Time series analysis model for forecasting unsteady electric load in buildings

作     者：Dandan Liu Hanlin Wang 

作者机构：Shanghai University of Electric PowerShanghai 201306China 

出 版 物：《Energy and Built Environment》 (能源与人工环境（英文）)

年 卷 期：2024年第5卷第6期

页      面：900-910页

核心收录：

学科分类：0711[理学-系统科学] 07[理学] 08[工学] 081101[工学-控制理论与控制工程] 0811[工学-控制科学与工程] 071102[理学-系统分析与集成] 081103[工学-系统工程] 

主　　题：Load forecasting EWT Neural networks Informer Autoformer 

摘      要：Accurate and reliable load forecasting is crucial for ensuring the security and stability of the power *** paper proposes a combined prediction method based on Empirical Wavelet Transform(EWT)and Autoformer time series prediction model for the non-stationary and non-linear time series of electric *** original sequence is first decomposed by EWT to obtain a set of stable subsequences,and then the Autoformer time series prediction model is used to predict each ***,the prediction results of each subsequence are combined to obtain the final prediction *** proposed EWT-Autoformer prediction model is applied to an electric load example,and the experimental results are compared with the Recurrent Neural Network(RNN)method,Long Short-Term Memory(LSTM)method,and Informer method under the same *** experimental results indicate that compared to LSTM,the method proposed in the paper has an R2 improvement of 9–20 percentage points,an improvement of 6–8 percentage points compared to RNN,an improvement of 3–7 percentage points compared to Informer,and an improvement of 2–3 percentage points compared to *** addition,the RMSE and MAE are also significantly lower than other models.