技术领域Technical Field
本发明涉及光伏发电技术领域，特别是涉及一种基于时空特征的分布式光伏电站辐照度预测方法及系统。The present invention relates to the technical field of photovoltaic power generation, and in particular to a method and system for predicting irradiance of a distributed photovoltaic power station based on temporal and spatial characteristics.
背景技术Background Art
本部分的陈述仅仅是提到了与本发明相关的背景技术，并不必然构成现有技术。The statements in this section merely mention background art related to the present invention and do not necessarily constitute prior art.
分布式光伏电站是一种小型化的太阳能发电系统，其发展有助于推进可持续能源的应用，在一定程度上缓解部分地区用电紧张，正在成为越来越受欢迎的清洁能源解决方案。Distributed photovoltaic power stations are a type of miniaturized solar power generation system. Their development helps promote the application of sustainable energy and alleviate electricity shortages in some areas to a certain extent. They are becoming an increasingly popular clean energy solution.
随着分布式光伏电站的不断发展，分布式光伏电站发电功率的预测对电网的运行调度和安全稳定运行直观重要。但分布式光伏电站的安装地点较为分散、装机规模不等、历史样本量较少，难以直接建立有效反应分布式光伏电站运行的功率预测模型。With the continuous development of distributed photovoltaic power stations, the prediction of the power generation of distributed photovoltaic power stations is directly important for the operation and dispatch of the power grid and the safe and stable operation. However, the installation locations of distributed photovoltaic power stations are relatively scattered, the installed capacity is uneven, and the historical sample size is small, making it difficult to directly establish a power prediction model that effectively reflects the operation of distributed photovoltaic power stations.
光伏发电的基本原理就是利用光伏电池将太阳能转换为电能，因此，分布式光伏电站的发电功率依赖于辐照度的大小，对分布式光伏电站的辐照度进行预测可以有效表征分布式光伏电站发电功率的发展。The basic principle of photovoltaic power generation is to use photovoltaic cells to convert solar energy into electrical energy. Therefore, the power generation of distributed photovoltaic power stations depends on the irradiance. Predicting the irradiance of distributed photovoltaic power stations can effectively characterize the development of the power generation of distributed photovoltaic power stations.
现有分布光伏电站的辐照度预测多为根据历史辐照度数据和气象数据，利于神经网络构建辐照度预测模型，通过辐照度预测模型对历史辐照度数据和气象数据进行处理，得到辐照度预测结果，其虽然在一定程度上提高了辐照度预测的准确率，但仍存在如下问题：The existing distributed photovoltaic power station irradiance prediction is mostly based on historical irradiance data and meteorological data, which is conducive to the construction of irradiance prediction model by neural network. The irradiance prediction model processes the historical irradiance data and meteorological data to obtain the irradiance prediction result. Although it improves the accuracy of irradiance prediction to a certain extent, it still has the following problems:
（1）分布式光伏电站多安装于住宅屋顶、农村或偏远地区的开阔地带、建筑物外墙或侧立面等地，安装区域内距离较近的建筑物、树木等不可避免的会对光伏组件的产生遮挡，影响太阳对其的辐射。而现有的辐照度预测仅单一考虑气象数据，通过学习历史时间段内的气象发展规律进行辐照度预测，忽略了分布式光伏电站的地理空间分布，无法反应分布式光伏电站的真实辐照情况。(1) Distributed photovoltaic power stations are mostly installed on residential roofs, open areas in rural or remote areas, exterior walls or side facades of buildings, etc. Buildings and trees that are close to the installation area will inevitably block the photovoltaic components and affect the solar radiation. The existing irradiance prediction only considers meteorological data and predicts irradiance by learning the meteorological development laws in the historical time period, ignoring the geographical spatial distribution of distributed photovoltaic power stations and failing to reflect the actual irradiation situation of distributed photovoltaic power stations.
（2）对于新建或位于偏远地区的分布式光伏电站，缺乏长期和连续的高质量历史气象数据，而现有的预测模型精度的提高依赖于大量标注数据的训练。(2) For newly built distributed photovoltaic power stations or those located in remote areas, there is a lack of long-term and continuous high-quality historical meteorological data, and improving the accuracy of existing prediction models depends on training with a large amount of labeled data.
发明内容Summary of the invention
为了解决现有技术的不足，本发明提供了一种基于时空特征的分布式光伏电站辐照度预测方法、系统、电子设备及计算机存储介质，将时间序列上的云层动态发展和体现空间分布的地理空间信息结合进行辐照度预测，提高分布式光伏电站辐照度预测的准确性和真实性。In order to address the deficiencies in the prior art, the present invention provides a distributed photovoltaic power station irradiance prediction method, system, electronic device and computer storage medium based on spatiotemporal characteristics, which combines the dynamic development of clouds in a time series with geographic spatial information reflecting spatial distribution to perform irradiance prediction, thereby improving the accuracy and authenticity of irradiance prediction for distributed photovoltaic power stations.
第一方面，本发明提供了一种基于时空特征的分布式光伏电站辐照度预测方法；In a first aspect, the present invention provides a method for predicting irradiance of a distributed photovoltaic power station based on spatiotemporal characteristics;
一种基于时空特征的分布式光伏电站辐照度预测方法，包括：A distributed photovoltaic power station irradiance prediction method based on spatiotemporal characteristics, comprising:
获取分布式光伏电站的卫星云图，基于卫星云图进行云层识别，获取云层覆盖特征图并进行云层动态追踪，生成云层覆盖预测特征图；Obtain satellite cloud images of distributed photovoltaic power stations, identify clouds based on satellite cloud images, obtain cloud coverage feature maps, perform cloud dynamic tracking, and generate cloud coverage prediction feature maps;
获取分布式光伏电站的理论辐照度，将理论辐照度和云层覆盖预测特征图关联并输入训练好的辐照度预测模型进行处理，获取分布式光伏电站下一时刻的预测辐照度；Obtain the theoretical irradiance of the distributed photovoltaic power station, associate the theoretical irradiance with the cloud cover prediction feature map and input it into the trained irradiance prediction model for processing to obtain the predicted irradiance of the distributed photovoltaic power station at the next moment;
获取分布式光伏电站的地理空间信息和安装参数，根据地理空间信息，利用GIS技术确定分布式光伏电站的辐照遮蔽特征；Obtain the geospatial information and installation parameters of distributed photovoltaic power stations, and use GIS technology to determine the radiation shielding characteristics of distributed photovoltaic power stations based on the geospatial information;
根据辐照遮蔽特征和安装参数对预测辐照度进行修正，获取辐照度预测结果。The predicted irradiance is corrected according to the irradiance shielding characteristics and installation parameters to obtain the irradiance prediction result.
