基于多源数据融合的分布式光伏聚合超短期预测方法

分布式光伏聚合发电的超短期预测是支撑其功率快速调节的前提保障,由于规模化接入的分布式光伏容量小、分布广,其发电时序特性差异性大、非平稳性强,导致其超短期预测精度难以保证。为此,文章提出基于多源数据融合的分布式光伏聚合超短期预测方法。该方法基于变分模态分解法,充分挖掘分布式光伏聚合发电非平稳性特性,并采用核主成分分析法对引发光伏发电非平稳性的影响因素即温度、湿度、光照、云量等多源数据进行量化解析,同时结合改进的长短期记忆神经网络,创建了多源数据融合方法,实现了分布式光伏聚合发电超短期预测。仿真结果表明,该方法有效提升了模型的预测精度。与传统方法相比,提出的预测方法对随机性波动严重的光伏超短期预测具有显著优势。     

基于马氏距离相似度量的光伏功率超短期预测方法的研究

提高光伏功率超短期预测精度可有效减小光伏发电并网对电力系统稳定性的影响。文章提出了一种基于马氏距离相似度量的光伏功率超短期预测方法。首先,文章采用Elkan K-means聚类分析方法对天气类型进行划分,并通过计算各气象因素与光伏电站输出功率间的灰色关联度,选出不同天气类型下影响光伏功率的主要气象因素;然后,根据样本日和预测日间主要气象因素的马氏距离选择若干个相似日,并将相似日的光伏功率作为预测模型的训练集,对预测日的光伏功率进行超短期预测。模拟结果表明:基于马氏距离相似度量得到的相似日光伏功率和预测日的相似度较高;将基于马氏距离相似度量得到的相似日光伏功率作为预测模型的训练集,可以提高光伏功率超短期预测精度,为光伏功率预测领域提供了有效的方法。     

考虑大气透明度修正的光伏发电超短期功率预测方法

为提高光伏发电功率超短期预测准确率,考虑到大气透明度能反映到达地面的太阳辐射量,建立了基于别尔梁德模型的超短期太阳辐射订正模型,分别对未来15min、1h及4h的预报总辐射进行实时订正,并采用光电转换效率模型及直流交流电转换模型完成了最终超短期功率预测结果的输出。结果表明,该方法能有效提高超短期功率预测准确率,第15min、1h及4h的相对均方根误差最多可分别减小4.27%、6.01%和6.12%。     

基于Kmeans++-Bi-LSTM的太阳辐照度超短期预测

针对地表太阳辐射的不确定性和随机波动性，进而对大型光伏发电并网对电力系统的稳定性造成冲击，提出一种新的太阳辐照度超短期预测方案。该方案通过使用皮尔逊相关性分析和无监督学习中的Kmeans++算法，对多种气象数据进行筛选，找出关键气象数据并进行划分以及添加标签，接着将带有标签的关键气象数据输入双向长短期记忆网络预测模型中，以达到10 min时间间隔的太阳辐照度超短期预测。结果表明所提预测模型相较于目前常用的模型提高了预测精度。     

基于提升小波-BP神经网络的光伏阵列短期功率预测

提高光伏阵列的短期功率预测的精度,对光伏电站运营管理效率具有重要作用。文章提出了一种提升小波变换与BP神经网络相结合的直流侧功率输出预测滑移算法,对光伏阵列的超短期功率进行预测。实验结果表明,文章所提出的算法对超短期功率预测具有较高的精度,适用于晴天、多云、阴雨等复杂天气条件。     

基于极限学习机的光伏发电短期预测校正方法

光伏发电短期预测在电力系统实时调度中具有重要意义。受诸多因素影响,光伏发电短期预测精度还无法达到光伏电站要求,对光伏并网调度带来较大影响。针对这一问题,提出了基于极限学习机（ELM）的光伏发电短期预测校正方法。说明了光伏发电短期预测中的误差特征,并利用提出的校正方法对原来光伏发电短期预测结果进行了优化。通过与其他方法的对比,验证了此方法的有效性,说明了论文方法能够有效提高光伏发电短期预测精度。     

基于时空图卷积神经网络的光伏发电功率超短期预测方法

为了解决传统光伏电站超短期功率预测方法不能同时准确提取发电功率的时间和空间特征的问题,提出一种基于时空图卷积神经网络的光伏发电功率超短期预测方法。针对同一区域内的多个光伏电站,首先对电站进行图建模,利用图卷积网络（GCN）与门控线性单元（GLU）提取发电功率的时空特征。利用提取到的时空特征信息以及区域内光伏电站的历史发电功率数据训练预测模型,最终实现对多个光伏电站发电功率超短期预测。实验结果表明,该方法能够将超短期功率预测均方根误差减小至1.122%,对工作人员根据实际情况进行电网的调度管理具有重要意义。     

基于高密度数值天气预报的分布式光伏功率预测主站研究应用

基于高密度的商业数值天气预报信息构建分布式光伏功率预测主站,对珠海全网、区域和分布式光伏电源进行短期、超短期功率预测,提高区域单点电源点预测精度,为后期研究大规模发电间歇性、波动性等新能源(风电、光伏等)接入电网后对电网运行及负荷预测精度的影响奠定基础。     

