基于AMBOA-DBN结合相似日的短期光伏功率预测

张程; 林谷青; 黄靖; 匡宇; 刘佳静

doi:10.19912/j.0254-0096.tynxb.2022-0275

PDF(1953 KB)

太阳能学报 ›› 2023, Vol. 44 ›› Issue (6) : 290-299. DOI: 10.19912/j.0254-0096.tynxb.2022-0275

基于AMBOA-DBN结合相似日的短期光伏功率预测

张程^1,2, 林谷青¹, 黄靖^1,2, 匡宇¹, 刘佳静¹

作者信息 +

SHORT-TERM PV POWER PREDICTION BASED ON AMBOA-DBN COMBINED WITH SIMILAR DAYS

Zhang Cheng^1,2, Lin Guqing¹, Huang Jing^1,2, Kuang Yu¹, Liu Jiajing¹

Author information +

文章历史 +

摘要

提出一种综合灰色关联理论的数据挖掘方法选取相似日,运用自适应动态权重的变异蝙蝠算法优化DBN神经网络。首先从历史数据集和预测日数据两方面分析主要影响光伏发电功率的因素,通过在原有模糊灰色关联分析的基础上,引入计算事物各属性发展趋势相似程度为衡量标准的综合灰色关联理论,选取更高相似度的相似日;利用自适应动态权重蝙蝠算法对DBN的权值参数进行优化,以此改进神经网络训练过程中因初始权值选取不当而陷入局部最优或收敛时间过长等问题。建立短期光伏功率预测模型,将此模型与其他预测模型进行对比,实验结果表明该模型更具预测精准性。

Abstract

A data mining method based on grey relational theory was proposed to select similar days, and adaptive dynamic weight variable bat algorithm was used to optimize the parameters of DBN neural network. Firstly, the main factors affecting photovoltaic power generation were analyzed from two aspects of historical data set and predicted date data. On the basis of the original fuzzy grey correlation analysis, the comprehensive grey correlation theory was introduced to calculate the similarity degree of development trend of various attributes of things as the measurement standard to select the similarity day with higher similarity degree. The weight parameters of DBN were optimized by adaptive dynamic weighted bat algorithm in order to improve the neural network training process due to the improper selection of initial weight into local optimal or convergence time is too long. A short-term photovoltaic power prediction model is established. Compared with other prediction models, the experimental results show that this model is more accurate in prediction.

导出引用

张程, 林谷青, 黄靖, 匡宇, 刘佳静. 基于AMBOA-DBN结合相似日的短期光伏功率预测[J]. 太阳能学报. 2023, 44(6): 290-299 https://doi.org/10.19912/j.0254-0096.tynxb.2022-0275

Zhang Cheng, Lin Guqing, Huang Jing, Kuang Yu, Liu Jiajing. SHORT-TERM PV POWER PREDICTION BASED ON AMBOA-DBN COMBINED WITH SIMILAR DAYS[J]. Acta Energiae Solaris Sinica. 2023, 44(6): 290-299 https://doi.org/10.19912/j.0254-0096.tynxb.2022-0275

