基于主成分分析和正则化神经网络的电力负荷预测方法Power Load Forecasting Method Based on Principal Component Analysis and Regularized Neural Network
徐江,冯雪,付兆庆,马宝明,苗耀庭
XU Jiang,FENG Xue,FU Zhaoqing,MA Baoming,MIAO Yaoting
摘要(Abstract):
为提高用电负荷预测的准确率,提出一种基于主成分分析(PCA)和正则化人工神经网络负荷预测方法。通过分析多个影响负荷变化的变量和因子,利用主成分分析法对变量进行线性降维,减少各变量之间的关联性,用得到的主成分作为BP神经网络的输入变量,同时增加正则化约束项优化神经网络训练过程,提高网络模型泛化能力。最后利用某售电公司所代理用户的实测用电数据进行网络建模和预测,结果表明,与其他预测方法进行对比,该预测方法有较高的准确性。
In order to improve the accuracy of electrical load forecasting, this paper proposes a load forecasting method based on principal component analysis(PCA) and regularized artificial neural network. By analyzing multiple variables and factors that affect the power load change, the principal component analysis method is used to linearly reduce the dimension of the variables to reduce the correlation among the variables. The obtained principal components are used as the input variables of the BP neural network. At the same time, the regularization constraints are added to optimize the training process of the neural network and improve the generalization ability of the network model. Finally, the network modeling and prediction are carried out by using the measured electricity consumption data of a power sales company. Compared with other prediction methods, the results show that the prediction method is of higher accuracy.
关键词(KeyWords):
负荷预测;主成分分析;正则化;神经网络;电力市场交易
load forecasting;principal component analysis;regularization;neural network;electricity market trading
基金项目(Foundation): 内蒙古电力(集团)有限责任公司科技项目“电力多边市场大数据挖掘研究及市场信息可视化展示平台开发”(2018-84)
作者(Author):
徐江,冯雪,付兆庆,马宝明,苗耀庭
XU Jiang,FENG Xue,FU Zhaoqing,MA Baoming,MIAO Yaoting
参考文献(References):
- [1]唐猛,董晓琦,蒋睿辰.电力现货市场的售电公司短期负荷预测[J].浙江电力,2019,38(3):87-91.
- [2]刘畅,刘天琪,陈振寰,等.基于KPCA和BP神经网络的短期负荷预测[J].电测与仪表,2016,53(10):57-61.
- [3]苏振宇,龙勇,赵丽艳.基于regARIMA模型的月度负荷预测效果研究[J].中国电力,2018,51(5):166-171.
- [4]王威,王波,何宇,等.基于负荷分解和灰色理论的电网最大负荷预测[J].浙江电力,2018,37(8):48-53.
- [5]孔祥玉,郑锋,鄂志君,等.基于深度信念网络的短期负荷预测方法[J].电力系统自动化,2018,42(5):133-139.
- [6]赵芝璞,高超,沈艳霞,等.基于关联模糊神经网络和改进型蜂群算法的负荷预测方法[J].中国电力,2018,51(2):54-57.
- [7]张齐家.基于PCA神经网络的电力系统短期负荷预测[D].兰州:兰州交通大学,2017.
- [8]张岩,李洋博,柳姗,等.基于蚁群优化神经网络模型的风电功率预测[J].内蒙古电力技术,2019,37(4):26-30.
- [9]黄宇腾,韩翊,赖尚栋.深度神经网络在配电网公变短期负荷预测中的应用研究[J].浙江电力,2018,37(5):1-6.
- [10]邓裕文,吴冠平,毛卫东,等.中长期负荷预测的多因素模型研究[J].内蒙古电力技术,2019,37(3):23-28.
- [11]孙海萌,孙君茹.基于蚁群算法的电力负荷预测[J].农村电气化,2018(10):9-10.
- [12]阙雷挺,苏亮,周灵江,等.基于多气象指标的地区短期负荷预测研究[J].云南电力技术,2016,44(1):32-35.
- [13]史佳琪,张建华.基于多模型融合Stacking集成学习方式的负荷预测方法[J].中国电机工程学报,2019,39(14):4032-4042.
- [14]王鸿玺,李飞,李翀,等.基于大数据分析的混沌神经网络模型在负荷预测中的应用[J].电力大数据,2017,20(8):1-5.
- [15]王增平,赵兵,纪维佳,等.基于GRU-NN模型的短期负荷预测方法[J].电力系统自动化,2019,43(5):53-58.
- [16]张冰玉.基于数据挖掘技术的短期电力负荷预测[J].电力大数据,2017,20(10):18-21.
- 负荷预测
- 主成分分析
- 正则化
- 神经网络
- 电力市场交易
load forecasting - principal component analysis
- regularization
- neural network
- electricity market trading