A photovoltaic power prediction method, system, device and medium for a photovoltaic power station

Abstract

A photovoltaic power prediction method, system, device and medium of a photovoltaic power station relate to the technical field of data processing. The method comprises: acquiring spatial position information of a plurality of photovoltaic power stations in a target area, and dividing each photovoltaic power station into an upstream power station group and a downstream power station group based on the spatial position information; receiving power change data and meteorological data of the upstream power station group in a first time period; when the power change data and the meteorological data satisfy a preset extreme weather judgment condition, calculating an extreme weather movement parameter based on the meteorological data, and determining an extreme weather propagation time sequence according to the extreme weather movement parameter and the relative position between the upstream power station group and the downstream power station group; and combining the power change data and the extreme weather propagation time sequence to predict photovoltaic power of the downstream power station group in a second time period. The technical scheme provided by the application achieves the effect of improving the accuracy of photovoltaic power prediction of the photovoltaic power station.

Description

Technical Field

[0001] This application relates to the field of data processing technology, specifically to a method, system, equipment, and medium for predicting photovoltaic power in a photovoltaic power plant. Background Technology

[0002] With the increasing global demand for renewable energy, solar photovoltaic power generation, as a clean energy technology, has been widely applied and developed. Photovoltaic power plants can convert sunlight into electricity, which is of great significance for reducing dependence on fossil fuels and mitigating environmental pollution. Therefore, how to accurately predict power output has become an urgent problem to be solved.

[0003] Currently, existing methods for predicting photovoltaic (PV) power output mainly rely on analyzing historical power data from PV power plants to forecast future output. However, in practical applications, the actual operation of PV power plants is affected by weather changes. Using only historical data for power prediction often fails to account for the impact of extreme weather events, leading to biased predictions and reducing the accuracy of PV power output forecasts. Summary of the Invention

[0004] This application provides a method, system, electronic device, and storage medium for predicting photovoltaic power in a photovoltaic power plant, which can improve the accuracy of photovoltaic power prediction in a photovoltaic power plant.

[0005] Firstly, this application provides a method for predicting the photovoltaic power output of a photovoltaic power plant, including:

[0006] Acquire spatial location information of multiple photovoltaic power stations within the target area, and based on the spatial location information, divide each photovoltaic power station into an upstream power station group and a downstream power station group;

[0007] Receive power change data and meteorological data of the upstream power station in the first time period;

[0008] When the power change data and the meteorological data meet the preset extreme weather judgment conditions, the extreme weather movement parameters are calculated based on the meteorological data, and the extreme weather propagation sequence is determined according to the extreme weather movement parameters and the relative positions between the upstream power station group and the downstream power station group.

[0009] By combining the power change data and the propagation timeline of the extreme weather, the photovoltaic power output of the downstream power plant in the second time period is predicted.

[0010] A second aspect of this application provides a photovoltaic power prediction system for a photovoltaic power plant, the system comprising:

[0011] The power station group division module is used to obtain the spatial location information of multiple photovoltaic power stations within the target area, and based on the spatial location information, divide each photovoltaic power station into an upstream power station group and a downstream power station group.

[0012] The data receiving module is used to receive power change data and meteorological data of the upstream power station in the first time period;

[0013] The propagation timing determination module is used to calculate extreme weather movement parameters based on the meteorological data when the power change data and the meteorological data meet the preset extreme weather judgment conditions, and to determine the extreme weather propagation timing based on the extreme weather movement parameters and the relative positions between the upstream power station group and the downstream power station group.

[0014] The photovoltaic power prediction module is used to combine the power change data and the propagation timeline of the extreme weather to predict the photovoltaic power of the downstream power plant in the second time period.

[0015] A third aspect of this application provides an electronic device including a memory, a processor, and a program stored in the memory and executable on the processor, the program being loaded and executed by the processor to implement a photovoltaic power prediction method for a photovoltaic power plant.

[0016] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, causes the processor to implement a photovoltaic power prediction method for a photovoltaic power plant.

[0017] In summary, one or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages:

[0018] By adopting the above technical solution, photovoltaic power plants are divided into upstream and downstream power plant groups based on the acquired spatial location information. This spatial division method enables the system to effectively capture the propagation patterns of extreme weather, providing spatial support for power prediction. The system establishes an extreme weather determination mechanism by analyzing power change data and meteorological data from the upstream power plant groups, enabling timely identification of weather systems that may significantly impact photovoltaic power generation. After confirming extreme weather conditions, the system calculates extreme weather movement parameters based on meteorological data. These parameters, combined with the relative location information of the upstream and downstream power plant groups, allow the system to accurately predict the propagation process of extreme weather, forming a complete propagation timeline. By combining the power change characteristics of the upstream power plant groups with the extreme weather propagation timeline and considering the attenuation effect of propagation distance, the system achieves accurate prediction of power changes in the downstream power plant groups. By considering both the dimensions of extreme weather impact and power data change, the system comprehensively predicts the photovoltaic power of the photovoltaic power plant, reducing deviations caused by weather influences and thus improving the accuracy of photovoltaic power prediction results. Attached Figure Description

[0019] Figure 1 This is a schematic flowchart of a photovoltaic power prediction method for a photovoltaic power plant provided in an embodiment of this application;

[0020] Figure 2 This is a schematic diagram of the structure of a photovoltaic power prediction system for a photovoltaic power station provided in an embodiment of this application;

[0021] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0022] Explanation of reference numerals in the attached drawings: 300, electronic device; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. Detailed Implementation

[0023] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0024] In the description of the embodiments of this application, the words "for example" or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design that is described as "for example" or "for instance" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design options. Rather, the use of the words "for example" or "for instance" is intended to present the relevant concepts in a specific manner.

[0025] In the description of the embodiments of this application, the term "multiple" means two or more. For example, multiple systems means two or more systems, and multiple screen terminals means two or more screen terminals. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the indicated technical features. Thus, a feature defined with "first" or "second" may explicitly or implicitly include one or more of that feature. The terms "comprising," "including," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized.