中图分类号： TM28

参考文献

[1] 陈国平, 李明节, 许涛, 等. 关于新能源发展的技术瓶颈研究[J]. 中国电机工程学报, 2017, 37(1): 20-27.
CHEN G P, LI M J, XU T, et al.Study on technical bottleneck of new energy development[J]. Proceedings of the CSEE, 2017, 37(1): 20-27.
[2] 赵东元, 胡楠, 傅靖, 等. 提升新能源电力系统灵活性的中国实践及发展路径研究[J]. 电力系统保护与控制, 2020, 48(24): 1-8.
ZHAO D Y, HU N, FU J, et al.Research on the practice and road map of enhancing the flexibility of a new generation power system in China[J]. Power system protection and control, 2020, 48(24): 1-8.
[3] JIANG H, DONG Y.Forecast of hourly global horizontal irradiance based on structured Kernel Support Vector Machine: a case study of Tibet area in China[J]. Energy conversion and management, 2017, 142: 307-321.
[4] KÖHLER C, STEINER A, SAINT-DRENAN Y-M, et al. Critical weather situations for renewable energies-Part B: low stratus risk for solar power[J]. Renewable energy, 2017, 101: 794-803.
[5] 李建文, 焦衡, 刘凤梧, 等. 基于相似时段的分时段光伏出力短期预测[J]. 电力自动化设备, 2018, 38(8): 183-188.
LI J W, JIAO H, LIU F W, et al.Short-time segmented photovoltaic output forecasting based on similar period[J]. Electric power automation equipment, 2018, 38(8): 183-188.
[6] 陈中, 宗鹏鹏. 基于样本扩张灰色关联分析的光伏出力预测[J]. 太阳能学报, 2017, 38(11): 2909-2915.
CHEN Z, ZONG P P.PV output forecast based on grey correlation analysis with expanded sample[J]. Acta energiae solaris sinica, 2017, 38(11): 2909-2915.
[7] YUAN T H, ZHU N, SHI Y F, et al.Sample data selection method for improving the prediction accuracy of the heating energy consumption[J]. Energy and buildings, 2018, 158: 234-243.
[8] 耿博, 高贞彦, 白恒远, 等. 结合相似日GA-BP神经网络的光伏发电预测[J]. 电力系统及其自动化学报, 2017, 29(6): 118-123.
GENG B, GAO Z Y, BAI H Y, et al.PV generation forecasting combined with similar days and GA-BP neural network[J]. Proceedings of the CSU-EPSA, 2017, 29(6): 118-123.
[9] 孟安波, 陈嘉铭, 黎湛联, 等. 基于相似日理论和CSO-WGPR的短期光伏发电功率预测[J]. 高电压技术, 2021, 47(4): 1176-1184.
MENG A B, CHEN J M, LI Z L, et al.Short-term photovoltaic power generation prediction based on similar day theory and CSO-WGPR[J]. High voltage engineering, 2021, 47(4): 1176-1184.
[10] 吴云, 雷建文, 鲍丽山, 等. 基于改进灰色关联分析与蝙蝠优化神经网络的短期负荷预测[J]. 电力系统自动化, 2018, 42(20): 67-72.
WU Y, LEI J W, BAO L S, et al.Short-term load forecasting based on improved grey relational analysis and neural network optimized by bat algorithm[J]. Automation of electric power systems, 2018, 42(20): 67-72.
[11] 张彩庆, 郑强. SKBA-LSSVM短期光伏发电功率预测模型[J]. 电力系统及其自动化学报, 2019, 31(8): 86-93.
ZHANG C Q, ZHENG Q.SKBA-LSSVM short-term forecasting model for PV power generation[J]. Proceedings of the CSU-EPSA, 2019, 31(8): 86-93.
[12] 葛磊蛟, 秦羽飞, 刘嘉恒, 等. 基于相似日与BA-WNN的分布式光伏数据虚拟采集方法[J]. 电力自动化设备, 2021, 41(6): 8-16.
GE L J, QIN Y F, LIU J H, et al.Virtual acquisition method of distributed photovoltaic data based on similarity day and BA-WNN[J]. Electric power automation equipment, 2021, 41(6): 8-16.
[13] 李正明, 梁彩霞, 王满商. 基于PSO-DBN神经网络的光伏短期发电出力预测[J]. 电力系统保护与控制, 2020, 48(8): 149-154.
LI Z M, LIANG C X, WANG M S.Short-term power generation output prediction based on a PSO-DBN neural network[J]. Power system protection and control, 2020, 48(8): 149-154.
[14] 许德刚, 赵萍. 蝙蝠算法研究及应用综述[J]. 计算机工程与应用, 2019, 55(15): 1-12.
XU D G, ZHAO P.Literature survey on research and application of bat algorithm[J]. Computer engineering and applications, 2019, 55(15): 1-12.
[15] LIU Q, WU L, XIAO W S, et al.A novel hybrid bat algorithm for solving continuous optimization problems[J]. Applied soft computing, 2018, 73: 67-82.
[16] RIZK-ALLAH R M, HASSANIEN A E. New binary bat algorithm for solving 0-1 knapsack problem[J]. Complex & intelligent systems, 2018, 4(1): 31-53.
[17] THARAKESHWAR T K, SEETHARAMU K N, PRASAD B D.Multi-objective optimization using bat algorithm for shell and tube heat exchangers[J]. Applied thermal engineering, 2017, 110: 1029-1038.
[18] GREWAL N S, RATTAN M, PATTERH M S.A linear antenna array failure correction using improved bat algorithm[J]. International journal of RF and microwave computer-aided engineering, 2017, 27(7): e21119.
[19] BENMAHAMED Y, KHERIF O, TEGUAR M, et al.Accuracy improvement of transformer faults diagnostic based on DGA data using SVM-BA classifier[J]. Energies, 2021, 14(10): 2970.
[20] BANGYAL W H, HAMEED A, AHMAD J, et al.New modified controlled bat algorithm for numerical optimization problem[J]. Materials and continua, 2022, 70(2): 2241-2259.
[21] LIU Q Z, SHEN Y B, WU L, et al.A hybrid FCW-EMD and KF-BA-SVM based model for short-term load forecasting[J]. CSEE journal of power and energy systems, 2018, 4(2): 226-237.
[22] HINTON G E, OSINDERO S, THE YW.A fast learning algorithm for deep beliet nets[J]. Neural computation, 2006, 18(7): 1527-1554.
[23] GU L Y, HUANG J F, YANG L H.On the representational power of restricted boltzmann machines for symmetric functions and boolean functions[J]. IEEE transactions on neural networks and learning systems, 2019, 30(5): 1335-1347.
[24] 张姗, 冬雷, 纪德洋, 等. 基于NWP相似性分析的超短期光伏发电功率预测[J]. 太阳能学报, 2022, 43(4): 142-147.
ZHANG S, DONG L, JI D Y, et al.Power forecasting of ultra-short-term photovoltaic station based on NWP similarity analysis[J]. Acta energiae solaris sinica, 2022, 43(4): 142-147.