在一些实施方式中，所述基于卫星云图进行云层识别具体为：将卫星云图转化为灰度图像，并基于预设的阈值对所述灰度图像中的每个像素点进行云层识别，确定云像素点并进行阈值分割，生成云层覆盖特征图。In some embodiments, the cloud layer identification based on satellite cloud images is specifically: converting the satellite cloud image into a grayscale image, and performing cloud layer identification on each pixel in the grayscale image based on a preset threshold, determining the cloud pixel points and performing threshold segmentation, and generating a cloud cover feature map.
在一些实施方式中，根据云层覆盖特征图进行云层动态追踪，生成云层覆盖预测特征图具体包括：In some embodiments, performing cloud dynamic tracking according to the cloud cover feature map to generate a cloud cover prediction feature map specifically includes:
将云层覆盖特征图分为多个子图，从子图中获取目标云层的像素矩阵图；The cloud cover feature map is divided into multiple sub-maps, and the pixel matrix map of the target cloud layer is obtained from the sub-maps;
根据像素矩阵图和相邻时刻云层覆盖特征图进行相似度计算，确定目标像素矩阵图；根据像素矩阵图和目标像素矩阵图中质心的位置坐标，确定目标云层的位移矢量；获取未来时间段内的风速和风向，根据目标云层的位移矢量、风速和风向，获取下一时刻目标云层的位置坐标，生成云层覆盖预测特征图。The target pixel matrix image is determined by performing similarity calculation on the pixel matrix image and the cloud coverage feature image at adjacent moments; the displacement vector of the target cloud layer is determined based on the position coordinates of the center of mass in the pixel matrix image and the target pixel matrix image; the wind speed and wind direction in the future time period are obtained, and the position coordinates of the target cloud layer at the next moment are obtained based on the displacement vector, wind speed and wind direction of the target cloud layer, to generate a cloud coverage prediction feature image.
在一些实施方式中，所述根据地理空间信息，利用GIS技术确定分布式光伏电站的辐照遮蔽特征具体包括：In some embodiments, determining the radiation shielding characteristics of the distributed photovoltaic power station using GIS technology based on geographic spatial information specifically includes:
根据地理空间信息，利用GIS技术构建分布式光伏电站的地理空间模型；Based on geographic spatial information, GIS technology is used to construct a geographic spatial model of distributed photovoltaic power stations;
基于地理空间模型，计算分布式光伏电站的安装面积和对应遮蔽物的总面积，生成遮蔽物对分布式光伏电站的辐照遮蔽面积。Based on the geospatial model, the installation area of the distributed photovoltaic power station and the total area of the corresponding shielding objects are calculated to generate the irradiation shielding area of the distributed photovoltaic power station caused by the shielding objects.
在一些实施方式中，所述根据辐照遮蔽特征和安装参数对预测辐照度进行修正，获取辐照度预测结果具体包括：In some embodiments, the step of correcting the predicted irradiance according to the irradiance shielding characteristics and the installation parameters to obtain the irradiance prediction result specifically includes:
将预测辐照度分解为太阳直射辐照强度和天空散射辐照强度；Decompose the predicted irradiance into direct solar irradiance and sky diffuse irradiance;
根据光伏组件的安装角度和太阳直射辐照强度，获取分布式光伏电站的表面直射辐照强度；根据安装参数和天空散射辐照强度，获取分布式光伏电站的表面散射辐照强度；According to the installation angle of photovoltaic modules and the direct solar radiation intensity, the surface direct radiation intensity of the distributed photovoltaic power station is obtained; according to the installation parameters and the sky scattered radiation intensity, the surface scattered radiation intensity of the distributed photovoltaic power station is obtained;
根据辐照遮蔽特征和安装参数，确定辐照遮蔽修正因子；Determine the radiation shielding correction factor based on the radiation shielding characteristics and installation parameters;
根据表面直射辐照强度和表面散热辐照强度，基于辐照遮蔽修正因子，获取辐照度预测结果。According to the surface direct radiation intensity and the surface heat dissipation radiation intensity, the irradiance prediction result is obtained based on the radiation shielding correction factor.
在一些实施方式中，所述辐照遮蔽修正因子表示为：In some embodiments, the radiation shielding correction factor is expressed as:
； ;
式中，为辐照遮蔽修正因子，为光伏安装总面积，为辐照遮蔽面积。In the formula, is the radiation shielding correction factor, is the total photovoltaic installation area, is the irradiation shielding area.
在一些实施方式中，所述辐照度预测模型为基于麻雀搜索算法优化的长短期记忆网络。In some embodiments, the irradiance prediction model is a long short-term memory network optimized based on a sparrow search algorithm.
第二方面，本发明提供了一种基于时空特征的分布式光伏电站辐照度预测系统；In a second aspect, the present invention provides a distributed photovoltaic power station irradiance prediction system based on spatiotemporal characteristics;
一种基于时空特征的分布式光伏电站辐照度预测系统，包括：A distributed photovoltaic power station irradiance prediction system based on spatiotemporal characteristics, comprising:
获取模块，被配置为：获取分布式光伏电站的卫星云图，基于卫星云图进行云层识别，获取云层覆盖特征图并进行云层动态追踪，生成云层覆盖预测特征图；The acquisition module is configured to: acquire satellite cloud images of the distributed photovoltaic power station, identify clouds based on the satellite cloud images, acquire cloud coverage feature maps and perform cloud dynamic tracking, and generate cloud coverage prediction feature maps;
预测模块，被配置为：获取分布式光伏电站的理论辐照度，将理论辐照度和云层覆盖预测特征图关联并输入训练好的辐照度预测模型进行处理，获取分布式光伏电站下一时刻的预测辐照度；The prediction module is configured to: obtain the theoretical irradiance of the distributed photovoltaic power station, associate the theoretical irradiance with the cloud cover prediction feature map and input the trained irradiance prediction model for processing, and obtain the predicted irradiance of the distributed photovoltaic power station at the next moment;
修正模块，被配置为：获取分布式光伏电站的地理空间信息和安装参数，根据地理空间信息，利用GIS技术确定分布式光伏电站的辐照遮蔽特征；根据辐照遮蔽特征和安装参数对预测辐照度进行修正，获取辐照度预测结果。The correction module is configured to: obtain the geographic spatial information and installation parameters of the distributed photovoltaic power station, determine the irradiation shielding characteristics of the distributed photovoltaic power station using GIS technology based on the geographic spatial information; correct the predicted irradiance based on the irradiation shielding characteristics and installation parameters to obtain the irradiance prediction result.
第三方面，本发明提供了一种电子设备；In a third aspect, the present invention provides an electronic device;
一种电子设备，包括存储器和处理器以及存储在存储器上并在处理器上运行的计算机指令，所述计算机指令被处理器运行时，完成上述的步骤。An electronic device includes a memory and a processor, and computer instructions stored in the memory and running on the processor. When the computer instructions are run by the processor, the above steps are completed.