[0026] This application provides a method for predicting photovoltaic power in a photovoltaic power plant. In one embodiment, please refer to... Figure 1 , Figure 1 This is a flowchart illustrating the photovoltaic power prediction method for a photovoltaic power plant provided in this application embodiment. This method can be implemented using a computer program, which can be integrated into an application or run as a standalone utility application. The method can also be implemented using a microcontroller and can run on a photovoltaic power prediction system for a photovoltaic power plant based on the von Neumann architecture. Specifically, the method may include the following steps:

[0027] Step 101: Obtain the spatial location information of multiple photovoltaic power stations within the target area, and based on the spatial location information, divide each photovoltaic power station into upstream power station group and downstream power station group.

[0028] Spatial location information refers to the distribution characteristics of photovoltaic power stations in geographic space, specifically including the geographical coordinates, altitude, and prevailing wind direction of the location. Spatial location information can be obtained through geographic information acquisition equipment installed at the photovoltaic power station or retrieved from a geographic information system database.

[0029] Upstream power plant clusters refer to a group of photovoltaic power plants within a target area, defined by geographical correlation and prevailing wind direction. Specifically, they refer to photovoltaic power plant groups with a geographical correlation greater than the correlation threshold and a prevailing wind direction upwind. These power plants are typically located at the forefront of weather system propagation paths and are the first to be affected by weather changes.

[0030] Downstream power plant clusters refer to the target power plant groups within the target area that are to be predicted. Due to their unique geographical location, photovoltaic power plants in downstream power plant clusters will be affected by similar weather conditions to upstream power plant clusters after a certain time delay.

[0031] Specifically, the altitude and prevailing wind direction of each photovoltaic (PV) power station are extracted from spatial location information, including upwind and downwind directions. Based on the altitude, the altitude difference between PV power stations is determined, and the distance difference between them is determined according to their locations. Subsequently, the weighted sum of the altitude and distance differences between PV power stations is obtained to determine their geographical correlation. This geographical correlation comprehensively reflects the spatial relationships between PV power stations, providing a basis for subsequent grouping. After obtaining the geographical correlation, multiple PV power stations with a geographical correlation greater than the correlation threshold and a prevailing wind direction of upwind are grouped into an upstream power station group. PV power stations with a geographical correlation greater than the correlation threshold with other PV power stations in the upstream power station group and a prevailing wind direction of downwind are grouped into a downstream power station group. This grouping method based on geographical correlation and wind direction accurately reflects the propagation sequence of weather system influences, providing a reliable spatial reference for subsequent power forecasting. By acquiring this spatial location information and grouping power plants, spatial relationships between photovoltaic power plants were established. This allows the system to predict the power change trends of downstream power plants based on the power changes of upstream power plants, thereby improving the accuracy of photovoltaic power prediction. Simultaneously, this grouping method also provides a foundation for subsequent analysis of the impact of extreme weather, enabling the system to better cope with power generation fluctuations caused by weather changes.

[0032] Based on the above embodiments, as an optional embodiment, step 101, which involves dividing each photovoltaic power station into upstream power station groups and downstream power station groups based on spatial location information, may further include the following steps:

[0033] Step 201: Extract the altitude and prevailing wind direction of each photovoltaic power station from the spatial location information. The prevailing wind direction includes the upwind and downwind directions. Based on the altitude, determine the altitude difference between each photovoltaic power station, and determine the distance difference between each photovoltaic power station according to their location.

[0034] Altitude refers to the vertical height of the photovoltaic power station relative to the mean sea level. Dominant wind direction refers to the most prevalent or longest-lasting wind direction in a specific observation period (such as monthly or quarterly), usually expressed as an angle, measured clockwise with true north as the reference (0 degrees or 360 degrees). Altitude and dominant wind direction can be understood as key parameters describing the geographical environment of photovoltaic power stations. Altitude reflects the spatial distribution of photovoltaic power stations in the vertical direction; power stations at different altitudes may face different meteorological conditions. Dominant wind direction characterizes the main features of atmospheric circulation in the region, with upwind indicating the direction of airflow and downwind indicating the direction of airflow. These two parameters together determine the propagation characteristics of weather systems in the region.

[0035] Specifically, the system first acquires altitude data for each photovoltaic (PV) power station using a geographic information system (GIS), and simultaneously obtains wind direction data for each PV power station's location from meteorological monitoring stations. The prevailing wind direction refers to the wind direction that occurs most frequently within a specific time period, which can be obtained through statistical analysis of historical wind direction data. The wind direction data is labeled as upwind and downwind according to the direction of airflow, respectively. This classification method helps in determining the propagation path of weather systems. After obtaining the altitude data, the altitude difference between any two PV power stations is calculated to obtain the height difference between them. Simultaneously, based on the geographic coordinates of each PV power station, the actual distance between them is calculated using the spherical distance calculation formula, yielding the distance difference. These difference data constitute the basic parameters describing the spatial relationship between PV power stations. The height difference and distance difference data obtained in this way provide fundamental data support for subsequent calculations of geographic correlation. This data objectively reflects the spatial location relationship between PV power stations, helping the system accurately determine the impact range and propagation path of weather systems.

[0036] Step 202: Weighted summation of the height and distance differences between the photovoltaic power stations to obtain the geographical correlation between the photovoltaic power stations.

[0037] Geographic correlation refers to a spatial relationship quantification index obtained by weighted summation of height and distance differences between photovoltaic power stations, used to characterize the degree of spatial correlation between different photovoltaic power stations.

[0038] Specifically, weighting coefficients α and β are first assigned to the height difference and distance difference, respectively. These weighting coefficients can be determined based on actual observation data and historical experience. The geographical correlation between any two photovoltaic power stations is calculated using the formula: Geographical Correlation = α × Height Difference + β × Distance Difference. The weighting coefficients α and β range from 0 to 1, and α + β = 1. In practical applications, the weighting coefficients can be dynamically adjusted based on the terrain features and meteorological conditions of the target area to obtain the optimal calculation results. This weighted summation method provides a comprehensive reflection of the spatial relationship between photovoltaic power stations. A higher geographical correlation indicates that the two power stations are closely connected spatially, and the influence of weather systems will propagate in similar ways; a lower geographical correlation indicates a weaker spatial connection between the two power stations, and the propagation characteristics of weather influences may differ significantly. This quantitative correlation calculation method provides an objective evaluation standard for subsequent power station grouping, helping to improve the scientific rigor and rationality of the grouping, thus providing a more reliable spatial reference for power prediction.

