Power Optimization of Floating Offshore Wind Farm Based on Surrogate-assisted Standard Particle Swarm Algorithm

被引：0

作者：

Song D. ^{[1
]}

Shen X. ^{[1
]}

Huang C. ^{[1
]}

Yang J. ^{[1
]}

Dong M. ^{[1
]}

Liu J. ^{[2
]}

Li Q. ^{[2
]}

机构：

[1] School of Automation, Central South University, Hunan Province, Changsha

[2] Institute of Engineering Thermophysics, Chinese Academy of Sciences, Haidian District, Beijing

来源：

Zhongguo Dianji Gongcheng Xuebao/Proceedings of the Chinese Society of Electrical Engineering | 2023年 / 43卷

基金：

中国国家自然科学基金;

关键词：

floating offshore wind farm; power optimization; standard particle swarm optimization algorithm; surrogate model; wake effect;

D O I：

10.13334/j.0258-8013.pcsee.231328

中图分类号：

学科分类号：

摘要：

A surrogate-assisted improved standard particle swarm optimization (PSO) algorithm is proposed to solve the power optimization problem of floating wind farm. First, local and global surrogate models are constructed using data generated from an improved PSO algorithm during the optimization process. Second, the local surrogate model is utilized to search for the optimal solution in the local design space and generate particle decision values, while the global surrogate model to screen out inferior candidate solutions in the population and generate particle tag values. Finally, the PSO algorithm updates its position and calculates its objective function value with the assistance of the generated decision values and tag values, improving the optimization efficiency. Simulation results on a floating wind farm with 18 wind turbines indicate that the proposed method can significantly improve the steady state output power of the wind farm under wind directions with severe wake effects, and has smaller time cost and better power optimization performance than conventional intelligent algorithms and numerical solution methods. ©2023 Chin.Soc.for Elec.Eng.

引用

页码：217 / 228

页数：11

共 27 条

[1]

YANG Jian, HUANG Chaoneng, SONG Dongran, Et al., Distributed optimization method for operation power of large-scale offshore wind farm based on two-step processing, Automation of Electric Power Systems, 47, 7, pp. 94-104, (2023)

[2]

BARTHELMIE R J, HANSEN K, FRANDSEN S T, Et al., Modelling and measuring flow and wind turbine wakes in large wind farms offshore[J], Wind Energy, 12, 5, pp. 431-444, (2009)

[3]

MUNTERS W, MEYERS J., Dynamic strategies for yaw and induction control of wind farms based on large-eddy simulation and optimization, Energies, 11, 1, (2018)

[4]

PARK J, LAW K H., Cooperative wind turbine control for maximizing wind farm power using sequential convex programming[J], Energy Conversion and Management, 101, pp. 295-316, (2015)

[5]

GU Bo, ZHANG Yang, REN Yan, Et al., Wake distribution calculation and optimization control method for wind farms, Automation of Electric Power Systems, 41, 18, pp. 124-129, (2017)

[6]

XIE Jingjie, DONG Hongyang, ZHAO Xiaowei, Et al., Wind farm power generation control via double-network-based deep reinforcement learning, IEEE Transactions on Industrial Informatics, 18, 4, pp. 2321-2330, (2022)

[7]

DONG Hongyang, ZHAO Xiaowei, Data-driven wind farm control via multiplayer deep reinforcement learning [J], IEEE Transactions on Control Systems Technology, 31, 3, pp. 1468-1475, (2023)

[8]

DONG Hongyang, ZHANG Jincheng, ZHAO Xiaowei, Intelligent wind farm control via deep reinforcement learning and high-fidelity simulations [J], Applied Energy, 292, (2021)

[9]

PADULLAPARTHI V R, NAGARATHINAM S, VASAN A, Et al., FALCON- farm level control for wind turbines using multi-agent deep reinforcement learning [J], Renewable Energy, 181, pp. 445-456, (2022)

[10]

SONG Ziqiu, FENG Hanyu, YU Zhaoguo, Et al., Coordinated control of semi-submersible floating turbine with model predictive control strategy [J], Proceedings of the CSEE, 42, 12, pp. 4330-4338, (2022)

← 1 2 3 →