基于BP神经网络与改进粒子群的光伏MPPT算法

针对光伏阵列在环境突变情况下尤其是局部阴影下的多峰值现象,提出一种基于反向传播(BP)神经网络与改进粒子群的最大功率点跟踪(MPPT)算法。该算法利用BP神经网络近似定位最大功率点,并利用对粒子群算法中的惯性权重值进行非线性动态优化后的改进粒子群精确定位最大功率点。仿真结果表明,复合算法可以更好地跟踪最大功率点,有效避免前期易陷入局部极值的问题,提高了精度,减小了功率振荡。     

结合量子粒子群算法的光伏多峰最大功率点跟踪改进方法

光伏阵列在局部阴影时的P-U曲线呈现多峰特性,需要设计光伏多峰最大功率点跟踪方法,以实现光伏发电最大功率输出,提高光伏发电效率。相比粒子群优化算法,量子粒子群优化算法具有收敛速度更快和全局收敛性等优势。提出了一种基于量子粒子群优化算法的光伏多峰最大功率点跟踪改进方法。该方法采用量子粒子群优化算法实现最大功率点的全局搜索;根据光伏阵列在局部阴影时P-U曲线上功率极值点的分布特点初始化种群中的粒子总数及其电压;并根据量子粒子群优化算法收敛时粒子自身最优位置的特点,提出了更适合光伏多峰最大功率点跟踪的收敛判据。仿真测试表明,提出的改进方法能够快速有效地实现光伏多峰最大功率点跟踪,收敛速度更快,避免了不收敛的问题,且具有应对光照情况变化的能力,提高了局部阴影时光伏发电的效率。     

粒子群算法在光伏阵列多峰MPPT中的应用

为了解决在局部阴影的条件下,传统的最大功率点跟踪(MPPT)控制方法不能准确跟踪到最大功率点的问题,采用了粒子群优化算法,并通过粒子初始位置的设定、粒子群算法参数的设定和终止策略的制定提高了算法的准确性。通过添加粒子淘汰环节,提高了算法的执行效率。在Matlab/Simulink环境下进行了仿真,并且对仿真结果进行了分析,验证了该方法的正确性。     

基于粒子群算法的MPPT仿真及应用

利用PSIM软件建立了太阳能电池仿真模型。光伏模块的伏安特性曲线显示了在出现局部阴影时,使用传统的最大功率点跟踪(MPPT)方案跟踪多个局部的最大功率点(MPP)以获得全局MPP是很难的。鉴于此,提出了一种新型基于粒子群优化算法(PSO)的MPPT。仿真及实验结果表明,即使在复杂的条件下,光伏模块的输出电压也能够稳定运行在MPP附近,基于PSO的跟踪算法为实时光伏系统提供了一个可行的替代解决方案。     

光伏列阵的全局最大功率点追踪研究

针对光伏电池的最大功率点跟踪(MPPT)影响着光伏系统的发电效率,对光伏阵列的功率输出特性曲线进行了建模仿真分析,根据MPPT的目标是保持光伏阵列输出电压一直保持在最大功率点处,重点分析在光伏阵列出现局部阴影情况时的,光伏阵列的P-V输出特性为多峰曲线情况下,提出了一种基于改进的模拟退火粒子群算法的最大功率点跟踪控制方法,将模拟退火算法思想融入到粒子群算法中,改善粒子的探索能力,提升了最大功率点跟踪算法的收敛速度和精确性。     

基于模拟退火粒子群算法的波浪发电系统最大功率跟踪控制

波浪发电系统最大功率点跟踪控制中,传统粒子群算法存在早熟收敛和局部搜索能力不足问题,为此提出基于模拟退火算法的粒子群优化方案。该算法每次更新粒子的速度和位置时,通过比较当前温度下各个粒子的适配值与随机数的大小,从所有粒子中确定全局最优解的替代值,从而使粒子群算法在发生早熟收敛时能够跳出局部最优并快速找到全局最优解。仿真结果表明,与传统粒子群优化算法相比,模拟退火粒子群算法可有效避免波浪发电系统陷入局部最大功率点,并快速实现全局最大功率跟踪,提高了波浪能捕获率。     

粒子群与细菌觅食混合算法在光伏阵列MPPT中的应用

为了提高光伏阵列光电转换效率,确保光伏阵列功率输出始终维持在最大功率点上,传统最大功率点跟踪算法在应用于局部阴影条件时,可能存在陷入局部最优或跟踪时间过长等问题.提出一种粒子群与细菌觅食混合算法,并将其应用于光伏阵列的最大功率点跟踪中,来改善跟踪过程中的收敛精度与速度.通过仿真实验结果,与传统扰动观察算法以及细菌觅食算...     

基于鲸鱼粒子群融合算法的MPPT研究

在局部阴影遮挡条件下,经典最大功率点跟踪(MPPT)算法容易失效,导致无法追踪到最大功率点,针对此问题,提出了一种基于鲸鱼粒子群融合算法的多峰MPPT控制策略。该算法实现了混合算法的优势互补,增强了鲸鱼算法后期收敛效率,且避免了粒子群算法易停滞于局部极值的缺陷,提高了鲸鱼粒子群融合算法的收敛精度和寻优效率。在MATLAB/Simulink环境中建立光伏阵列仿真模型,仿真结果表明：该算法追踪过程中震荡幅度减小,能够快速准确地搜索到最大功率点。     

基于改进粒子群算法的光伏最大功率跟踪研究

在局部阴影情况下,带有旁路二极管的光伏阵列P-U呈现多峰特性,导致常规的最大功率点跟踪方法失效。针对多峰值问题,在建立和分析光伏阵列P-U特性曲线的基础上,提出了采用自适应变异粒子群算法进行光伏阵列的最大功率点跟踪方法。该算法根据光伏阵列在局部阴影时P-U曲线上功率极值点的分布特点初始化种群,在传统粒子群算法基础上,通过引入自适应权因子和变异机制来加速算法收敛及防止算法陷入局部极值。仿真测试表明,提出的改进方法能够快速有效地实现光伏局部阴影下的最大功率点跟踪,相比于粒子群算法,可有效避免陷入局部极值点,收敛速度更快,且具有应对太阳光照变化的能力,提高了局部阴影时光伏发电的效率。     

基于储能型准Z源光伏并网逆变器的改进型自适应粒子群最大功率点跟踪算法研究

在解决光伏电池阵列在局部阴影条件下的多峰寻优问题中,传统的粒子群(PSO)最大功率点跟踪(MPPT)算法存在稳定性差、振荡严重、跟踪速度慢等缺点.针对上述缺点,结合准Z源逆变器的优点并在准Z源阻抗网络电容上并联储能单元,提出了一种基于储能型准Z源光伏并网逆变器的改进型自适应粒子群最大功率点跟踪算法.该算法不再依赖迭代次数,而是直接采用个体最优功率和全局最优功率更新惯性权重和学习因子并引入电压窗口限制,有效地提高了跟踪速度和减小了功率振荡.仿真结果验证了该优化算法在储能型准Z源光伏并网逆变器应用中具有较好的多峰值光伏曲线全局最大功率点跟踪能力,提高了光伏阵列的发电效率,具有较好的可行性.     

Optimal Thermal Unit Commitment Integrated with Renewable Energy Sources Using Advanced Particle Swarm Optimization

This paper presents a methodology for solving generation planning problem for thermal units integrated with wind and solar energy systems. The renewable energy sources are included in this model due to their low electricity cost and positive effect on environment. The generation planning problem also known by unit commitment problem is solved by a genetic algorithm operated improved binary particle swarm optimization (PSO) algorithm. Unlike trivial PSO, this algorithm runs the refinement process through the solutions within multiple populations. Some genetic algorithm operators such as crossover, elitism, and mutation are stochastically applied within the higher potential solutions to generate new solutions for next population. The PSO includes a new variable for updating velocity in accordance with population best along with conventional particle best and global best. The algorithm performs effectively in various sized thermal power system with equivalent solar and wind energy system and is able to produce high quality (minimized production cost) solutions. The solution model is also beneficial for reconstructed deregulated power system. The simulation results show the effectiveness of this algorithm by comparing the outcome with several established methods. Copyright © 2009 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.     

海岛智能微电网系统优化调度

海岛上风能、太阳能、海浪潮汐能等可再生能源发电系统构成了智能微电网。将优化调度应用于孤岛运行的海岛智能微电网系统,建立了微电网的优化调度模型,使其运行成本最小化,应用粒子群算法（PSO）对该模型进行求解。最后,利用微电网算例验证了该模型的有效性。     

PSO_SVM算法在太阳能电池板裂缝缺陷检测研究

针对太阳能电池板在生产过程中出现的裂缝问题,在太阳能电池板缺陷数据集有限的条件下,提出应用粒子群算法(particle swarm optimization,PSO)优化支持向量机(support vector machines,SVM)的太阳能电池板裂缝缺陷检测算法。首先,为减少图像采集过程中由电致发光(electroluminescence,EL)检测产生的光照分布不均影响,对太阳能电池板组件图像进行Retinex增强处理;其次,在频域上利用Gabor变换对图像进行纹理特征提取,以获取裂缝特征;最后,将各个太阳能电池板组件的纹理特征经主成分分析法(principal component analysis,PCA)降维后输入到PSOSVM系统中进行分类识别。应用该方法对600幅太阳能电池板EL图像进行实验,仅有1幅出现误检,分类识别准确率为99.33%。将该算法与决策树分类、极限学习机、卷积神经网络及SVM算法进行对比实验,PSOSVM获得最高识别准确率。     