[0039] Step 203: Divide multiple photovoltaic power stations with a geographical correlation greater than the correlation threshold and a prevailing wind direction upwind into an upstream power station group, and divide photovoltaic power stations with a geographical correlation greater than the correlation threshold with each photovoltaic power station in the upstream power station group and a prevailing wind direction downwind into a downstream power station group.

[0040] Specifically, photovoltaic (PV) power plants are grouped based on geographical correlation and prevailing wind direction. This grouping method aims to identify PV power plant clusters with sequential relationships along the propagation path of weather systems, thereby establishing an effective early warning and forecasting mechanism. Since weather systems typically propagate along the prevailing wind direction, and power plants in similar spatial locations experience more similar weather impacts, geographical correlation and prevailing wind direction are used as the primary criteria for grouping. In practice, a correlation threshold is first set, which can be determined by analyzing historical data and actual operational experience. The system first filters out PV power plants with the prevailing wind direction upwind and calculates the geographical correlation between these power plants. When the geographical correlation between some power plants exceeds the correlation threshold, these power plants are assigned to the upstream power plant group. These upstream power plants, being at the forefront of the weather system's propagation path, are the first to perceive the impact of weather changes. Subsequently, the system calculates the geographical correlation between each power plant in the upstream power plant group and other ungrouped power plants. For PV power plants whose geographical correlation with any power plant in the upstream power plant group exceeds the correlation threshold and whose prevailing wind direction is downwind, they are assigned to the downstream power plant group. This grouping method, based on correlation propagation, ensures a stable spatial correlation between power stations in downstream power stations and those in upstream power stations. Through this grouping, the system establishes a predictive framework based on spatial propagation characteristics. Power changes in upstream power stations can serve as early warning signals, while power changes in downstream power stations can be predicted by analyzing data from upstream power stations. This grouping method not only considers the spatial distance between power stations but also incorporates wind direction, making the grouping results more consistent with actual weather impact propagation patterns, thereby improving the accuracy of power prediction.

[0041] Based on the above embodiments, as an optional embodiment, in step 101: based on spatial location information, each photovoltaic power station is divided into upstream power station groups and downstream power station groups. After this step, the following steps may also be included:

[0042] Step 204: Classify the photovoltaic power stations within the target area that are not located in the upstream or downstream power station groups as the benchmark power station groups.

[0043] Specifically, the system first identifies all photovoltaic power plants within the target area, then excludes those already classified as upstream or downstream power plant groups. For the remaining power plants, the system analyzes them based on their geographical location, operational characteristics, and the degree of weather impact. These power plants, not directly affected by extreme weather, are located in similar geographical and climatic environments, and their power variation characteristics can reflect their power generation performance under normal meteorological conditions. When determining the benchmark power plant group, the system considers the spatial distribution characteristics of the power plants, ensuring that the power plants in the benchmark group have a certain geographical correlation with the upstream and downstream power plant groups, but are not directly affected by the target extreme weather system. This selection method ensures that the benchmark power plant group reflects regional meteorological characteristics and serves as a control group for power variation. The benchmark power plant group, classified in this way, has strong reference value. It can not only be used to verify the accuracy of the prediction method but also help identify abnormal power variations caused by extreme weather. By comparing the power variation characteristics of the benchmark power plant group with those of the affected power plant groups, the system can more accurately assess the actual impact of extreme weather and improve the accuracy of the prediction results.

[0044] Step 205: Obtain the benchmark photovoltaic power of each photovoltaic power station in the benchmark power station group; when there is a photovoltaic power station in the benchmark power station group whose benchmark photovoltaic power is greater than the photovoltaic power threshold, generate an early warning message and send the early warning message to the photovoltaic power station manager terminal in the target area.

[0045] Specifically, the system first collects real-time power data from each photovoltaic power station in the benchmark power station group, compares the collected actual power with the station's nominal power, and calculates the power deviation. This benchmark photovoltaic power data reflects the actual operating status of power stations not directly affected by extreme weather. The system compares the calculated power deviation with a preset photovoltaic power threshold. When the deviation exceeds the threshold, it indicates that the power station may have been affected by unexpected weather or other abnormalities. Upon detecting an anomaly, the system automatically generates an early warning message. The early warning message includes key information such as the location of the abnormal power station, its current power value, and the degree of anomaly, and sends this information to the terminal of the person in charge of the photovoltaic power station in the target area through a preset communication channel. This timely information transmission mechanism ensures that operation and management personnel can quickly learn about the anomaly and take necessary countermeasures in a timely manner. Through this monitoring and early warning mechanism based on the benchmark power station group, the system can effectively identify and respond to potential risks. This early warning method not only expands the monitoring range of the forecasting system but also provides additional safety assurance. The timely push of early warning information enables power station operators to have a more comprehensive understanding of the weather impact in the region, improving the operational reliability and safety of the entire photovoltaic power generation system.

[0046] Step 102: Receive power change data and meteorological data from the upstream power plant during the first time period.

[0047] The first time period refers to the time interval during which upstream power plants collect power change data and meteorological data, which is usually set as a continuous observation period before the current moment.

[0048] Power variation data refers to the dynamic change characteristics of photovoltaic power generation by upstream power plants during the first time period, mainly including two key parameters: power variation amplitude and variation duration. The power variation amplitude indicates the degree of deviation of the power plant's output power from its nominal power, while the variation duration indicates the duration of the power fluctuation. This data is collected in real time by the photovoltaic power plant's power monitoring system.

[0049] Meteorological data refers to the set of meteorological parameters in the area where the upstream power station is located during a specific time period, mainly including wind speed, cloud cover, and cloud movement trajectory data. Wind speed indicates the speed of air movement; cloud cover indicates the degree to which the sky is covered by clouds, usually expressed as a percentage; cloud movement trajectory data records the direction and positional changes of clouds in space. These data are monitored and recorded in real time using specialized equipment at meteorological monitoring stations.

[0050] Specifically, the system receives power change data and meteorological data from upstream power plants during the first time period. This is because upstream power plants, due to their unique geographical location, are the first to be affected by weather systems, and their power output changes and local meteorological conditions provide important references for predicting power changes in downstream power plants. By simultaneously analyzing power change data and meteorological data, the impact and propagation characteristics of weather systems can be accurately determined. In practice, the system collects power output data from each photovoltaic power plant in the upstream power plant group through real-time monitoring devices. Power change data includes the magnitude and duration of power change, which are obtained by calculating the power difference between adjacent time points. Simultaneously, meteorological data for the area where the upstream power plants are located is obtained from meteorological monitoring stations, including wind speed, cloud cover, and cloud movement trajectory data. Wind speed and cloud cover data are used to determine whether extreme weather conditions have occurred, while cloud movement trajectory data is used to analyze the movement characteristics of weather systems. The system collects and stores this data according to a preset time window. The first time period is usually a continuous period preceding the current time, and the duration can be adjusted according to actual needs. After preliminary processing, this data is formatted into a standardized data format for subsequent analysis. Data obtained in this way is characterized by its timeliness and high relevance, and can promptly reflect the actual impact of weather systems on photovoltaic power plants.

[0051] Step 103: When the power change data and meteorological data meet the preset extreme weather judgment conditions, calculate the extreme weather movement parameters based on the meteorological data, and determine the extreme weather propagation sequence according to the extreme weather movement parameters and the relative positions between the upstream power station and the downstream power station.

[0052] Among them, the preset extreme weather judgment conditions refer to a set of multi-dimensional judgment criteria used to identify extreme weather, mainly including power change rate threshold, wind speed threshold and cloud cover threshold.

[0053] Extreme weather movement parameters are key indicators describing the spatial movement characteristics of weather systems, mainly including two parameters: average direction of movement and average speed of movement. The average direction of movement is expressed as an angle value, calculated clockwise with true north as the reference direction; the average speed of movement represents the distance the weather system displaces per unit time. These parameters are calculated by analyzing cloud movement trajectory data in meteorological data.

[0054] Extreme weather propagation time series refers to the temporal sequence and arrival time of a weather system from upstream power plants to downstream photovoltaic power plants. This time series data is obtained by calculating the projected distance of the weather system in its direction of movement and combining it with the average speed of movement, forming a time series that includes the expected times when each downstream power plant will be affected.

[0055] Specifically, the first step is to determine whether the conditions for extreme weather are met. The system calculates the power change rate of the upstream power plants. When the power change rate exceeds a preset threshold, and simultaneously the observed wind speed exceeds a wind speed threshold or cloud cover exceeds a cloud cover threshold, extreme weather conditions are determined to have occurred. This multi-dimensional determination method can effectively identify weather systems that have a significant impact on photovoltaic power generation. Once extreme weather conditions are confirmed, the system calculates extreme weather movement parameters based on cloud movement trajectory data from meteorological data. These parameters include two key parameters: average movement direction and average movement speed. The average movement direction is obtained by analyzing the positional changes of the cloud's centroid at continuous time points, while the average movement speed is determined by calculating the cloud's displacement per unit time. These parameters describe the spatial motion characteristics of the weather system. Subsequently, based on the obtained extreme weather movement parameters and the relative positional relationship between the upstream and downstream power plants, the system determines the propagation sequence of the extreme weather. First, a distance matrix between the upstream and downstream power plants is constructed. Then, the projected distance of the extreme weather in the movement direction is calculated, and combined with the average movement speed, the estimated arrival time of the extreme weather from the upstream power plants to each photovoltaic power plant in the downstream power plants is calculated. The extreme weather propagation timeline determined in this way accurately reflects the temporal sequence of weather system impacts. This not only provides a time reference for predicting power changes in downstream power plants but also allows for adjustments to the power change amplitude based on propagation distance, improving prediction accuracy.

[0056] Based on the above embodiments, as an optional embodiment, step 103, when the power change data and meteorological data meet the preset extreme weather determination conditions, may further include the following steps:

[0057] Step 301: Obtain the total power change rate of the power change data and the wind speed and cloud cover in the meteorological data; when the absolute value of the power change rate is greater than the change rate threshold, and the wind speed is greater than the wind speed threshold or the cloud cover is greater than the cloud cover threshold, determine that the power change data and meteorological data meet the preset extreme weather judgment conditions.

[0058] Specifically, the power change rate of the upstream power station is first calculated. The system analyzes power data from continuous sampling points within the first time period, calculating the ratio of the power change amplitude per unit time to the nominal power, thus obtaining the power change rate. Simultaneously, wind speed and cloud cover data are extracted from meteorological data. Wind speed data reflects the intensity of airflow, while cloud cover data indicates the degree of cloud cover over the sky.

[0059] During the determination process, the system first compares the calculated absolute value of the power change rate with a preset change rate threshold (e.g., 15% per minute). A larger power change rate usually indicates significant fluctuations in the output of the photovoltaic power plant. Subsequently, the system compares the monitored wind speed with a wind speed threshold (e.g., 10 meters per second) and cloud cover with a cloud cover threshold (e.g., 80%). When the absolute value of the power change rate exceeds the change rate threshold, and either the wind speed exceeds the wind speed threshold or the cloud cover exceeds the cloud cover threshold, the system determines that the extreme weather conditions are met. This determination method based on multi-parameter thresholds has strong reliability. The power change rate determination ensures that only weather changes that substantially affect power generation are identified as extreme weather; while the wind speed and cloud cover determinations provide meteorological support, preventing power fluctuations caused by non-weather factors from being misjudged as extreme weather. Furthermore, the parameters of this determination method can be dynamically adjusted based on actual operating experience, improving the system's adaptability and accuracy.

[0060] Based on the above embodiments, as an optional embodiment, step 103, which calculates extreme weather movement parameters based on meteorological data, may further include the following steps:

[0061] Step 302: Obtain cloud movement trajectory data from meteorological data; based on a preset time window and cloud movement trajectory data, calculate the average movement direction and average movement speed of the cloud movement trajectory; use the average movement direction and average movement speed as extreme weather movement parameters.

