针对外界环境因素快速变化时,光伏发电系统难以保持在最大功率点输出的问题,提出遗传算法与GRU神经网络相结合的最大功率跟踪算法（GA-GRU-MPPT）。该算法在构建的最大功率点预测模型基础上,采用遗传算法对GRU神经网络的参数进行优化。考虑到数据的关联性,将前一时刻的太阳电池温度、太阳辐照度、最大功率点电压及当前时刻的太阳电池温度和太阳辐照度作为预测模型的输入变量,输出为当前时刻的最大功率点电压。针对3种不同气候情形的仿真结果表明,该算法跟踪精度可达99%,能显著提高光伏系统的能量转换效率。
Abstract
This paper proposes a maximum power point tracking algorithm that combines genetic algorithm and GRU neural network （GA-GRU-MPPT） to address the problem of photovoltaic power generation systems struggling to maintain maximum power point output in the face of rapidly changing external environmental factors. Based on the constructed maximum power point prediction model, this algorithm optimizes the parameters of the GRU neural network using genetic algorithm. Considering the correlation of the data, the previous moment's solar cell temperature, solar irradiance, maximum power point voltage, as well as the current moment’s solar cell temperature and solar irradiance, are taken as input variables for the prediction model, with the output being the current moment’s maximum power point voltage. Simulation results for three different climate scenarios show that the tracking accuracy of this algorithm can reach 99%, significantly improving the energy conversion efficiency of solar photovoltaic systems.
关键词
太阳电池 /
最大功率点跟踪 /
遗传算法 /
GRU神经网络 /
仿真
Key words
solar cells /
maximum power point trackers /
genetic algorithms /
GRU neural network /
simulation
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 王义飞, 吴伟, 杨宇, 等. 光伏系统最大功率点快速判断和跟踪方法[J]. 系统仿真学报, 2013, 25(2): 389-393.
WANG Y F, WU W, YANG Y, et al.Novel method of MPP tracking in photovoltaic system[J]. Journal of system simulation, 2013, 25(2): 389-393.
[2] ABOUADANE H, FAKKAR A, SERA D, et al.Multiple-power-sample based P&O MPPT for fast-changing irradiance conditions for a simple implementation[J]. IEEE journal of photovoltaics, 2020, 10(5): 1481-1488.
[3] ALSUMIRI M.Residual incremental conductance based nonparametric MPPT control for solar photovoltaic energy conversion system[J]. IEEE access, 2019, 7: 87901-87906.
[4] 李晶, 窦伟, 徐正国, 等. 光伏发电系统中最大功率点跟踪算法的研究[J]. 太阳能学报, 2007, 28(3): 268-273.
LI J, DOU W, XU Z G, et al.Research on MPPT methods of photovoltaic power generation system[J]. Acta energiae solaris sinica, 2007, 28(3): 268-273.
[5] ELTAMALY A M.An improved cuckoo search algorithm for maximum power point tracking of photovoltaic systems under partial shading conditions[J]. Energies, 2021, 14(4): 953-953.
[6] LAXMAN B, ANNAMRAJU A, SRIKANTH N V.A grey wolf optimized fuzzy logic based MPPT for shaded solar photovoltaic systems in microgrids[J]. International journal of hydrogen energy, 2021, 46(18): 10653-10665.
[7] WAFA H, EMANUELE O, ALBERTO D, et al.Improved PSO: a comparative study in MPPT algorithm for PV system control under partial shading conditions[J]. Energies, 2020, 13(8): 2035.
[8] MOSAAD M I, ABED EL RAOUF M O, AL AHMAR M A, et al. Maximum power point tracking of PV system based cuckoo search algorithm; review and comparison[J]. Energy procedia, 2019, 162: 117-126.
[9] 胥芳, 张任, 吴乐彬, 等. 自适应BP神经网络在光伏MPPT中的应用[J]. 太阳能学报, 2012, 33(3): 468-472.
XU F, ZHANG R, WU L B, et al.Self-adaption BP neural network for the maximum-power-point tracking in photovoltaic[J]. Acta energiae solaris sinica, 2012, 33(3): 468-472.
[10] SURABHI C, PRERNA G.Radial basis function neural network technique for efficient maximum power point tracking in solar photo-voltaic system[J]. Procedia computer science,2020, 167: 2354-2363.
[11] 林虹江, 周步祥, 冉伊, 等. 基于遗传优化BP神经网络算法的光伏系统最大功率点跟踪研究[J]. 电测与仪表, 2015, 52(5): 35-40.
LIN H J, ZHOU B X, RAN Y, et al.Research on the maximum power point tracking of the photovoltaic system based on the genetic optimization BP neural network algorithm[J]. Electrical measurement instrumentation, 2015, 52(5): 35-40.
[12] 王志豪, 李自成, 王后能, 等. 基于RBF神经网络的光伏系统MPPT研究[J]. 电力系统保护与控制, 2020, 48(6): 85-91.
WANG Z H, LI Z C, WANG H N, et al.MPPT study of solar PV power system based on RBF neural network algorithm[J]. Power system protection and control, 2020, 48(6): 85-91.
[13] 茆美琴, 余世杰, 苏建徽. 带有MPPT功能的光伏阵列Matlab通用仿真模型[J]. 系统仿真学报, 2005, 17(5): 1248-1251.
MAO M Q, YU S J, SU J H.Versatile matlab simulation model for photovoltaic array with MPPT function[J]. Acta simulata systematica sinica, 2005, 17(5): 1248-1251.
[14] 崔岩, 蔡炳煌, 李大勇, 等. 太阳能光伏模板仿真模型的研究[J]. 系统仿真学报, 2006, 18(4): 829-831, 834.
CUI Y, CAI B H, LI D Y, et al.Study on simulation model of PV module[J]. Journal of system simulation, 2006, 18(4): 829-831, 834.
[15] WEI X, ZHANG L L, YANG H Q, et al.Machine learning for pore-water pressure time-series prediction: application of recurrent neural networks[J]. Geoscience frontiers, 2021, 12(1): 453-467.
基金
嘉兴市公益性研究计划（2020AY10012）
PDF(2158 KB)
