Multi-Objective Optimization Design of Micro-Site Selection of Complex Terrain Wind Farms Assisted by Proxy Model

doi:10.16183/j.cnki.jsjtu.2023.486

Abstract

Abstract:

To tackle the challenges of high difficulty and time-consuming micro-site optimization of wind farms in complex terrains, a multi-objective optimization method for micro-site selection is proposed, assisted by proxy model. First, considering the geographical features of complex terrains with significent undulations, the ruggedness index is calculated and the ground flatness is numerically quantified, constraining the points with excessive ruggedness. Then, a mathematical model for three-dimensional windy downward wake superposition calculation of power generation is established, a three-dimensional terrain collector line topology optimization agent model is constructed, and the prediction accuracy of the proxy model is verified, demonstrating the ability to replace numerous calculations in collector line topology optimization and effectively improving the computing efficiency. Finally, taking a real complex terrain wind farm in Xinjiang Uygur Autonomous Region, China as an example, multi-objective micro-site selection of complex terrain wind farm is realized, and the results are compared with those obtained through the single-objective optimization. The simulation results show that the multi-objective discrete state transfer algorithm assisted by the proxy model can reduce the total cable laying length, decrease the construction costs, and provide more feasible layout schemes while optimizing the annual power generation.

Key words: wind farms, microscopic situation, complex terrain, multi-objective optimization algorithm, terrain ruggedness index (TRI), proxy model

CLC Number:

TK81

LIU Jiahui, WANG Cong, ZHANG Hongli, MA Ping, LI Xinkai, DONG Yingchao. Multi-Objective Optimization Design of Micro-Site Selection of Complex Terrain Wind Farms Assisted by Proxy Model[J]. Journal of Shanghai Jiao Tong University, 2025, 59(9): 1315-1326.

