摘要
为了提高短期电力负荷的预测精度,提出了一种短期电力负荷预测模型。该模型包括蚁群算法优化的BP神经网络模型和灰色理论模型。蚁群算法优化的BP神经网络可以提高BP神经网络预测精度和收敛速度,灰色理论削弱了数据自身的随机性。结合两者优点,根据电力负荷的数据特征和两种子模型的预测误差,得出其在组合模型中所占权重,然后得到基于组合模型的预测值。应用组合模型对河南省某地区进行短期电力负荷预测,结果表明该方法比单个模型预测精度更高,能有效预测短期电力负荷。
In order to improve the accuracy of short-term power load forecasting, this paper puts forward a model of short term load forecasting. The whole model includes Ant colony optimization BP neural network model and gray theory model. Ant colony optimization BP neural network can improve prediction accuracy and increase the convergence speed of BP neural network, The grey theoretical model weakens the randomness of the data itself. The advantages of both, Based on the data characteristics of the power load and the prediction error of the two models, the weight of the combined model is obtained and the predicted value based on the combined model is obtained. And the application of combination model for short-term load forecasting of a certain area of Henan province, The results show that this method has higher prediction accuracy than single model, and it is an effec tive method for short-term power load forecasting.
作者
王瑞
周晨曦
逯静
WANG Rui ZHOU Chen-xi LU Jing(School of Electrical Engineering and Automation, Henan Polytechnic University College of Computer Science and Technology, Henan Polytechnic University, Jiaozuo 454000,)
出处
《软件导刊》
2017年第10期150-153,共4页
Software Guide
基金
河南省高等学校重点科研项目(18A470012)
河南省控制工程重点学科开放实验室开放基金项目(KG2016-09)
关键词
电力负荷预测
蚁群算法
BP神经网络
灰色理论
power load forecasting
ant colony algorithm
BP neural network
grey theory
