为准确辨识太阳电池模型参数,提出一种基于强化学习的知识获取共享算法（RLGSK）。针对知识获取共享算法（GSK）初级阶段和高级阶段的选择机制过于死板,处理太阳电池模型参数辨识问题时难以充分平衡全局与局部搜索,存在收敛慢、精度低等问题,一方面,通过强化学习调整迭代时初级和高级阶段的个体比例,实现不同情景下知识获取与共享的灵活调整;另一方面,依靠性能导向的种群规模缩减实现计算资源的高效利用,提高算法性能。将RLGSK应用于5种案例,并与其他算法进行比较。结果表明,与GSK相比,RLGSK的搜索精度、稳定度和收敛速度提升极大,与其他算法相比也有很强的竞争力。
Abstract
A reinforcement learning gaining-sharing knowledge-based algorithm （RLGSK） is proposed to accurately identify the parameters of solar cell models. The selection mechanism of the junior and senior phases of gaining-sharing knowledge-based algorithm （GSK） is too rigid, which makes GSK difficult to fully balance the global and local searches when dealing with the solar cell model parameter identification. Besides, it has some problems such as slow convergence and low accuracy. In this regard, on the one hand, the ratio of individuals in the junior and senior phases during iteration is adjusted by reinforcement learning to achieve flexible adjustment of knowledge gaining and sharing in different scenarios. On the other hand, a performance-oriented population size reduction technique is used to achieve efficient use of computational resources and improve algorithm performance. RLGSK is applied to five cases and compared with other algorithms. The results show that the search accuracy, stability and convergence speed of RLGSK are greatly improved compared to GSK, and it is also very competitive with other algorithms.
关键词
参数辨识 /
太阳电池 /
光伏组件 /
强化学习 /
知识获取共享算法
Key words
parameter identification /
solar cells /
PV module /
reinforcement learning /
gaining-sharing knowledge-based algorithm
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 叶睿明, 张民, 薛鹏飞, 等. 一种可应用于新能源发电系统的双绕组高效率高升压DC-DC变换器[J]. 太阳能学报, 2023, 44(6): 161-169.
YE R M, ZHANG M, XUE P F, et al.Two-winds high efficiency high step-up DC-DC converter applicable to new energy power generation system[J]. Acta energiae solaris sinica, 2023, 44(6): 161-169.
[2] 范瑞祥, 尹国明, 苗洁蓉, 等. 基于参数辨识的光伏组件快速MPPT方法[J]. 太阳能学报, 2020, 41(2): 296-302.
FAN R X, YIN G M, MIAO J R, et al.A quick MPPT method of PV panel based on parameter identification[J]. Acta energiae solaris sinica, 2020, 41(2): 296-302.
[3] XIONG G J, ZHANG J, SHI D Y, et al.Winner-leading competitive swarm optimizer with dynamic Gaussian mutation for parameter extraction of solar photovoltaic models[J]. Energy conversion and management, 2020, 206: 112450.
[4] HUMADA A M, DARWEESH S Y, MOHAMMED K G, et al.Modeling of PV system and parameter extraction based on experimental data: review and investigation[J]. Solar energy, 2020, 199: 742-760.
[5] ABBASSI A, GAMMOUDI R, ALI DAMI M, et al.An improved single-diode model parameters extraction at different operating conditions with a view to modeling a photovoltaic generator: a comparative study[J]. Solar energy, 2017, 155: 478-489.
[6] 简献忠, 翁志远, 王如志. CIJAYA算法在光伏组件参数辨识中的应用[J]. 太阳能学报, 2021, 42(11): 19-26.
JIAN X Z, WENG Z Y, WANG R Z.CIJAYA algorithm for parameters identification of photovoltaic module model[J]. Acta energiae solaris sinica, 2021, 42(11): 19-26.
[7] 吴子牛, 孟润泉, 韩肖清. 基于改进多种群遗传算法的光伏阵列多峰值MPPT研究[J]. 电网与清洁能源, 2022, 38(8): 102-109, 120.
WU Z N, MENG R Q, HAN X Q.Research on multi-peak MPPT of photovoltaic array based on improved multi-population genetic algorithm[J]. Power system and clean energy, 2022, 38(8): 102-109, 120.
[8] JIANG L L, MASKELL D L, PATRA J C.Parameter estimation of solar cells and modules using an improved adaptive differential evolution algorithm[J]. Applied energy, 2013, 112: 185-193.
[9] HU Z Z, GONG W Y, LI S J.Reinforcement learning-based differential evolution for parameters extraction of photovoltaic models[J]. Energy reports, 2021, 7: 916-928.
[10] 吴忠强, 刘重阳. 基于IHHO算法的光伏电池工程模型的参数辨识[J]. 计量学报, 2021, 42(2): 221-227.
WU Z Q, LIU C Y.Parameter identification of photovoltaic cell engineering model based on IHHO algorithm[J]. Acta metrologica sinica, 2021, 42(2): 221-227.
[11] CHEN X, YU K J, DU W L, et al.Parameters identification of solar cell models using generalized oppositional teaching learning based optimization[J]. Energy, 2016, 99: 170-180.
[12] CHEN X, XU B, MEI C L, et al.Teaching-learning-based artificial bee colony for solar photovoltaic parameter estimation[J]. Applied energy, 2018, 212: 1578-1588.
[13] XIONG G J, LI L, MOHAMED A W, et al.A new method for parameter extraction of solar photovoltaic models using Gaining-sharing? knowledge based algorithm[J]. Energy reports, 2021, 7: 3286-3301.
[14] 曾一婕, 王龙, 黄超. 基于Jaya-DA算法的太阳电池模型参数辨识[J]. 太阳能学报, 2022, 43(2): 198-202.
ZENG Y J, WANG L, HUANG C.Parameter identification of solar cell model based on Jaya-DA algorithm[J]. Acta energiae solaris sinica, 2022, 43(2): 198-202.
[15] LI S J, GONG W Y, WANG L, et al.A hybrid adaptive teaching-learning-based optimization and differential evolution for parameter identification of photovoltaic models[J]. Energy conversion and management, 2020, 225: 113474.
[16] FAN Y, WANG P J, HEIDARI A A, et al.Random reselection particle swarm optimization for optimal design of solar photovoltaic modules[J]. Energy, 2022, 239: 121865.
基金
国家自然科学基金（52167007）; 贵州大学勘察设计研究院有限责任公司创新基金项目（贵大勘察[2022]03号）
PDF(1384 KB)