Figures/Tables 18

Fig.1

Tab.1

Fig.2

Fig.3

Fig.4

Fig.5

Fig.6

Tab.2

Tab.3

Tab.4

Fig.7

Fig.8

Tab.5

Tab.6

Fig.9

Fig.10

Fig.11

Tab.7

References 21

[1]	ANTONINI E G A, ROMERO D A, AMON C H. Optimal design of wind farms in complex terrains using computational fluid dynamics and adjoint methods[J]. Applied Energy, 2020, 261: 114426.
[2]	YANG K, KWAK G, CHO K, et al. Wind farm layout optimization for wake effect uniformity[J]. Energy, 2019, 183: 983-995. doi: 10.1016/j.energy.2019.07.019
[3]	刘永前, 邵振州, 颜灵伟, 等. 基于改进二进制萤火虫算法的风电场微观选址优化研究[J]. 可再生能源, 2019, 37(1): 112-118.
	LIU Yongqian, SHAO Zhenzhou, YAN Lingwei, et al. Optimization research of wind farm micro-sitting based on improved binary firefly algorithm[J]. Renewable Energy Resources, 2019, 37(1): 112-118.
[4]	王洁, 许昌, 韩星星, 等. 基于风力机尾流排斥的平坦地形风电场微观选址优化[J]. 电力系统自动化, 2020, 44(15): 62-69.
	WANG Jie, XU Chang, HAN Xingxing, et al. Micro-siting optimization of wind farm in flat terrain based on wind turbine wake repellency[J]. Automation of Electric Power Systems, 2020, 44(15): 62-69.
[5]	PÉREZ-ARACIL J, CASILLAS-PÉREZ D, JIMÉNEZ-FERNÁNDEZ S, et al. A versatile multi-method ensemble for wind farm layout optimization[J]. Journal of Wind Engineering and Industrial Aerodynamics, 2022, 225: 104991.
[6]	FENG J, SHEN W Z. Solving the wind farm layout optimization problem using random search algorithm[J]. Renewable Energy, 2015, 78: 182-192.
[7]	FENG J, SHEN W, LI Y. An optimization framework for wind farm design in complex terrain[J]. Applied Sciences, 2018, 8(11): 2053.
[8]	HU W, YANG Q, CHEN H P, et al. A novel approach for wind farm micro-siting in complex terrain based on an improved genetic algorithm[J]. Energy, 2022, 251: 123970.
[9]	唐程辉, 张凡, 张宁, 等. 基于风电场总功率条件分布的电力系统经济调度二次规划方法[J]. 电工技术学报, 2019, 34(10): 2069-2078.
	TANG Chenghui, ZHANG Fan, ZHANG Ning, et al. Quadratic programming for power system economic dispatch based on the conditional probability distribution of wind farms sum power[J]. Transactions of China Electrotechnical Society, 2019, 34(10): 2069-2078.
[10]	盛四清, 范林涛, 李兴, 等. 基于帕累托最优的配电网多目标规划[J]. 电力系统自动化, 2014, 38(15): 51-57.
	SHENG Siqing, FAN Lintao, LI Xing, et al. Multi-objective planning of distribution network based on Pareto optimality[J]. Automation of Electric Power Systems, 2014, 38(15): 51-57.
[11]	RILEY S J, DEGLORIA S D, ELLIOT R. Index that quantifies topographic heterogeneity[J]. Intermountain Journal of Sciences, 1999, 5(1-4): 23-27.
[12]	董颖超, 张宏立, 王聪. 带有策略自适应的状态转移算法[J]. 控制与决策, 2022, 37(3): 574-582.
	DONG Yingchao, ZHANG Hongli, WANG Cong. State transition algorithm with strategy adaptation[J]. Control and Decision, 2022, 37(3): 574-582.
[13]	周晓君, 阳春华, 桂卫华. 状态转移算法原理与应用[J]. 自动化学报, 2020, 46(11): 2260-2274.
	ZHOU Xiaojun, YANG Chunhua, GUI Weihua. The principle of state transition algorithm and its applications[J]. Acta Automatica Sinica, 2020, 46(11): 2260-2274.
[14]	余佳英, 张宏立, 董颖超. 基于离散状态转移算法的无等待流水车间调度研究[J]. 系统仿真学报, 2023, 35(5): 1034-1045. doi: 10.16182/j.issn1004731x.joss.22-0048
	YU Jiaying, ZHANG Hongli, DONG Yingchao, et al. Research on no-wait flow shop scheduling based on discrete state transition algorithm[J]. Journal of System Simulation, 2023, 35(5): 1034-1045. doi: 10.16182/j.issn1004731x.joss.22-0048
[15]	董天雪, 阳春华, 周晓君, 等. 一种求解企业员工指派问题的离散状态转移算法[J]. 控制理论与应用, 2016, 33(10): 1378-1388.
	DONG Tianxue, YANG Chunhua, ZHOU Xiaojun, et al. A novel discrete state transition algorithm for staff assignment problem[J]. Control Theory & Applications, 2016, 33(10): 1378-1388.
[16]	LI W, HAN J, LI Y, et al. Optimal sensor placement method for wastewater treatment plants based on discrete multi-objective state transition algorithm[J]. Journal of Environmental Management, 2022, 307: 114491.
[17]	HAO J, YANG X, WANG C, et al. An improved NSGA-II algorithm based on adaptive weighting and searching strategy[J]. Applied Sciences, 2022, 12(22): 11573.
[18]	HAN J, YANG C, LIM C C, et al. Power scheduling optimization under single-valued neutrosophic uncertainty[J]. Neurocomputing, 2020, 382: 12-20.
[19]	WEN Y, SONG M, WANG J. Wind farm layout optimization with uncertain wind condition[J]. Energy Conversion and Management, 2022, 256: 115347.
[20]	REDDY S R. Wind farm layout optimization (Wind FLO): An advanced framework for fast wind farm analysis and optimization[J]. Applied energy, 2020, 269: 115090.
[21]	王凯, 许昌, 韩星星, 等. 基于边界适应和风电场间影响的海上风电场微观选址优化研究[J]. 可再生能源, 2022, 40(4): 481-486.
	WANG Kai, XU Chang, HAN Xingxing, et al. Micro-siting optimization of offshore wind farms based on boundary adaptation and inter-wind farm impacts[J]. Renewable Energy Resources, 2022, 40(4): 481-486.

总样本比例区间	训练样本数量
0.7N	0.85S_tot
0.7N~0.8N	S_ave
0.8N~0.85N	0.85S_tot
0.85N~0.95N	S_ave
0.95N~N	S_ave

θ/(°)	k(θ)	c(θ)	θ/(°)
348.75~11.25	1.408 0	3.443 4	168.75~191.25	1.680 8	4.373 5
11.25~33.75	1.487 7	4.565 9	191.25~213.75	2.068 9	5.402 1
33.75~56.25	1.889 4	7.708 3	213.75~236.25	2.075 9	7.570 5
56.25~78.75	1.938 7	9.582 5	236.25~258.75	2.148 1	9.534 0
78.75~101.25	1.650 7	8.176 7	258.75~281.25	2.156 2	9.634 1
101.25~123.75	1.633 6	5.648 9	281.25~303.75	1.783 7	9.853 7
123.75~146.25	1.296 1	5.513 1	303.75~326.25	1.571 9	7.066 4
146.25~168.75	1.360 9	5.789 3	326.25~348.75	1.497 2	3.481 6

参数	取值
轮毂高度/m	110
叶轮直径/m	191
切入风速/(m·s^-1)	2.5
切出风速/(m·s^-1)	20
额定风速/(m·s^-1)	8.9

DSTA	DMOSTA
S_e=10	S'_e=5
M_xit=50	G_ner=20
m_a=1 000	T=5
m_b=1	N=75
m_c=1	m_a=1 000
	m_b=1
	m_c=1

方案	A_EP/(MW·h)	L/m
01	359 385.69	183 673.16
02	359 403.80	196 050.94
03	359 295.61	166 408.48
04	358 277.44	117 050.69
05	359 174.25	152 501.29
06	358 482.79	122 395.84
07	359 093.88	135 843.85
08	358 503.18	128 507.61
09	359 279.34	158 308.29
10	359 316.02	181 074.42