基于雨滴侵蚀算法的风电数据清洗及盈余电量制氢分析

郭志勇; 韩巧丽; 魏方正

doi:10.19912/j.0254-0096.tynxb.2024-2056

PDF(1701 KB)

太阳能学报 ›› 2026, Vol. 47 ›› Issue (3) : 430-438. DOI: 10.19912/j.0254-0096.tynxb.2024-2056

基于雨滴侵蚀算法的风电数据清洗及盈余电量制氢分析

郭志勇¹, 韩巧丽², 魏方正¹

作者信息 +

RAINDROP EROSION ALGORITHM FOR WIND POWER DATA CLEANING AND SURPLUS ELECTRICITY FOR HYDROGEN PRODUCTION ANALYSIS

Guo Zhiyong¹, Han Qiaoli², Wei Fangzheng¹

Author information +

文章历史 +

摘要

针对现有风电数据清洗算法在处理风电数据效率较低的问题,提出一种基于雨滴侵蚀算法的数据清洗方法。该算法通过模拟雨滴对地形的冲击和侵蚀过程,有效去除了风电数据中的异常值。实验结果表明,雨滴侵蚀算法的风速与功率的相关性系数达到0.977,在降低数据离散性方面的效果显著,且运行时间为2.1 s。另外,采用雨滴侵蚀算法进行数据清洗后,结合贝叶斯优化的支持向量回归（SVR）模型,拟合了单台风电机组的最佳风功率曲线,并据此计算了调度后的盈余电量。随后,使用质子交换膜（PEM）电解槽和碱性水（ALK）电解槽的仿真模型,对两者利用盈余电量制氢的耗电量进行对比分析。仿真结果表明,PEM电解槽的电耗为39.4 kW·h/kg,ALK电解槽的电耗为53.9 kW·h/kg,PEM电解槽更适合盈余电量制氢。

Abstract

Addressing the inefficiency of existing wind power data cleaning algorithms, a data cleaning method based on the raindrop erosion algorithm is proposed. This algorithm effectively removes outliers from wind power data by simulating the impact and erosion of raindrops on terrain. Experimental results indicate that the correlation coefficient between wind speed and power using the raindrop erosion algorithm reaches 0.977, demonstrating significant effectiveness in reducing data dispersion with a runtime of 2.1 seconds. Additionally, after cleaning the data using the raindrop erosion algorithm, the optimal wind power curve for a single wind turbine is fitted using a support vector regression （SVR） model with Bayesian optimization, from which the scheduled surplus electricity is calculated. Subsequently, simulation models of proton exchange membrane （PEM） electrolyzers and alkaline water （ALK） electrolyzers are used for comparative analysis of electricity consumption for hydrogen production utilizing surplus electricity. Simulation results show that the electricity consumption is 39.4 kW·h/kg for the PEM electrolyzer and 53.9 kW·h/kg for the ALK electrolyzer, suggesting that the PEM electrolyzer is more suitable for hydrogen production from surplus electricity.

导出引用

郭志勇, 韩巧丽, 魏方正. 基于雨滴侵蚀算法的风电数据清洗及盈余电量制氢分析[J]. 太阳能学报. 2026, 47(3): 430-438 https://doi.org/10.19912/j.0254-0096.tynxb.2024-2056

Guo Zhiyong, Han Qiaoli, Wei Fangzheng. RAINDROP EROSION ALGORITHM FOR WIND POWER DATA CLEANING AND SURPLUS ELECTRICITY FOR HYDROGEN PRODUCTION ANALYSIS[J]. Acta Energiae Solaris Sinica. 2026, 47(3): 430-438 https://doi.org/10.19912/j.0254-0096.tynxb.2024-2056

