针对光伏-温差混合发电系统因两种发电方式特性不同导致功率输出波动大、影响整体能效,且当前控制方法未考虑天气因素、缺少前期功率主动抑制思维的问题,提出考虑气象因素的光伏-温差混合发电系统的输出功率控制技术。考虑天气条件对光伏-温差混合发电系统输出功率的直接影响,并对天气因素进行分类与分析。通过预测和控制系统在不同天气条件下的输出功率,从而不再依赖于单一的后置终端信息。利用粒子群优化算法（PSO）优化K均值算法对输出功率的概率分布进行计算,以获得更全面的功率输出信息。在此基础上,将概率分布区域功率数据输入到最小二乘支持向量机中,完成输出功率的控制。结果表明：所提方法在电池温度30 ℃和串联数量为3的条件下,无遮蔽和完全遮蔽以及遮蔽后有效光辐照度为无遮蔽时的25%和50%这4种情况均可有效控制光伏-温差混合发电系统的输出功率,且Skill值整体降幅以及曲面波动幅度较小,平均绝对误差（MAE）值和均方误差（MSE）值均约在0.3,说明该方法具有有效提高发电系统输出功率控制的精度和稳定性的作用,实际应用性较强。
Abstract
Aiming at the problem of large power output fluctuations and overall energy efficiency impact caused by the different characteristics of the photovoltaic temperature difference hybrid power generation system due to the two power generation methods, and the current control methods not considering weather factors and lacking proactive power suppression thinking in the early stage, a photovoltaic temperature difference hybrid power generation system output power control technology considering meteorological factors is proposed. This article considers the direct impact of weather conditions on the output power of photovoltaic temperature difference hybrid power generation systems, and classifies and analyzes weather factors. By predicting and controlling the output power of the system under different weather conditions, it no longer relies on a single rear terminal information. Using PSO algorithm to optimize K-means algorithm to calculate the probability distribution of output power, in order to obtain a more comprehensive power output information base. On this basis, input the power data of the desired probability distribution area into the least squares support vector machine to complete the control of output power. The experimental results show that the proposed method can effectively control the output power of the photovoltaic temperature difference hybrid power generation system under the conditions of a battery temperature of 30 ℃ and three series numbers, whether it is unshielded, completely shielded, and the effective light irradiance after shielding is 25 % and 50 % of the unshielded, and the overall decrease in Skill values and surface fluctuations are small, with MAE and MSE values both around 0.3. This method effectively improves the accuracy and stability of output power control in power generation systems, and has strong practical applicability.
关键词
光伏-温差混合发电系统 /
功率控制 /
概率神经网络 /
概率分布属性 /
最小二乘支持向量机
Key words
photovoltaic-thermoelectric hybrid power generation system /
power control /
probabilistic neural network /
probability distribution attributes /
least squares support vector machine
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 王乐, 陈雪, 张舒, 等. 光伏组件热斑效应研究[J]. 太阳能学报, 2023, 44(7): 155-161.
WANG L, CHEN X, ZHANG S, et al.Hot spot effect for photovoltaic modules[J]. Acta energiae solaris sinica, 2023, 44(7): 155-161.
[2] 张家安, 郝峰, 董存, 等. 基于两阶段不确定性量化的光伏发电超短期功率预测[J]. 太阳能学报, 2023, 44(1): 69-77.
ZHANG J A, HAO F, DONG C, et al.Ultra-short-term power forecasting of photovoltaic power generation based on two-stage uncertainty quantization[J]. Acta energiae solaris sinica, 2023, 44(1): 69-77.
[3] 李忠文, 吴龙, 程志平, 等. 参与微电网频率调节的光伏发电系统模糊自适应功率控制[J]. 电机与控制学报, 2023, 27(9): 126-138.
LI Z W, WU L, CHENG Z P, et al.Fuzzy adaptive power control for photovoltaic power generation participating in frequency regulation of microgrid[J]. Electric machines and control, 2023, 27(9): 126-138.
[4] 蔡斌军, 何雍, 李朝旗. 基于Boost变换器的D-PMSG风力发电系统MPPT控制[J]. 微特电机, 2023, 51(3): 59-62.
