一种基于双深度神经网络的光功率预测方法
DOI:
作者:
作者单位:

国家电网公司东北分部

作者简介:

通讯作者:

中图分类号:

TP391

基金项目:

国家电网公司科技项目


An Optical Power Prediction Method Based on Double Deep Neural Networks
Author:
Affiliation:

Northeast Branch of State Grid Corporation of China

Fund Project:

Science and Technology Project of State Grid Corporation

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    光伏发电是新兴的清洁能源发电方式之一,其光功率受辐照度等环境因素影响较大,导致注入电网的电量不稳定。通过采集的环境数据来准确预测发电量变化趋势对电网平稳运行具有重要意义。本文提出了一种以BPNN和LSTM为基础判别器,通过遗传算法将二者融合为更高精度的双深度神经网络光功率预测方法。文中首先介绍了BPNN、LSTM与遗传算法的原理,之后给出了构造双深度神经网络判别模型的具体方法,最后进行了实验验证。实验结果表明该方法相比于单一神经网络的模型具有较高的判别精度。

    Abstract:

    Photovoltaic power generation is one of the emerging clean energy power generation methods. However, its efficiency in electricity generation is severely influenced by light intensity in the external environment and products unstable electricity to the power grid. So, it is very important to predict the trend of power generation through the collection and analysis of the external environment for stability of the power grid. To address this prediction problem, we propose a higher-precision dual-depth neural network optical power prediction method based on BPNN and LSTM-based discriminator, which are combined by genetic algorithms. We first introduce the principles of BPNN, LSTM and genetic algorithm, and then give the specific method of constructing a dual-depth neural network discriminative model. Finally, we perform a verification experiment. Experimental results show that the method has higher discrimination accuracy than the single neural network model.

    参考文献
    相似文献
    引证文献
引用本文
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2020-01-08
  • 最后修改日期:2020-02-24
  • 录用日期:2020-02-24
  • 在线发布日期:
  • 出版日期: