基于灰关联分段优选组合模型的短期电力负荷预测研究

针对已有GM(1,1)灰色预测模型在数据波动、突变和转折等不确定情况下预测精度较低的问题,提出一种基于灰关联分段优选组合模型的短期电力负荷预测模型。基于GM(1,1)模型在平滑上升和下降区段预测效果好、而一天的用电负荷可划分为几个峰谷区段的特点,对预测日进行灰关联分段和优选组合,避免出现由于初始条件选择不当而将误差引入模型并被逐步放大的风险;同时,通过组合不同角度GM(1,1)模型,解决负荷的多因素影响。经广西贵港市实际工程验证,本模型预测平均误差在3%左右,预测精度有明显提高,完全可满足该地区短期电力负荷预测的实际要求。

Research on Short-Term Electrical Load Forecasting Based on Optimized Combination Model of Grey Correlation Segmentation

Aimed at the low precision of general GM(1,1) grey forecasting model in the uncertain conditions of original data sequence fluctuation, mutation or transition, the paper proposes a short-term electrical load forecasting on optimized combination model of grey correlation-segmentation. GM(1,1) presents good forecasting result within the smoothly upward or downward segment, while daily power load can be divided into several segments with peaks or valleys. Therefore, grey correlation segmentation and optimized ...