基于改进递归深度信念网络的CSP电站短期出力预测

李锦键; 王兴贵; 杨维满; 赵玲霞

doi:10.19912/j.0254-0096.tynxb.2020-1079

PDF(1778 KB)

太阳能学报 ›› 2022, Vol. 43 ›› Issue (7) : 225-232. DOI: 10.19912/j.0254-0096.tynxb.2020-1079

基于改进递归深度信念网络的CSP电站短期出力预测

李锦键, 王兴贵, 杨维满, 赵玲霞

作者信息 +

CSP STATION OUTPUT POWER SHORT-TERM FORECAST BASED ON IMPROVED RNN-DBN

Li Jinjian, Wang Xinggui, Yang Weiman, Zhao Lingxia

Author information +

文章历史 +

摘要

以预测CSP电站短期出力为目的,首先引入自适应思想对递归深度信念网络的训练算法进行改进,并建立直接法向辐射的短期预测模型。随后提出一种结合静态模型的CSP电站短期出力预测方法。最后进行性能检验,验证了改进递归深度信念网络的可行性,以及CSP电站短期出力预测方法的有效性。研究结果表明：建立的改进递归深度信念网络可提升预测准确性和收敛速度;提出的CSP电站短期出力预测方法可较为准确地预测其短期出力情况。

Abstract

For the purpose of predicting the short-term output power of concentrating solar power （CSP） station, firstly introduce adaptive idea to improve the training algorithm of the recursive deep belief network, and establish a direct normal irradiance short-term prediction model. Secondly, a method for forecasting the short-term output power of CSP station combined with its static model is proposed. Finally, a performance test is carried out to verify the feasibility of improved recursive deep belief network and the effectiveness of the CSP station short-term output power prediction method. The research results show that the established improved recursive deep belief network can improve the prediction accuracy and training speed. Also, the proposed CSP station short-term output power prediction method can predict its output power more accurately.

导出引用

李锦键, 王兴贵, 杨维满, 赵玲霞. 基于改进递归深度信念网络的CSP电站短期出力预测[J]. 太阳能学报. 2022, 43(7): 225-232 https://doi.org/10.19912/j.0254-0096.tynxb.2020-1079

Li Jinjian, Wang Xinggui, Yang Weiman, Zhao Lingxia. CSP STATION OUTPUT POWER SHORT-TERM FORECAST BASED ON IMPROVED RNN-DBN[J]. Acta Energiae Solaris Sinica. 2022, 43(7): 225-232 https://doi.org/10.19912/j.0254-0096.tynxb.2020-1079

