基于VMD-CIGWO-BP-DTA算法的空调负荷预测
Research on air conditioning load forecasting based on VMD-CIGWO-BP-DTA
陆卫东1
作者信息
摘要
提出一种Circle混沌化灰狼算法(CIGWO)优化BP神经网络与变分模态分解(VMD)结合的预测模型(VMD-CIGWO-BP-DTA),对蓄能空调负荷进行预测分析.采用CIGWO算法对BP神经网络模型寻优得到最优神经元阈值和权值,将其与多种单一模型进行实验比较,CIGWO-BP模型预测精度最高.采用变分模态分解(VMD)对单一模型的预测残差进行分解,利用决策树(DTA)模型对分解量预测,将其与原模型预测值合并为最终预测结果,预测精度均有较大提升,其中VMD-CIGWO-BP-DTA模型的MAE、MAPE和RMSE相较于CIGWO-BP模型分别降低了20.79％、45.58％、55.12％.
Abstract
A prediction model(VMD-CIGWO-BP-DTA)based on Circle Chaotic Grey Wolf Optimizer(CIGWO)optimized BP neural network combined with variational mode decomposition(VMD)was proposed to predict and analyze the load of storage air conditioning.The CIGWO algorithm is used to optimize the BP neural network model to obtain the optimal neuron threshold and weight,and the CIGWO-BP model has the highest prediction accuracy.Variational mode decomposition(VMD)was used to decompose the prediction residual of a single model,and decision tree(DTA)model was used to predict the decomposition quantity,which was combined with the predicted value of the original model into the final prediction result,and the prediction accuracy was greatly improved.MAE,MAPE and RMSE of VMD-CIGWO-BP-DTA model decreased by 20.79％,45.58％and 55.12％,respectively,compared with CIGWO-BP model.
关键词
计量学/实验动物房/空调负荷/混沌映射序列/灰狼算法/BP神经网络/变分模态分解Key words
metrology/laboratory animal room/air conditioning load/Chaotic mapping sequence/Grey Wolf Optimizer/BP neural network/variational mode decomposition引用本文复制引用
出版年
2024
NETL
NSTL
万方数据