|本期目录/Table of Contents|

[1]李嵩山,马志程,张晓英,等.基于深度学习的聚光太阳能电站热功率预测研究[J].工业仪表与自动化装置,2021,(06):58-64.[doi:10.19950/j.cnki.cn61-1121/th.2021.06.011]
 LI Songshan,MA Zhicheng,ZHANG Xiaoying,et al.Research on thermal power prediction of concentrating solar power station based on deep learning[J].Industrial Instrumentation & Automation,2021,(06):58-64.[doi:10.19950/j.cnki.cn61-1121/th.2021.06.011]
点击复制

基于深度学习的聚光太阳能电站热功率预测研究

《工业仪表与自动化装置》[ISSN:1000-0682/CN:61-1121/TH]

卷:
期数:
2021年06期
页码:
58-64
栏目:
出版日期:
2021-12-15

文章信息/Info

Title:
Research on thermal power prediction of concentrating solar power station based on deep learning
作者:
李嵩山1马志程2张晓英1周 强2陈 伟1
(1.兰州理工大学 电气工程与信息工程学院,甘肃 兰州 730050;2.国网甘肃省电力公司电力科学研究院,甘肃 兰州 730000)
Author(s):
LI Songshan1MA Zhicheng2ZHANG Xiaoying1ZHOU Qiang2CHEN Wei1
(1. School of electrical engineering and information engineering, Lanzhou University of technology, Gansu Lanzhou 730050,China;2. Electric Power Research Institute of State Grid Gansu Electric Power Company, Gansu Lanzhou 730000,China;)
关键词:
聚光太阳能电站热功率预测神经网络时空耦合特征
Keywords:
concentrating solar power station Thermal power prediction Neural networkSpatiotemporal coupling characteristics
分类号:
TM621
DOI:
10.19950/j.cnki.cn61-1121/th.2021.06.011
文献标志码:
A
摘要:
由于太阳能具有不确定性和随机性,使得对聚光太阳能电站的热功率进行准确预测难度较大。该文提出了一种基于深度学习的热功率预测方法。首先建立标准贯入实验装置的机理模型,识别主要气象因素,避免模型输入选择的主观性;其次利用卷积神经网络和长短期记忆网络对识别出的主要气象因子进行特征提取,充分挖掘气象因子之间的时空耦合特征;最后,由完全连接的层输出得到热功率。仿真结果表明,该文提出的深度学习预测法能够得到更优的热功率预测结果。
Abstract:
Due to the uncertainty and randomness of solar energy, it is difficult to accurately predict the thermal power of concentrating solar power station. In this paper, a thermal power prediction method based on deep learning is proposed. Firstly, the mechanism model of solar power tower (SPT) is established to identify the main meteorological factors and avoid the subjectivity of model input selection; Secondly, convolution neural network and long-term and short-term memory network are used to extract the features of the identified main meteorological factors, and the spatiotemporal coupling features between meteorological factors are fully exploited; Finally, the thermal power is obtained from the output of the fully connected layer. Simulation results show that the proposed deep learning prediction method can get better thermal power prediction results.

参考文献/References:

[1] 国家发展改革委运行局.能源综合供应能力不断提升 迎峰度夏高峰期电力等能源需求得到有效保障[N].中国经济导报,2021-07-22(003).

[2] 曹彬,吕干云,王楠,等.综合能源系统优化调度下的需求响应研究与应用[J].电力需求侧管理,2021,23(04):45-50.
[3] 严干贵,王月,李军徽,等.匹配风电接纳可行域的储能系统控制方法及其经济性评估[J].高电压技术,2015,41(7):2148-2155.
[4] 张亚超,刘开培,秦亮,等.计及柔性资源的含风电场电力系统多目标动态协调调度[J].高电压技术,2017,43(4):1186-1193.
[5] 刘皓明,陆丹,杨波,等.可平抑高渗透分布式光伏发电功率波动的储能电站调度策略[J].高电压技术,2015,41(10):3213-3223.
[6] COLLADO F J, GUALLAR J. A review of optimized design layouts for solar power tower plants with campo code[J]. Renewable and Sustainable Energy Reviews,2013,20:142-54.
[7] BEHAR O, KHELLAF A, MOHAMMEDI K. A review of studies on central receiver solar thermal power plants[J]. Renewable and Sustainable Energy Reviews, 2013;23:12-39.
[8] 秦军,胡娥,内森。具有不同“配置运行”组合的太阳辅助发电设备的性能。能源转换管理2016;124:155-167.
[9] Díaze-Vico D, Torrese-Barran A, Omari A, Dorronsoro JR. Deep neural networks for wind and solar energy prediction[J]. Neural Process Lett,2017;46(3):829-44.
[10] Hocaoglu F O, Serttas F. A novel hybrid (Mycielski-Markov) model for hourly solar radiation forecasting[J].Renew Energy,2017;108:635-43.
[11] Sharma V, Yang D, Walsh W, Reindl T. Short term solar irradiance forecasting using a mixed wavelet neural network[J]. Renew Energy,2016;90:481-92.
[12] 姜海东.基于结构核支持向量机的全球逐时水平辐照度预测:以中国西藏地区为例.能源转换管理2017;142:307-21.
[13] 王赫,彭杰等. 可再生能源预测深度学习综述.能源转换管理 2019;198:111-799.
[14] Srivastava S, Lessmann S. A comparative study of LSTM neural networks in forecasting day-ahead global horizontal irradiance with satellite data[J]. Sol Energy 2018,162:232-47.
[15] Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks[J]. Commun ACM 2017;60(6):84-90.
[16] 黎静华,骆怡辰,杨舒惠,等.可再生能源电力不确定性预测方法综述[J].高电压技术,2021,47(04):1144-1157.
[17] 余洋,陈庚,余佳磊,等.基于聚类和长短期记忆神经网络的光热电站并网电力预测[J].热力发电,2021,50(09):128-136.?div>[18] 肖雄,王健翔,张勇军,等.一种用于轴承故障诊断的二维卷积神经网络优化方法[J].中国电机工程学报,2019,39(15):4558-4568.
[19] Hochreiter S , Schmidhuber J . Long Short-Term Memory[J]. Neural Computation, 1997, 9(8):1735-1780.
[20] 郭玥秀,杨伟,刘琦,等.残差网络研究综述[J].计算机应用研究,2020,37(05):1292-1297.

相似文献/References:

备注/Memo

备注/Memo:
收稿日期:2021-07-29
基金项目:甘肃省科技重大专项计划(19ZD2GA003
)作者简介:李嵩山(1995),男,甘肃武威人,硕士研究生,研究方向为能源电力系统稳定与控制。
更新日期/Last Update: 1900-01-01