第四方面，本发明提供了一种计算机可读存储介质；In a fourth aspect, the present invention provides a computer-readable storage medium;
一种计算机可读存储介质，用于存储计算机指令，所述计算机指令被处理器执行时，完成上述的步骤。A computer-readable storage medium is used to store computer instructions, and when the computer instructions are executed by a processor, the above steps are completed.
与现有技术相比，本发明的有益效果是：Compared with the prior art, the present invention has the following beneficial effects:
1、本发明提供的技术方案，根据分布式光伏电站的理论辐照度和云层动态发展趋势进行辐照度的初步预测，理论辐照度通过晴空模型计算即可得到，卫星云图通过气象局官方网站即可获取，无需在现场布置气象数据采集设备即可实现大量训练样本的获取，提高辐照度预测模型的预测精度。1. The technical solution provided by the present invention makes a preliminary prediction of irradiance based on the theoretical irradiance of the distributed photovoltaic power station and the dynamic development trend of the cloud layer. The theoretical irradiance can be obtained by calculating the clear sky model, and the satellite cloud map can be obtained through the official website of the Meteorological Bureau. A large number of training samples can be obtained without deploying meteorological data collection equipment on site, thereby improving the prediction accuracy of the irradiance prediction model.
2、本发明提供的技术方案，在进行辐照度预测时，充分考虑分布式光伏电站的地理空间分布以及云层随时间发展的动态变化趋势，结合时空特征，得到反应分布式光伏电站真实状态的辐照度预测结果，提高了辐照度预测的准确性。2. The technical solution provided by the present invention fully considers the geographical spatial distribution of distributed photovoltaic power stations and the dynamic change trend of cloud development over time when making irradiance predictions, and combines the temporal and spatial characteristics to obtain irradiance prediction results that reflect the actual state of distributed photovoltaic power stations, thereby improving the accuracy of irradiance predictions.
3、本发明提供的技术方案，在进行辐照度预测时，考虑光伏组件的安装角度对辐照度的影响，以适用于不同安装场景下的多种分布式光伏电站，并提高辐照度预测的准确性。3. The technical solution provided by the present invention takes into account the influence of the installation angle of photovoltaic modules on the irradiance when predicting irradiance, so as to be applicable to a variety of distributed photovoltaic power stations under different installation scenarios and improve the accuracy of irradiance prediction.
附图说明BRIEF DESCRIPTION OF THE DRAWINGS
构成本发明的一部分的说明书附图用来提供对本发明的进一步理解，本发明的示意性实施例及其说明用于解释本发明，并不构成对本发明的不当限定。The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.
图1为本发明实施例提供的基于时空特征的分布式光伏电站辐照度预测方法的流程示意图；FIG1 is a schematic diagram of a flow chart of a distributed photovoltaic power station irradiance prediction method based on spatiotemporal characteristics provided by an embodiment of the present invention;
图2为本发明实施例提供的基于时空特征的分布式光伏电站辐照度预测系统的系统框架示意图。FIG2 is a schematic diagram of the system framework of a distributed photovoltaic power station irradiance prediction system based on spatiotemporal characteristics provided by an embodiment of the present invention.
具体实施方式DETAILED DESCRIPTION
应该指出，以下详细说明都是示例性的，旨在对本发明提供进一步的说明。除非另有指明，本发明使用的所有技术和科学术语具有与本发明所属技术领域的普通技术人员通常理解的相同含义。It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used in the present invention have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.
需要注意的是，这里所使用的术语仅是为了描述具体实施方式，而非意图限制根据本发明的示例性实施方式。如在这里所使用的，除非上下文另外明确指出，否则单数形式也意图包括复数形式，此外，还应当理解的是，术语“包括”和“具有”以及他们的任何变形，意图在于覆盖不排他的包含，例如，包含了一系列步骤或单元的过程、方法、系统、产品或设备不必限于清楚地列出的那些步骤或单元，而是可包括没有清楚地列出的或对于这些过程、方法、产品或设备固有的其它步骤或单元。It should be noted that the terms used herein are only for describing specific embodiments, and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should also be understood that the terms "include" and "have" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
在不冲突的情况下，本发明中的实施例及实施例中的特征可以相互组合。In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.
实施例一Embodiment 1
现有分布式光伏电站的辐照度预测依赖于历史气象数据，且忽略了分布式光伏电站实际安装场景对辐照度预测的影响，无法反应其真实情形；因此，本发明提供了一种基于时空特征的分布式光伏电站辐照度预测方法，结合随时间发展的云层覆盖特征和受地理空间分布影响的辐照遮蔽特征进行分布式光伏电站的辐照度预测，提高预测的真实性和准确性。The irradiance prediction of existing distributed photovoltaic power stations relies on historical meteorological data, and ignores the impact of the actual installation scenarios of distributed photovoltaic power stations on the irradiance prediction, and cannot reflect the actual situation; therefore, the present invention provides an irradiance prediction method for distributed photovoltaic power stations based on temporal and spatial characteristics, which combines the cloud coverage characteristics that develop over time and the radiation shielding characteristics affected by geographic spatial distribution to predict the irradiance of distributed photovoltaic power stations, thereby improving the authenticity and accuracy of the prediction.
接下来，结合图1，对本实施例公开的一种基于时空特征的分布式光伏电站辐照度预测方法进行详细说明。该基于时空特征的分布式光伏电站辐照度预测方法，包括如下步骤：Next, in conjunction with FIG1 , a distributed photovoltaic power station irradiance prediction method based on spatiotemporal characteristics disclosed in this embodiment is described in detail. The distributed photovoltaic power station irradiance prediction method based on spatiotemporal characteristics includes the following steps:
S1、获取分布式光伏电站的卫星云图，基于卫星云图进行云层识别，获取云层覆盖特征图并进行云层动态追踪，生成云层覆盖预测特征图。S1. Obtain satellite cloud images of distributed photovoltaic power stations, identify clouds based on the satellite cloud images, obtain cloud coverage feature maps and perform cloud dynamic tracking to generate cloud coverage prediction feature maps.
随机移动的云层对太阳辐射的遮挡是影响分布式光伏电站辐照度的重要因素，因此，在本实施例中对云层随时间的发展趋势进行动态预测，以进行后续的辐照度预测。The shielding of solar radiation by randomly moving clouds is an important factor affecting the irradiance of distributed photovoltaic power stations. Therefore, in this embodiment, the development trend of clouds over time is dynamically predicted to perform subsequent irradiance prediction.
作为一种实施方式，S1具体包括：As an implementation mode, S1 specifically includes:
S101、根据分布式光伏电站的地理区域范围和历史时刻，通过气象局网站获取对应的卫星云图。S101. According to the geographical area and historical time of the distributed photovoltaic power station, the corresponding satellite cloud map is obtained through the website of the Meteorological Bureau.