[0062] Specifically, the system first extracts cloud movement trajectory data from meteorological data. This data includes the spatial coordinates of the cloud's centroid at different time points. The system sets a preset time window (e.g., 30 minutes) to track and analyze the cloud's movement within this window. The selection of the time window needs to consider the statistical significance of the data and the changing characteristics of the weather system, ensuring sufficient data for effective analysis while ensuring the calculation results reflect the current weather system's movement characteristics. After obtaining the cloud's position data within the time window, the system first calculates the average direction of movement. By analyzing the changes in the cloud's centroid position at consecutive time points, the direction of movement at each time point is calculated. These direction values ​​are then weighted and averaged to obtain the average direction of movement. This direction is expressed as an angle value, calculated clockwise from true north (0 degrees or 360 degrees). Simultaneously, the system calculates the displacement distance of the cloud between adjacent time points and, combined with the time interval, calculates the movement speed at each time point, obtaining the average movement speed through weighted averaging. The calculated average direction of movement and average movement speed are used as extreme weather movement parameters, which comprehensively describe the weather system's movement characteristics. This parameter calculation method, based on actual observation data, possesses strong scientific validity and reliability. The system employs a weighted average approach, which not only smooths out the impact of short-term fluctuations but also highlights the importance of the most recent data, making the calculation results more representative. The extreme weather movement parameters obtained in this way provide a data basis for subsequent forecasting of weather system propagation.

[0063] Based on the above embodiments, as an optional embodiment, step 103, which involves determining the propagation sequence of extreme weather based on extreme weather movement parameters and the relative positions between upstream and downstream power plants, may further include the following steps:

[0064] Step 303: Based on the relative positions of the upstream and downstream power plants, construct the distance matrix between the upstream and downstream power plants.

[0065] Specifically, the system first acquires the geographical coordinates of each photovoltaic power station in both the upstream and downstream power station groups, including the longitude and latitude of each station. To improve calculation accuracy, the system employs a great circle distance calculation method. This method considers the curvature of the Earth's surface and can obtain the actual distance between two geographical coordinate points. During the distance calculation process, the system constructs a matrix structure. The number of rows in this matrix corresponds to the number of power stations in the upstream power station group, and the number of columns corresponds to the number of power stations in the downstream power station group. For each element in the matrix, the system calculates the great circle distance between the corresponding upstream and downstream power stations. In this way, each element in the matrix accurately records the actual geographical distance between a pair of upstream and downstream power stations. The distance matrix constructed in this way is characterized by completeness and accuracy. Each element of the matrix contains precise distance information, which provides an important basis for subsequent calculations of extreme weather propagation timelines. Simultaneously, the matrix structure design facilitates rapid access and processing of distance data, improving computational efficiency. This matrix construction method based on actual geographical distance not only considers the influence of the Earth's curvature, improving the accuracy of distance calculations, but also provides a reliable spatial reference for subsequent calculations of propagation timelines in conjunction with extreme weather movement parameters. This systematic description of spatial relationships allows for more accurate prediction of the time process by which extreme weather propagates from upstream power plants to downstream power plants.

[0066] Step 304: Based on the average moving speed and average moving direction in the extreme weather movement parameters, calculate the effective propagation speed of extreme weather in the projection direction of the distance matrix.

[0067] Specifically, the system first calculates the direction of the connection between each pair of upstream and downstream power stations based on the geographical location information of the power stations in the distance matrix. For each distance value in the distance matrix, the system calculates the angle between the corresponding power station connection line and due north, which is taken as the power station connection direction angle. Then, the system compares the average movement direction in the extreme weather movement parameters with the power station connection direction to calculate the angle between the two directions. This angle reflects the degree of deviation between the weather system's movement path and the power station connection line. After determining the direction angle, the system uses the average movement speed for projection calculation. By multiplying the average movement speed by the cosine of the direction angle, the velocity component of the extreme weather system in the direction of the power station connection line is obtained, i.e., the effective propagation speed. This calculation method considers the impact of directional deviation on the propagation effect. The effective propagation speed is maximized when the weather system's movement direction is completely consistent with the power station connection direction; when there is a directional deviation, the effective propagation speed decreases accordingly. The effective propagation speed calculated in this way is more consistent with the actual physical process. It not only reflects the movement characteristics of the weather system but also considers the impact of spatial location relationships on the propagation effect, making subsequent propagation timing predictions more accurate. For each distance value in the distance matrix, the system calculates the corresponding effective propagation velocity, thus forming a complete velocity projection dataset. This provides a reliable velocity basis for subsequent calculations of extreme weather propagation time series. This velocity calculation method that considers directional factors improves the accuracy of propagation time series prediction.

[0068] Step 305: Based on the effective propagation speed and distance matrix, determine the estimated arrival time of extreme weather propagation from the upstream power station group to each photovoltaic power station in the downstream power station group; sort the estimated arrival times in time sequence to obtain the extreme weather propagation time sequence.

[0069] Specifically, the system first uses the distance data between each pair of upstream and downstream power stations recorded in the distance matrix, combined with the calculated effective propagation speed, to calculate the estimated arrival time of extreme weather propagation from each power station in the upstream power station group to each power station in the downstream power station group. The calculation process considers multiple propagation paths originating from different upstream power stations. For each power station in the downstream power station group, the earliest estimated arrival time is selected as the impact time for that power station. After obtaining the estimated arrival times of all downstream power stations, the system sorts these times. The starting time point for sorting is the initial moment when extreme weather affects the upstream power station group, and the ending time point is the estimated arrival time of the last downstream power station. Through this sorting, the system establishes a complete time series, clearly showing the temporal order in which extreme weather affects each power station in the downstream power station group. The extreme weather propagation time series determined in this way is systematic and practical. It not only considers the influence of spatial distance and propagation speed but also ensures the accuracy of the time series prediction through multi-path comparison. This time series calculation method based on physical characteristics can provide a reliable time reference for power prediction of the downstream power station group.

[0070] Step 104: Combine power change data and extreme weather propagation timeline to predict the photovoltaic power output of downstream power plants in the second time period.

[0071] The second period refers to the time range during which extreme weather systems affect downstream power plants, specifically the entire period from when the weather system begins to affect the first downstream power plant until it completely leaves the last downstream power plant.

[0072] Specifically, the system first determines the time range of the second period based on the propagation sequence of extreme weather. The start time of the second period is set as the expected arrival time of the earliest affected downstream power station, and the end time is determined based on the expected arrival time of the last downstream power station and the expected duration of the impact. Within this period, the system predicts the power changes of each downstream power station sequentially according to the propagation sequence. During the prediction process, the system analyzes the power change data of the upstream power station group in the first period, extracting key characteristics of the power change, including the magnitude and duration of the change. Considering the attenuation effect of the weather system during propagation, the system performs distance correction on the power change magnitude based on the distance between the upstream and downstream power stations. The greater the distance, the smaller the expected power change magnitude; this correction takes into account the natural attenuation characteristics of the weather system intensity with propagation distance. Simultaneously, the system also needs to consider the actual characteristics of the downstream power station group, such as power station capacity, component type, and installation method, and adjust the prediction results accordingly. This prediction method that considers power station characteristics can better adapt to the actual conditions of different power stations and improve the accuracy of the prediction. Based on the propagation sequence, the system applies the corrected power change characteristics to each downstream power station sequentially, thereby obtaining the power prediction results for each power station in the second period. By employing this time-series-based forecasting method, the system can accurately reflect the impact of extreme weather on downstream power plants. The forecast results not only include the magnitude of power changes but also precisely describe the timing of these changes, providing comprehensive decision support for power plant operation and management.

[0073] Based on the above embodiments, as an optional embodiment, step 104: combining power change data and extreme weather propagation timelines to predict the photovoltaic power of downstream power plants in the second time period, this step may further include the following steps:

[0074] Step 401: Extract the power change amplitude and duration of the upstream power plant group in the first time period from the power change data; determine the time interval between the extreme weather reaching each photovoltaic power plant in the downstream power plant group based on the extreme weather propagation sequence.

[0075] Specifically, the system first extracts the power change characteristics of upstream power plants within the first time period from the power change data. By analyzing the power curve, the system identifies the moments when significant power changes begin and when power returns to normal, and calculates the duration of the change. Simultaneously, the power change amplitude is obtained by calculating the ratio of the maximum deviation of the power change to the nominal power. These characteristic parameters reflect the intensity and persistence of the impact of extreme weather on photovoltaic power plants. When determining the time interval, the system calculates the time difference from the time of extreme weather affecting the upstream power plants to the time of arrival at each downstream photovoltaic power plant, based on the propagation time series of the extreme weather. Specifically, the system uses the initial moment of extreme weather affecting the upstream power plants as a benchmark to calculate the time difference to the expected moment of arrival at each downstream power plant. This time interval calculation method based on propagation time series considers the actual propagation characteristics of the weather system. This feature extraction and time interval calculation method is highly practical. The extraction process of power change characteristics considers the complete process of power change, including not only the magnitude of the change but also its duration, enabling the prediction results to more comprehensively reflect the impact of extreme weather. At the same time, the time interval calculated based on the propagation time series provides an accurate time reference for subsequent power prediction, allowing the system to accurately predict the specific moment when extreme weather affects each downstream power plant.

[0076] Step 402: Perform distance correction on the power change amplitude based on each time interval to determine the target power change amplitude for each photovoltaic power station in the downstream power station group.

[0077] Specifically, the system first calculates the actual distance from the extreme weather system to each downstream power station based on time intervals and the effective propagation speed of extreme weather. This distance reflects the actual path the weather system travels from the upstream power station group to each downstream power station and is a crucial basis for distance correction. During distance correction, the system uses an attenuation function to correct the power change amplitude of the upstream power station group. The attenuation function considers the natural attenuation characteristics of the weather system intensity with propagation distance; the greater the distance, the smaller the corrected power change amplitude. Simultaneously, the system also considers the influence of terrain features and meteorological conditions along the propagation path on the attenuation effect, adjusting the attenuation coefficient to adapt to different propagation environments. For each power station in the downstream power station group, the system calculates the corresponding attenuation coefficient based on its corresponding propagation distance and multiplies this coefficient by the original power change amplitude to obtain the target power change amplitude for that power station. This correction method based on physical characteristics can better reflect the spatial variation law of the intensity of extreme weather impacts. The target power change amplitude obtained through this distance correction method is more consistent with reality. It not only considers the initial impact intensity of the weather system but also reflects the attenuation effect during propagation, making the prediction results more accurate.

[0078] Step 403: For each photovoltaic power station in the downstream power station group, sum the target power change amplitude and nominal power corresponding to the photovoltaic power station to obtain the photovoltaic power of the photovoltaic power station in the second time period; take the average photovoltaic power of each photovoltaic power station in the downstream power station group in the second time period as the photovoltaic power of the downstream power station group in the second time period.

[0079] Specifically, the system first processes the power prediction for each photovoltaic power station in the downstream power plant group. For each power station, its nominal power is algebraically summed with the previously calculated target power change amplitude to obtain the predicted power for that power station in the second time period. This calculation method takes into account power deviations caused by extreme weather; the target power change amplitude may be positive or negative, representing an increase or decrease in power, respectively. After obtaining the predicted power for each power station, the system calculates the overall photovoltaic power of the downstream power plant group. By arithmetically averaging the predicted power of all power stations in the downstream power plant group, the comprehensive photovoltaic power of the entire power plant group in the second time period is obtained. This averaging calculation method can smooth out extreme changes in individual power stations, providing more stable prediction results. This power calculation method has strong practicality and reliability. It not only considers the individual characteristics of each power station but also reflects the overall performance of the entire power plant group through averaging. The prediction results include both the impact of extreme weather and maintain a correlation with the actual power generation capacity of the power stations, making the prediction more accurate.

[0080] Reference Figure 2 This application provides a photovoltaic power prediction system for a photovoltaic power plant, comprising: a power plant group division module, a data receiving module, a propagation timing determination module, and a photovoltaic power prediction module, wherein:

[0081] The power station group division module is used to obtain the spatial location information of multiple photovoltaic power stations within the target area, and based on the spatial location information, divide each photovoltaic power station into upstream power station groups and downstream power station groups;

[0082] The data receiving module is used to receive power change data and meteorological data from upstream power plants during the first time period;

[0083] The propagation timing determination module is used to calculate the extreme weather movement parameters based on the meteorological data when the power change data and meteorological data meet the preset extreme weather judgment conditions, and to determine the extreme weather propagation timing based on the extreme weather movement parameters and the relative positions between the upstream power station and the downstream power station.

[0084] The photovoltaic power prediction module is used to combine power change data and extreme weather propagation timelines to predict the photovoltaic power of downstream power plants in the second time period.

