基于卷积门控循环单元的波浪发电系统输出功率预测

吴凡曈; 杨俊华; 杨梦丽; 林炳骏; 梁惠溉; 邱达磊

doi:10.19912/j.0254-0096.tynxb.2023-0641

PDF(1121 KB)

太阳能学报 ›› 2024, Vol. 45 ›› Issue (8) : 682-688. DOI: 10.19912/j.0254-0096.tynxb.2023-0641

基于卷积门控循环单元的波浪发电系统输出功率预测

吴凡曈¹, 杨俊华¹, 杨梦丽², 林炳骏¹, 梁惠溉¹, 邱达磊¹

作者信息 +

OUTPUT POWER PREDICTION OF WAVE POWER GENERATION SYSTEM BASED ON CONVOLUTIONAL GATED CYCLIC UNIT

Wu Fantong¹, Yang Junhua¹, Yang Mengli², Lin Bingjun¹, Liang Huigai¹, Qiu Dalei¹

Author information +

文章历史 +

摘要

为高效准确预测波浪输出功率,提出卷积神经网络和门控循环单元混合模型波浪预测算法。采用间接预测方法,搭建直驱式波浪发电系统模型,运用CORREL函数分析不同波浪特征的相关性,结合卷积神经网络提取特征与高维空间中的波高关系,构造特征向量,通过门控循环单元网络进行训练,将全连接层的输出值经反归一化后获得预测波高值,输入所搭建模型,获得波浪输出功率预测值。仿真结果表明,与其他网络模型相比,在多特征输入情况下,混合模型波浪预测算法预测效率更高、精度更准确。

Abstract

In order to predict the wave output power efficiently and accurately, a mixture model of convolutional neural network and gated cyclic unit is proposed. The indirect prediction method is used to build a direct drive wave power generation system model, and CORREL function is used to analyze the correlation of different wave characteristics. Combining convolutional neural network to extract the relationship between characteristics and wave height in high-dimensional space, feature vectors are constructed. Through the gated cycle unit network for training, the output value of the full connection layer is inversely normalized to obtain the predicted wave height value. Input the built model to obtain the prediction value of wave output power. The simulation results show that the wave prediction algorithm of the mixture model is more efficient and accurate than that of other network models in the case of multiple feature inputs.

导出引用

吴凡曈, 杨俊华, 杨梦丽, 林炳骏, 梁惠溉, 邱达磊. 基于卷积门控循环单元的波浪发电系统输出功率预测[J]. 太阳能学报. 2024, 45(8): 682-688 https://doi.org/10.19912/j.0254-0096.tynxb.2023-0641

Wu Fantong, Yang Junhua, Yang Mengli, Lin Bingjun, Liang Huigai, Qiu Dalei. OUTPUT POWER PREDICTION OF WAVE POWER GENERATION SYSTEM BASED ON CONVOLUTIONAL GATED CYCLIC UNIT[J]. Acta Energiae Solaris Sinica. 2024, 45(8): 682-688 https://doi.org/10.19912/j.0254-0096.tynxb.2023-0641

