Electrical Power Output Prediction of Combined Cycle Power Station

doi:10.12096/j.2096-4528.pgt.22046

Abstract

Abstract:

In order to maximize the profit of a combined cycle power plant, it is important to accurately predict its full load power output. When a combined cycle power plant operates, the exhaust gas produced by the previous stage is used to drive the next stage heat engine to drive the generator, and its full-load electrical output is affected by ambient temperature, atmospheric pressure, relative humidity and exhaust pressure. Firstly, the kernel principle component analysis (KPCA) was used to perform feature combination dimensionality reduction for power generation related features to complete feature extraction. Then, the extreme gradient boosting algorithm (XGBoost) was used to score feature importance and the optimal feature subset was obtained by forward selection (FS). Finally, a KPCA-XGB-FS model was constructed for the prediction of hourly power output under full load of combined cycle power plants. By experimenting with real data from a combined power station and comparing with existing research methods using the same data, it is found that the method proposed in this paper can effectively predict the power output, and is better than the existing research methods.

Key words: combined cycle power plant, electrical power output, feature extraction, kernel principle component analysis (KPCA), forward selection

CLC Number:

TK 01

Daijun CHEN, Lili CHEN, Yangtao LI. Electrical Power Output Prediction of Combined Cycle Power Station[J]. Power Generation Technology, 2024, 45(1): 99-105.