S102、将上一时刻的卫星云图转化为灰度图像，并基于预设的阈值对灰度图像中的每个像素点进行云层识别，确定云像素点并进行阈值分割，生成云层覆盖特征图。S102, converting the satellite cloud image at the last moment into a grayscale image, and performing cloud layer recognition on each pixel in the grayscale image based on a preset threshold, determining cloud pixels and performing threshold segmentation to generate a cloud layer coverage feature map.
具体的，在本步骤中，首先，将卫星云图转化为灰度图像，以在充分反应云层特征的同时，提高数据的处理速度。Specifically, in this step, first, the satellite cloud image is converted into a grayscale image to improve the data processing speed while fully reflecting the characteristics of the cloud layer.
然后，由于卫星图像中通常含有云层信息和地面信息，因此，基于灰度图像进行云层识别，将灰度图像中像素值大于等于预设的阈值的像素点视为云层像素点，将灰度图像中小于预设的阈值的像素点视为非云层像素点。Then, since satellite images usually contain cloud information and ground information, cloud recognition is performed based on grayscale images. Pixels in the grayscale image with pixel values greater than or equal to a preset threshold are regarded as cloud pixels, and pixels in the grayscale image with pixel values less than the preset threshold are regarded as non-cloud pixels.
本实施例中，考虑到不同天气状况下，云层的状态不同，因此，预设的阈值的大小根据天气确定，例如，晴天下，预设的阈值为120。In this embodiment, considering that the states of clouds are different under different weather conditions, the value of the preset threshold is determined according to the weather. For example, under sunny conditions, the preset threshold is 120.
对于云层动态追踪而言，地面信息为无用信息，因此，接下来，将卫星云图转化为灰度图像，并为了消除地面信息和其他无关信息中的干扰，将灰度图像中的非云层像素点的像素值设置为0，云层像素点的像素值仍为其灰度值，进而生成云层覆盖特征图。For dynamic cloud tracking, ground information is useless. Therefore, next, the satellite cloud image is converted into a grayscale image. In order to eliminate the interference from ground information and other irrelevant information, the pixel values of non-cloud pixels in the grayscale image are set to 0, and the pixel values of cloud pixels remain their grayscale values, thereby generating a cloud cover feature map.
S103、根据云层覆盖特征图进行云层动态追踪，生成云层覆盖预测特征图。具体包括：S103, tracking the cloud layer dynamically according to the cloud layer coverage feature map, and generating a cloud layer coverage prediction feature map. Specifically including:
S1031、将云层覆盖特征图分为多个子图，从子图中提取目标云层的像素矩阵图。S1031, dividing the cloud cover feature map into multiple sub-maps, and extracting a pixel matrix map of the target cloud layer from the sub-maps.
考虑到一张云层覆盖特征图中可能具有多个云层，因此，在本实施例中，将云层覆盖特征图划分为多个大小相等的子图，以便于计算。Considering that a cloud cover feature map may have multiple cloud layers, in this embodiment, the cloud cover feature map is divided into multiple sub-maps of equal size to facilitate calculation.
S1032、根据像素矩阵图和当前时刻的云层覆盖特征图进行相似度计算，确定目标像素矩阵图；根据像素矩阵图和目标像素矩阵图中质心的位置坐标，确定目标云层的位移矢量。S1032, performing similarity calculation based on the pixel matrix image and the cloud cover feature image at the current moment to determine the target pixel matrix image; determining the displacement vector of the target cloud layer based on the position coordinates of the center of mass in the pixel matrix image and the target pixel matrix image.
具体的，从相邻时刻云层覆盖特征图中提取像素矩阵图对应的目标子图，将像素矩阵图在对应的目标子图的行和列两个维度上同时进行滑动，在滑动过程中，对像素矩阵图和目标子图中被像素矩阵图覆盖的区域进行二维卷积运算，并将二维卷积运算值以矩阵形式表示，作为相似度矩阵。将相似度矩阵中最大二维卷积运算值对应的位置坐标作为上一时刻和当前时刻目标云层的质心坐标。将上一时刻和当前时刻目标云层的质心坐标相减，得到目标云层在时间间隔内的位移矢量，表示如下：Specifically, the target sub-image corresponding to the pixel matrix image is extracted from the cloud coverage feature image at adjacent moments, and the pixel matrix image is slid simultaneously in the row and column dimensions of the corresponding target sub-image. During the sliding process, a two-dimensional convolution operation is performed on the pixel matrix image and the area covered by the pixel matrix image in the target sub-image, and the two-dimensional convolution operation value is expressed in matrix form as a similarity matrix. The position coordinates corresponding to the maximum two-dimensional convolution operation value in the similarity matrix are used as the centroid coordinates of the target cloud layer at the previous moment and the current moment. The centroid coordinates of the target cloud layer at the previous moment and the current moment are subtracted to obtain the centroid coordinates of the target cloud layer at the time interval. The displacement vector within is expressed as follows:
； ;
式中，为位移矢量，单位为像素点，为横坐标位移矢量，为当前时刻目标云层质心的横坐标，为上一时刻目标云层质心的横坐标，为纵坐标位移矢量，为当前时刻目标云层的纵坐标，为上一时刻目标云层质心的纵坐标。In the formula, is the displacement vector, in pixels. is the horizontal displacement vector, is the horizontal coordinate of the target cloud layer mass center at the current moment, is the horizontal coordinate of the target cloud layer mass center at the previous moment, is the vertical displacement vector, is the ordinate of the target cloud layer at the current moment, It is the ordinate of the centroid of the target cloud layer at the previous moment.
S1033、获取未来时间段内的风速和风向，根据目标云层的位移矢量、风速和风向，获取下一时刻目标云层的位置坐标，生成云层覆盖预测特征图。具体流程如下：S1033, obtaining the wind speed and wind direction in the future time period, obtaining the position coordinates of the target cloud layer at the next moment according to the displacement vector, wind speed and wind direction of the target cloud layer, and generating a cloud cover prediction feature map. The specific process is as follows:
（1）根据目标云层的位移矢量，确定在时间间隔内的云层移动速度和云层移动方向，表示如下：(1) According to the displacement vector of the target cloud layer, determine the time interval The speed of the clouds moving within and the direction of cloud movement , which is expressed as follows:
； ;
式中，为时间间隔∆t内的云层移动速度，为时间间隔∆t内的云层移动方向。In the formula, is the cloud moving speed within the time interval ∆t, is the cloud moving direction within the time interval ∆t.
（2）获取数值天气预报中的风速和风向，根据云层移动速度和云层移动方向，计算风速修正系数和风向修正系数，表示如下：(2) Obtain the wind speed and wind direction in the numerical weather forecast, and calculate the wind speed correction coefficient and wind direction correction coefficient according to the cloud movement speed and cloud movement direction, which are expressed as follows:
； ;
式中，为风速修正系数，为风向修正系数，为子图个数，为时刻的风速，为时刻的云层移动速度，为时刻的风向，为时刻的云层移动方向。In the formula, is the wind speed correction factor, is the wind direction correction factor, is the number of sub-graphs, for The wind speed at the moment, for The speed of cloud movement at a given moment, for The wind direction at the moment, for The direction of cloud movement at the moment.