中图分类号： TM615

参考文献

[1] 杜尔顺, 张宁, 康重庆, 等. 太阳光热发电并网运行及优化规划研究综述与展望[J]. 中国电机工程学报, 2016, 36(21): 5765-5775, 6019.
DU E S, ZHANG N, KANG C Q, et al.Reviews and prospects of the operation and planning optimization for grid integrated concentrating solar power[J]. Proceedings of the CSEE, 2016, 36(21): 5765-5775, 6019.
[2] 崔杨, 杨志文, 严干贵, 等. 降低火电机组调峰成本的光热电站储热容量配置方法[J]. 中国电机工程学报, 2018, 38(6): 1605-1611, 1896.
CUI Y, YANG Z W, YAN G G, et al.Capacity configuration of thermal energy storage within CSP to reduce the cost of peak load regulation[J]. Proceedings of the CSEE, 2018, 38(6): 1605-1611, 1896.
[3] 陈润泽, 孙宏斌, 李正烁, 等. 含光热储能电站的电网调度模型与并网效益分析[J]. 电力系统自动化, 2014, 38(19): 1-7.
CHEN R Z, SUN H B, LI Z S, et al.Grid dispatch model and interconnection benefit analysis of concentrating solar power plants with thermal storage[J]. Automation of electric power system, 2014, 38(19): 1-7.
[4] 周晋, 吴业正, 晏刚, 等. 基于神经网络估算太阳辐射[J]. 太阳能学报, 2005, 26(4): 509-512.
ZHOU J, WU Y Z, YAN G, et al.Solar radiation estimation using artificial neural networks[J]. Acta energiae solaris sinica, 2005, 26(4): 509-512.
[5] 高亮, 张新燕, 张家军, 等. 基于拟合剔除的优化小波神经网络太阳辐射量预测[J]. 电测与仪表, 2019, 56(11): 89-93.
GAO L, ZHANG X Y, ZHANG J J, et al.Prediction of solar radiation based on optimized wavelet neural network with fitting and culling[J]. Electrical measurement & instrumentation, 2019, 56(11): 89-93.
[6] 杨琪, 王维庆, 王海云, 等. 基于相关性分析和GBDT组合的太阳辐射量预测算法[J]. 安徽大学学报(自然科学版), 2020, 44(3): 65-71.
YANG Q, WANG W Q, WANG H Y, et al.Prediction algorithm of solar radiation based on correlation analysis and GBDT combination[J]. Journal of Anhui University(natural science edition), 2020, 44(3): 65-71.
[7] 王守相, 王亚旻, 刘岩, 等. 基于经验模态分解和ELM神经网络的逐时太阳能辐照量预测[J]. 电力自动化设备, 2019, 34(8): 7-12.
WANG S X, WANG Y M, LIU Y, et al.Hourly solar radiation forecasting based on EMD and ELM neural network[J]. Electrical power automation equipment, 2019, 34(8): 7-12.
[8] 田翠霞, 黄敏, 朱启兵. 基于EMD-LMD-LSSVM联合模型的逐时太阳辐照度预测[J]. 太阳能学报, 2018, 39(2): 504-512.
TIAN C X, HUANG M, ZHU Q B.Hourly solar irradiance forecast based on EMD-LMD-LSSVM joint model[J]. Acta energiae solaris sinica, 2018, 39(2): 504-512.
[9] 姚海成, 周剑, 林琳, 等. 利用蝙蝠算法优化SVR的太阳辐照度预测方法研究[J]. 可再生能源, 2018, 36(11): 1612-1617.
YAO H C, ZHOU J, LIN L, et al.Solar radiation prediction method using bat algorithm optimized SVR[J]. Renewable energy resources, 2018, 36(11): 1612-1617.
[10] 常建芳. 基于集成学习和卷积神经网络的太阳能辐照度预测方法[D]. 天津: 天津大学, 2018.
CHANG J F.Solar irradiance prediction method based on ensemble learning and convolutional neural network[D]. Tianjin: Tianjin University, 2018.
[11] HINTON G E, SALAKHUTDINOV P R.Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786): 504-507.
[12] CHATURVED I, ONG Y S, TSANG I W, et al.Learning word dependencies in text by means of a deep recurrent belief network[J] . Knowledge-based system, 2016, 108: 144-154.
[13] 国家电网公司. 光伏发电站功率预测技术要求: Q/GDW1998-2013[S].
State Grid Corporation of China. Technical requirements for power prediction of photovoltaic power stations: Q/GDW1998—2013[S].
[14] 张中丹, 李锦键, 王兴贵, 等. 基于静态模型的光热储能电站发电量优化策略[J]. 电力建设, 2019, 40(10): 111-117.
ZHANG Z D, LI J J, WANG X G, et al.Power generation optimization strategy based on static model for concentrating solar power plant[J]. Electric power construction, 2019, 40(10): 111-117.
[15] 乔俊飞, 王功明, 李晓理, 等. 基于自适应学习率的深度信念网设计与应用[J]. 自动化学报, 2017, 43(8): 1339-1349.
QIAO J F, WANG G M, LI X L, et al.Design and application of deep belief network with adaptive learning rate[J]. Acta automatica sinica, 2017, 43(8): 1339-1349.
[16] 田启明, 许和明, 袁亚洲, 等. 光热电站太阳能资源典型年选取方法及验证的探讨[J]. 电力勘测设计, 2020, 8(8): 61-66.
TIAN Q M, XU H M, YUAN Y Z, et al.Discussion on the method selection and verification for typical year of solar energy resources in solar thermal power plant[J]. Electric power survey & design, 2020, 8(8): 61-66.
[17] 张悦, 申彦波, 石广玉. 面向光热发电的太阳能短期预报技术[J]. 电力系统自动化, 2016, 40(19): 158-167.
ZHANG Y, SHEN Y B, SHI G Y.Short-term forecasting technology of solar energy for concentrating solar power[J].Automation of electric power system, 2016, 40(19): 158-167.
[18] 国家气象信息中心. 中国辐射气候标准值年值数据集[EB/OL].(2018-03-01) [2020-07-03]. http://data.cma.cn.
National Meteorological Information Center. China radiation climate standard value annual data set[EB/OL]. (2018-03-01)[2020-07-03]. http://data.cma.cn.
[19] 王功明, 乔俊飞, 关丽娜, 等. 深度信念网络研究现状与展望[J]. 自动化学报, 2021, 47(1): 35-49.
WANG G M, QIAO J F, GUAN L N, et al.Review and prospect on deep belief netwrok[J]. Acta automatica sinica, 2021, 47(1): 35-49.