检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:钱嫣然 何慧之 仇海英 邓渝亭 吴悦晨 QIAN Yan-ran;HE Hui-zhi;QIU Hai-ying;DENG Yu-ting;WU Yue-chen(State Grid Shanghai SHINAN Electric Power Company,Shanghai 201100,China)
出 处:《信息技术》2023年第1期180-185,共6页Information Technology
摘 要:传统区域用电量预测方法存在预测能力差的问题,为此,提出基于ARIMA模型的区域用电量预测方法。获取区域的历年用电量数据进行预处理,获取统一的用电量数据;再利用ARIMA模型对用电量时间序列进行平稳性检测,利用最小二乘估计方法估值用电量参数;最后结合线性神经网络构建区域用电量预测模型,将统一的用电量数据放入模型中进行计算,以此完成区域用电量的预测。实验结果表明,所提方法可以有效检测出电量负荷及电量同比增速,预测能力强、预测精度高。The traditional regional electricity consumption prediction method has the problem of poor prediction ability, therefore, a regional electricity consumption prediction method based on ARIMA model is proposed. The regional electricity consumption data over the years is obtained, and preprocessed to obtain the unified power consumption data. Then the stability of electricity consumption time series is detected by ARIMA model, and the electricity consumption parameters are estimated by least square estimation method. Finally, combined with the linear neural network, the regional electricity consumption prediction model is constructed, and the unified electricity consumption data is put into the model for calculation, so as to complete the prediction of regional electricity consumption. The experiment results show that this method can effectively detect the power load and the year-on-year growth rate of power, with excellent prediction ability and high prediction accuracy.
关 键 词:ARIMA模型 区域用电量 预测 数据预处理 线性神经网络
分 类 号:TM714[电气工程—电力系统及自动化]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.198