基于长短期记忆神经网络的电力用电量预测  

Power Consumption Prediction Based on Long Short-term Memory Neural Networks

作　　者：陈伟伟 荆世博 边家瑜 易庚 安琪 CHEN Weiwei;JING Shibo;BIAN Jiayu;YI Geng;AN Qi(Economic Research Institute,State Grid Xinjiang Electric Power Company,Urumqi 830002,China)

机构地区：[1]国网新疆电力公司经研院,新疆乌鲁木齐830002

出　　处：《机械与电子》2024年第5期18-23,共6页Machinery & Electronics

摘　　要：为解决现有用电量预测精确度较低等问题,提出了基于长短期记忆神经网络的电力用电量预测方法。分析了电力负荷分类以及典型负荷曲线,说明了支持向量回归以及长短期记忆神经网络的基本原理,提出了基于支持向量回归和长短期记忆神经网络结合的预测方法,说明了预测流程,给出了预测结果统计评价标准。根据所提出的方法进行了案例分析,论证了所提方法的有效性。To solve the problem of low accuracy in predicting available electricity consumption,a power consumption prediction method based on long short-term memory neural networks is proposed.The classification of power loads and typical load curves were analyzed,and the basic principles of support vector regression and long short-term memory neural networks were explained.A prediction method based on the combination of support vector regression and long short-term memory neural networks was proposed,and the prediction process was explained,and statistical evaluation criteria for the prediction results were provided.A case study was analyzed based on the proposed method to demonstrate its effectiveness.

关 键 词：负荷特征 用电量预测 长短期记忆神经网络 支持向量回归 

分 类 号：TM715[电气工程—电力系统及自动化]