基于粗糙集理论的神经网络预测算法及其在短期负荷预测中的应用.pdfVIP

第 34 卷 第 12 期 电 网 技 术 Vol. 34 No. 12 2010 年 12 月 Power System Technology Dec. 2010 文章编号：1000-3673 （2010 ）12-0168-06 中图分类号：TM 715 文献标志码：A 学科代码：470·4054 基于粗糙集理论的神经网络预测算法及其 在短期负荷预测中的应用 庞清乐 （山东工商学院信息与电子工程学院，山东省 烟台市 264005 ） A Rough Set-Based Neural Network Load Forecasting Algorithm and Its Application in Short-Term Load Forecasting PANG Qingle (School of Information and Electronic Engineering, Shandong Institute of Business and Technology, Yantai 264005, Shandong Province, China) ABSTRACT: Due to its remarkable approximation ability, 预测负荷作为神经网络的输出，利用粗糙集理论对神经网络 neural network is widely applied in pattern recognition, model 预测模型输出的预测负荷进行补偿，使预测精度更高。仿真 prediction and data mining. However, the approximation error 结果表明，该方法能显著提高函数的预测精度。 of neural network at the peak value of the approximated 关键词：负荷预测；神经网络；粗糙集理论 nonlinear function is great, especially the error is greater when the slope difference at both sides of the peak value. An 0 引言 improved rough set-based neural network algorithm is 系统非线性复杂度越来越高，系统精确的数学 proposed and applied in short-term load forecasting. Taking the load in current time interval, load in prior time interval, load 模型已经很难得到，神经网络以其强大的学习能力 difference between current time interval and prior time interval 与对连续函数的逼近能力受到控制界的普遍欢 and current time as the inputs of neural network forecasting [1] 迎