ZHENG Dan,MA Shang-chang,ZHANG Su-juan.Research on Solar Radiation Observation Algorithm based on PCA[J].Journal of Chengdu University of Information Technology,2017,(06):584-589.[doi:10.16836/j.cnki.jcuit.2017.06.002]
基于PCA的太阳辐射观测算法研究
- Title:
- Research on Solar Radiation Observation Algorithm based on PCA
- 文章编号:
- 2096-1618(2017)06-0584-06
- Keywords:
- solar radiation; principal component analysis(PCA); genetic algorithm(GA); BP neural network(BPNN); error analysis
- 分类号:
- TP183
- 文献标志码:
- A
- 摘要:
- 研究太阳辐射对认识气候变化有重要影响,而中国地面台站的太阳辐射观测数据不足,质量不佳。针对提高太阳辐射观测的精确度,提出利用主成分分析法(PCA)对影响太阳辐射观测的多个气象要素进行降维处理,剔除冗余变量,结合遗传算法(GA)获取BP模型的最优权值阈值,并用实测数据加以验证该模型的可行性,充分提高模型性能以实现对太阳辐射的观测研究。结果表明:基于PCA的 GA-BP网络模型的观测精度高于传统BP模型,该模型有效地提高模型的泛化能力,具有一定的可行性及指导意义。
- Abstract:
- The study of solar radiation has an important impact on the understanding of climate change, while the solar radiation observation data of ground stations in China is insufficient and of poor quality. In order to improve the accuracy of solar radiation observation, this paper proposes a method of principal component analysis(PCA)to reduce the number of meteorological factors that influence the solar radiation, which eliminate redundant variables. Combining with the genetic algorithm(GA)to obtain the optimal weights and thresholds of BP model, and using the measured data to verify the feasibility of the model,it can fully improve the network performance to achieve the observation of solar radiation. The results show that the accuracy of GA-BP network model based on PCA is higher than traditional BP model, which can improve the generalization ability of the model and has certain feasibility and guidance significance.
参考文献/References:
[1] 左大康,王懿贤,陈建绥.中国地区太阳总辐射的空间分布特征[J].气象学报,1963,33(1):78-95.
[2] 曹双华,曹家枞.太阳逐时总辐射混沌优化神经网络预测模型研究[J].太阳能学报,2006,27(2):164-169.
[3] 田景文,高美娟.人工神经网络算法研究及应用[M].北京:北京理工大学出版社,2006.
[4] 周晋,吴业正,晏刚,等.利用神经网络估算太阳辐射[J].太阳能学报,2005,26(4):509-512.
[5] 贺文,齐爽,陈厚合.蚁群BP神网络的光伏电站辐照强度预测[J].电力系统及其自动化学报,2016,28(7):26-31.
[6] 夏玫.BP神经网络泛化能力改进研究[D].太原:太原科技大学,2009.
[7] 苏高利,柳钦火.基于LS-SVM方法的晴空逐时太阳辐射模型[J].北京师范大学学报(自然科学版)2007,43(3):274-278.
[8] 王炳忠,张富国,李立贤.我国太阳能资源极其计算[J].太阳能学报,1980,1(1):1-9.
[9] 邢杰,萧德云.基于PCA的概率神经网络结构优化[J].清华大学学报(自然科学版),2008,48(1):141-144.
[10] 叶林,陈政,赵永宁,等.基于遗传算法-模糊径向基神经网络的光伏发电功率预测模型[J].电力系统自动化,2015,39(16):16-22.
[11] 周文全.BP网络泛化能力的增强改进[D].广州:暨南大学,2012.
[12] 廖东进,刘晓龙.基于BP神经网络的光伏电站辐照度预测研究[J].太阳能,2016(10).
[13] 米增强.光伏电站辐照度ANN 预测及其两维变尺度修正方法[J].太阳能学报,2013,34(2):251-258.
[14] 孙娓娓. BP神经网络算法改进及其应用研究[D].重庆:重庆大学,2009.
[15] 司杨.基于模式匹配的地面接受太阳辐射功率预测方法研究[J].青海大学学报(自然科学版),2012,30(1):30-34.
备注/Memo
收稿日期:2017-05-07 基金项目:省科技厅科技支撑资助项目(2015GZ0278)