[0085] Based on the above embodiments, the power station group division module is also used to extract the altitude and prevailing wind direction of each photovoltaic power station from the spatial location information. The prevailing wind direction includes upwind and downwind. Based on each altitude, the module determines the altitude difference between each photovoltaic power station and the distance difference between each photovoltaic power station according to each location. The module performs a weighted summation of the altitude difference and distance difference between each photovoltaic power station to obtain the geographical correlation degree between each photovoltaic power station. Multiple photovoltaic power stations with a geographical correlation degree greater than the correlation degree threshold and a prevailing wind direction of upwind are divided into upstream power station groups, and photovoltaic power stations with a geographical correlation degree greater than the correlation degree threshold with each photovoltaic power station in the upstream power station group and a prevailing wind direction of downwind are divided into downstream power station groups.

[0086] Based on the above embodiments, the propagation timing determination module is also used to obtain the total power change rate of the power change data and the wind speed and cloud cover in the meteorological data; when the absolute value of the power change rate is greater than the change rate threshold, and the wind speed is greater than the wind speed threshold or the cloud cover is greater than the cloud cover threshold, it is determined that the power change data and the meteorological data meet the preset extreme weather determination conditions.

[0087] Based on the above embodiments, the propagation timing determination module is also used to acquire cloud movement trajectory data in meteorological data; calculate the average movement direction and average movement speed of the cloud movement trajectory based on a preset time window and cloud movement trajectory data; and use the average movement direction and average movement speed as extreme weather movement parameters.

[0088] Based on the above embodiments, the propagation timing determination module is also used to construct a distance matrix between the upstream and downstream power stations based on their relative positions; calculate the effective propagation speed of extreme weather in the projection direction of the distance matrix based on the average moving speed and average moving direction in the extreme weather movement parameters; determine the expected arrival time of extreme weather from the upstream power station to each photovoltaic power station in the downstream power station based on the effective propagation speed and the distance matrix; and sort the expected arrival times to obtain the extreme weather propagation timing.

[0089] Based on the above embodiments, the photovoltaic power prediction module is also used to extract the power change amplitude and duration of the upstream power station group in the first time period from the power change data; determine the time interval for extreme weather to reach each photovoltaic power station in the downstream power station group according to the extreme weather propagation sequence; perform distance correction on the power change amplitude based on each time interval to obtain the target power change amplitude corresponding to each photovoltaic power station in the downstream power station group; for each photovoltaic power station in the downstream power station group, sum the target power change amplitude and nominal power corresponding to the photovoltaic power station to obtain the photovoltaic power of the photovoltaic power station in the second time period; and take the average photovoltaic power of each photovoltaic power station in the downstream power station group in the second time period as the photovoltaic power of the downstream power station group in the second time period.

[0090] Based on the above embodiments, the power station group division module is also used to divide photovoltaic power stations in the target area that are not in the upstream power station group or the downstream power station group into a benchmark power station group; obtain the benchmark photovoltaic power of each photovoltaic power station in the benchmark power station group; when there is a photovoltaic power station in the benchmark power station group whose benchmark photovoltaic power is greater than the photovoltaic power threshold, generate early warning information and send the early warning information to the photovoltaic power station manager terminal in the target area.

[0091] It should be noted that the above embodiments of the apparatus are only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the apparatus and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be found in the method embodiments, which will not be repeated here.

[0092] This application also discloses an electronic device. (See reference...) Figure 3 , Figure 3 This is a schematic diagram of the structure of an electronic device disclosed in an embodiment of this application. The electronic device 300 may include: at least one processor 301, at least one network interface 304, a user interface 303, a memory 305, and at least one communication bus 302.

[0093] The communication bus 302 is used to enable communication between these components.

[0094] The user interface 303 may include a display interface and a camera interface. Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0095] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface).

[0096] The processor 301 may include one or more processing cores. The processor 301 connects to various parts of the server using various interfaces and lines, and performs various server functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 305, and by calling data stored in the memory 305. Optionally, the processor 301 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 301 may integrate one or a combination of several of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface graphics, and applications; the GPU is responsible for rendering and drawing the content required for display; and the modem handles wireless communication. It is understood that the modem may also not be integrated into the processor 301 and may be implemented as a separate chip.

[0097] The memory 305 may include random access memory (RAM) or read-only memory. Optionally, the memory 305 may include a non-transitory computer-readable storage medium. The memory 305 may be used to store instructions, programs, code, code sets, or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-described method embodiments, etc.; the data storage area may store data involved in the above-described method embodiments, etc. Optionally, the memory 305 may also be at least one storage device located remotely from the aforementioned processor 301. (Refer to...) Figure 3 The memory 305, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and an application program for a photovoltaic power prediction method for a photovoltaic power plant.

[0098] exist Figure 3In the illustrated electronic device 300, the user interface 303 is mainly used to provide an input interface for the user and to acquire user input data; while the processor 301 can be used to call an application program stored in the memory 305 for predicting the photovoltaic power of a photovoltaic power station. When executed by one or more processors 301, the electronic device 300 performs one or more methods as described in the above embodiments. It should be noted that, for the foregoing method embodiments, for the sake of simplicity, they are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, because according to this application, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also understand that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0099] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0100] In the various embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some service interface; the indirect coupling or communication connection between apparatuses or units may be electrical or other forms.

[0101] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0102] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0103] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, portable hard drives, magnetic disks, or optical disks.

[0104] The above are merely exemplary embodiments of this disclosure and should not be construed as limiting the scope of this disclosure. Any equivalent changes and modifications made in accordance with the teachings of this disclosure shall still fall within the scope of this disclosure. Other embodiments of this disclosure will be readily apparent to those skilled in the art upon consideration of the specification and practical disclosure.

[0105] This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not described in this disclosure. The specification and embodiments are to be considered exemplary only.

