Jiaojiao Qiao, Dongming Song, Rui Jiang, Wujun Hao, Chunhao Liu
{"title":"基于SSA-VMD-LSTM的家庭能耗预测方法研究","authors":"Jiaojiao Qiao, Dongming Song, Rui Jiang, Wujun Hao, Chunhao Liu","doi":"10.1109/EEI59236.2023.10212906","DOIUrl":null,"url":null,"abstract":"Considering the non-linear, periodic, and non-smooth characteristics of household energy consumption data, a short-term household energy consumption prediction method based on the integration of Variational Mode Decomposition (VMD) and Long Short-Term Memory (LSTM) with Sparrow Search Algorithm (SSA) is proposed in order to improve the accuracy and stability of energy consumption prediction. First, the VMD parameters are optimized with the SSA algorithm, and then the complex original complex sequence is decomposed with VMD to derive intrinsic modal functions (IMFS) of various frequency bands with relatively simple fluctuations. Second, LSTM prediction models are constructed separately for each mode, and the prediction results of each component are aggregated and reconstructed to acquire the predicted energy consumption for the entire system. This study contributes to the extraction of electricity consumption patterns and provides technical support for the rational planning of power supply.","PeriodicalId":363603,"journal":{"name":"2023 5th International Conference on Electronic Engineering and Informatics (EEI)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2023-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Research on Home Energy Consumption Prediction Method Based on SSA-VMD-LSTM\",\"authors\":\"Jiaojiao Qiao, Dongming Song, Rui Jiang, Wujun Hao, Chunhao Liu\",\"doi\":\"10.1109/EEI59236.2023.10212906\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Considering the non-linear, periodic, and non-smooth characteristics of household energy consumption data, a short-term household energy consumption prediction method based on the integration of Variational Mode Decomposition (VMD) and Long Short-Term Memory (LSTM) with Sparrow Search Algorithm (SSA) is proposed in order to improve the accuracy and stability of energy consumption prediction. First, the VMD parameters are optimized with the SSA algorithm, and then the complex original complex sequence is decomposed with VMD to derive intrinsic modal functions (IMFS) of various frequency bands with relatively simple fluctuations. Second, LSTM prediction models are constructed separately for each mode, and the prediction results of each component are aggregated and reconstructed to acquire the predicted energy consumption for the entire system. This study contributes to the extraction of electricity consumption patterns and provides technical support for the rational planning of power supply.\",\"PeriodicalId\":363603,\"journal\":{\"name\":\"2023 5th International Conference on Electronic Engineering and Informatics (EEI)\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-06-30\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2023 5th International Conference on Electronic Engineering and Informatics (EEI)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/EEI59236.2023.10212906\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 5th International Conference on Electronic Engineering and Informatics (EEI)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/EEI59236.2023.10212906","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Research on Home Energy Consumption Prediction Method Based on SSA-VMD-LSTM
Considering the non-linear, periodic, and non-smooth characteristics of household energy consumption data, a short-term household energy consumption prediction method based on the integration of Variational Mode Decomposition (VMD) and Long Short-Term Memory (LSTM) with Sparrow Search Algorithm (SSA) is proposed in order to improve the accuracy and stability of energy consumption prediction. First, the VMD parameters are optimized with the SSA algorithm, and then the complex original complex sequence is decomposed with VMD to derive intrinsic modal functions (IMFS) of various frequency bands with relatively simple fluctuations. Second, LSTM prediction models are constructed separately for each mode, and the prediction results of each component are aggregated and reconstructed to acquire the predicted energy consumption for the entire system. This study contributes to the extraction of electricity consumption patterns and provides technical support for the rational planning of power supply.