摘要
基于深度学习下的长短期记忆循环神经网络对家庭短期用电预测进行研究。本研究引入卷积神经网络(convolutional neural network, CNN)和长短期记忆(long short term memory, LSTM)模型结合的混合深度神经网络模型C-LSTM,并在此模型基础上提出多步预测策略。根据对5个真实家庭日常用电数据集的研究,C-LSTM实现了以5 min为单位的家庭电力需求预测。通过不断修改模型参数、完善模型,从本研究提供的3种误差指标的分析来看,C-LSTM预测准确性高于自回归集成移动平均模型、支持向量回归模型和LSTM模型。本研究评价模型预测效果的主要依据是平均绝对百分比误差值(mean absolute percentage error, MAPE),从试验结果可得C-LSTM模型在5 min的家庭需求电力预测,比支持向量回归模型提升4.63%,比LSTM提升22.8%,比自回归集成移动平均模型提升34.74%。因此,C-LSTM模型为智能电网对家庭层面电需求的准确及时预测提供了保障,对推动个性化用电套餐的广泛普及、减少能源浪费产生重要影响。
Research on short-term household electricity consumption prediction based on long-term short-term memory recurrent neural network under deep learning. This research introduced a hybrid deep neural network model C-LSTM that combines convolutional neural network(CNN) and long short term memory(LSTM) models, and proposed a multi-step prediction strategy based on this model. According to the research on the daily electricity consumption data set of 5 real households, C-LSTM realized household electricity demand forecasting in 5 min. Through continuous modification of model parameters and improvement of the model, from the analysis of the three error indicators provided in this study, the prediction accuracy of C-LSTM was higher than the autoregressive integrated moving average model, support vector regression model and LSTM model. The main basis for the evaluation of the model prediction effect in this study was the average absolute percentage error value. From the test results, it could be obtained that the C-LSTM model′s household electricity demand forecast in 5 minutes was 4.63% higher than the support vector regression model, 22.8% higher than the LSTM, and 34.74% higher than the autoregressive integrated moving average model. Therefore, the C-LSTM model provided a guarantee for the smart grid′s accurate and timely prediction of household-level electricity demand, and had an important impact on promoting the widespread popularity of personalized electricity packages and reducing energy waste.
作者
廖锦萍
莫毓昌
YAN Ke
LIAO Jinping;MO Yuchang;YAN Ke(College of Mathematical Sciences,Huaqiao University,Quanzhou 362000,Fujian,China;College of Information Engineering,China Jiliang University,Hangzhou 310000,Zhejiang,China)
出处
《山东大学学报（工学版）》
CAS
CSCD
北大核心
2021年第2期90-97,共8页
Journal of Shandong University（Engineering Science）
基金
国家自然科学基金项目(61972165)
数据科学福建省高校科技创新团队项目(MJK-2018-49)
大数据分析与安全泉州市高层次人才团队项目(2017ZT012)。
关键词
短期家庭用电预测
多步预测
卷积神经网络
长短期记忆模型
混合深度学习神经网络
short-term household electricity forecast
multi-step forecasting
convolutional neural network
long short term memory model
hybrid deep learning neural network