Claims

1. A method for predicting the photovoltaic power of a photovoltaic power plant, characterized in that, include: Acquire spatial location information of multiple photovoltaic power stations within the target area, and based on the spatial location information, divide each photovoltaic power station into an upstream power station group and a downstream power station group; Receive power change data and meteorological data of the upstream power station in the first time period; When the power change data and the meteorological data meet the preset extreme weather judgment conditions, the extreme weather movement parameters are calculated based on the meteorological data, and the extreme weather propagation sequence is determined according to the extreme weather movement parameters and the relative positions between the upstream power station group and the downstream power station group. By combining the power change data and the propagation timeline of the extreme weather, the photovoltaic power output of the downstream power plant in the second time period is predicted; The calculation of extreme weather movement parameters based on the meteorological data includes: Obtain the cloud movement trajectory data from the meteorological data; Based on a preset time window and the cloud movement trajectory data, the average movement direction and average movement speed of the cloud movement trajectory are calculated. The average direction of movement and the average speed of movement are used as extreme weather movement parameters; The step of determining the propagation sequence of extreme weather based on the extreme weather movement parameters and the relative positions between the upstream and downstream power plants includes: Based on the relative positions between the upstream and downstream power plants, a distance matrix between the upstream and downstream power plants is constructed. Based on the average speed and average direction of movement in the extreme weather movement parameters, calculate the effective propagation speed of extreme weather in the projection direction of the distance matrix. Based on the effective propagation speed and the distance matrix, the estimated arrival time of extreme weather from the upstream power station group to each photovoltaic power station in the downstream power station group is determined; The predicted arrival times are sorted in chronological order to obtain the propagation timeline of extreme weather.

2. The photovoltaic power prediction method for a photovoltaic power station according to claim 1, characterized in that, The process of dividing each photovoltaic power station into an upstream power station group and a downstream power station group based on the spatial location information includes: The altitude and prevailing wind direction of each photovoltaic power station are extracted from the spatial location information, whereby the prevailing wind direction includes the upwind and downwind directions. Based on the altitudes of each of the aforementioned photovoltaic power stations, the altitude difference between each of the aforementioned photovoltaic power stations is determined, and based on the locations of each of the aforementioned photovoltaic power stations, the distance difference between each of the aforementioned photovoltaic power stations is determined; The geographical correlation between the photovoltaic power stations is obtained by weighted summation of the height and distance differences between the photovoltaic power stations. Multiple photovoltaic power stations with a geographical correlation greater than the correlation threshold and a prevailing wind direction upwind are classified into an upstream power station group. Photovoltaic power stations with a geographical correlation greater than the correlation threshold with each photovoltaic power station in the upstream power station group and a prevailing wind direction downwind are classified into a downstream power station group.

3. The photovoltaic power prediction method for a photovoltaic power station according to claim 1, characterized in that, The condition that the power change data and the meteorological data meet the preset extreme weather determination conditions includes: Obtain the total power change rate of the power change data and the wind speed and cloud cover from the meteorological data; When the absolute value of the power change rate is greater than the change rate threshold, and the wind speed is greater than the wind speed threshold or the cloud cover is greater than the cloud cover threshold, the power change data and the meteorological data are determined to meet the preset extreme weather determination conditions.

4. The photovoltaic power prediction method for a photovoltaic power station according to claim 1, characterized in that, The method of combining the power change data and the propagation timeline of extreme weather to predict the photovoltaic power output of the downstream power plant in the second time period includes: Extract the power change amplitude and duration of the upstream power plant group in the first time period from the power change data; Based on the propagation sequence of the extreme weather, the time interval between the extreme weather events reaching each photovoltaic power station in the downstream power station group is determined; Based on each of the aforementioned time intervals, the power change amplitude is respectively corrected for distance, and the target power change amplitude corresponding to each photovoltaic power station in the downstream power station group; For each photovoltaic power station in the downstream power station group, the target power change amplitude and nominal power corresponding to the photovoltaic power station are summed to obtain the photovoltaic power of the photovoltaic power station in the second time period; The average photovoltaic power of each photovoltaic power station in the downstream power station group during the second time period is taken as the photovoltaic power of the downstream power station group during the second time period.

5. The photovoltaic power prediction method for a photovoltaic power station according to claim 2, characterized in that, After dividing each photovoltaic power station into upstream power station groups and downstream power station groups based on the spatial location information, the method further includes: Photovoltaic power plants within the target area that are not located in the upstream power plant group or the downstream power plant group are classified as the benchmark power plant group; Obtain the reference photovoltaic power of each photovoltaic power station in the reference power station group; When there is a photovoltaic power station in the benchmark power station group whose benchmark photovoltaic power is greater than the photovoltaic power threshold, an early warning message is generated and sent to the photovoltaic power station manager terminal in the target area.

6. A photovoltaic power prediction system for a photovoltaic power station, characterized in that, The system includes: The power station group division module is used to obtain the spatial location information of multiple photovoltaic power stations within the target area, and based on the spatial location information, divide each photovoltaic power station into an upstream power station group and a downstream power station group. The data receiving module is used to receive power change data and meteorological data of the upstream power station in the first time period; The propagation timing determination module is used to calculate extreme weather movement parameters based on the meteorological data when the power change data and the meteorological data meet the preset extreme weather judgment conditions, and to determine the extreme weather propagation timing based on the extreme weather movement parameters and the relative positions between the upstream power station group and the downstream power station group. A photovoltaic power prediction module is used to combine the power change data and the propagation timeline of extreme weather to predict the photovoltaic power of the downstream power plant in the second time period; The calculation of extreme weather movement parameters based on the meteorological data includes: Obtain the cloud movement trajectory data from the meteorological data; Based on a preset time window and the cloud movement trajectory data, the average movement direction and average movement speed of the cloud movement trajectory are calculated. The average direction of movement and the average speed of movement are used as extreme weather movement parameters; The step of determining the propagation sequence of extreme weather based on the extreme weather movement parameters and the relative positions between the upstream and downstream power plants includes: Based on the relative positions between the upstream and downstream power plants, a distance matrix between the upstream and downstream power plants is constructed. Based on the average speed and average direction of movement in the extreme weather movement parameters, calculate the effective propagation speed of extreme weather in the projection direction of the distance matrix. Based on the effective propagation speed and the distance matrix, the estimated arrival time of extreme weather from the upstream power station group to each photovoltaic power station in the downstream power station group is determined; The predicted arrival times are sorted in chronological order to obtain the propagation timeline of extreme weather.

7. An electronic device, characterized in that, The device includes a processor, a memory, a user interface, and a network interface. The memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory to enable the electronic device to perform the photovoltaic power prediction method for a photovoltaic power plant as described in any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions that, when executed, perform the photovoltaic power prediction method for a photovoltaic power plant as described in any one of claims 1-5.

Images