中图分类号： TK81

参考文献

[1] HASSAN Q, VIKTOR P, AL-MUSAWI T J, et al. The renewable energy role in the global energy transformations[J]. Renewable energy focus, 2024, 48: 100545.
[2] ZOU M Z, DJOKIC S Z.A review of approaches for the detection and treatment of outliers in processing wind turbine and wind farm measurements[J]. Energies, 2020, 13(16): 4228.
[3] 胥佳, 李韶武, 王桂松, 等. 基于Change-Point的风电数据挖掘算法研究[J]. 太阳能学报, 2020, 41(5): 136-141.
XU J, LI S W, WANG G S, et al.Wind turbine data mining alogorithm based on Change-Point research[J]. Acta energiae solaris sinica, 2020, 41(5): 136-141.
[4] 章小卫, 苏星宇, 周京华, 等. 可再生能源电解水制氢电源并联方案研究[J]. 太阳能学报, 2025, 46(1): 353-362.
ZHANG X W, SU X Y, ZHOU J H, et al.Research on parallel scheme of hydrogen production from electrolytic water based on renewable energy generation[J]. Acta energiae solaris sinica, 2025, 46(1): 353-362.
[5] 夏杨红, 胡致远, 韦巍, 等. 可再生能源电解制氢宽范围运行控制策略[J]. 太阳能学报, 2024, 45(8): 34-43.
XIA Y H, HU Z Y, WEI W, et al.Wide range operation control strategy for electrolysis hydrogen production based on renewable energy[J]. Acta energiae solaris sinica, 2024, 45(8): 34-43.
[6] YAO Q T, ZHU H W, XIANG L, et al.A novel composed method of cleaning anomy data for improving state prediction of wind turbine[J]. Renewable energy, 2023, 204: 131-140.
[7] HOU G L, WANG J J, FAN Y Z.Wind power forecasting method of large-scale wind turbine clusters based on DBSCAN clustering and an enhanced hunter-prey optimization algorithm[J]. Energy conversion and management, 2024, 307: 118341.
[8] ZHENG L, HU W, MIN Y.Raw wind data preprocessing: a data-mining approach[J]. IEEE transactions on sustainable energy, 2015, 6(1): 11-19.
[9] 黄越辉, 曲凯, 李驰, 等. 基于K均值 MCMC算法的中长期风电时间序列建模方法研究[J]. 电网技术, 2019, 43(7): 2469-2476.
HUANG Y H, QU K, LI C, et al.Research on modeling method of medium-and long-term wind power time series based on K-means MCMC algorithm[J]. Power system technology, 2019, 43(7): 2469-2476.
[10] 夏博, 李春杨, 万露露, 等. 基于深度学习的风力发电机组故障预警方法研究综述[J]. 科学技术与工程, 2023, 23(9): 3577-3587.
XIA B, LI C Y, WAN L L, et al.Review of wind turbine fault warning methods based on deep learning[J]. Science technology and engineering, 2023, 23(9): 3577-3587.
[11] WANG P, LI Y T, ZHANG G Y.Probabilistic power curve estimation based on meteorological factors and density LSTM[J]. Energy, 2023, 269: 126768.
[12] PANDIT R, INFIELD D, SANTOS M.Accounting for environmental conditions in data-driven wind turbine power models[J]. IEEE transactions on sustainable energy, 2023, 14(1): 168-177.
[13] ZHANG Y G, KONG X, WANG J C, et al.Wind power forecasting system with data enhancement and algorithm improvement[J]. Renewable and sustainable energy reviews, 2024, 196: 114349.
[14] CHEN S, XIAO Y X, ZHANG C Y, et al.Cost dynamics of onshore wind energy in the context of China’s carbon neutrality target[J]. Environmental science and ecotechnology, 2024, 19: 100323.
[15] CANBULAT S, BALCI K, CANBULAT O, et al.Techno-economic analysis of on-site energy storage units to mitigate wind energy curtailment: a case study in Scotland[J]. Energies, 2021, 14(6): 1691.
[16] NADALETI W C, DOS SANTOS G B, LOURENÇO V A. Integration of renewable energies using the surplus capacity of wind farms to generate H₂ and electricity in Brazil and in the Rio Grande do Sul state: energy planning and avoided emissions within a circular economy[J]. International journal of hydrogen energy, 2020, 45(46): 24190-24202.
[17] CHEN H, CHEN J C, HAN G Y, et al.Winding down the wind power curtailment in China: What made the difference?[J]. Renewable and sustainable energy reviews, 2022, 167: 112725.
[18] NASCIMENTO DA SILVA G, ROCHEDO P R R, SZKLO A. Renewable hydrogen production to deal with wind power surpluses and mitigate carbon dioxide emissions from oil refineries[J]. Applied energy, 2022, 311: 118631.
[19] REN Y, JIN K Y, GONG C L, et al.Modelling and capacity allocation optimization of a combined pumped storage/wind/photovoltaic/hydrogen production system based on the consumption of surplus wind and photovoltaics and reduction of hydrogen production cost[J]. Energy conversion and management, 2023, 296: 117662.
[20] ROGA S, BARDHAN S, KUMAR Y, et al.Recent technology and challenges of wind energy generation: a review[J]. Sustainable energy technologies and assessments, 2022, 52: 102239.
[21] 刘国永, 任永峰, 薛宇, 等. 基于PEM电解槽的风氢耦合系统能量管理研究[J]. 太阳能学报, 2024, 45(7): 240-248.
LIU G Y, REN Y F, XUE Y, et al.Research on energy management of wind-hydrogen coupling system based on PEM electrolyzer[J]. Acta energiae solaris sinica, 2024, 45(7): 240-248.
[22] HUYGHUES-BEAUFOND N, TINDEMANS S, FALUGI P, et al.Robust and automatic data cleansing method for short-term load forecasting of distribution feeders[J]. Applied energy, 2020, 261: 114405.
[23] QIN S G, LIU D S.Distribution characteristics of wind speed relative volatility and its influence on output power[J]. Journal of marine science and engineering, 2023, 11(5): 967.
[24] WANG Y J, WANG J D, CAO M, et al.Prediction method of wind farm power generation capacity based on feature clustering and correlation analysis[J]. Electric power systems research, 2022, 212: 108634.
[25] LISO V, SAVOIA G, ARAYA S S, et al.Modelling and experimental analysis of a polymer electrolyte membrane water electrolysis cell at different operating temperatures[J]. Energies, 2018, 11(12): 3273.
[26] MO J K, KANG Z Y, YANG G Q, et al.Thin liquid/gas diffusion layers for high-efficiency hydrogen production from water splitting[J]. Applied energy, 2016, 177: 817-822.
[27] STEWART K, LAIR L, DE LA TORRE B, et al. Modeling and optimization of an alkaline water electrolysis for hydrogen production[C]//2021 IEEE Green Energy and Smart Systems Conference (IGESSC). Long Beach, CA, USA, 2021: 1-6.
[28] XIONG X, ZOU R L, SHENG T, et al.An ultra-short-term wind speed correction method based on the fluctuation characteristics of wind speed[J]. Energy, 2023, 283: 129012.