（3）根据风速修正系数、风向修正系数、下一时刻的风速和风向，计算下一时刻的云层的移动速度和移动方向，表示如下：(3) Based on the wind speed correction coefficient, wind direction correction coefficient, wind speed and wind direction at the next moment, calculate the moving speed and moving direction of the cloud layer at the next moment, as shown below:
； ;
式中，为下一时刻云层的移动速度，为下一时刻的风速，通过数值天气预报获取，为下一时刻云层的移动方向，为下一时刻的风向。In the formula, is the moving speed of the cloud at the next moment, is the wind speed at the next moment, obtained through numerical weather forecast, is the moving direction of the cloud at the next moment, The wind direction for the next moment.
（4）根据下一时刻的云层的移动速度和移动方向，得到下一时刻云层像素点的位置坐标，生成云层覆盖预测特征图；下一时刻云层各像素点的位置坐标表示如下：(4) According to the moving speed and direction of the cloud layer at the next moment, the position coordinates of the cloud layer pixel point at the next moment are obtained , generate the cloud cover prediction feature map; the position coordinates of each pixel point in the cloud layer at the next moment are expressed as follows:
。 .
S2、获取分布式光伏电站的理论辐照度，将理论辐照度和云层覆盖预测特征图关联并输入训练好的辐照度预测模型进行处理，获取分布式光伏电站下一时刻的预测辐照度。S2. Obtain the theoretical irradiance of the distributed photovoltaic power station, associate the theoretical irradiance with the cloud cover prediction feature map and input the trained irradiance prediction model for processing to obtain the predicted irradiance of the distributed photovoltaic power station at the next moment.
本实施例中，分布式光伏电站的理论辐照度可以通过现有理论辐照度计算软件获取或晴空模型获取，辐照度预测模型为基于麻雀搜索算法优化的长短期记忆网络，并未对长短期记忆网络的架构及麻雀优化算法做改进，在此不再赘述。辐照度预测模型的输入为理论辐照度和云层覆盖预测特征图关联，输出为分布式光伏电站下一时刻的预测辐照度。In this embodiment, the theoretical irradiance of the distributed photovoltaic power station can be obtained through the existing theoretical irradiance calculation software or the clear sky model. The irradiance prediction model is a long short-term memory network optimized based on the sparrow search algorithm. The architecture of the long short-term memory network and the sparrow optimization algorithm have not been improved, which will not be repeated here. The input of the irradiance prediction model is the association between the theoretical irradiance and the cloud cover prediction feature map, and the output is the predicted irradiance of the distributed photovoltaic power station at the next moment.
具体的，训练长短期记忆网络时，以训练样本平均平方误差最小为目标函数，利用麻雀搜索算法对长短期记忆网络的超参数进行寻优处理，超参数包括隐藏层神经元数量、批大小和初始学习率。目标函数表示如下：Specifically, when training the LSTM network, the objective function is to minimize the mean square error of the training samples, and the sparrow search algorithm is used to optimize the hyperparameters of the LSTM network. The hyperparameters include the number of neurons in the hidden layer, the batch size, and the initial learning rate. The objective function is expressed as follows:
； ;
式中，表示训练样本平均平方误差，表示第j个时间点的预测值，表示第j个时间点的真实值，m为训练集数量。In the formula, represents the mean square error of the training samples, represents the predicted value at the jth time point, represents the true value at the jth time point, and m is the number of training sets.
通过麻雀搜索算法强大的寻优能力，能够快速确定超参数的最佳配置，实现辐照度预测模型的快速训练。同时，在本实施例中，综合考虑云层发展趋势对辐照度发展的影响，提高了辐照度预测的准确性。Through the powerful optimization ability of the sparrow search algorithm, the optimal configuration of the hyperparameters can be quickly determined, and the rapid training of the irradiance prediction model can be achieved. At the same time, in this embodiment, the impact of the cloud development trend on the irradiance development is comprehensively considered to improve the accuracy of the irradiance prediction.
S3、获取分布式光伏电站的地理空间信息和安装参数，根据地理空间信息，利用GIS技术确定各光伏组件的辐照遮蔽特征。S3. Obtain the geospatial information and installation parameters of the distributed photovoltaic power station, and use GIS technology to determine the radiation shielding characteristics of each photovoltaic module based on the geospatial information.
在分布式光伏电站的使用过程中，遮挡物对太阳光的潜在遮蔽会对最终照射至光伏组件的阳光造成很大影响，因此，在本实施例中，充分考虑潜在遮蔽对辐照度预测的影响，通过GIS技术对相邻遮挡物的遮蔽特征进行量化。During the use of distributed photovoltaic power stations, the potential shielding of sunlight by obstructions will have a great impact on the sunlight that ultimately reaches the photovoltaic modules. Therefore, in this embodiment, the impact of potential shielding on irradiance prediction is fully considered, and the shielding characteristics of adjacent obstructions are quantified through GIS technology.
作为一种实施方式，S3具体包括：As an implementation mode, S3 specifically includes:
S301、根据地理空间信息，利用GIS技术构建分布式光伏电站的地理空间模型。S301. Based on the geographic spatial information, a geographic spatial model of a distributed photovoltaic power station is constructed using GIS technology.
具体的，获取分布式光伏电站区域范围内建筑物的经纬度信息、高度信息、物理信息和建筑资料，将经纬度信息、高度信息、物理信息和建筑资料导入GIS平台，生成分布式光伏电站的地理空间模型。Specifically, the longitude and latitude information, altitude information, physical information and construction data of the buildings within the distributed photovoltaic power station area are obtained, and the longitude and latitude information, altitude information, physical information and construction data are imported into the GIS platform to generate a geographic spatial model of the distributed photovoltaic power station.
现有GIS技术的发展已经较为成熟，通过GIS平台构建地理空间模型是现有技术的常规技术手段，本实施例也并未对其做改进，在此不再赘述。The development of existing GIS technology is relatively mature. Building a geographic spatial model through a GIS platform is a conventional technical means of the prior art. This embodiment does not make any improvements thereto, and will not be described in detail here.
S302、基于地理空间模型，计算分布式光伏电站对应遮蔽物的总面积，生成遮蔽物对分布式光伏电站的辐照遮蔽面积。S302: Based on the geographic space model, the total area of the shielding objects corresponding to the distributed photovoltaic power station is calculated to generate the irradiation shielding area of the distributed photovoltaic power station caused by the shielding objects.