中图分类号： TM619

参考文献

[1] 肖曦, 摆念宗, 康庆, 等. 波浪发电系统发展及直驱式波浪发电系统研究综述[J]. 电工技术学报, 2014, 29(3): 1-11.
XIAO X, BAI N Z, KANG Q, et al.A review of the development of wave power system and the research on direct-drive wave power system[J]. Transactions of China Electrotechnical Society, 2014, 29(3): 1-11.
[2] MCARTHUR S, BREKKEN T K A. Ocean wave power data generation for grid integration studies[C]//IEEE PES General Meeting. Minneapolis, MN, USA, 2010: 1-6.
[3] 熊锋俊, 杨俊华, 沈辉, 等. 基于纵横交叉算法的波浪发电装置最大功率跟踪控制[J]. 电测与仪表, 2019, 56(8): 124-130, 143.
XIONG F J, YANG J H, SHEN H, et al.The maximum power point tracking control based on crisscross optimization algorithm for wave power generation[J]. Electrical measurement & instrumentation, 2019, 56(8): 124-130, 143.
[4] 刘春元, 余海涛, 胡敏强, 等. 永磁直线发电机在直驱式波浪发电系统的应用[J]. 中国电机工程学报, 2013, 33(21): 90-98, 197.
LIU C Y, YU H T, HU M Q, et al.Application of permanent magnet tubular linear generators using direct-driver wave power generation take-off systems[J]. Proceedings of the CSEE, 2013, 33(21): 90-98, 197.
[5] 霍政界, 吴峰, 陶爱峰, 等. 直驱式波浪发电系统输出功率的短期预测[J]. 电力系统自动化, 2014, 38(21): 13-18.
HUO Z J, WU F, TAO A F, et al.Short-term prediction on output power of direct-drive wave power generation system[J]. Automation of electric power systems, 2014, 38(21): 13-18.
[6] 黄宝洲, 杨俊华, 卢思灵, 等. 基于改进粒子群优化神经网络算法的波浪捕获功率预测[J]. 太阳能学报, 2021, 42(2): 302-308.
HUANG B Z, YANG J H, LU S L, et al.Wave capture power forecasting based on improved particle swarm optimization neural network algorithm[J]. Acta energiae solaris sinica, 2021, 42(2): 302-308.
[7] 王丽婕, 廖晓钟, 高阳, 等. 风电场发电功率的建模和预测研究综述[J]. 电力系统保护与控制, 2009, 37(13): 118-121.
WANG L J, LIAO X Z, GAO Y, et al.Summarization of modeling and prediction of wind power generation[J]. Power system protection and control, 2009, 37(13): 118-121.
[8] 金权, 华锋, 杨永增. 基于SVM的海浪要素预测试验研究[J]. 海洋科学进展, 2019, 37(2): 199-209.
JIN Q, HUA F, YANG Y Z.Prediction of the significant wave height based on the support vector machine[J]. Advances in marine science, 2019, 37(2): 199-209.
[9] 栗然, 马涛, 张潇, 等. 基于卷积长短期记忆神经网络的短期风功率预测[J]. 太阳能学报, 2021, 42(6): 304-311.
LI R, MA T, ZHANG X, et al.Short-term wind power prediction based on convolutional long-short-term memory neural networks[J]. Acta energiae solaris sinica, 2021, 42(6): 304-311.
[10] YAN Y, WU J Q, CAO Y F, et al.An open-circuit fault diagnosis method for three-level neutral point clamped inverters based on multi-scale shuffled convolutional neural network[J]. Sensors, 2024, 24(6): 1745.
[11] CHOI H, PARK M, SON G, et al.Real-time significant wave height estimation from raw ocean images based on 2D and 3D deep neural networks[J]. Ocean engineering, 2020, 201: 107129.
[12] NIU Z W, YU Z Y, TANG W H, et al.Wind power forecasting using attention-based gated recurrent unit network[J]. Energy, 2020, 196: 117081.
[13] 潘海鹏, 丁海波, 雷美珍, 等. 基于遗传算法的直驱式海浪发电系统最大功率跟踪控制[J]. 太阳能学报, 2021, 42(3): 221-227.
PAN H P, DING H B, LEI M Z, et al.Maximum power tracking control of direct drive ocean wave power generation system based on genetic algorithm[J]. Acta energiae solaris sinica, 2021, 42(3): 221-227.
[14] SADEGHIFAR T, NOURI MOTLAGH M, TORABI AZAD M, et al.Coastal wave height prediction using recurrent neural networks (RNNs) in the south caspian sea[J]. Marine geodesy, 2017, 40(6): 454-465.
[15] FAN S T, XIAO N H, DONG S.A novel model to predict significant wave height based on long short-term memory network[J]. Ocean engineering, 2020, 205: 107298.
[16] LI X F, CAO J F, GUO J H, et al.Multi-step forecasting of ocean wave height using gate recurrent unit networks with multivariate time series[J]. Ocean engineering, 2022, 248: 110689.
[17] YANG S B, DENG Z G, LI X F, et al.A novel hybrid model based on STL decomposition and one-dimensional convolutional neural networks with positional encoding for significant wave height forecast[J]. Renewable energy, 2021, 173: 531-543.
[18] 毕贵红, 赵鑫, 李璐, 等. 双模式分解CNN-LSTM集成的短期风速预测模型[J]. 太阳能学报, 2023, 44(3): 191-197.
BI G H, ZHAO X, LI L, et al.Dual-mode decomposition CNN-LSTM integrated short-term wind speed forecasting model[J]. Acta energiae solaris sinica, 2023, 44(3): 191-197.
[19] 姚程文, 杨苹, 刘泽健. 基于CNN-GRU混合神经网络的负荷预测方法[J]. 电网技术, 2020, 44(9): 3416-3424.
YAO C W, YANG P, LIU Z J.Load forecasting method based on CNN-GRU hybrid neural network[J]. Power system technology, 2020, 44(9): 3416-3424.
[20] 盛松伟, 游亚戈, 张亚群, 等. 一种点吸收式波浪能装置水动力学研究[J]. 太阳能学报, 2013, 34(8): 1443-1449.
SHENG S W, YOU Y G, ZHANG Y Q, et al.Study of hydrodynamics of point-absorbing wave-energy device[J]. Acta energiae solaris sinica, 2013, 34(8): 1443-1449.
[21] 林巧梅, 杨俊华, 蔡浩然, 等. 基于滑模控制的直驱式波浪发电系统MPPT控制策略[J]. 电测与仪表, 2018, 55(10): 90-95.
LIN Q M, YANG J H, CAI H R, et al.MPPT algorithm for direct-drive wave power generation system based on sliding mode control[J]. Electrical measurement & instrumentation, 2018, 55(10): 90-95.
[22] 鲍明昱, 熊建嘉, 崔铭芳, 等. 某单井站场管道积液及腐蚀特性研究[J]. 中国安全生产科学技术, 2021, 17(7): 60-64.
BAO M Y, XIONG J J, CUI M F, et al.Study on liquid accumulation and corrosion characteristics of pipelines in a single well station[J]. Journal of safety science and technology, 2021, 17(7): 60-64.