基于气象因子的华中电网负荷预测方法研究
FORECAST TECHNIQUE OF ELECTRIC NETWORK LOADS IN CENTRAL CHINA BASED ON METEOROLOGICAL ELEMENTS
-
摘要: 在分析各种节假日负荷变化规律的基础上, 利用气象因子作预报变量, 使用动态的综合线性回归和自回归相结合的混合线性回归方法及非线性的人工神经网络方法来进行华中电网日负荷和日最大负荷及日最小负荷的预测。对12个月共365天的独立样本试预报表明, 该客观方案对华中电网负荷的预测精度可满足业务调度的需要。Abstract: Based on the variation analysis of electric network loads on various holidays, the models for forecasting the daily load of the electric power network and its maximum and minimum loads per day in the Central China are given.Using meteorological variables as predictor, the dynamical colligating linear regression combined with auto-regression and the dynamical nonlinear artificial neural network methods are used.The prediction with 365 independent samplesshows that the methods have a high precision in electric load forecasting in Central China and can be used for the operational practice.
-
表 1 华中电网日负荷、日最大及日最小负荷在春节期间的节假日效应项lh
表 2 试验期间华中电网负荷的预测效果
表 3 试验期间华中电网日负荷、日最大及日最小负荷预报误差分布
表 4 华中四省各省电网日负荷、日最大及日最小负荷的预测平均误差
-
[1] Douglas M L C, Henry E W.Modeling the impact of summer temperatures on national electricity consumption.J.Appl.Metero., 1981, 20 :1415~1419. doi: 10.1175/1520-0450(1981)020<1415:MTIOST>2.0.CO;2 [2] Quayle R G, Diaz H F.Heating degree day data applied to residential heating energy consumption.J.Appl.Meteor., 1980, 19 :241~246. doi: 10.1175/1520-0450(1980)019<0241:HDDDAT>2.0.CO;2 [3] 陈正洪, 杨荆安, 洪斌.华中电网用电量与气候的变化及其相关性诊断分析.华中师范大学学报, 1998, 32(4):515~520. http://www.cnki.com.cn/Article/CJFDTOTAL-HZSZ804.028.htm [4] 胡江林, 陈正洪, 洪斌, 等.华中电网日负荷与气象因子的关系研究.气象, 2002, 28(3):14~18. doi: 10.7519/j.issn.1000-0526.2002.03.003 [5] 杨位钦, 顾岚.时间序列分析与动态数据建模.北京:北京理工大学出版社, 1988.537~542. http://cpfd.cnki.com.cn/Article/CPFDTOTAL-ZGDW200508001374.htm [6] 李学桥, 马莉.神经网络·工程应用.重庆:重庆大学出版社, 1996.37~41. http://www.cnki.com.cn/Article/CJFDTOTAL-HJXU200703020.htm