基于Gauss插值的正交化预测方法在智能电网用电量预测中的应用研究  

Application research on Gaussian orthogonal interpolation method for electricity consumption forecasting of smart grid

作　　者：王晓佳[1] 沈建新[1,2] 杨善林[1] 

机构地区：[1]合肥工业大学,安徽合肥230009 [2]江苏省电力公司,江苏南京210024

出　　处：《电力系统保护与控制》2010年第21期141-145,151,共6页Power System Protection and Control

基　　金：国家863计划重点项目(2008AA042901);国家自然科学基金项目(70631003;90718037);合肥工业大学基金项目(2010HGXJ0083)

摘　　要：智能电网的一个重要特征是通过高精度的用电量预测进行电能智能调配,用电量信息的精确预测是电网智能化的关键指标。在此背景下,将高斯正交化插值方法与灰色GM(1,1)预测模型相结合,构造一类新的灰色正交化预测模型——NGGM(1,1),并将此模型应用于智能电网用电量预测研究中。该模型可以有效地解决非等距序列的预测问题,较大程度提高模型的预测精度,优化数据质量,加强电网运行及调配的智能性,为智能电网的辅助决策提供更为符合实际的、可操作的科学参考。最后用所提出的方法对江苏省2008年工业用电量进行预测研究,其结果表明了所提方法的有效性。An important feature of smart grid is the intelligent power distribution function based on electricity consumption forecasting with high accuracy.A ccurate prediction of electricity consumption is the key indicator of power intelligence.As a result of this,this paper combines Gaussian orthogonal method with gray prediction model and constructs a new grey orthogonal forecast model-NGGM(1,1),which is used in electricity demand forecasting in smart grid.This model can solve the forecasting problem of non-isometric series,g reatly improve the accuracy of prediction model,o ptimize data quality,strengthen the intelligence on operation and deployment,and provide more realistic,workable scientific reference for the decision support of smart grid.Finally,t he proposed method is applied to predict the industrial electricity consumption of Jiangsu province in 2008.The results prove the effectiveness of the method.

关 键 词：智能电网 正交化插值 NGGM(1 1)模型 用电量预测 

分 类 号：N941.5[自然科学总论—系统科学] TM715[电气工程—电力系统及自动化]