A NEW METHOD OF WIND SPEED PREDICTION BASED ON COMPLEX NETWORK

Zhang Dongji; Xiao Qin

doi:10.19912/j.0254-0096.tynxb.2021-1215

PDF(1852 KB)

Acta Energiae Solaris Sinica ›› 2023, Vol. 44 ›› Issue (3) : 90-96. DOI: 10.19912/j.0254-0096.tynxb.2021-1215

A NEW METHOD OF WIND SPEED PREDICTION BASED ON COMPLEX NETWORK

Zhang Dongji, Xiao Qin

Author information +

History +

Abstract

Wind speed prediction is widely concerned in wind power industry because of its wide application in wind power generation. In order to predict wind speed more accurately, a new method is proposed in this paper. First, the visibility graph is used to map the wind speed series to a directed weighted network, the similarity matrix of nodes in the network is determined by calculating the similarity of neighbor time nodes and combining the shortest path method, then on the basis of the node similarity analysis of directed weighted network, the adjacent prediction method and linear approximation method are combined to predict. In the prediction experiment, the applicability and predictability of this method are illustrated by comparing the errors with other models. This method can predict wind speed more accurately and provide reference for power system operation.

Key words

wind speed / complex network / time series analysis / visibility graph / shortest path / node similarity

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

Zhang Dongji, Xiao Qin. A NEW METHOD OF WIND SPEED PREDICTION BASED ON COMPLEX NETWORK[J]. Acta Energiae Solaris Sinica. 2023, 44(3): 90-96 https://doi.org/10.19912/j.0254-0096.tynxb.2021-1215

