本文已被:浏览 1255次 下载 498次
投稿时间:2013-10-10
投稿时间:2013-10-10
中文摘要: 利用灰色理论中累加生成方法能够削弱负荷中随机成分的特点,以及人工神经网络可以逼近任意函数的能力,对具有任意变化规律的数据序列进行拟合和预测.实验结果表明,基于灰色理论和神经网络的最优组合模型的平均相对误差为1.307%,比BP神经网络预测和灰色理论模型预测的精度更高,具有明显优势.
Abstract:The accumulated generating method of gray theory can weaken the random ingredients of the load,and artificial neural networks can be adjacent to any function,a sequence which changes arbitrarily is fitted and forecasted.The experimental results show that the average relative error based on gray theory and neural network model for the optimal combination is1.307%,and this method has obvious advantages in forecast precision over BP neural network forecast and gray theory model forecast.
keywords: BP neural network gray theory load forecasting
文章编号:20130604 中图分类号: 文献标志码:
基金项目:上海市教育委员会创新基金(11YZ192)
作者 | 单位 | |
陈帅 | 上海电力学院电力与自动化工程学院,上海 200090 | chenshuai_1988@ 126.com |
王勇 | 上海电力学院电力与自动化工程学院,上海 200090 | |
吕丰 | 金山供电公司电力调度部门,上海 200540 | |
杨恒 | 上海电力学院电力与自动化工程学院,上海 200090 |
引用文本:
陈帅,王勇,吕丰,等.基于灰色理论和神经网络的短期电力负荷预测[J].上海电力大学学报,2013,29(6):527-531.
CHEN Shuai,WANG Yong,LYU Feng,et al.Short-term Load Forecasting Based on Gray Theory and Neural Network[J].Journal of Shanghai University of Electric Power,2013,29(6):527-531.
陈帅,王勇,吕丰,等.基于灰色理论和神经网络的短期电力负荷预测[J].上海电力大学学报,2013,29(6):527-531.
CHEN Shuai,WANG Yong,LYU Feng,et al.Short-term Load Forecasting Based on Gray Theory and Neural Network[J].Journal of Shanghai University of Electric Power,2013,29(6):527-531.