using the CNN method,and the temporal characteristics of the load are extracted using the LSTM method.Compo-nent prediction is performed,and the prediction results of the model components are reconstructed.Finally,based on the load data of agricultural greenhouses in Shouguang,Shandong Province,the experimental results show that compared with the traditional neural network model,the proposed VMD-CNN-LSTM model can effectively improve the precision of short-term load prediction of agri-cultural greenhouses.
张培霄;尹晓红;李少远;王新立
青岛科技大学自动化与电子工程学院,山东青岛 266061山东大学控制科学与工程学院,山东济南 250061
动力与电气工程
农业大棚园区负荷变分模态分解短期负荷预测卷积神经网络长短期记忆网络
agricultural greenhouse park loadvariational mode decomposi-tionshort-term load forecastingconvolutional neural networklong short-term memory net-work
《信息与控制》 2024 (002)
238-249 / 12
国家自然科学基金项目(61703223);山东省重点研发计划重大科技创新工程项目(2020CXGC011402)
评论