具体的，通过地理空间模型和GIS平台中的量测功能，得到分布式光伏电站的安装面积和对应遮蔽物的总面积，根据分布式光伏电站对应遮蔽物的总面积，生成遮蔽物对分布式光伏电站的辐照遮蔽面积，表示如下：Specifically, through the measurement function in the geospatial model and the GIS platform, the installation area of the distributed photovoltaic power station and the total area of the corresponding shielding objects are obtained. According to the total area of the distributed photovoltaic power station corresponding to the shielding objects, the irradiation shielding area of the distributed photovoltaic power station by the shielding objects is generated, which is expressed as follows:
； ;
式中，为辐照遮蔽面积，为第一权重参数，为太阳高度角，为遮蔽物的总面积。In the formula, is the irradiation shielding area, is the first weight parameter, is the solar altitude angle, is the total area of the shelter.
S4、根据辐照遮蔽特征和安装参数对预测辐照度进行修正，获取辐照度预测结果。S4. Correct the predicted irradiance according to the irradiance shielding characteristics and installation parameters to obtain the irradiance prediction result.
作为一种实施方式，S4具体包括：As an implementation mode, S4 specifically includes:
S401、将预测辐照度分解为太阳直射辐照强度和天空散射辐照强度；根据光伏组件的安装角度和太阳直射辐照强度，获取分布式光伏电站的表面直射辐照强度；根据安装参数和天空散射辐照强度，获取分布式光伏电站的表面散射辐照强度。S401. Decompose the predicted irradiance into direct solar radiation intensity and sky diffuse radiation intensity; obtain the surface direct radiation intensity of the distributed photovoltaic power station according to the installation angle of the photovoltaic modules and the direct solar radiation intensity; obtain the surface diffuse radiation intensity of the distributed photovoltaic power station according to the installation parameters and the sky diffuse radiation intensity.
示例性的，首先，根据理论辐射系数，计算天空散射辐照强度，天空散射辐照强度，表示如下：Exemplarily, first, the sky diffuse irradiance intensity is calculated according to the theoretical radiation coefficient. The sky diffuse irradiance intensity is expressed as follows:
； ;
式中，为天空散射辐照强度，为理论总辐射系数，为全球总的水平辐照度，可通过Pvsyst软件根据地理位置、日期和时间获取。In the formula, is the sky diffuse irradiance intensity, is the theoretical total radiation coefficient, It is the total global horizontal irradiance and can be obtained through Pvsyst software according to geographic location, date and time.
然后，根据预测辐照度和天空散热辐射强度，计算太阳直射辐照强度，太阳直射辐照强度表示如下：Then, the direct solar radiation intensity is calculated based on the predicted irradiance and the sky heat radiation intensity. The direct solar radiation intensity is expressed as follows:
； ;
式中，为太阳直射辐照强度，I为预测辐照度。In the formula, is the direct solar radiation intensity, and I is the predicted irradiance.
根据光伏组件的安装角度和太阳直射辐照强度，计算光伏组件的表面直射辐照强度和表面散射强度，表面直射辐照强度表示如下：According to the installation angle of the photovoltaic module and the direct solar radiation intensity, the surface direct radiation intensity and surface scattered intensity of the photovoltaic module are calculated. The surface direct radiation intensity is expressed as follows:
； ;
式中，为表面直射辐照强度，为太阳的赤纬角，为光伏组件的安装角度，为太阳的时角。In the formula, is the direct radiation intensity on the surface, is the solar declination angle, is the installation angle of the photovoltaic module, is the hour angle of the sun.
表面散射辐照强度表示如下：The surface scattered irradiance intensity is expressed as follows:
； ;
； ;
式中，为中间参数。In the formula, is the intermediate parameter.
S402、根据辐照遮蔽特征和安装参数，确定辐照遮蔽修正因子，辐照遮蔽修正因子表示为：S402. Determine the radiation shielding correction factor according to the radiation shielding characteristics and installation parameters. The radiation shielding correction factor is expressed as:
； ;
式中，为辐照遮蔽修正因子，为光伏安装总面积。In the formula, is the radiation shielding correction factor, is the total photovoltaic installation area.
S403、根据表面直射辐照强度和表面散热辐照强度，基于辐照遮蔽修正因子，获取辐照度预测结果。S403: Obtain irradiance prediction results according to the surface direct radiation intensity and the surface heat dissipation radiation intensity based on the radiation shielding correction factor.
示例性的，辐照度预测结果表示如下：Exemplarily, the irradiance prediction result is expressed as follows:
； ;
式中，为辐照度预测结果，为第二权重参数。In the formula, is the irradiance prediction result, is the second weight parameter.
实施例二Embodiment 2
结合图2，本实施例公开了一种基于时空特征的分布式光伏电站辐照度预测系统，包括：In conjunction with FIG2 , this embodiment discloses a distributed photovoltaic power station irradiance prediction system based on spatiotemporal characteristics, including:
获取模块，被配置为：获取分布式光伏电站的卫星云图，基于卫星云图进行云层识别，获取云层覆盖特征图并进行云层动态追踪，生成云层覆盖预测特征图；The acquisition module is configured to: acquire satellite cloud images of the distributed photovoltaic power station, identify clouds based on the satellite cloud images, acquire cloud coverage feature maps and perform cloud dynamic tracking, and generate cloud coverage prediction feature maps;
预测模块，被配置为：获取分布式光伏电站的理论辐照度，将理论辐照度和云层覆盖预测特征图关联并输入训练好的辐照度预测模型进行处理，获取分布式光伏电站下一时刻的预测辐照度；The prediction module is configured to: obtain the theoretical irradiance of the distributed photovoltaic power station, associate the theoretical irradiance with the cloud cover prediction feature map and input the trained irradiance prediction model for processing, and obtain the predicted irradiance of the distributed photovoltaic power station at the next moment;
修正模块，被配置为：获取分布式光伏电站的地理空间信息和安装参数，根据地理空间信息，利用GIS技术确定分布式光伏电站的辐照遮蔽特征；根据辐照遮蔽特征和安装参数对预测辐照度进行修正，获取辐照度预测结果。The correction module is configured to: obtain the geographic spatial information and installation parameters of the distributed photovoltaic power station, determine the irradiation shielding characteristics of the distributed photovoltaic power station using GIS technology based on the geographic spatial information; correct the predicted irradiance based on the irradiation shielding characteristics and installation parameters to obtain the irradiance prediction result.
此处需要说明的是，上述获取模块、预测模块和修正模块对应于实施例一中的步骤，上述模块与对应的步骤所实现的示例和应用场景相同，但不限于上述实施例一所公开的内容。需要说明的是，上述模块作为系统的一部分可以在诸如一组计算机可执行指令的计算机系统中执行。It should be noted that the acquisition module, prediction module and correction module described above correspond to the steps in Embodiment 1, and the examples and application scenarios implemented by the modules and the corresponding steps are the same, but are not limited to the contents disclosed in Embodiment 1. It should be noted that the modules described above as part of the system can be executed in a computer system such as a set of computer executable instructions.
