Deep neural network modeling on power curve based on multivariable selection

Abstract

Abstract:

A wind turbine power curve can reflect the generating capacity of a unit. Power curve modeling based on historical data is significant to the operation and management of wind farms.The partial least squares (PLS) method is introduced to analyze the correlation between multiple variables and output power of units on data layer. The crossvalidity principle and the variable importance in projection (VIP) are used in dimension reduction screening for multiple variables.The subset of optimal variables is used as the input to the deep neural network (DNN), from which the DNN model of the power curve is obtained. Taking the data of a wind turbine in an Anhui wind farm as an example, the effectiveness of the proposed method is verified by comparing it with other modeling methods.

Key words:

font-size: 10.5pt, mso-spacerun: 'yes', mso-font-kerning: 1.0000pt">wind turbine, power curve, partial least squares, DNN, wind farm, dimension reduction screeningfont-size: 10.5pt, mso-spacerun: 'yes', mso-font-kerning: 1.0000pt">

XIE Jiaying，GUO Peng.

Deep neural network modeling on power curve based on multivariable selection [J]. Huadian Technology, 2019, 41(8): 27-31.

[1]	WANG Kangping, ZHANG Xingke, LIU Caihua, SHEN Xicheng, ZHOU Xia. Reactive power and voltage control strategy based on adaptive droop control for wind power plants [J]. Integrated Intelligent Energy, 2022, 44(4): 12-19.
[2]	YANG Mingming. Wind speed correction for wind turbine based on convolutional neural network [J]. Huadian Technology, 2021, 43(5): 75-79.
[3]	CHEN Hongyan，TANG Zhiguo，CHEN Qi，WANG Yongxu，WU Luming. Optimized method on distributed reactive power compensation in lowvoltage distribution network based on interval power flow calculation [J]. Huadian Technology, 2020, 42(6): 1-5.
[4]	WANG Lijie，WANG Hongteng，SUN Bo. Operation region partition for hydraulic turbine generator units based on stability test data [J]. Huadian Technology, 2020, 42(6): 6-9.
[5]	WU Luming，XUE Mingjun，CHEN Qi，WANG Yongxu，TANG Zhiguo，CHEN Hongyan1,2. 一起电子互感器异常引发的复杂发展性故障分析及改进 [J]. Huadian Technology, 2020, 42(6): 10-15.
[6]	NIU Ben. Water quality control technology for circulating cooling water taking soft water as source [J]. Huadian Technology, 2020, 42(6): 16-21.
[7]	SHANG Liyang，FAN Suxiang，ZHANG Zhiyong，YU Penghui，HE Yong，JI Yanru. Design and application of intelligent algaeblocking equipment for water conveyance main canal [J]. Huadian Technology, 2020, 42(6): 22-24.
[8]	ZHANG Hailong，YANG Guangrui，JING Xinjing，XING Leqiang，LIU Chao，DANG Lijun. Research on energysaving optimization for mediumspeed mill pulverizing systems [J]. Huadian Technology, 2020, 42(6): 25-30.
[9]	WANG Yunpeng,DUAN Xiaoyun. Retrofit and combustion adjustment of a lownitrogen burner in a 330MW cogeneration unit [J]. Huadian Technology, 2020, 42(6): 35-42.
[10]	SHAO Lei，PAN Guangqiang，ZHANG Yuquan，CHU Hao，CAO Wei. Application of acoustic blockage removal technique applied in urea pyrolysis furnaces [J]. Huadian Technology, 2020, 42(6): 43-46.
[11]	WANG Zhiyong，XU He，ZHU Huimin，GE Junpei，XU Jing. Comparative analysis of calculation models for thermal efficiencies of waste heat boilers in gassteam combined cycle units [J]. Huadian Technology, 2020, 42(6): 47-51.
[12]	WANG Dongzhen，GE Leijiao. Optimization strategy of multiple output cables samephase parallel operation for gas turbine generators [J]. Huadian Technology, 2020, 42(6): 52-56.
[13]	GAO Yong，TIAN Xin，WU Yinchen. Evaluation of prefilter improvement effect of gas turbine air intake filtration system [J]. Huadian Technology, 2020, 42(6): 57-61.
[14]	XING Wu，GUO Xiao，WANG Zhe，SHI Bolun. Application of parameter identification principle in the protection of magnetic shunt reactor [J]. Huadian Technology, 2020, 42(6): 47-51.
[15]	WU Siming，TONG Jialin，WU Yueseng，QI Yong，SUN Wuyi. Comprehensive upgrading reconstruction and performance analysis of a subcritical boiler [J]. Huadian Technology, 2020, 42(6): 66-71.

Deep neural network modeling on power curve based on multivariable selection

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics

Comments