摘要
常规区域长期用电需求量动态预测方法多采用大数据分析技术,无法定量计算用电量与负荷特性指标之间的关联性,使得预测结果准确度较低,因此提出计及历史数据库与负荷特性的区域长期用电需求量动态预测算法。通过研究负荷特性指标,结合研究区域实际情况及历史数据分析负荷特性;利用互信息原理辨识用电量与负荷特性指标间的关联性,并选取强关联因素进行预测建模;将预测矩阵作为组合预测模型的输入,实现区域长期用电需求量动态预测。对所提方法的预测性能进行验证,结果证明,所提方法可以准确地预测出用电需求量,表明将该方法应用于区域长期用电需求量预测中是可行的。
The conventional regional long-term power demand dynamic forecasting methods mostly uses big data analysis tech-nology,which cannot quantitatively calculate the correlation between power demand and load characteristic indicators,resulting in low accuracy of forecasting results.Therefore,a dynamic forecasting method of regional long-term power demand which considers historical database and load characteristics is proposed.This paper studies load characteristic indicators,analyzes load characteristics,and combines with the actual situation and historical data of the study regional.The mutual information princi-ple is used to identify the correlation between power demand and load characteristics,and select strong correlation factors for forecasting modeling.The forecasting matrix is used as the input of the combined forecasting model to realize the dynamic fore-casting of regional long-term power demand.The forecasting performance of the proposed method is verified,and the results show that the proposed method can accurately predict the power demand.The comparison method is used to verify the effec-tiveness of the design method.The comparing results show that the forecasting accuracy of the proposed method is high,and the method can be applied to the power demand prediction neighborhood,which indicates that it is feasible to apply the method to regional long-term power demand prediction.
作者
明捷
吴昊
张哲原
MING Jie;WU Hao;ZHANG Zheyuan(Power China Hubei Electric Engineering Co.,Ltd.,Wuhan 430040,China)
出处
《微型电脑应用》
2025年第5期213-217,共5页
Microcomputer Applications
关键词
负荷特性
动态预测
年度用电数据
区域长期用电量
load characteristic
dynamic forecasting
annual power demand data
regional long-term power demand