基于微粒群辨识算法的电力负荷综合模型的建模与仿真

微粒群优化(PSO)算法具有全局性能好、搜索效率高等优点.应用该算法进行电力系统负荷模型的参数辨识,辩识结果表明PSO算法在计算时间、全局性方面均有比较明显的优势.辨识的模型具有较高精确性,最后通过工程实例进行仿真实验,实验结果验证了模型和算法的有效性.     

A Novel Modified Robust Load Frequency Control for Mass-Less Inertia Photovoltaics Penetrations via Hybrid PSO-WOA Approach

Abstract

The high penetrations of distributed energy resources (DERs) leads to severe problems such as reducing system inertia and increasing the frequency deviations from the nominal value. The main target of this study is to enable modern photovoltaics (PVs) with large penetration amounts to participate effectively in the load frequency control in the interconnected power systems, in which frequency and tie-line power sharing deviations exist. In this research, a model for the solar PV is developed to help study the heavy penetration of the solar PVs within interconnected power systems. Secondly, a time domain objective function based on the norm of the area control error is formulated. Thirdly, in order to tune the PI controllers, a combined meta-heuristic algorithm based on particle swarm optimization and whale optimization algorithm (PSO-WOA) is developed and compared with the individual PSO and WOA controllers. From the studied scenarios, the developed combined scheme outperforms the other algorithms in terms of system performance indices. Therefore, the developed PSO-WOA approach is plausible and straightforward to solve many engineering problems as it benefits from the exploitation characteristics of the conventional PSO and the exploration features of the WOA.     

Modeling resonant frequency of microstrip antenna based on neural network ensemble

Resonant frequency is an important parameter in designing microstrip antenna (MSA). Selective neural network ensemble (NNE) methods based on decimal particle swarm optimization (PSO) algorithm and binary PSO algorithm are proposed in this study. The basic idea of the methods is to optimally select neural networks (NNs) to construct NNE with the aid of PSO algorithm. This may maintain the diversity of NNs and decrease the effects of collinearity and noise of sample. Simultaneously, chaos mutation is adopted to increase the diversity of particles of PSO. Experimental results show that the chaos PSO algorithm can improve the generalization ability of NNE. Moreover, by using this algorithm, model of resonant frequency of MSA is established. Computing results indicate that the model is better than the available ones. Copyright © 2010 John Wiley & Sons, Ltd.     

基于混合粒子群算法的分布式微网电源规划

将自然选择机理与粒子群算法结合应用到可再生能源分布式微网电源规划中,应用罚函数法引入约束条件,建立微网电源规划模型,以满足负荷、成本的需求。在实际算例中将混合粒子群算法与基本粒子群算法进行对比,说明了混合例子群算法在分布式微网电源规划中的有效性。     

自适应多策略粒子群算法在水库群优化调度中的应用

根据梯级水电站优化调度特点,建立粒子群算法求解多阶段最优化问题数学模型.针对基本粒子群算法(PSO)在早期存在精度较低、易发散等缺点,后期出现"趋同性"和"早熟"等现象,提出了自适应多策略粒子群算法.并将该算法与基本PSO、改进型PSO、杂交PSO和收敛因子PSO分别在雅砻江梯级水库群优化调度中应用,通过对其优化结果的比较,验证了改进算法在加快收敛速度和提高算法精度方面的有效性.     

Artificial immune system-based parameter extraction of proton exchange membrane fuel cell

For a better understanding of the characteristics, performance evaluation and design analysis of proton exchange membrane fuel cell (PEMFC) system an accurate mathematical model is an imperative tool. Although various models have been developed in the literature, because of the shortage of manufacture information about the precise values of the parameters required for the modeling, the parameter extraction is an essential task. So, in order to obtain the PEMFC actual performance, its parameters have to be identified by an optimization technique. Artificial immune system (AIS) is a soft computing method with promising results in the field of optimization problems. In this paper, an AIS-based algorithm for parameter identification of a PEMFC stack model is proposed. In order to study the usefulness of the proposed algorithm, the AIS-based results are compared with the obtained results by the genetic algorithm (GA) and particle swarm optimization (PSO). It is shown that the AIS algorithm is a helpful and reliable technique for identifying the model parameters so that the PEMFC model with extracted parameters agrees with the experimental data well. Moreover, the AIS algorithm outperforms the GA and PSO methods. Therefore, the AIS can be applied to solve other complex identification problems of fuel cell models.