基于变权缓冲灰色模型的中长期负荷预测  

Medium- and Long-Term Load Forecasting Based on Variable Weights Buffer Grey Model

作　　者：王大鹏[1] 汪秉文[1] 

机构地区：[1]华中科技大学控制科学与工程系,湖北省武汉市430074

出　　处：《电网技术》2013年第1期167-171,共5页Power System Technology

基　　金：国家自然科学基金资助项目(60773190;60802002)~~

摘　　要：为解决传统灰色模型和缓冲算子在中长期电力负荷预测应用中存在的问题,提出了变权缓冲灰色模型。该模型将变权缓冲算子与背景值优化灰色模型相结合,实现对原始负荷数据的动态预处理。基于粒子群优化算法,以拟合值与实际值的灰色关联度最大为目标,选择最优缓冲系数,在提高模型精度的同时,使预测结果最大程度地体现原有负荷数据的内在发展趋势,提高拟合和预测的稳定性。为验证模型效果,使用2003—2008年全国全社会用电量数据建模,预测2009—2011年的用电量,预测结果证明了该模型在中长期负荷预测中的有效性和可用性。To remedy the defects in the applications of traditional grey model and buffer operators in medium- and long-term load forecasting, a variable weights buffer grey model is proposed. The proposed model integrates the variable weights buffer operator with the background value optimized GM（1,1） model to implement dynamic preprocessing of original load data. Taking the maximum grey correlation degree between fitted value and true value as objective function, based on particle swarm optimization （PSO）, the optimal buffer factor is chosen, which can improve forecasting precision, make forecasting results embodying the internal trend of original load data to the maximum extent, and improve the stability of fitting and forecasting. To verify the effectiveness of the proposed model, the electricity consumption of the whole society in China from 2003 to 2008 is used for the modeling to forecast the electricity consumption of the whole society from 2009 to 2011, and the forecasting results prove the validity and applicability of the proposed model in medium- and long-term load forecasting.

关 键 词：变权缓冲算子 变权缓冲灰色模型 灰色关联度 粒子群优化 中长期负荷预测 

分 类 号：TM715[电气工程—电力系统及自动化]