CAI B J, HE Y, LI C Q.D-PMSG wind power generation system MPPT control based on boost converter[J]. Small & special electrical machines, 2023, 51(3): 59-62.
[5] COCCO G M, GRIGOLETTO F B, SCHERER L G, et al.Modeling and control of hydro-PV hybrid power system with three-phase three-leg split-source inverter[J]. Journal of control, automation and electrical systems, 2022, 33(5): 1563-1575.
[6] HASHEMI S T, SIAHI M, HOSSEINPOUR M, et al.Multi-input multi-output sliding-mode control of LCL-based grid-connected modified Y-source inverter for power conditioning of photovoltaic generation[J]. International journal of automation and control, 2023, 17(3): 328.
[7] 李健, 杨明任, 杜玉山, 等. 概率神经网络在盐水水淹层识别中的应用[J]. 油气地质与采收率, 2022, 29(6): 121-129.
LI J, YANG M R, DU Y S, et al.Application of probabilistic neural network in saline water flooded layer identification[J]. Petroleum geology and recovery efficiency, 2022, 29(6): 121-129.
[8] 陈一镖, 倪陈义, 陈浩, 等. 基于MPA优化PNN的电能质量扰动识别方法仿真[J]. 计算机仿真, 2023, 40(6): 107-113.
CHEN Y B, NI C Y, CHEN H, et al.Simulation of power quality disturbance identification method based on MPA optimized PNN[J]. Computer simulation, 2023, 40(6): 107-113.
[9] 孟志强, 邵武, 唐杰, 等. 准Z源级联光伏并网逆变器功率平衡控制[J]. 太阳能学报, 2023, 44(1): 8-15.
MENG Z Q, SHAO W, TANG J, et al.Power balance control of quasi-Z source cascaded photovoltaic grid-connected inverter[J]. Acta energiae solaris sinica, 2023, 44(1): 8-15.
[10] 何建强, 张玉萍, 滕志军. 基于K-means和改进KNN算法的风电功率短期预测系统[J]. 计算机测量与控制, 2022, 30(5): 156-162.
HE J Q, ZHANG Y P, TENG Z J.Wind power short-term forecasting system based on K-means and improved KNN algorithm[J]. Computer measurement & control, 2022, 30(5): 156-162.
[11] 张良, 孙成龙, 蔡国伟, 等. 基于PSO算法的电动汽车有序充放电两阶段优化策略[J]. 中国电机工程学报, 2022, 42(5): 1837-1851.
ZHANG L, SUN C L, CAI G W, et al.Two-stage optimization strategy for coordinated charging and discharging of EVs based on PSO algorithm[J]. Proceedings of the CSEE, 2022, 42(5): 1837-1851.
[12] 朱英亮, 仇旭阳, 徐磊. 基于改进ReliefF与K-means算法的良恶性肺结节分类模型[J]. 小型微型计算机系统, 2021, 42(3): 566-571.
ZHU Y L, QIU X Y, XU L.Classification model of benign and malignant pulmonary nodules based on unbiased ReliefF and weighted K-means algorithm[J]. Journal of Chinese computer systems, 2021, 42(3): 566-571.
[13] 舒星, 刘永刚, 申江卫, 等. 基于改进最小二乘支持向量机与Box-Cox变换的锂离子电池容量预测[J]. 机械工程学报, 2021, 57(14): 118-128.
SHU X, LIU Y G, SHEN J W, et al.Capacity prediction for lithium-ion batteries based on improved least squares support vector machine and Box-Cox transformation[J]. Journal of mechanical engineering, 2021, 57(14): 118-128.
[14] 侯捷, 陈谋, 刘楠. 基于径向基函数神经网络与扩张状态观测器的无人直升机控制[J]. 控制理论与应用, 2021, 38(9): 1361-1371.
HOU J, CHEN M, LIU N.Unmanned helicopter control based on radial basis function neural network and extended state observer[J]. Control theory & applications, 2021, 38(9): 1361-1371.
基金
河南省科学院科技开放合作项目（220826308）
PDF(4316 KB)