实施例三Embodiment 3
本发明实施例三提供一种电子设备，包括存储器和处理器以及存储在存储器上并在处理器上运行的计算机指令，计算机指令被处理器运行时，完成上述基于时空特征的分布式光伏电站辐照度预测方法的步骤。Embodiment 3 of the present invention provides an electronic device, including a memory and a processor, and computer instructions stored in the memory and executed on the processor. When the computer instructions are executed by the processor, the steps of the above-mentioned distributed photovoltaic power station irradiance prediction method based on spatiotemporal characteristics are completed.
实施例四Embodiment 4
本发明实施例四提供一种计算机可读存储介质，用于存储计算机指令，所述计算机指令被处理器执行时，完成上述基于时空特征的分布式光伏电站辐照度预测方法的步骤。Embodiment 4 of the present invention provides a computer-readable storage medium for storing computer instructions. When the computer instructions are executed by a processor, the steps of the above-mentioned distributed photovoltaic power station irradiance prediction method based on spatiotemporal characteristics are completed.
本发明是参照根据本发明实施例的方法、设备（系统）、和计算机程序产品的流程图和／或方框图来描述的。应理解可由计算机程序指令实现流程图和／或方框图中的每一流程和／或方框、以及流程图和／或方框图中的流程和／或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和／或方框图一个方框或多个方框中指定的功能的装置。The present invention is described with reference to the flowcharts and/or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and/or box in the flowchart and/or block diagram, as well as the combination of the processes and/or boxes in the flowchart and/or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device for implementing the functions specified in one or more processes in the flowchart and/or one or more boxes in the block diagram.
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和／或方框图一个方框或多个方框中指定的功能。These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device that implements the functions specified in one or more processes in the flowchart and/or one or more boxes in the block diagram.
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和／或方框图一个方框或多个方框中指定的功能的步骤。These computer program instructions may also be loaded onto a computer or other programmable data processing device, and a series of operating steps may be executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and/or one or more boxes in the block diagram.
上述实施例中对各个实施例的描述各有侧重，某个实施例中没有详述的部分可以参见其他实施例的相关描述。The description of each embodiment in the above embodiments has different emphases. For parts not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
以上所述仅为本发明的优选实施例而已，并不用于限制本发明，对于本领域的技术人员来说，本发明可以有各种更改和变化。凡在本发明的精神和原则之内，所作的任何修改、等同替换、改进等，均应包含在本发明的保护范围之内。The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411034426.9ACN118587608B (en) | 2024-07-31 | 2024-07-31 | Distributed photovoltaic power station irradiance prediction method and system based on spatiotemporal characteristics |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411034426.9ACN118587608B (en) | 2024-07-31 | 2024-07-31 | Distributed photovoltaic power station irradiance prediction method and system based on spatiotemporal characteristics |
| Publication Number | Publication Date |
|---|---|
| CN118587608Atrue CN118587608A (en) | 2024-09-03 |
| CN118587608B CN118587608B (en) | 2024-10-15 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411034426.9AActiveCN118587608B (en) | 2024-07-31 | 2024-07-31 | Distributed photovoltaic power station irradiance prediction method and system based on spatiotemporal characteristics |
| Country | Link |
|---|---|
| CN (1) | CN118587608B (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119808608A (en)* | 2025-03-14 | 2025-04-11 | 苏州大学 | A method and device for identifying partial shading of photovoltaic modules |
| CN119962929A (en)* | 2025-04-09 | 2025-05-09 | 上海艾涛信息科技发展有限公司 | Power dispatching method, system and storage medium of microgrid based on Internet of Things |
| CN120275756A (en)* | 2025-06-10 | 2025-07-08 | 国网黑龙江省电力有限公司哈尔滨供电公司 | New energy access fault detection method considering three-phase unbalance of power distribution system |
| CN120632801A (en)* | 2025-08-15 | 2025-09-12 | 云南师范大学 | Solar irradiance prediction method and system based on data fusion |
| CN120632801B (en)* | 2025-08-15 | 2025-10-14 | 云南师范大学 | A solar irradiance prediction method and system based on data fusion |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015160604A1 (en)* | 2014-04-17 | 2015-10-22 | Siemens Aktiengesellschaft | Short term cloud coverage prediction using ground-based all sky imaging |
| US20170127008A1 (en)* | 2015-10-29 | 2017-05-04 | Microsoft Technology Licensing, Llc | Tracking object of interest in an omnidirectional video |
| FR3047829A1 (en)* | 2016-02-12 | 2017-08-18 | Cie Nat Du Rhone | METHOD FOR ESTIMATING THE POSITION OF THE SOLAR DISK IN A SKY IMAGE |
| CN108369816A (en)* | 2015-11-11 | 2018-08-03 | 微软技术许可有限责任公司 | Apparatus and method for creating video clips from omnidirectional video |
| US20180367777A1 (en)* | 2017-06-15 | 2018-12-20 | Lenovo (Singapore) Pte. Ltd. | Tracking a point of interest in a panoramic video |
| CN110570448A (en)* | 2019-09-07 | 2019-12-13 | 深圳岚锋创视网络科技有限公司 | Target tracking method and device of panoramic video and portable terminal |
| CN113076865A (en)* | 2021-03-31 | 2021-07-06 | 国能日新科技股份有限公司 | Method and system for inverting irradiance based on sky photographing image and satellite cloud image |
| WO2021204226A1 (en)* | 2020-04-09 | 2021-10-14 | 国网江苏省电力有限公司苏州供电分公司 | Photovoltaic power prediction method under lightning condition based on thundercloud trajectory tracking |
| CN115759483A (en)* | 2023-01-06 | 2023-03-07 | 国能日新科技股份有限公司 | Photovoltaic electric field solar irradiance prediction method, electronic device and storage medium |
| CN116610186A (en)* | 2023-05-11 | 2023-08-18 | 福建万芯科技有限公司 | New energy photovoltaic power generation and energy storage method and related equipment |
| CN117498321A (en)* | 2023-11-02 | 2024-02-02 | 国网江苏省电力有限公司电力科学研究院 | Distributed photovoltaic output prediction method, system and storage medium |
| CN117709482A (en)* | 2023-12-14 | 2024-03-15 | 国网新能源云技术有限公司 | A method, device, equipment and medium for predicting regional photovoltaic power generation |
| CN118117603A (en)* | 2023-11-06 | 2024-05-31 | 中电投新疆能源化工集团木垒新能源有限公司 | Digital management method and system for photovoltaic power station, electronic equipment and medium |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015160604A1 (en)* | 2014-04-17 | 2015-10-22 | Siemens Aktiengesellschaft | Short term cloud coverage prediction using ground-based all sky imaging |
| US20170127008A1 (en)* | 2015-10-29 | 2017-05-04 | Microsoft Technology Licensing, Llc | Tracking object of interest in an omnidirectional video |
