基于多重联合概率与改进加权HMM的风电功率预测方法

师洪涛; 李艺萱; 丁茂生; 高峰; 李希彬; 何竹

doi:10.19912/j.0254-0096.tynxb.2022-1055

PDF(1953 KB)

太阳能学报 ›› 2023, Vol. 44 ›› Issue (11) : 247-254. DOI: 10.19912/j.0254-0096.tynxb.2022-1055

基于多重联合概率与改进加权HMM的风电功率预测方法

师洪涛, 李艺萱, 丁茂生, 高峰, 李希彬, 何竹

作者信息 +

WIND POWER PREDICTION METHOD BASED ON MULTIPLE JOINT PROBABILITY AND IMPROVED WEIGHTED HMM

Shi Hongtao, Li Yixuan, Ding Maosheng, Gao Feng, Li Xibin, He Zhu

Author information +

文章历史 +

摘要

为解决传统风电功率预测中气象因素与功率数据结合应用时相互约束性不足且风电功率序列的历史时序信息随时间逐步衰减的问题,提出一种基于多重联合概率与改进加权隐马尔可夫模型（HMM）的风电功率预测方法。首先,提出多重联合概率方法将数值天气预报（NWP）中的气象因素进行逐步联合,并改进HMM中的释放概率,使NWP气象数据与功率时间序列融合以互相约束;然后,采用条件熵改进粗糙集以计算多步预测的合理属性权重,加权运算多步预测值,以获得风电功率预测值;最后,经过风电场实际算例验证,通过将NWP数据与功率数据相互融合、互相约束,可有效地提高风电功率预测精度。

Abstract

Solving the poor constraint of combining meteorological factors data with power data and the decay of historical time series information of wind power in traditional wind power prediction, a wind power prediction method based on multiple joint probabilities and improved weighted Hidden Markov Model （HMM） is proposed in this paper. Meteorological factors in Numerical Weather Prediction （NWP） are combined by multiple joint probability firstly. Subsequently, the NWP data and the power time series are fused by improving the release probabilities in the HMM to constrain each other. Then, the multi-step predicted values are weighted by the conditional entropy improved rough set with improved conditional entropy, and obtain the final wind power prediction results. Finally, the wind power prediction accuracy can be effectively improved by fusing and confining NWP data and power data with each other, as verified by actual arithmetic cases in wind farms.

导出引用

师洪涛, 李艺萱, 丁茂生, 高峰, 李希彬, 何竹. 基于多重联合概率与改进加权HMM的风电功率预测方法[J]. 太阳能学报. 2023, 44(11): 247-254 https://doi.org/10.19912/j.0254-0096.tynxb.2022-1055

Shi Hongtao, Li Yixuan, Ding Maosheng, Gao Feng, Li Xibin, He Zhu. WIND POWER PREDICTION METHOD BASED ON MULTIPLE JOINT PROBABILITY AND IMPROVED WEIGHTED HMM[J]. Acta Energiae Solaris Sinica. 2023, 44(11): 247-254 https://doi.org/10.19912/j.0254-0096.tynxb.2022-1055