References

[1] 袁如意. 基于深度学习的股票预测分析[J]. 中国集体经济, 2021(24): 105-106.
YUAN R Y.Stock prediction analysis based on deep learning[J]. China’s collective economy, 2021(24): 105-106.
[2] 高学金, 马东阳, 韩华云, 等. 基于DAE和TCN的复杂工业过程故障预测[J]. 仪器仪表学报, 2021, 42(6): 140-151.
GAO X J, MA D Y, HAN H Y, et al.Fault prediction of complex industrial process based on DAE and TCN[J]. Chinese journal of scientific instrument, 2021, 42(6): 140-151.
[3] NOH B, PARK H, YEO H.Analyzing vehicle pedestrian interactions combining data cube structure and predictive collision risk estimation model[J]. Accident analysis & prevention, 2022, 165: 106539.
[4] 杨洪玖, 鞠爽, 张金会, 等. 基于因果逻辑关系的耦合系统预测云控制[J]. 控制工程, 2021(8): 1-7.
YANG H J, JU S, ZHANG J H, et al.Predictive cloud control of coupled systems based on causal logic[J]. Control engineering of China, 2021(8): 1-7.
[5] 王旭. 几类随机系数整值时间序列模型的统计分析[D]. 长春: 吉林大学, 2020.
WANG X.Statistical analysis of several kinds of random coefficient integer-valued time series models[D]. Changchun: Jilin University, 2020.
[6] 王红珂, 刘啸天, 林磊, 等. 机器学习在材料服役性能预测中的应用[J]. 装备环境工程, 2021(8): 1-18.
WANG H K, LIU X T, LIN L, et al.Application of machine learning in prediction of material service performance[J]. Equipment environmental engineering, 2021(8): 1-18.
[7] LIMA V, DELLAJUSTINA F J, SHIMOURA R O, et al.Granger causality in the frequency domain: derivation and applications[J]. Revista brasileira de ensino de física, 2020, 42: e20200007.
[8] STAVROGLOU S K, ANTELOUS A A, STANLEY H E, et al.Hidden interactions in financial markets[J]. Proceedings of the National Academy of Sciences of the United States of America, 2019, 116(22): 10646-10651.
[9] TAVASOLI A, HENRY T, SHAKERI H.A purely data-driven framework for prediction, optimization, and control of networked processes: application to networked SIS epidemic model[J]. arXiv: 2108. 02005
[10] DEVI D R, SASIKALA S. Online feature selection (OFS) with accelerated bat algorithm (ABA) andensemble incremental deep multiple layer perceptron (EIDMLP) for big data streams[J]. Journal of big data, 2019, 6: 103: https://doi.org/ro.1186/SAO537-019-02673.
[11] 赵慧敏, 房才华, 邓武, 等. 基于智能优化方法的SVM电机故障诊断模型研究[J]. 大连交通大学学报, 2016, 37(1): 92-96.
ZHAO H M, FANG C H, WU D, et al.Research on motor fault diagnosis model for support vector machine based on intelligent optimization methods[J]. Journal of Dalian Jiaotong University, 2016, 37(1): 92-96.
[12] 孙浩, 陶建峰, 余宏淦, 等. 基于高斯过程的阀控非对称液压缸模型预测控制[J]. 液压与气动, 2021, 45(8): 26-33.
SUN H, TAO J F, YU H G, et al.Model predictive control of valve-controlled asymmetric hydraulic cylinder based on gaussian process[J]. Chinese hydraulics & pneumatics, 2021, 45(8): 26-33.
[13] 吴奉亮, 霍源, 高佳南. 基于随机森林回归的煤矿瓦斯涌出量预测方法[J]. 工矿自动化, 2021(8): 1-7.
WU F L, HUO Y, GAO J N.Prediction method of coal mine gas emission based on random forest regression[J]. Industrial and mining automation, 2021(8): 1-7.
[14] 王志建, 张炜健, 刘士杰. 基于EMD-GRU循环神经网络的转向交通流量组合预测[J]. 工业控制计算机, 2020, 33(12): 73-76.
WANG J W, ZHANG Y J, LIU S J.Combination prediction of steering traffic flow based on EMD-GRU recurrent neural network[J]. Industrial control computer, 2020, 33(12): 73-76.
[15] 曾春, 武新乾. 含非参数趋势的残差MA模型的预测方法[J]. 洛阳师范学院学报, 2019, 38(5): 1-5.
ZENG C, WU X Q.Prediction methods of residual MA models with nonparametric trends[J]. Journal of Luoyang Normal University, 2019, 38(5): 1-5.
[16] 隋宗震, 王秋潇, 贾丹桐, 等. 基于AR模型与贝叶斯优化的SVM的结构损伤识别研究[J]. 低温建筑技术, 2020, 42(12): 74-76.
SUI Z Z, WANG Q X, JIA D T, et al.Research on structural damage identification of SVM based on AR model and bayesian optimization[J]. Low temperature architecture technology, 2020, 42(12): 74-76.
[17] ALKHUZAI K A. Sastic data generation technique using autoregressive moving average (ARMA) model[J]. Innovative systems design and engineering, 2019, 10(1): 10.7176/IS-DE.
[18] 汤斐斐. 安徽省卫生人力资源预测——基于非季节性霍尔特指数法的研究[J]. 中国农村卫生事业管理, 2019, 39(5): 333-337.
TANG F F.Prediction of health human resources in Anhui province——a study based on the non-seasonal holt index method[J]. China’s rural health service administration,2019, 39(5): 333-337.
[19] EARNEST A, EVANS S M, SAMPURNO F, et al.Forecasting annual incidence and mortality rate for prostate cancer in Australia until 2022 using autoregressive integrated moving average (ARIMA) models[J]. BMJ open, 2019, 9(8): 031331.
[20] 张群, 唐振浩, 王恭. 基于长短时记忆网络的超短期风功率预测模型[J]. 太阳能学报, 2021, 42(10): 275-281.
ZHANG Q, TANG Z H, WANG G.Ultra-short-term wind power prediction model based on long-short-term memory network[J]. Acta energiae solaris sinica, 2021, 42(10): 275-281.
[21] 刘擘龙, 张宏立, 王聪. 基于序列到序列和注意力机制的超短期风速预测[J]. 太阳能学报, 2021, 42(9): 286-294.
LIU B L, ZHANG H L, WANG C.Ultra-short-term wind speed prediction based on sequence-to-sequence and attention mechanism[J]. Acta energiae solaris sinica, 2021, 42(9): 286-294.
[22] CHEN G G, TANG B R, ZENG X J, et al.Short-term wind speed forecasting based on long short-term memory and improved BP neuralnetwork[J]. International journal of electrical power and energy systems, 2021, 134: 107365.
[23] 杜宝祥, 李永利, 马志强, 等. 多特征嵌入的Seq2Seq风速预测模型[J]. 计算机工程与设计, 2021, 42(7): 2061-2068.
DU B X, LI Y L, MA Z Q, et al.Seq2Seq wind speed prediction model with multi-feature embedding[J]. Computer engineering and design, 2021, 42(7): 2061-2068.
[24] FOTSO H R F, KAZÉ C VA, DJUIDJE K G. A novel hybrid model based on weather variables relationships improving applied for wind speed forecasting[J]. International journal of energy and environmental engineering, 2022(13): 43-56.
[25] WANG Y, ZHU C A, ZHAO J H, et al.Short-term time wind speed forecasting based on spatio-temporal geostatistical approach and kriging method[J]. International journal of pattern recognition and artificial intelligence, 2021, 35(7): 2159025.
[26] LACASA L, LUQUE B, LUQUE J, et al.The visibility graph: a new method for estimating the Hurst exponent of fractional Brownian motion[J]. Europhys lett, 2009, 86(3): 30001-30005.
[27] FENG Q X, WEI H P, HU J, et al.Analysis of the attention to COVID-19 epidemic based on visibility graph network[J]. Modern physics letters B, 2021, 35(19): 2150316.
[28] ZHU X Y, MA Y H, LIU Z Y.A novel evolutionary algorithm on communities detection in signed networks[J]. Physica A, 2018, 503: S0378437118310550.
[29] MUTUA S, GU C G, YANG H J, et al.Visibility graphlet approach to chaotic time series[J]. Chaos, 2016, 26(5): 53107-53107.
[30] SYMEONIDIS P, TIAKAS E.Titive node similarity: predicting and recommending links in signed social networks[J]. World wide web, 2014, 17(4): 743-776.
[31] MAO S Z, XIAO F Y.A novel method for forecasting construction cost index based on complex network[J]. Physica A: Statistical mechanics and its applications, 2019, 527: 121306.
[32] 郑凤, 李长俊. 线性逼近法在管网系统优化运行中的应用[J]. 天然气与石油, 2007(3): 27-29.
ZHNEG F, LI C J.Application of linear approximation method in optimal operation of pipe network system[J]. Natural gas and oil, 2007(3): 27-29.
[33] 王志浩, 孙先波. 基于遗传算法优化BP神经网络的风速预测[J]. 电力设备管理, 2020(8): 128-130.
WANG Z H, SUN X B.Wind speed prediction based on genetic algorithm optimizing BP neural network[J]. Electric power equipment management, 2020(8): 128-130.
[34] JANANK T,MANDALAPU S D,DAVE D J.Vehicle classification using the convolution neural network approach[J]. Scientific Journal of Silesian University of Technology(series transport), 2021, 112: 136-190.