摘要
传统的负荷特性分析方法,由于基础数据及处理方法的限制一般无法达到用户级的精细化预测。研究基于大数据技术中的决策树、神经网络等算法建立用户级的短期负荷预测模型,首先基于灰色关联度分析方法,定量分析气象因素对用电负荷特性的影响,并选取关键影响因素,作为决策树算法的输入向量;在对用户的历史负荷数据进行聚类分析后,为每一条日负荷曲线建立类别标签;通过决策树算法建立分类规则,并将待预测日进行分类;最终采用Elman神经网络对某用户进行短期负荷预测,验证模型的有效性。
Because of the limitation of basic data and processing methods,the traditional load characteristic analysis method can not achieve user-level refined prediction.This research builds a user-level short-term load forecasting model based on algorithms such as decision trees and neural networks in big data technology.Firstly,based on the grey relational analysis method,the influence of meteorological factors on load characteristics is quantitatively analyzed.The key factors are selected as input vectors of decision tree algorithm.After clustering the historical load data of users,the classification label is established for each daily load curve.The decision tree algorithm is used to establish classification rules and classify the days to be predicted.Finally,Elman neural network is used to predict the short-term load of a user,and the validity of the model is verified.
作者
陈寒冬
郭佳田
施海斌
范华东
施春波
姚超群
CHEN Han-dong;GUO Jia-tian;SHI Hai-bin;FAN Hua-dong;SHI Chun-bo;YAO Chao-qun(State Grid Shanghai Chongming Electric Power Supply Company,Shanghai 202150,China;Shanghai Poower Industrial&Commercial Co.,Ltd,Shanghai 200001,China)
出处
《电力学报》
2019年第5期423-430,共8页
Journal of Electric Power
基金
国网上海市电力公司(5209HZ170004)