中图分类号： TM615

参考文献

[1] 占颖, 吴琛, 谢小荣, 等. 风电并网系统次同步振荡的频域模式分析[J]. 电力系统自动化, 2020, 44(18): 90-97.
ZHAN Y, WU C, XIE X R, et al.Frequency domain modal analysis of subsynchronous oscillation in grid-connected wind power system[J]. Automation of electric power system, 2020, 44(18): 90-97.
[2] 王勃, 刘纯, 冯双磊, 等. 基于集群划分的短期风电功率预测方法[J]. 高电压技术, 2018, 44(4): 1254-1260.
WANG B, LIU C, FENG S L, et al.Prediction method for short-term wind power based on wind farm clusters[J]. High voltage engineering, 2018, 44(4): 1254-1260.
[3] 王伟胜, 王铮, 董存, 等. 中国短期风电功率预测技术现状与误差分析[J]. 电力系统自动化, 2021, 45(1):17-27.
WANG W S, WANG Z, DONG C, et al.Status and error analysis of short-term forecasting technology of wind power in China[J]. Automation of electric power system, 2021, 45(1): 17-27.
[4] 王勃, 刘纯, 张俊, 等. 基于Monte-Carlo方法的风电功率预测不确定性估计[J]. 高电压技术, 2015, 41(10): 3385-3391.
WANG B, LIU C, ZHANG J, et al.Uncertainty estimation of wind power prediction based on Monte-Carlo method[J]. High voltage engineering, 2015, 41(10): 3385-3391.
[5] 王铮, 刘纯, 冯双磊, 等. 基于非参数回归的风电场理论功率计算方法[J]. 电网技术, 2015, 39(8): 2148-2153.
WANG Z, LIU C, FENG S L, et al.The wind farm theoretical power calculation method research based on non-parameter regression[J]. Power system technology , 2015, 39(8): 2148-2153.
[6] 王勃, 冯双磊, 刘纯. 基于天气分型的风电功率预测方法[J]. 电网技术, 2014, 38(1): 93-98.
WANG B, FENG S L, LIU C.Study on weather typing based wind power prediction[J]. Power system technology , 2014, 38(1): 93-98.
[7] 王铮, 冯双磊, 申宏, 等. 基于加权系数动态修正的短期风电功率组合预测方法[J]. 电网技术, 2017, 41(2): 500-507.
WANG Z, FENG S L,SHEN H,et al.Short-term wind power combination forecasting method based on dynamic coefficient updating[J]. Power system technology, 2017, 41(2): 500-507.
[8] 王钊, 王伟胜, 刘纯, 等. 风电功率的特征近邻搜索概率预测方法[J]. 电网技术, 2022, 46(3): 880-887.
WANG Z, WANG W S, LIU C, et al.Probabilistic forecast of wind power based on nearest neighbor feature searching[J]. Power system technology, 2022,46(3): 880-887.
[9] 李卓, 叶林, 戴斌华, 等. 基于IDSCNN-AM-LSTM组合神经网络超短期风电功率预测方法[J]. 高电压技术, 2022, 48(6): 2117-2127.
LI Z, YE L, DAI B H, et al.Ultra-short-term wind power prediction method based on IDSCNN-AM-LSTM combined neural network[J]. High voltage engineering, 2022, 48(6): 2117-2127.
[10] 谢丽蓉, 王斌, 包洪印, 等. 基于EEMD-WOA-LSSVM的超短期风电功率预测[J]. 太阳能学报, 2021, 42(7): 290-296.
XIE L R, WANG B, BAO H Y, et al.Super-short-term wind power forecasting based on EEMD-WOA-LSSVM[J].Acta energiae solaris sinica, 2021, 42(7): 290-296.
[11] 赵冬梅, 杜刚, 刘鑫, 等. 基于时序分解及机器学习的风电功率组合预测模型[J]. 现代电力, 2022, 39(1): 9-18.
ZHAO D M, DU G, LIU X, et al.Wind power combination prediction model based on time series decomposition and machine learning[J]. Modern electric power, 2022, 39(1): 9-18.
[12] 梁志峰, 王铮, 冯双磊, 等. 基于波动规律挖掘的风电功率超短期预测方法[J]. 电网技术, 2020, 44(11): 4096-4104.
LIANG Z F, WANG Z, FENG S L, et al.Ultra-short-term forecasting method of wind power based on fluctuation law mining[J]. Power system technology, 2020, 44(11): 4096-4104.
[13] SHI J, DING Z H, LEE W J, et al.Hybrid forecasting model for very-short term wind power forecasting based on grey relational analysis and wind speed distribution features[J]. IEEE transactions on smart grid, 2014, 5(1): 521-526.
[14] LI D, YAN W, LI W Y, et al.A two-tier wind power time series model considering day-to-day weather transition and intraday wind power fluctuations[J]. IEEE transactions on power systems, 2016, 31(6): 4330-4339.
[15] WANG S X, ZHANG N, WU L, et al.Wind speed forecasting based on the hybrid ensemble empirical mode decomposition and GA-BP neural network method[J]. Renewable energy, 2016, 94: 629-636.
[16] 师洪涛, 杨静玲, 丁茂生, 等. 基于小波-BP神经网络的短期风电功率预测方法[J]. 电力系统自动化, 2011, 35(16): 44-48.
SHI H T, YANG J L, DING M S, et al.A short-term wind power prediction method based on wavelet decomposition and BP neural network[J]. Automation of electric power systems, 2011, 35(16): 44-48.
[17] SASSER C, YU M, DELGADO R.Improvement of wind power prediction from meteorological characterization with machine learning models[J]. Renewable energy, 2022, 183: 491-501.
[18] 师洪涛, 李梓鑫, 丁茂生, 等. 基于WP风向趋变特性与决策树的风电功率预测[J]. 现代电子技术, 2021, 44(23): 175-179.