Figures/Tables 7

References 23

1	孙喜春．关于发展燃气-蒸汽联合循环发电的探讨[J]．企业技术开发，2013，32(14)：93-94．
	SUN X C ．Discussion on the development of gas-steam combined cycle power generation[J]．Technological Development of Enterprise，2013，32(14)：93-94．
2	张全斌，周琼芳．基于“双碳”目标的中国火力发电技术发展路径研究[J]．发电技术，2023，44(2)：143-154． doi:10.12096/j.2096-4528.pgt.22092
	ZHANG Q B， ZHOU Q F ．Research on the development path of China’s thermal power generation technology based on the goal of “carbon peak and carbon neutralization”[J]．Power Generation Technology，2023，44(2)：143-154． doi:10.12096/j.2096-4528.pgt.22092
3	刘兰华，王瑞林，洪慧．塔式太阳能辅助燃气蒸汽联合循环钙基碳捕集系统设计[J]．发电技术，2021，42(4)：517-524． doi:10.12096/j.2096-4528.pgt.21081
	LIU L H， WANG R L， HONG H ．Design of calcium-based carbon capture system for gas-steam combined cycle assisted by solar thermal tower[J]．Power Generation Technology，2021，42(4)：517-524． doi:10.12096/j.2096-4528.pgt.21081
4	张治忠，陈继平，谭学谦，等．天然气联合循环电厂燃烧后CO₂捕集一体化技术经济评价[J]．南方能源建设，2023，10(2)：55-61． doi:10.16516/j.gedi.issn2095-8676.2023.02.008
	ZHANG Z Z， CHEN J P， TAN X Q，et al ．Economic evaluation of post-combustion CO₂ capture integration technology in natural gas combined cycle power plant[J]．Southern Energy Construction，2021，42(2)：403-409． doi:10.16516/j.gedi.issn2095-8676.2023.02.008
5	成珂，孙琦琦，马晓瑶．基于主成分回归分析的气象因子对光伏发电量的影响[J]．太阳能学报，2021， 42(2)：403-409． doi:10.19912/j.0254-0096.tynxb.2018-0933
	CHENG K， SUN Q Q， MA X Y ．Influence of meteorological factors on photovoltaic power generation based on principal component regression analysis[J]．Acta Energiae Solaris Sinica，2021，42(2)：403-409． doi:10.19912/j.0254-0096.tynxb.2018-0933
6	仲仕晶，赵书杰．多因素耦合对光伏发电性能影响的实验研究[J]．科学技术与工程，2020，20(7)：2727-2732．
	ZHONG S J， ZHAO S J ．Experimental study on the effect of multi-factor coupling on photovoltaic power generation performance[J]．Science Technology and Engineering，2020，20(7)：2727-2732．
7	张玉，莫寒，张烈平．基于模糊支持向量机的光伏发电量预测[J]. 热力发电，2017，46(1)：116-120． doi:10.3969/j.issn.1002-3364.2017.01.116
	ZHANG Y， MO H， ZHANG L P ．Prediction of photovoltaic power generation based on fuzzy support vector machine[J]．Thermal Power Generation，2017， 46(1)：116-120． doi:10.3969/j.issn.1002-3364.2017.01.116
8	陈国栋，罗素芹，刘文斌，等．基于改进相似日的光伏系统日发电量预测[J]．照明工程学报，2018，29(3)：115-119． doi:10.3969/j.issn.1004-440X.2018.03.023
	CHEN G D， LUO S Q， LIU W B，et al ．Daily power generation forecast of photovoltaic system based on improved similar days[J]．China Illuminating Engineering Journal，2018，29(3)：115-119． doi:10.3969/j.issn.1004-440X.2018.03.023
9	赵亮，刘友波，余莉娜，等．基于深度信念网络的光伏电站短期发电量预测[J]．电力系统保护与控制，2019，47(18)：11-19.
	ZHAO L， LIU Y B， YU L N，et al ．Short-term power generation forecast of photovoltaic power station based on deep belief network[J]．Power System Protection and Control，2019，47(18)：11-19.
10	周灵杰，李博彤，汪鸿，等．基于改进神经网络和能量守恒法的热电联产机组发电量计算[J]．热力发电，2020，49(1)：70-77． doi:10.19666/j.rlfd.201907183
	ZHOU L J， LI B T， WANG H，et al ．Calculation of power generation of cogeneration units based on improved neural network and energy conservation method[J]．Thermal Power Generation，2020，49(1)：70-77． doi:10.19666/j.rlfd.201907183
11	张成，白建波，兰康，等．基于数据挖掘和遗传小波神经网络的光伏电站发电量预测[J]．太阳能学报，2021，42(3)：375-382． doi:10.19912/j.0254-0096.tynxb.2019-0867
	ZHANG C， BAI J B， LAN K，et al ．Prediction of photovoltaic power plant power generation based on data mining and genetic wavelet neural network[J]．Acta Energiae Solaris Sinica，2021，42(3)：375-382． doi:10.19912/j.0254-0096.tynxb.2019-0867
12	黄树帮，陈耀，金宇清．碳中和背景下多通道特征组合超短期风电功率预测[J]．发电技术，2021，42(1)：60-68． doi:10.12096/j.2096-4528.pgt.20103
	HUANG S B， CHEN Y， JIN Y Q ．Ultra-short-term wind power prediction with multi-channel feature combination under carbon neutrality[J]．Power Generation Technology，2021，42(1)：60-68． doi:10.12096/j.2096-4528.pgt.20103
13	朱芳．基于KPCA与混合蛙跳算法的并网光伏电站发电量预测模型研究[J]．可再生能源，2018，36(2)：236-240． doi:10.3969/j.issn.1671-5292.2018.02.012
	ZHU F ．Research on power generation forecast model of grid-connected photovoltaic power station based on KPCA and hybrid leapfrog algorithm[J]．Renewable Energy Resources，2018，36(2)：236-240． doi:10.3969/j.issn.1671-5292.2018.02.012
14	梁胜杰，张志华，崔立林．主成分分析法与核主成分分析法在机械噪声数据降维中的应用比较[J]．中国机械工程，2011，22(1)：80-83．
	LIANG S J， ZHANG Z H， CUI L L ．Application comparison of principal component analysis method and kernel principal component analysis method in dimension reduction of mechanical noise data[J]．China Mechanical Engineering，2011，22(1)：80-83．
15	郭廷华，赵帅．基于KPCA-WOA-KELM的岩爆烈度预测[J]．河北工程大学学报(自然科学版)，2021，38(2)：1-7．
	GUO T H， ZHAO S ．Rockburst intensity prediction based on KPCA-WOA-KELM[J]．Journal of Hebei University of Engineering (Natural Science Edition)，2021，38(2)：1-7．
16	ANOWAR F， SADAOUI S， SELIM B ．Conceptual and empirical comparison of dimensionality reduction algorithms (PCA，KPCA，LDA，MDS，SVD，LLE，ISOMAP，LE，ICA，t-SNE)[J]．Computer Science Review，2021，40：100378． doi:10.1016/j.cosrev.2021.100378
17	HARIS M J， GANESH B C， GOWRI S M ．Performance analysis of dimensionality reduction using PCA，KPCA and LLE for ECG signals[C]//IOP Conference Series：Materials Science and Engineering．Strasbourg，France：IOP，2021：1084-1092． doi:10.1088/1757-899x/1084/1/012005
18	YONG X， DAVID Z， FENGXI S，et al ．A method for speeding up feature extraction based on KPCA[J]．Neurocomputing，2006，70(4)：1056-1061． doi:10.1016/j.neucom.2006.09.005
19	吴彤，高彩霞，付子义．基于改进EEMD、KPCA与RBF结合的变负载下滚动轴承故障程度识别[J]．制造业自动化，2018，40(8)：63-67． doi:10.3969/j.issn.1009-0134.2018.08.017
	WU T，GAO C X，FU Z Y，Fault degree identification of rolling bearing under variable load based on the combination of improved EEMD，KPCA and RBF[J]．Manufacturing Automation，2018，40(8)：63-67． doi:10.3969/j.issn.1009-0134.2018.08.017
20	史佳琪，张建华．基于多模型融合Stacking集成学习方式的负荷预测方法[J]．中国电机工程学报，2019，39(14)：4032-4042． doi:10.13334/j.0258-8013.pcsee.181510
	SHI J Q， ZHANG J H ．Load forecasting method based on multi-model fusion stacking ensemble learning method[J]．Proceedings of the CSEE，2019，39(14)：4032-4042． doi:10.13334/j.0258-8013.pcsee.181510
21	朱江行，邹晓松，熊炜，等．基于Prophet与XGBoost混合模型的短期负荷预测[J]．现代电力，2021，38(3)：325-331． doi:10.19725/j.cnki.1007-2322.2020.0321
	ZHU J X， ZOU X S， XIONG W，et al ．Short-term load forecasting based on Prophet and XGBoost hybrid model[J]．Modern Electric Power，2021，38(3)：325-331． doi:10.19725/j.cnki.1007-2322.2020.0321
22	王桂兰，赵洪山，米增强．XGBoost算法在风机主轴承故障预测中的应用[J]．电力自动化设备，2019，39(1)：73-77． doi:10.16081/j.issn.1006-6047.2019.01.011
	WANG G L， ZHAO H S， MI Z Q ．Application of XGBoost algorithm in fault prediction of fan main bearing[J]．Electric Power Automation Equipment，2019，39(1)：73-77． doi:10.16081/j.issn.1006-6047.2019.01.011
23	TÜFEKCI P ．Prediction of full load electrical power output of a base load operated combined cycle power plant using machine learning methods[J]．International Journal of Electrical Power & Energy Systems，2014，60：126-140． doi:10.1016/j.ijepes.2014.02.027

