{"title":"基于优化器集成的深度神经网络智能电网能源需求预测","authors":"P. Seethalakshmi, K. Venkatalakshmi","doi":"10.1109/ICCMC48092.2020.ICCMC-000109","DOIUrl":null,"url":null,"abstract":"The smart grid is a combination of smart network devices and systems that support the efficient generation, distribution and transmission of energy from source to destination. Energy is becoming one of the most important resources of daily life. In general, technology advancements are rapidly increasing and energy demand is also increasing due to the discovery of new electrical/electronic devices. Most of the conditions, there is a mismatch between energy generation and energy consumption. The big challenge is to maintain a balance between generating energy and using it. The service providers need to forecast the energy demand well in advance with minimal error to maintain the equilibrium state, even a small error in the predictive mechanism leads to a loss for both service providers and consumers. To address these problems we proposed an energy prediction model based on Long Short Term Memory (LSTM). It has emerged as a promising Artificial Neural Network (ANN) technique for predicting time series issues due to the properties of selective retrieval patterns for a long time. Further, the LSTM model is optimized by using Optimizer Ensembles to improve the efficiency of the proposed model. The simulation results show that the proposed LSTM achieves better predictive results (less error, high efficiency) compared to existing methods such as Moving Average (MA), Linear Regression (LR) and k-Nearest Neighbors (k-NN) techniques.","PeriodicalId":130581,"journal":{"name":"2020 Fourth International Conference on Computing Methodologies and Communication (ICCMC)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"Prediction of Energy Demand in Smart Grid Using Deep Neural Networks with Optimizer Ensembles\",\"authors\":\"P. Seethalakshmi, K. Venkatalakshmi\",\"doi\":\"10.1109/ICCMC48092.2020.ICCMC-000109\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The smart grid is a combination of smart network devices and systems that support the efficient generation, distribution and transmission of energy from source to destination. Energy is becoming one of the most important resources of daily life. In general, technology advancements are rapidly increasing and energy demand is also increasing due to the discovery of new electrical/electronic devices. Most of the conditions, there is a mismatch between energy generation and energy consumption. The big challenge is to maintain a balance between generating energy and using it. The service providers need to forecast the energy demand well in advance with minimal error to maintain the equilibrium state, even a small error in the predictive mechanism leads to a loss for both service providers and consumers. To address these problems we proposed an energy prediction model based on Long Short Term Memory (LSTM). It has emerged as a promising Artificial Neural Network (ANN) technique for predicting time series issues due to the properties of selective retrieval patterns for a long time. Further, the LSTM model is optimized by using Optimizer Ensembles to improve the efficiency of the proposed model. The simulation results show that the proposed LSTM achieves better predictive results (less error, high efficiency) compared to existing methods such as Moving Average (MA), Linear Regression (LR) and k-Nearest Neighbors (k-NN) techniques.\",\"PeriodicalId\":130581,\"journal\":{\"name\":\"2020 Fourth International Conference on Computing Methodologies and Communication (ICCMC)\",\"volume\":\"8 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-03-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2020 Fourth International Conference on Computing Methodologies and Communication (ICCMC)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICCMC48092.2020.ICCMC-000109\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 Fourth International Conference on Computing Methodologies and Communication (ICCMC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICCMC48092.2020.ICCMC-000109","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Prediction of Energy Demand in Smart Grid Using Deep Neural Networks with Optimizer Ensembles
The smart grid is a combination of smart network devices and systems that support the efficient generation, distribution and transmission of energy from source to destination. Energy is becoming one of the most important resources of daily life. In general, technology advancements are rapidly increasing and energy demand is also increasing due to the discovery of new electrical/electronic devices. Most of the conditions, there is a mismatch between energy generation and energy consumption. The big challenge is to maintain a balance between generating energy and using it. The service providers need to forecast the energy demand well in advance with minimal error to maintain the equilibrium state, even a small error in the predictive mechanism leads to a loss for both service providers and consumers. To address these problems we proposed an energy prediction model based on Long Short Term Memory (LSTM). It has emerged as a promising Artificial Neural Network (ANN) technique for predicting time series issues due to the properties of selective retrieval patterns for a long time. Further, the LSTM model is optimized by using Optimizer Ensembles to improve the efficiency of the proposed model. The simulation results show that the proposed LSTM achieves better predictive results (less error, high efficiency) compared to existing methods such as Moving Average (MA), Linear Regression (LR) and k-Nearest Neighbors (k-NN) techniques.