基于MADRL算法的海上風(fēng)電場(chǎng)功率與載荷聯(lián)合優(yōu)化
趙偉康,張宇琪,唐淵
(湖南工業(yè)大學(xué) 交通與電氣工程學(xué)院,湖南 株洲 412007)
摘 要 :針對(duì)海上風(fēng)電場(chǎng)尾流損失明顯和疲勞損耗分布不均勻?qū)е嘛L(fēng)電場(chǎng)維護(hù)頻率高的問(wèn)題,提出了一種基于多智能體深度強(qiáng)化學(xué)習(xí) (MADRL) 的風(fēng)電場(chǎng)控制策略。通過(guò)分析風(fēng)機(jī)的發(fā)電功率與疲勞載荷, 建立發(fā)電量與疲勞損耗的衡量模型,明確控制變量與狀態(tài)變量 ;再根據(jù)風(fēng)機(jī)之間的氣動(dòng)耦合關(guān)系進(jìn)行分組,構(gòu)建MADRL優(yōu)化控制框架,將全部風(fēng)機(jī)之間的合作轉(zhuǎn)變?yōu)榻M內(nèi)合作加組間合作模式。在WFSim風(fēng)電場(chǎng)模型中采用MADRL算法進(jìn)行多目標(biāo)優(yōu)化求解,結(jié)果表明,所提策略能在風(fēng)況變化的情況下有效減輕尾 流效應(yīng)帶來(lái)的影響,在提升風(fēng)電場(chǎng)整體發(fā)電效率的同時(shí)平衡機(jī)組間的疲勞損耗。
關(guān)鍵詞 : 海上風(fēng)電場(chǎng) ;尾流效應(yīng) ;多智能體深度強(qiáng)化學(xué)習(xí) ;疲勞損耗 ;發(fā)電效率
中圖分類(lèi)號(hào) :TM614 ;TM714 文獻(xiàn)標(biāo)識(shí)碼 :A 文章編號(hào) :1007-3175(2025)12-0009-07
Joint Optimization of Power and Load in Offshore Wind Farms Based on MADRL Algorithm
ZHAO Wei-kang, ZHANG Yu-qi, TANG Yuan
(School of Traffic and Electrical Engineering, Hunan University of Technology, Zhuzhou 412007, China)
Abstract: To address the high maintenance frequency of offshore wind farms caused by significant wake losses and uneven fatigue damage distribution, a wind farm control strategy based on multi-agent deep reinforcement learning (MADRL) is proposed. By analyzing the relationship between turbine power generation and fatigue loads, a measurement model linking power output and fatigue damage is established to define control variables and state variables. Wind turbines are grouped based on aerodynamic coupling relationships, establishing a MADRL optimization control framework that transforms inter-turbine cooperation into a hybrid model of intra-group and inter-group collaboration. Multi-objective optimization using the MADRL algorithm is performed within the WFSim wind farm model. Results demonstrate that the proposed strategy effectively mitigates wake effects under varying wind conditions, simultaneously enhancing overall power generation efficiency while balancing fatigue losses across turbines.
Key words: offshore wind farm; wake effect; multi-agent deep reinforcement learning; fatigue loss; power generation efficiency
參考文獻(xiàn)
[1] Global Wind Energy Council.Global offshore wind report 2025[R].Brussels :GWEC,2025.
[2] 陳婕 .考慮尾流效應(yīng)的風(fēng)電場(chǎng)多目標(biāo)分層隨機(jī)控制 [D]. 北京 :華北電力大學(xué),2023.
[3] 魏賞賞,李智寒,陳一凱,等 . 基于狀態(tài)擴(kuò)張輸入輸出動(dòng)態(tài)模態(tài)分解的風(fēng)力機(jī)尾流降階模型 [J]. 太陽(yáng)能學(xué) 報(bào),2024,45(10) :580-587.