统计值	AT/℃	V/kPa	AP/kPa	RH/%	EP/MW
平均值	19.65	72.23	101.326	73.31	454.37
方差	7.45	16.90	0.594	14.60	17.07
最小值	1.81	33.73	99.289	25.56	420.26
最大值	37.11	108.47	103.330	100.16	495.76

统计值	AT/℃	V/kPa	AP/kPa	RH/%	EP/MW
平均值	19.65	72.23	101.326	73.31	454.37
方差	7.45	16.90	0.594	14.60	17.07
最小值	1.81	33.73	99.289	25.56	420.26
最大值	37.11	108.47	103.330	100.16	495.76

方法	MAE	RMSE	MAPE	ME
文献[23]	2.818	3.787	—	—
原始特征+XGBoost	2.252	3.086	0.497%	-0.019
KPCA-XGB-FS	2.021	2.846	0.446%	-0.02

方法	MAE	RMSE	MAPE	ME
文献[23]	2.818	3.787	—	—
原始特征+XGBoost	2.252	3.086	0.497%	-0.019
KPCA-XGB-FS	2.021	2.846	0.446%	-0.02

[1]	Guangde DONG, Daoming LI, Yongtao CHEN, Xing MA, Ang FU, Gang MU, Bai XIAO. Power Quality Disturbance Classification Method Based on Particle Swarm Optimization and Convolutional Neural Network [J]. Power Generation Technology, 2023, 44(1): 136-142.
[2]	Shangnian CHEN, Luping LI, Shihai ZHANG, Minnan OUYANG, Ang FAN, Xiankui WEN. Research Progress of Vibration Fault Diagnosis Technology for Steam Turbine Generator Sets [J]. Power Generation Technology, 2021, 42(4): 489-499.
[3]	Lingxing LU,Honglu ZHU,Weiwei LIAN,Songyuan DAI,Jianxi YAO. Application of FCM Method in Data Division of Photovoltaic Array Fault Samples [J]. Power Generation Technology, 2018, 39(2): 188-194.