基于数字孪生和改进LSTM的光伏发电预测技术

为提高光伏发电功率预测的精度和时效性,降低电网调度的安全隐患,提出了一种基于数字孪生模型、联合神经网络以及融合预测模型的光伏发电功率预测技术。该技术以针对常态预测的CNN LSTM网络和针对超短期预测的集成学习融合预测模型为核心,以光伏发电系统的数字孪生模型为基础框架,以某光伏电站的实测数据为基础进行了分析,实现了实时的多模式光伏发电功率精确预测。结果表明：改进的CNN LSTM联合网络模型能够实现较高预测精度,相比于现有的主流预测算法精度提高了约36%~58%;针对超短期的发电功率预测这一难点,集成学习融合框架可以进一步将预测精度提高25%左右。     

结合太阳辐射量计算与CNN-LSTM组合的光伏功率预测方法研究

为了提高模型预测性能,提出一种综合太阳辐射模型及深度学习的光伏功率预测模型。首先,利用太阳辐射机理建立太阳辐射模型（SRM）,估算出水平面上总辐射值,再由斜面辐照度转换方法计算出光伏组件所接收的斜面辐射值。其次,通过皮尔逊相关分析法筛选出对光伏功率影响较大的主要因素,将斜面辐射计算值及主要影响因素作为输入,采用卷积神经网络（CNN）和长短期记忆网络（LSTM）建立光伏功率SRM-CNN-LSTM预测模型。分别利用春夏秋冬四季典型日的数据开展对比实验,结果表明：与几种其他方法相比,该文方法具有更好的预测效果。     

基于滚动的BP神经网络的光伏发电功率预报

鉴于准确预测光伏发电功率可减少大规模光伏并网发电对电网造成的冲击,以河南省某并网的光伏发电站7~11月共5个月的数据为例,通过建立非滚动的和滚动的BP神经网络模型,分别进行数值预报辐射订正和发电功率预报,并对预报的72h结果分为第1、2、3d分别进行检验。结果表明,滚动的BP神经网络对辐射订正和功率预报均具有较好的泛化能力,方法简便、实用,能够有效降低光伏发电功率的预报误差。     

基于MIV-PSO-BPNN的光伏出力短期预测

针对高比例光伏接入电网时,光伏出力的波动性会严重影响电力系统稳定运行的问题提出一种基于平均影响值与改进粒子群优化神经网络的组合式光伏出力短期预测模型。首先,采用直接预测法,选取总辐射量、直接辐射量、散射量、相对湿度、气温、风速和降雨量7个影响光伏出力的因素,构建MIV-PSO-BPNN模型,基于Rapid Miner数据挖掘得出降雨量对光伏出力平均影响值为0.0099,影响较小,不作为模型输入变量。然后,用改进PSO优化算法对BPNN的权值与阈值进行优化。最后,利用上海浦东国际机场T2-2光伏电站数据进行验证,结果表明MIV-PSO-BPNN模型对光伏出力预测有效,在实际中有一定应用价值。     

Electromagnetic transients in the control system of output parameters of a solar power plant in Tajikistan Central Asia region

At present, as the demand for electricity increases in all sectors, there is an urgent need to introduce alternative renewable energy sources into modern energy systems. Renewable energy sources, which consist of solar (photovoltaic, PV), wind and hydro power, are key alternative sources of “green energy’’ energies, but it can also be used to produce “green” hydrogen. Thanks to scientific and technological progress, the cost of photovoltaic solar radiation converters is constantly decreasing at a high rate, which makes it possible to build solar power plants of sufficiently large capacity. In the coming decades, solar energy will become an incentive for the economic development of countries that have the maximum “solar” resource. The Republic of Tajikistan is one of these countries with a high potential for solar energy.The article presents an analysis of the resources and potential of solar energy in the Republic of Tajikistan. The study of electromagnetic transients in networks with photovoltaic solar power plants is performed. The main equations, simulation model and calculations of transients are presented, taking into account changes in voltage on DC buses. An algorithm for controlling the system of automatic control of output parameters is proposed. The analysis of dynamic and static modes in parallel operation of a solar power plant with the grid is carried out. A block diagram and computer model is constructed in the MATLAB package together with Simulink and Power System Blockset.     

Hybrid control approach for PV/FC fed voltage source converter tied to grid

A hybrid and adaptive control approach for solar photovoltaic system and fuel cell fed voltage source converter (VSC) is presented in this work. Further maximum power from solar photovoltaic array is extracted by using incremental conductance (INC) based maximum power point tracking approach. This hybrid approach combines I cos ? technique and gradient descent back propagation learning (GDBP) neural network (NN) to extract fundamental components from load current for efficient harmonics compensation and provides power quality improvement and support the three-phase AC grid by supplying power to the grid and as well as connected loads. The proposed system includes photovoltaic (PV) array, a voltage source converter (VSC), ripple filter and combination of linear and non-linear loads. The proposed control approach provides a fast response during dynamic conditions as well. Results of the proposed control technique also compared with the other available control techniques for its superiority analysis. The developed control technique is demonstrated by using MATLAB/SIMULINK platform.     