[4] 樊濤,李剛,馬晨陽(yáng),等 . 考慮經(jīng)濟(jì)性和舒適性的海上風(fēng)電運(yùn)維規(guī)劃優(yōu)化方法 [J]. 船舶工程,2025, 47(4) :160-169.
[5] MUNOZ-PALOMEQUE E, SIERRA-GARCIAJ E, SANTOS M. Wind turbine maximum power pointtracking control based on unsupervised neural networks[J].Journal of Computational Design and Engineering,2023,10(1) :108-121.
[6] 蔡瑋,胡陽(yáng),劉吉臻 . 計(jì)及尾流的風(fēng)電場(chǎng)智能等效建模及偏航優(yōu)化控制 [J]. 動(dòng)力工程學(xué)報(bào),2024, 44(7) :1051-1059.
[7] 王冠朝,霍雨翀,李群,等 . 基于深度強(qiáng)化學(xué)習(xí)與 改進(jìn)Jensen模型的風(fēng)電場(chǎng)功率優(yōu)化 [J]. 中國(guó)電力, 2025,58(4) :78-89.
[8] 褚夢(mèng)珂,劉春,張勇,等 . 基于多智能體深度強(qiáng)化學(xué)習(xí)算法的風(fēng)電場(chǎng)偏航控制策略 [J]. 上海電力大學(xué)學(xué)報(bào),2025,41(4) :310-317.
[9] YAO Q, MA B, ZHAO T, et al.Optimized active power dispatching of wind farms considering data-driven fatigue load suppression[J].IEEE Transactions on Sustainable Energy,2022, 14(1) :371-380.
[10] 葛暢,閻潔,劉永前,等 . 海上風(fēng)電場(chǎng)運(yùn)行控制維護(hù)關(guān)鍵技術(shù)綜述 [J]. 中國(guó)電機(jī)工程學(xué)報(bào),2022, 42(12) :4278-4291.
[11] 蔡瑋,胡陽(yáng),劉吉臻 . 基于尾流判定的風(fēng)電場(chǎng)偏航角分群優(yōu)化控制 [J]. 動(dòng)力工程學(xué)報(bào),2024,44(8) : 1234-1243.
[12] 張勇,劉春,褚夢(mèng)珂,等 . 計(jì)及尾流的改進(jìn)深度確定性策略梯度風(fēng)電場(chǎng)功率優(yōu)化控制策略 [J]. 電力系統(tǒng)及 其自動(dòng)化學(xué)報(bào),2025,37(2) :68-77.
[13] 陳皓勇,席松濤 . 海上風(fēng)電成本構(gòu)成及價(jià)格機(jī)制 [J]. 風(fēng)能,2022(1) :12-15.
[14] BOERSMA S, DOEKEMEIJER B, VALI M, et al.A control-oriented dynamic wind farm model: WFSim[J].Wind Energy Science,2018,3(1) :75-95.
[15] HE R, YANG H, LU L.Optimal yaw strategy and fatigue analysis of wind turbines under the combined effects of wake and yaw control[J].Applied Energy,2023,337 :120878.
[16] 許曉玥 . 考慮風(fēng)機(jī)疲勞的風(fēng)電場(chǎng)功率優(yōu)化策略 [D]. 長(zhǎng)沙 :湖南大學(xué),2021.
[17] WANG X, ZHOU J, QIN B, et al.Coordinated power smoothing control strategy of multi-wind turbines and energy storage systems in wind farm based on MADRL[J].IEEE Transactions on Sustainable Energy,2023,15(1) :368-380.
[18] JONKMAN J, BUTTERFIELD S, MUSIAL W, et al. Definition of a 5-MW reference wind turbine for offshore system development[R].Golden :National Renewable Energy Laboratory(NREL),2009.
[19] 閆曄 . 考慮風(fēng)電不確定性的分時(shí)電價(jià)研究 [D]. 西安 : 西安理工大學(xué),2020.