期刊文献+

基于双深度神经网络的光功率预测方法 被引量:3

Optical power prediction method based on double deep neural networks
下载PDF
导出
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。采集的环境数据能准确预测发电量变化趋势,对电网平稳运行具有重要意义。现有光功率预测方法大多采用单个模型构建预测结构,当面对不同环境数据时预测结果不够稳定。文中提出一种基于双深度神经网络的光功率预测方法,该方法以BPNN(back propagation neural networks)和LSTM(long short term memory)为基础判别器,并通过遗传算法将二者融合为更加精确和鲁棒的光功率预测模型。在东北电网实际数据集上的实验结果表明,相比现有单一神经网络模型,文中提出的方法具有更高的判别精度,且预测结果更加稳定。 Photovoltaic power generation is one of the emerging clean energy power generation methods. However, its efficiency is severely influenced by light intensity in the external environment, resulting in unstable electricity input to the power grid. Therefore, it is very important to predict the trend of change in power generation through collecting and analyzing external environmental factors. Currently, most of the existing methods use a single model to construct the prediction structure, which leads to unstable prediction results when faced with different environmental data. To address this problem, we propose an optical power prediction method based on double deep neural networks. It employs BPNN(back propagation neural networks) and LSTM(long short term memory) as the basic discriminators and combines them into a more accurate and robust optical power prediction model through the genetic algorithm. Experiments on the real datasets of northeast power grid show that compared with existing single neural network models, the proposed method has higher discrimination accuracy and more stable prediction results.
作者 张弘鹏 刘家庆 郭希海 孙羽 徐峥 ZHANG Hongpeng;LIU Jiaqing;GUO Xihai;SUN Yu;XU Zheng(Northeast Branch of State Grid Corporation of China,Shenyang 110180,P.R.China)
出处 《重庆大学学报》 CSCD 北大核心 2022年第1期50-58,共9页 Journal of Chongqing University
基金 国家电网有限公司科技资助项目(52992618009Q)。
关键词 光功率预测 BPNN LSTM 遗传算法 optical power prediction BPNN LSTM genetic algorithm
  • 相关文献

参考文献11

二级参考文献95

  • 1李碧君,方勇杰,杨卫东,徐泰山.光伏发电并网大电网面临的问题与对策[J].电网与清洁能源,2010,26(4):52-59. 被引量:76
  • 2曹石亚,李琼慧,黄碧斌,汪晓露,王乾坤.光伏发电技术经济分析及发展预测[J].中国电力,2012,45(8):64-68. 被引量:47
  • 3王惠文,孟洁.多元线性回归的预测建模方法[J].北京航空航天大学学报,2007,33(4):500-504. 被引量:242
  • 4GIEBEL G, LANDBERG L, KARINIOTAKIS G. State-of-the- art on methods and software tools for short-term, prediction of wind energy production [ C ]// European Wind Energy Conference & Exhibition, June 16-19, 2003, Madrid, Spain.
  • 5KARINIOTAKIS G, MAYER D, MOUSSAFIR J. ANEMOS.- development of a next generation wind power forecasting system for the large-scale integration of onshore & offshore wind farms [C]// European Wind Energy Conference & Exhibition, June 16-19, 2003, Madrid, Spain.
  • 6VON BREMEN L, SALECK N, HEINEMANN D. Enhanced regional forecasting considering single wind farm distribution for upscaling[EB/OL]. [2012 05 06]. http://stacks, iop. org/ 1742 6596/75/012040.
  • 7PINSON P, SIEBERT N, KARINIOTAKIS G. Forecasting of regional wind generation by a dynamic fuzzy-neural networks based upscaling approach [C]// European Wind Energy Conference ~ Exhibition, June 16-19, 2003, Madrid, Spain.
  • 8FOCKEN U, LANGE M, WALDL H P. Previento a wind power prediction system with an innovative upscaling algorithm [C]// Proceedings of European Wind Energy Conference Exhibition, July 2 6, 2001, Copenhagen, Denmark.
  • 9Q/GDW588-2011风电功率预测功能规范[S].2011.
  • 10FOCKEN U, LANGE M, MONNICH K, et al. Short-term prediction of the aggregated power output of wind farms a statistical analysis of the reduction of the prediction error by spatial smoothing effects[J]. Journal of Wind Engineering and Industrial Aerodynamics, 2002, 90(3): 231-246.

共引文献151

同被引文献42

引证文献3

二级引证文献3

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部