基于概念格的神经网络日最大负荷预测输入参数选择

J4 ›› 2011, Vol. 49 ›› Issue (01): 87-93.

基于概念格的神经网络日最大负荷预测输入参数选择

任海军^1,2, 张晓星¹, 肖波³, 周湶¹

1. 重庆大学输配电装备及系统安全与新技术国家重点实验室, 重庆 400044;2. 重庆大学软件工程学院, 重庆 400044|3. 重庆市电力公司城区供电局, 重庆 400050

收稿日期:2010-04-11 出版日期:2011-01-26 发布日期:2011-02-19
通讯作者: 任海军 E-mail:jhren@cqu.edu.cn

Input Parameters Selection in Neural Network Load ForecastingMode Based on Concept Lattice

REN Haijun^1,2, ZHANG Xiaoxing¹, XIAO Bo³, ZHOU Quan¹

1. State Key Laboratory of Power Transmission Equipment &|System Security and New Technology, Chongqing University,Chongqing 400044, China|2. School of Software Engineering, Chongqing University, Chongqing 400044, China;3. Chengdu Power Supply Bureau, Chongqing Electric Power Company, Chongqing 400050, China

Received:2010-04-11 Online:2011-01-26 Published:2011-02-19
Contact: REN Haijun E-mail:jhren@cqu.edu.cn

摘要/Abstract

摘要：

针对电力系统中影响负荷预测精度的众多因素如何选择问题, 提出一种概念格属性约简算法, 采用该算法挖掘出与待预测负荷量相关性较大的各属性作为神经网络预测模型的输入参数, 降低了输入参数规模, 确保了负荷预测模型输入参数的合理性, 解决了神经网络模型输入参数的确定问题. 通过对重庆市某区实际日最大负荷数据的计算分析, 结果表明该算法提高了神经网络模型的预测精度, 从而证实了所提出约简算法的合理性和有效性.

关键词: 神经网络；概念格；属性约简；负荷预测

Abstract:

There are many factors to affect the accuracy of load forecasting. The problem is how to choose the factors. To solve the problem, an attribute reduction algorithm of concept lattice was introduced. We chose a property parameter that has good relativity to forecasting load as the input parameter of the forecasting model of neural network. It reduces the scope of the input parameters, ensures the rationality of input parameters of the forecasting model, and solves the problem how to determine the input parameters of the neural network model. The actual data of the maximum load in some place of Chongqing City was calculated. The results show the prediction accuracy of neural network model is improved with such a method, and reduction algorithm is reasonable and effective.

Key words: neural network, concept lattice, attribute reduction, load forecasting

中图分类号:

TP181

任海军, 张晓星, 肖波, 周湶. 基于概念格的神经网络日最大负荷预测输入参数选择[J]. J4, 2011, 49(01): 87-93.

LIN Hai-Jun, ZHANG Xiao-Xing, XIAO Bei, ZHOU Quan. Input Parameters Selection in Neural Network Load ForecastingMode Based on Concept Lattice[J]. J4, 2011, 49(01): 87-93.