摘要
阐述了传统组合预测方法的基本原理,并从理论上论证了组合预测方法相对于单一预测模型的优越性。在此基础上,总结了组合预测方法的具体步骤,对组合预测方法基于最小二乘法的最优权重确定方法进行了改进,提出了一种新的基于BP神经网络模型的最优权重确定方法。最后将改进后的组合预测方法应用于电力系统短期负荷的预测中。通过分析和比较,验证了该方法的有效性。
The principle of conventional combination forecast method is explicated, and the predominance of combination forecast method compared with single forecast model is demonstrated from the theoretical aspect. On this basis, the steps of combination forecast method are explained. The method for determining optimal weights in combination forecast based on least square method is improved, and a novel method based on BP artificial neural networks (ANN) is proposed. In the end, the improved combination forecast method is applied to the short-term load forecasting of a power system, and its availability is verified by means of analysis and comparison.
出处
《系统工程与电子技术》
EI
CSCD
北大核心
2004年第6期842-844,共3页
Systems Engineering and Electronics
关键词
组合预测
电力系统
负荷预测
BP人工神经网络
combination forecast
power system
load forecasting
BP artificial neural networks