GA-BP neural network photovoltaic power generation short-term forecast based on MIV analysis

被引：0
|
作者：
Wang, Yingli [1 ]
Tao, Shuai [1 ]
Hou, Xiaoxiao [1 ]
Qi, Hong [2 ]
机构：
[1] School of Measurement and Communication, Harbin University of Science and Technology, Harbin,150080, China
[2] College of Energy Science and Engineering, Harbin Institute of Technology, Harbin,150000, China
来源：
Taiyangneng Xuebao/Acta Energiae Solaris Sinica | 2020年 / 41卷 / 08期
关键词：
In view of the problem of low stability and precision of network prediction caused by too many input variables in the neural network forecast model of photovoltaic power generation; a GA-BP neural network short-term forecast method of photovoltaic power generation based on improved MIV(Mean Impact Value) algorithm is proposed. Combining the Spearman correlation coefficient significance test and the improved MIV analysis in which Euclidean distance is adopted to calculate the variation factor; this approach obtains the degree of external correlation and internal correlation between the input variables (meteorological factor) and the output variable (photovoltaic power generation capacity); singles out the input variable which has the greatest correlation degree with the output variable; and utilizes the optimized neural network to conduct short-term forecast on photovoltaic power generation. The experimental results show that the mean square error of the approach is reduced to 0.6450 from 3.7034 of BP and 1.8552 of GA-BP forecast networks to 0.6450; which implies greater stability and precision of the forecast network. © 2020; Solar Energy Periodical Office Co; Ltd. All right reserved;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
引用
收藏
页码：236 / 242
相关论文
共 50 条
  • [31] Short-term photovoltaic power forecasting method based on convolutional neural network
    He, Yutong
    Gao, Qingzhong
    Jin, Yuanyuan
    Liu, Fang
    ENERGY REPORTS, 2022, 8 : 54 - 62
  • [32] Intelligent Forecast Model for Project Cost in Guangdong Province Based on GA-BP Neural Network
    Li, Changqing
    Xiao, Yang
    Xu, Xiaofu
    Chen, Zhuoyu
    Zheng, Haofeng
    Zhang, Huiling
    BUILDINGS, 2024, 14 (11)
  • [33] Forecast of Foreclosure Property Market Trends during the Epidemic Based on GA-BP Neural Network
    Fang, YaoChing
    SCIENTIFIC PROGRAMMING, 2022, 2022
  • [34] Short-Term Photovoltaic Generation Forecasting Based on LVQ-PSO-BP Neural Network and Markov Chain Method
    Wang, Xiran
    Ma, Xue
    Lou, Suhua
    Peng, Fei
    Wu, Song
    2019 3RD INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE, AUTOMATION AND CONTROL TECHNOLOGIES (AIACT 2019), 2019, 1267
  • [35] Short-term power generation forecast of PV power station based on deep belief network
    Zhao L.
    Liu Y.
    Yu L.
    Liu J.
    Dianli Xitong Baohu yu Kongzhi/Power System Protection and Control, 2019, 47 (18): : 11 - 19
  • [36] Short-term ensemble forecast for purchased photovoltaic generation
    Takeda, Hisashi
    SOLAR ENERGY, 2017, 149 : 176 - 187
  • [37] Short-Term Photovoltaic Power Forecast Based on Grey Relational Analysis and GeoMAN Model
    Shi M.
    Xu K.
    Wang J.
    Yin R.
    Zhang P.
    Diangong Jishu Xuebao/Transactions of China Electrotechnical Society, 2021, 36 (11): : 2298 - 2305
  • [38] Short-term power load forecast based on dimension reduction by elastic network and flower pollination algorithm optimized BP neural network
    Zhang S.
    Yang Z.
    Zhang L.
    Yuan S.
    Wang Z.
    Yi Qi Yi Biao Xue Bao/Chinese Journal of Scientific Instrument, 2019, 40 (07): : 47 - 54
  • [39] A method of short-term wind power forecast based on wavelet transform and neural network
    Wang S.
    Su J.
    Du S.
    Nongye Gongcheng Xuebao/Transactions of the Chinese Society of Agricultural Engineering, 2010, 26 (SUPPL. 2): : 125 - 129
  • [40] Research on BP Neural Network Algorithm Based on Genetic Algorithm Optimization in Short-Term Power Generation Forecasting
    Zhao, Jianna
    He, Xiaobo
    PROCEEDINGS OF THE 2016 INTERNATIONAL CONFERENCE ON EDUCATION, MANAGEMENT SCIENCE AND ECONOMICS (ICEMSE 2016), 2016, 65 : 359 - 362
12345