{"title":"基于Python平台LSTM深度学习模型的GUI能源需求预测","authors":"B. Rohith, T. Santhosh, R. B. Alfred, R. R. Singh","doi":"10.1109/i-PACT52855.2021.9696760","DOIUrl":null,"url":null,"abstract":"This article proposes a technique for power distribution in the smart grid. This concept is based on a deep learning technique that employs the long short-term memory (LSTM), which is a recurrent neural network (RNN) architecture with respect to various parameters. The smart meter acquires data of different parameters including active power, reactive power, global intensity, and voltage from three independent households. The collected data is synced with a cloud and used with a sequential neural network model to forecast electricity consumption. In addition, the entire system was integrated by building a graphical user interface that allows customers to examine power at any specific date and time. This could be used to seek more power from the subsystem.","PeriodicalId":335956,"journal":{"name":"2021 Innovations in Power and Advanced Computing Technologies (i-PACT)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"GUI Energy Demand Forecast using LSTM Deep Learning Model in Python Platform\",\"authors\":\"B. Rohith, T. Santhosh, R. B. Alfred, R. R. Singh\",\"doi\":\"10.1109/i-PACT52855.2021.9696760\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This article proposes a technique for power distribution in the smart grid. This concept is based on a deep learning technique that employs the long short-term memory (LSTM), which is a recurrent neural network (RNN) architecture with respect to various parameters. The smart meter acquires data of different parameters including active power, reactive power, global intensity, and voltage from three independent households. The collected data is synced with a cloud and used with a sequential neural network model to forecast electricity consumption. In addition, the entire system was integrated by building a graphical user interface that allows customers to examine power at any specific date and time. This could be used to seek more power from the subsystem.\",\"PeriodicalId\":335956,\"journal\":{\"name\":\"2021 Innovations in Power and Advanced Computing Technologies (i-PACT)\",\"volume\":\"9 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-11-27\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2021 Innovations in Power and Advanced Computing Technologies (i-PACT)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/i-PACT52855.2021.9696760\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 Innovations in Power and Advanced Computing Technologies (i-PACT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/i-PACT52855.2021.9696760","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
GUI Energy Demand Forecast using LSTM Deep Learning Model in Python Platform
This article proposes a technique for power distribution in the smart grid. This concept is based on a deep learning technique that employs the long short-term memory (LSTM), which is a recurrent neural network (RNN) architecture with respect to various parameters. The smart meter acquires data of different parameters including active power, reactive power, global intensity, and voltage from three independent households. The collected data is synced with a cloud and used with a sequential neural network model to forecast electricity consumption. In addition, the entire system was integrated by building a graphical user interface that allows customers to examine power at any specific date and time. This could be used to seek more power from the subsystem.