SHI H T, LI Z X, DING M S, et al.Wind power prediction based on WP-based wind direction trend changing characteristics and decision tree[J]. Modern electronic technique, 2021, 44(23): 175-179.
[19] 高天霁. 基于多因素数据特征提取与组合的风电功率短期预测方法研究[D]. 银川: 北方民族大学, 2021.
GAO T J.Research on short-term wind power forecasting method based on feature extraction and combination of multi-factor data[D]. Yinchuan: Northern University for Nationalities, 2021.
[20] FU C, LI G Q, LIN K P, et al.Short-term wind power prediction based on improved chicken algorithm optimization support vector machine[J]. Sustainability, 2019, 11(2): 512.
[21] LIU Y, SHI J, YANG Y, et al.Short-term wind-power prediction based on wavelet transform-support vector machine and statistic-characteristics analysis[J]. IEEE transactions on industry applications, 2012, 48(4): 1136-1141.
[22] ZHENG L, ZHOU B, OR S W, et al.Spatio-temporal wind speed prediction of multiple wind farms using capsule network[J]. Renewable energy, 2021, 175: 718-730.
[23] 张颖超, 王雅晨, 邓华, 等. 基于IAFSA-BPNN的短期风电功率预测[J]. 电力系统保护与控制, 2017, 45(7): 58-63.
ZHANG Y C, WANG Y C, DENG H, et al.IAFSA-BPNN for wind power probabilistic forecasting[J]. Power system protection and control, 2017, 45(7): 58-63.
[24] 顾东红. 基于空间相关性的风电功率预测研究[D]. 沈阳: 沈阳工业大学, 2020.
GU D H.Research on wind power prediction based on spatial correlation[D]. Shenyang: Shenyang University of Technology, 2020.
[25] 闫佳. 基于多维聚类及马尔可夫链组合模型的风电功率短期预测方法研究[D]. 银川: 北方民族大学, 2021.
YAN J.Research on short-term forecasting method of wind power based on multi-dimensional clustering and markov chain combination model[D]. Yinchuan: Northern University for Nationalities, 2021.
[26] CHEN S, YE L, ZHANG G W, et al.Short-term wind power prediction based on combined grey-Markov model[C]//2011 International Conference on Advanced Power System Automation and Protection, Beijing, China, 2011.
[27] 宋家康, 彭勇刚, 蔡宏达, 等. 考虑多位置NWP和非典型特征的短期风电功率预测研究[J]. 电网技术, 2018, 42(10): 3234-3240.
SONG J K, PENG Y G, CAI H D, et al.Research of short-term wind power forecasting considering multi-location NWP and uncanonical feature[J]. Power system technology, 2018, 42(10): 3234-3240.
[28] 杨辉明, 雷勇. 基于改进马尔科夫链的风电日前不确定性建模方法[J]. 南方电网技术, 2021, 15(7): 54-60.
YANG H M, LEI Y.Day-ahead uncertainty simulation method of wind power based on improved Markov chain[J]. Southern power system technology, 2021, 15(7): 54-60.
[29] 孙荣富, 张涛, 和青, 等. 风电功率预测关键技术及应用综述[J]. 高电压技术, 2021, 47(4): 1129-1143.
SUN R F, ZHANG T, HE Q, et al.Review on key technologies and applications in wind power forecasting[J].High voltage engineering, 2021, 47(4): 1129-1143.
[30] 刘晓宇. 基于隐马尔可夫链的风电功率短期预测研究[D]. 呼和浩特: 内蒙古大学, 2018.
LIU X Y.Wind power prediction based on hidden Markov chain[D]. Huhhot: Inner Mongolia University, 2018.
[31] 张俊峰, 薛青, 王常琳, 等. 基于粗糙集的指挥决策仿真可信性评估方法[J]. 计算机仿真, 2020, 37(7): 14-19.
ZHANG J F, XUE Q, WANG C L, et al.Credibility evaluation method of command decision-making simulation based on rough sets[J]. Computer simulation, 2020, 37(7): 14-19.
[32] 闫晓龙. 基于多尺度熵的加权HMM网络安全态势预测方法研究[D]. 长沙: 湖南大学, 2016.
YAN X L.Research on weighted hmm network security situation prediction method based on multi-scale entropy[D]. Changsha: Hunan University, 2016.
[33] 樊昌信. 通信原理[M]. 7版. 北京: 国防工业出版社, 2012: 11-12.
FAN C X, Principles of communication[M]. 7th ed. Beijing: National Defense Industry Press, 2012: 11-12.
[34] 莫文雄, 白剑锋, 朱文, 等. 基于风速风向联合概率的输电线路漂浮物故障风险评估[J]. 高电压技术, 2018, 44(4): 1085-1092.
MO W X, BAI J F, ZHU W, et al.Risk assessment of transmission lines trip-out caused by floaters based on joint probability density function of extreme wind speed and direction[J]. High voltage engineering, 2018, 44(4): 1085-1092.
[35] 陈隽, 赵旭东. 总体样本风速风向联合概率分析方法[J]. 防灾减灾工程学报, 2009, 29(1): 63-70.
CHEN J, ZHAO X D.Analytical method of joint probability density function of wind speed and direction from parent population[J]. Journal of disaster prevention and mitigation engineering, 2009, 29(1): 63-70.
[36] 熊菊霞, 吴尽昭, 王秋红. 邻域互信息熵的混合型数据决策代价属性约简[J]. 小型微型计算机系统, 2021, 42(8): 1584-1590.
XIONG J X, WU J Z, WANG Q H.Decision cost attribute reduction of hybrid data based on neighborhood mutual information entropy[J]. Journal of Chinese computer systems, 2021, 42(8): 1584-1590.