A two dimensional thermal network model for a photovoltaic solar wall

A two dimensional thermal network model is proposed to predict the temperature distribution for a section of photovoltaic solar wall installed in an outdoor room laboratory in Concordia University, Montréal, Canada. The photovoltaic solar wall is constructed with a pair of glass coated photovoltaic modules and a polystyrene filled plywood board as back panel. The active solar ventilation through a photovoltaic solar wall is achieved with an exhaust fan fixed in the outdoor room laboratory. The steady state thermal network nodal equations are developed for conjugate heat exchange and heat transport for a section of a photovoltaic solar wall. The matrix solution procedure is adopted for formulation of conductance and heat source matrices for obtaining numerical solution of one dimensional heat conduction and heat transport equations by performing two dimensional thermal network analyses. The temperature distribution is predicted by the model with measurement data obtained from the section of a photovoltaic solar wall. The effect of conduction heat flow and multi-node radiation heat exchange between composite surfaces is useful for predicting a ventilation rate through a solar ventilation system.     

神经网络短期光伏发电预测的应用研究进展

准确的太阳能发电功率短期预测是保证电力调度和大规模光伏并网的关键。该文对近年来光伏发电功率短期预测研究进展进行综述,并对影响光伏发电功率的各种气象因素进行相关性分析。针对用于光伏发电短期功率预测的人工神经网络模型和深度学习模型进行总结和评述。太阳辐照度是影响预测模型精度的主要气象参数。在光伏发电功率短期预测中,神经网络及其组合模型均表现出较好的预测精度,但组合模型整体上优于单一预测模型。     

Review of modern methods and technologies for using of solar energy in the operation of anaerobic digestion systems

The article presents various methods and technologies for using of solar energy in anaerobic bioconversion systems. Various methods of convertion of solar radiation are consistently considered – from its direct use to photovoltaic, thermal, photovoltaic thermal and concentrating. Schemes for introducing solar energy converters into anaerobic bioconversion systems, as well as various solar radiation converters for heat and electricity supply of anaerobic bioconversion systems, are proposed. As power generating components in the article also discusses photovoltaic modules with an extended rated power period, photovoltaic thermal roofing panels with a two-component polysiloxane compound, thermal and photovoltaic thermal solar roofing panels, air-cooled photovoltaic thermal siding panel and concentrator solar photovoltaic thermal module with high-voltage matrix photovoltaic converters. The proposed schemes of systems and design of solar modules will ensure a reduction in the use of thermal energy from the produced gas for power supply for the own needs of anaerobic bioconversion systems, which will make them cheaper and more efficient in operation.     

Bidirectional energy storage photovoltaic grid-connected inverter application system

A novel topology of the bidirectional energy storage photovoltaic grid-connected inverter was proposed to reduce the negative impact of the photovoltaic grid-connected system on the grid caused by environmental instability. Using the proposed Inverter as a UPS power supply in case of a grid failure, storage electrical energy and regulating the energy delivered to the grid for reducing the pressure on the grid. A new artificial fish-swarm algorithm and variable step voltage perturbation method were presented to track the maximum power point of the solar panels. Analysis was done to reduce the output ripple of the inverter and sinusoidal pulse width modulation (SPWM) was selected to control the inverter. Model simulation was performed using PSpice software to obtain the volt-ampere characteristic curve of the solar panel output. The solar array simulator was used to verify the effect of maximum power point tracking at different light intensities. The study concludes that the maximum power point tracking (MPPT) efficiency of the bidirectional energy storage photovoltaic grid-connected inverter designed was as high as 99.9%. The distortion rate of the grid-connected current waveform was within 2% and the DC current component was less than 0.5%. The output voltage and power were in full compliance with the grid connection standard.     

基于水库大坝的水能与太阳能融合型并网发电系统研究与应用

针对中国大中型面南的水库电站大坝,向光性比较好,具备安装太阳能光伏发电系统的条件,并使得2种可再生能源融合并网发电模式具有一定的创新性.水库电站的发电系统是已建成的,增加太阳能光伏发电系统并建设融合型并网发电系统,不仅体现了投资成本低发电效益高等特点,同时具有节约国土资源、保护大坝和节能减排等社会效益.在设计和实践过程...     

高速铁路上空安装光伏系统的节能潜力研究

高速铁路的运营需要大量电力供给,为缓解铁路电网压力,减少能源消耗,提出一种在高速铁路上方架设光伏组件的发电系统;对上述系统进行相关计算,量化全国设计时速超过200 km/h高速铁路线路的光伏发电潜力。研究结果表明,在中国太阳年辐射量大于1200 kWh/m²的高速铁路线架设光伏系统,年发电量超过7×10⁴GWh,接近三峡大坝的年发电量,能有效缓解铁路电网压力;时速350 km/h的列车全速运行时,其上方4.5 m处的光伏组件表面压强分布正/负极值为140 Pa/-225 Pa,风速极值为3.5 m/s,满足光伏组件最大风载荷极限值要求,高速铁路光伏系统节能减排效益显著,并具有投资的经济可行性。