| CN108369816A (en)* | 2015-11-11 | 2018-08-03 | 微软技术许可有限责任公司 | Apparatus and method for creating video clips from omnidirectional video |
| FR3047829A1 (en)* | 2016-02-12 | 2017-08-18 | Cie Nat Du Rhone | METHOD FOR ESTIMATING THE POSITION OF THE SOLAR DISK IN A SKY IMAGE |
| US20180367777A1 (en)* | 2017-06-15 | 2018-12-20 | Lenovo (Singapore) Pte. Ltd. | Tracking a point of interest in a panoramic video |
| CN110570448A (en)* | 2019-09-07 | 2019-12-13 | 深圳岚锋创视网络科技有限公司 | Target tracking method and device of panoramic video and portable terminal |
| WO2021204226A1 (en)* | 2020-04-09 | 2021-10-14 | 国网江苏省电力有限公司苏州供电分公司 | Photovoltaic power prediction method under lightning condition based on thundercloud trajectory tracking |
| CN113076865A (en)* | 2021-03-31 | 2021-07-06 | 国能日新科技股份有限公司 | Method and system for inverting irradiance based on sky photographing image and satellite cloud image |
| CN115759483A (en)* | 2023-01-06 | 2023-03-07 | 国能日新科技股份有限公司 | Photovoltaic electric field solar irradiance prediction method, electronic device and storage medium |
| CN116610186A (en)* | 2023-05-11 | 2023-08-18 | 福建万芯科技有限公司 | New energy photovoltaic power generation and energy storage method and related equipment |
| CN117498321A (en)* | 2023-11-02 | 2024-02-02 | 国网江苏省电力有限公司电力科学研究院 | Distributed photovoltaic output prediction method, system and storage medium |
| CN118117603A (en)* | 2023-11-06 | 2024-05-31 | 中电投新疆能源化工集团木垒新能源有限公司 | Digital management method and system for photovoltaic power station, electronic equipment and medium |
| CN117709482A (en)* | 2023-12-14 | 2024-03-15 | 国网新能源云技术有限公司 | A method, device, equipment and medium for predicting regional photovoltaic power generation |
| Title |
|---|
| B KIM: "A Hybrid Spatio-Temporal Prediction Model for Solar Photovoltaic Generation Using Numerical Weather Data and Satellite Images", IEEE, 31 December 2020 (2020-12-31)* |
| 刘刚: "基于K-Means和GBR...分布式光伏中短期发电量预测", 能源与环保, 31 December 2023 (2023-12-31)* |
| 陈志宝;李秋水;程序;周海;丁杰;: "基于地基云图的光伏功率超短期预测模型", 电力系统自动化, no. 19, 10 October 2013 (2013-10-10)* |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119808608A (en)* | 2025-03-14 | 2025-04-11 | 苏州大学 | A method and device for identifying partial shading of photovoltaic modules |
| CN119962929A (en)* | 2025-04-09 | 2025-05-09 | 上海艾涛信息科技发展有限公司 | Power dispatching method, system and storage medium of microgrid based on Internet of Things |
| CN120275756A (en)* | 2025-06-10 | 2025-07-08 | 国网黑龙江省电力有限公司哈尔滨供电公司 | New energy access fault detection method considering three-phase unbalance of power distribution system |
| CN120275756B (en)* | 2025-06-10 | 2025-08-15 | 国网黑龙江省电力有限公司哈尔滨供电公司 | Fault detection method for new energy access considering three-phase imbalance in distribution system |
| CN120632801A (en)* | 2025-08-15 | 2025-09-12 | 云南师范大学 | Solar irradiance prediction method and system based on data fusion |
| CN120632801B (en)* | 2025-08-15 | 2025-10-14 | 云南师范大学 | A solar irradiance prediction method and system based on data fusion |
| Publication number | Publication date |
|---|---|
| CN118587608B (en) | 2024-10-15 |
| Publication | Publication Date | Title |
|---|---|---|
| Si et al. | Hybrid solar forecasting method using satellite visible images and modified convolutional neural networks | |
| Rodríguez et al. | Assessment of the photovoltaic potential at urban level based on 3D city models: A case study and new methodological approach | |
| CN118587608B (en) | Distributed photovoltaic power station irradiance prediction method and system based on spatiotemporal characteristics | |
| Agoua et al. | Short-term spatio-temporal forecasting of photovoltaic power production | |
| Vulkan et al. | Modeling the potential for PV installation in residential buildings in dense urban areas | |
| CN103971169B (en) | A prediction method of ultra-short-term photovoltaic power generation based on cloud cover simulation | |
| Liu et al. | A novel approach for assessing rooftop-and-facade solar photovoltaic potential in rural areas using three-dimensional (3D) building models constructed with GIS | |
| Wen et al. | A regional solar forecasting approach using generative adversarial networks with solar irradiance maps | |
| Moreno et al. | A day-ahead irradiance forecasting strategy for the integration of photovoltaic systems in virtual power plants | |
| CN116722544B (en) | Distributed photovoltaic short-term prediction method and device, electronic equipment and storage medium | |
| CN115496263A (en) | Short-term photovoltaic power generation prediction method based on space-time genetic attention network | |
| CN111121956A (en) | Photovoltaic agricultural solar radiation amount analysis method based on flat single-axis tracking support | |
| CN116128170A (en) | Photovoltaic power station power ultra-short-term prediction method and device and related equipment | |
| CN115455811A (en) | Layout method of photovoltaic power station panels based on digital twin and deep reinforcement learning | |
| Tan et al. | Application of multi-source data fusion on intelligent prediction of photovoltaic power | |
| Deng et al. | Distributed photovoltaic power forecasting based on personalized federated adversarial learning | |
| CN118332520B (en) | Time sequence prediction model construction method considering space-time proximity | |
| CN114819257A (en) | Irradiation calculation method, device and equipment | |
| Su et al. | An Intra-Hour photovoltaic power generation prediction method for flexible building energy systems and its application in operation scheduling strategy | |
| Liu et al. | Ultra-Short-Term Power Forecasting for Distributed PV based on Multi-Source Remote Sensing Information and Adaptive Feature Extraction | |
| Sow et al. | Towards deep learning methods to improve photovoltaic prediction and building decarbonization in benchmarking study | |
| CN117036979A (en) | Artificial intelligent image recognition method based on deep learning | |
| CN114037901B (en) | Photovoltaic power generation forecast-oriented real-time satellite near-infrared image calculation method | |
| Li et al. | Clean Energy Technology and Energy Storage Systems: 8th International Conference on Life System Modeling and Simulation, LSMS 2024 and 8th International Conference on Intelligent Computing for Sustainable Energy and Environment, ICSEE 2024, Suzhou, China, September 13–15, 2024, Proceedings, Part III | |
| Zhang et al. | Multi-variable photovoltaic power prediction method based on deep attention convolutional neural network |
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |