A photovoltaic power station ultra-short-term power prediction method, system, device and medium

Abstract

The application provides a photovoltaic power station ultra-short-term power prediction method, system, device and medium, comprising the following steps: taking the central coordinates of a centralized inverter subarray as a reference point, obtaining the sun running track of a day in a set time period in the coordinate system of the reference point; calculating the irradiance of multiple time points based on the sun running track of the day; predicting the cloud position information corresponding to the time points of the multiple time points in the day, correcting the irradiance of the corresponding time points by using the obtained multiple cloud position information to obtain the corrected irradiance; combining the multiple corrected irradiance corresponding to the sun running track of the day to form an irradiance vector in the set time period, and predicting the power vector in the set time period by using the irradiance vector; the accuracy of the ultra-short-term power prediction is improved, the stability of the power system is improved, and the economic loss caused by power fluctuation can be effectively reduced.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of new energy photovoltaic power generation, and particularly relates to a photovoltaic power station ultra-short-term power prediction method, system, device and medium. BACKGROUND

[0002] The photovoltaic power station ultra-short-term power prediction is a process of predicting the active power of a photovoltaic power station through the application of technical means such as meteorological conditions and statistical rules. It refers to predicting the power within 15 minutes to 4 hours in the future, with a time resolution of 15 minutes. Its importance lies in its direct relationship with the stability of the power system, which can effectively reduce the economic loss caused by power fluctuations. With the popularization of renewable energy and the expansion of photovoltaic power stations, it is particularly important to improve the accuracy of prediction. According to research, for every 1% increase in prediction accuracy, the dispatching cost can be reduced by 2%. At the same time, it can also assist power stations in more refined operation and maintenance management, such as reasonably arranging equipment maintenance through prediction data, improving equipment utilization, and reducing operation and maintenance costs.

[0003] In terms of technical implementation, photovoltaic power prediction involves data collection and preprocessing, feature extraction, time series analysis methods (such as ARIMA model), and the application of machine learning models (such as support vector machines, neural networks, etc.). These methods combine historical meteorological and photovoltaic data to further improve the accuracy of power prediction. Data cleaning is a fundamental step that can improve prediction accuracy by removing outliers and filling missing data.

[0004] However, the uncertainty and randomness of photovoltaic output prediction caused by weather factors have not been completely solved, especially for the Gobi open area where there is no component shading problem. There is currently no effective prediction method for the power drop caused by shading due to the randomness of clouds in meteorological phenomena. SUMMARY

[0005] The purpose of the present application is to provide a photovoltaic power station ultra-short-term power prediction method, system, device and medium, which solves the problem of effective prediction of power drop caused by shading due to the randomness of clouds in meteorological phenomena in the Gobi open area where there is no component shading problem.

[0006] In order to achieve the above purpose, the technical scheme adopted by the present application is:

[0007] The photovoltaic power station ultra-short-term power prediction method provided by the present application comprises the following steps:

[0008] Step 1: Establish a coordinate system with the center coordinates of the centralized inverter subarray as the reference point, and obtain the running track of the sun in the coordinate system in one day;

[0009] Step 2, calculating the irradiance at multiple time points in the future time period based on the one-day sun trajectory;

[0010] Step 3, obtaining the current position information of the cloud in the sky at the coordinate system at the current time, and predicting the cloud position information at multiple time points in the future time period using the cloud position information;

[0011] Step 4, combining the multiple corrected irradiance to form an irradiance vector in the future time period, and using the irradiance vector to predict the power vector in the future time period.

[0012] Step 4, combining the multiple corrected irradiance to form an irradiance vector in the future time period, and using the irradiance vector to predict the power vector in the future time period.

[0013] Preferably, in step 1, the obtained one-day sun trajectory satisfies the following coordinate relationship:

[0014] s n →t[(R,θ n11 ,θ n21 ),(R,θ n12 ,θ n22 ),…,(R,θ n1γ ,θ n2γ )]

[0015] 1≤n≤k

[0016] Wherein, s n is the sun trajectory curve of the nth day in a year; R is the relative distance radius of the sun; θ n1γ is the horizontal angle of the sun at the γth position point on the trajectory curve; θ n2γ is the vertical angle of the sun at the γth position point on the trajectory curve; k=365 / 366.

[0017] Preferably, in step 2, the irradiance at multiple time points in the future time period is calculated based on the one-day sun trajectory, and the specific method is:

[0018] Cal_t1=C(R,θ n11 ,θ n21 )

[0019] Wherein, Cal_t1 is the irradiance corresponding to t1; C is a standard irradiance function; (R, θ n11 , θ n21 ) is the sun position point corresponding to t1 on the sun trajectory curve of the nth day in a year; R is the relative distance radius of the sun; θ n11 is the horizontal angle of the sun; θ n21 is the vertical angle of the sun.

[0020] Preferably, in step 3, the obtained position information of the cloud is composed of a series of boundary points, and satisfies the following expression:

[0021] P u = (p u1 , p u2 , …, p uj , …, p um )

[0022] p uj → (D, α u1j , α u2j )

[0023] 1≤j≤m

[0024] wherein P u is a set of boundary points of the u-th cloud which are not connected to each other; p um is the m-th boundary point coordinate of the u-th cloud which are not connected to each other; D is the relative distance radius of the cloud; α 11j is the horizontal included angle; and α 12j is the vertical included angle.

[0025] Preferably, in step 3, the cloud position information is used to correct the irradiance at the corresponding time to obtain the corrected irradiance, and the specific method is as follows:

[0026] determine whether the sun at the set time is blocked by the cloud at the corresponding time, wherein:

[0027] if the sun at the set time is blocked by the cloud at the corresponding time, the irradiance is corrected by using the following formula:

[0028] Cal'_t1= ω·Cal_t1

[0029] if the sun at the set time is not blocked by the cloud at the corresponding time, the irradiance is corrected by using the following formula:

[0030] Cal'_t1= Cal_t1

[0031] In the above formula, ω is a correction factor, Cal'_t1 is the corrected irradiance at t1, and Cal_t1 is the irradiance corresponding to t1.

[0032] Preferably, the method for determining whether the sun at the set time is blocked by the cloud at the corresponding time is as follows:

[0033] if the sun position point at the set time is located in the range covered by the u clouds which are not connected to each other in the sky at the corresponding time, it is determined that the sun at the set time is blocked by the cloud at the corresponding time, otherwise it is determined that the sun at the set time is not blocked by the cloud at the corresponding time.

[0034] Preferably, in step 4, the irradiance vector is combined with the following formula to predict the power vector in the set time period:

[0035] W = mu * Cal = mu [Cal'_t1, Cal'_t2, Cal'_t3, …, Cal'_t 16 ]

[0036] In the above formula, mu is the irradiance conversion power factor of the photovoltaic system; W is the power vector in the set time period; and Cal is the irradiance vector.

[0037] A photovoltaic power plant ultra-short-term power prediction system comprises:

[0038] A sun running track curve calculation module is configured to establish a coordinate system with the central coordinates of the centralized inverter subarray as a reference point, and obtain the running track of the sun in the coordinate system in a day.

[0039] A cloud position information monitoring module is configured to obtain the position information of the clouds in the sky at the current time in the coordinate system, and predict the position information of the clouds at multiple time points in a future time period by using the cloud position information.

[0040] A power prediction module is configured to calculate the irradiance at multiple time points in a set future time period based on the sun running track in the day, correct the obtained irradiance by using the predicted cloud position information, obtain the corrected irradiance, and:

[0041] Combine the obtained multiple corrected irradiance to form an irradiance vector in the set future time period, and predict the power vector in the set future time period by using the irradiance vector.

[0042] A computer device comprises:

[0043] A processor adapted to execute a computer program;

[0044] A computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program is executed by the processor to execute the method.

[0045] A computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program is executed by the processor to execute the method.

[0046] Compared with the prior art, the present application has the following beneficial effects:

[0047] This invention provides a method for ultra-short-term power prediction of photovoltaic power plants. By monitoring the position information of clouds in the sky at the initial moment of the sun's trajectory within a day, and predicting the cloud position information at multiple moments in the sky during that day, the irradiance is corrected using the cloud position information. This systematically solves the problem that there is currently no effective way to predict power drop caused by cloud cover due to the randomness of meteorological phenomena in open areas where there is no component shading. This method improves the accuracy of ultra-short-term power prediction, enhances the stability of the power system, effectively reduces economic losses caused by power fluctuations, and assists power plants in more refined operation and maintenance management.

[0048] In summary, this invention is applicable to ultra-short-term power prediction correction for photovoltaic power plants, and has broad application prospects and social benefits. Attached Figure Description

[0049] Figure 1 This is a flowchart illustrating the present invention. Detailed Implementation

[0050] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0051] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0052] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0053] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0054] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0055] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0056] Example 1

[0057] like Figure 1 As shown in the figure, this embodiment provides a method for ultra-short-term power prediction of photovoltaic power plants, including the following steps:

[0058] Step 1: Obtain the set of solar trajectory curves and cloud location information at the reference point.

[0059] S11, using the center coordinates of the centralized inverter subarray (denoted as #1 subarray) as the reference point, calculate the set of trajectory curves S of the sun's movement at the reference point;

[0060] The set S of the solar trajectory curves at this reference point refers to the set of solar trajectory curves for each day of the year, that is:

[0061] S = [s1, s2, ..., s k ]

[0062] k = 365 / 366

[0063] Where s1, s2, ..., s k These are the curves of the sun's trajectory for each day of the year, where k=365 is a common year and k=366 is a leap year;

[0064] The trajectory curve of the sun's movement each day of the year: s1, s2, ..., s k The following coordinate relationships must be satisfied:

[0065] s n →t[(R,θ n11 ,θ n21 ),(R,θ n12 ,θ n22 ),…,(R,θ n1γ ,θn2γ )]

[0066] 1≤n≤k

[0067] In the above formula, s n The curve represents the trajectory of the sun on the nth day of a year. This curve contains γ position points, and the analytical expression for each position point can be derived from the relative distance radius R, the horizontal angle of the sun, the vertical angle of the sun, and is a single variable function of time t. In this application, the relative distance radius R is set to remain constant throughout the day.

[0068] Where (R,θ) n11 ,θ n21 ) represent the relative distance radius R, the horizontal angle of the sun, and the vertical angle of the sun at the moment of sunrise (i.e., time t1), respectively; (R, θ) n1γ ,θ n2γ ) represent the time when the sun completely sets (i.e., t) γ The relative distance radius R at time (time), the horizontal angle of the sun, and the vertical angle of the sun; the time interval between two adjacent positions, i.e., among the γ positions, is 15 minutes;

[0069] S12, acquires in real time the position information of clouds in the sky (i.e., within the range of spherical coordinate radius D, azimuth (0-2π), and elevation (0-π) with the reference point as the origin of the spherical coordinate system). The position information of the clouds consists of a series of boundary points and satisfies:

[0070] P1=(p 11 ,p 12 ,…,p 1j …,p 1m )

[0071] p 1j →(D,α 11j ,α 12j )

[0072] P2=(p 21 ,p 22 ,…,p 2j …,p 2m )

[0073] p 2j →(D,α 21j ,α 22j )

[0074] And so on,

[0075] P u =(p u1 ,p u2 ,…,p uj …,p um )

[0076] p uj →(D,α u1j ,α u2j )

[0077] 1≤j≤m

[0078] In the above formula, it indicates that there are u unconnected clouds in the sky at the current moment, P1, P2, ... P... u Let p be the set of boundary points of the unconnected clouds in block u at the current moment, in a coordinate system with the center coordinates of the centralized inverter subarray as the reference point; 11 ,p 12 ,…,p 1j …,p 1m Let p be the coordinates of the boundary points of cloud #1. 1j Let be a point within this, and the analytical expression of this point can be derived from the relative distance radius D of the cloud and the horizontal angle α. 11j Vertical angle α 12j The unique determination; similarly, in this application, the relative distance radius D of the cloud is set to remain constant throughout the day.

[0079] Step 3: Based on the sun's trajectory curve for the day, the current cloud and celestial phenomena monitoring module information, and the wind speed and direction forecast information for the next 4 hours, the power prediction result of subarray #1 for the next 4 hours is obtained.

[0080] S21, taking the nth day of the year as an example, the same applies to the other days; on that day, the trajectory curve s of the sun's movement. n Let be a single variable function of time t, starting from the first trajectory point (R, α) of the trajectory curve. n11 ,α n21 Starting from time t1, first calculate the irradiance Cal_t1 at the current time (i.e., sunrise time t1); calculate according to the following formula:

[0081] Cal_t1=C(R,θ n11 ,θ n21 )

[0082] Where C is the standard irradiance function, R,θ n11 ,θ n21 Let R be the relative distance radius at time t1, R be the horizontal angle of the sun, and R be the vertical angle of the sun.

[0083] S22, obtain the real-time position information of clouds in the sky at time t1. Suppose there are u unconnected cloud blocks in the sky at time t1, P1, P2, ... P u Let p be the set of boundary points of the unconnected clouds in block u at the current moment, in a spherical coordinate system with the center coordinates of the centralized inverter subarray as the reference point;11 ,p 12 ,…,p 1j …,p 1m Let p be the coordinates of the boundary points of cloud #1. 1j Let be a point within this, and the analytical expression of this point can be derived from the relative distance radius D of the cloud and the horizontal angle α. 11j Vertical angle α 12j If the boundary points of all unconnected clouds in the u-block are uniquely determined, then the analytical expressions for these boundary points are also unique. The following judgments are then made:

[0084] If, (R,θ) n11 ,θ n21 The area covered by u unconnected cloud blocks in the sky at time t1 means the sun is currently obscured by clouds. Cal_t1 is corrected as follows:

[0085] Cal′_t1=ω·Cal_t1

[0086] In the above formula, ω is the correction factor, and Cal′_t1 is the corrected irradiance.

[0087] If, (R,θ) n11 ,θ n21 The sun is not located within the area covered by u unconnected cloud clusters in the sky at time t1, meaning the sun is not obscured by clouds at this moment, and Cal_t1 is not modified.

[0088] Cal′_t1=Cal_t1

[0089] To determine whether the sun is currently obscured by clouds, the K-means clustering method is used to calculate (R, θ) n11 ,θ n21 Is it located at P1, P2, ... P? u The interior of any set in the set;

[0090] Preferably, the K-means clustering method here follows:

[0091] For P1=(p 11 ,p 12 ,…,p 1j …,p 1m The K-means center of the P1 point set is (R, x1, y1); where x1 and y1 are the horizontal and vertical angles of the clouds in spherical coordinates, respectively. Since the relative distance radius R remains unchanged, the cluster center in spherical coordinates can be transformed into (x1, y1). The clustering vector from each point in the P1 point set to the cluster center in spherical coordinates is:

[0092] Dis1 = (dis 11 ,dis 12,…,dis 1j …,dis 1m )

[0093] in,

[0094] (R,θ n11 ,θ n21 The distance to the cluster center is

[0095] Use K-means clustering to calculate whether disθ is inside vector Dis1; if the result is yes, it means that the sun is currently blocked by cloud #1.

[0096] If the result is negative, continue to determine P2, ... P u Continue until all analyses are completed;

[0097] S23, calculate the irradiance Cal_t2 at time t2; calculate according to the following formula:

[0098] Cal_t2=C(R,θ n12 ,θ n22 )

[0099] Where C is the standard irradiance function, R,θ n12 ,θ n22 Let R be the relative distance radius at time t2, R be the horizontal angle of the sun, and R be the vertical angle of the sun.

[0100] S24, update the position information of u unconnected cloud blocks in the sky at time t1, that is, at time t2, the original u unconnected cloud blocks evolve into y unconnected cloud blocks, and have:

[0101] P1=(p 11 ,p 12 ,…,p 1j …,p 1m )

[0102] p 1j →(D,α 11j ,α 12j )

[0103] P2=(p 21 ,p 22 ,…,p 2j …,p 2m )

[0104] p 2j →(D,α 21j ,α 22j )

[0105] And so on,

[0106] P y =(p y1 ,p y2 ,…,p yj …,p ym )

[0107] p uj →(D,α y1j ,α y2j )

[0108] 1≤k≤m

[0109] Specifically:

[0110] An initial model for predicting cloud location information was constructed using a bidirectional long short-term memory (Bi-LSTM) algorithm.

[0111] By using historical meteorological data on cloud changes, an initial model for predicting cloud location information is trained to obtain a cloud location information prediction model that ensures that the prediction results and the actual changes meet a confidence interval of 95%.

[0112] p 11 ,p 12 ,…,p 1j …,p 1m Let p be the coordinates of the boundary points of cloud #1. 1j Let be a point within this, and the analytical expression of this point can be derived from the relative distance radius D of the cloud and the horizontal angle α. 11j Vertical angle α 12j If the boundary points of all non-connected cloud blocks are uniquely determined, then the analytical expressions for these boundary points are also unique. The following judgments are then made:

[0113] If, (R,θ) n12 ,θ n22 The area covered by u unconnected clouds in the sky at time t2 is where the sun is currently obscured by clouds. Cal_t2 is corrected as follows.

[0114] Cal′_t2=ω·Cal_t2

[0115] In the above formula, ω is the correction factor, and Cal′_t2 is the corrected irradiance.

[0116] If, (R,θ) n12 ,θ n22 If the sun is not located within the area covered by u unconnected clouds in the sky at time t2, then Cal_t2 is not modified.

[0117] Cal′_t2=Cal_t2

[0118] To determine whether the sun is currently obscured by clouds, the K-means clustering method is used to calculate (R, θ) n12 ,θ n22 Is it located at P1, P2, ... P? y The interior of any set in the set;

[0119] S25, repeat S23 and S24 to obtain Cal′_t3, Cal′_t4, Cal′_t5,…,Cal′_t 16 Together with cal′_t1 and Cal′_t2, they form a vector Cal, which is the irradiance vector for the next 4 hours, with a time interval of 15 minutes.

[0120] Cal=[Cal′_t1, Cal′_t2, Cal′_t3,…,Cal′_t 16 ]

[0121] S26, the power vector W is calculated according to the irradiance vector, and the calculation method is as follows:

[0122] W=μ·Cal=μ[Cal′_t1, Cal′_t2, Cal′_t3,…,Cal′_t 16 ]

[0123] In the above formula, μ is the irradiance conversion power factor of the photovoltaic system.

[0124] Example 2

[0125] This embodiment provides a photovoltaic power plant ultra-short-term power prediction system, including:

[0126] The solar trajectory curve calculation module is used to obtain the solar trajectory within a set time period in the coordinate system of the centralized inverter subarray, with the center coordinates of the subarray as the reference point.

[0127] The cloud location information monitoring module is used to obtain the location information of clouds in the sky at multiple times corresponding to the coordinate system of the reference point;

[0128] The power prediction module calculates irradiance at multiple times based on the sun's trajectory throughout the day, and corrects the irradiance at corresponding times using cloud location information to obtain the corrected irradiance, and:

[0129] Multiple corrected irradiance values ​​corresponding to the sun's trajectory on a given day are combined to form an irradiance vector for a set time period. This irradiance vector is then used to predict the power vector for the set time period.

[0130] Example 3

[0131] This embodiment 3 provides a computer device, including: a memory for storing a computer program; and a processor for executing the computer program to implement the steps of a computer method.

[0132] When the processor executes the computer program, it implements the steps of the above-described computer method.

[0133] Alternatively, when the processor executes the computer program, it implements the functions of each module in the above system. The computer device can be a desktop computer, laptop, handheld computer, cloud server, or other computing device. The computer device may include, but is not limited to, a processor and memory. Those skilled in the art will understand that the above are examples of computer devices and do not constitute a limitation on the computer device. It may include more components than described above, or combine certain components, or different components. For example, the computer device may also include input / output devices, network access devices, buses, etc.

[0134] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor, or any conventional processor. The processor is the control center of the computer device, connecting various parts of the computer device via various interfaces and lines.

[0135] The memory can be used to store the computer program and / or module, and the processor implements various functions of the computer device by running or executing the computer program and / or module stored in the memory, and by calling the data stored in the memory.

[0136] The memory may primarily include a program storage area and a data storage area. The program storage area may store the operating system and at least one application program required for a given function (such as sound playback or image playback). The data storage area may store data created based on the use of the phone (such as audio data or a phonebook). Furthermore, the memory may include high-speed random access memory (RAM) and non-volatile memory, such as hard disks, RAM, plug-in hard disks, SmartMediaCards (SMC), Secure Digital (SD) cards, flash cards, at least one disk storage device, flash memory device, or other volatile solid-state storage devices.

[0137] Example 4

[0138] This embodiment 4 also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method described.

[0139] If the modules / units integrated in the computer system are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium.

[0140] Based on this understanding, all or part of the processes in the above-described method can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the above-described computer method. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or a preset intermediate form, etc.

[0141] The computer-readable storage medium may include: any entity or device capable of carrying the computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0142] It should be noted that the content contained in the computer-readable storage medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable storage medium does not include electrical carrier signals and telecommunication signals.

[0143] Example 5

[0144] This embodiment 5 provides a computer product, which includes a computer program stored in a computer-readable storage medium. The processor of the computer device reads the computer program from the computer-readable storage medium and executes the computer program, so that the computer device can perform the method in embodiment 1, which will not be described again here.

[0145] It should be noted that those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods.

[0146] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for predicting ultra-short-term power output of a photovoltaic power plant, characterized in that, Includes the following steps: Step 1: Establish a coordinate system with the center coordinates of the centralized inverter subarray as the reference point, and obtain the sun's trajectory in that coordinate system over a day. Step 2: Calculate the irradiance at multiple times within the set future time period based on the sun's trajectory on that day; Step 3: Obtain the current position information of the clouds in the sky in the coordinate system, and use the cloud position information to predict the cloud position information at multiple times in the future time period. The irradiance obtained in step 2 is corrected using the predicted cloud location information to obtain the corrected irradiance. Step 4: Combine the obtained multiple corrected irradiance values ​​to form an irradiance vector for a set future time period, and use this irradiance vector to predict the power vector for the set future time period. In step 3, the obtained cloud location information consists of a series of boundary points and satisfies the following expression: in, For unconnected first The set of boundary points of a block cloud; For unconnected first The first cloud Coordinates of the boundary points; The relative distance radius of the cloud; The included angle is horizontal; It is a vertical angle; In step 3, the irradiance at the corresponding time is corrected using cloud location information to obtain the corrected irradiance. The specific method is as follows: Determine whether the sun at a given time is obscured by clouds at the corresponding time, where: If the sun at a given time is obscured by clouds at the corresponding time, the irradiance is corrected using the following formula: If the sun at a given time is not obscured by clouds at the corresponding time, the irradiance is corrected using the following formula: In the above formula, As a correction factor, for Irradiance corrected for time; for The irradiance corresponding to the time; To determine whether the sun is obscured by clouds at a given time, the specific method is as follows: If the sun's position at a given time is located in a sky that is not connected to the sun at that time... Within the area covered by the cloud, determine if the sun at the set time is obscured by the cloud at the corresponding time; otherwise, determine if the sun at the set time is not obscured by the cloud at the corresponding time.

2. The method for ultra-short-term power prediction of a photovoltaic power plant according to claim 1, characterized in that, In step 1, the obtained daily solar trajectory satisfies the following coordinate relationship: in, The first of the year The trajectory curve of the sun in the sky; The radius represents the relative distance from the sun. For the first part of the trajectory curve The horizontal angle of the sun at each location point; For the first part of the trajectory curve The vertical angle of the sun at each location point; ; For time.

3. The method for ultra-short-term power prediction of a photovoltaic power plant according to claim 1, characterized in that, In step 2, the irradiance at multiple times within a set future time period is calculated based on the sun's trajectory on that day. The specific method is as follows: in, for The irradiance corresponding to the time; Standard irradiance function; The first of the year In the curve of the sun's orbit over the day The position of the sun at that moment; The radius represents the relative distance from the sun. The horizontal angle between the sun and the sun; The vertical angle is the angle between the sun and the earth.

4. The method for ultra-short-term power prediction of a photovoltaic power plant according to claim 1, characterized in that, In step 4, the power vector within a set time period is predicted using this irradiance vector in conjunction with the following formula: In the above formula, The irradiance conversion power factor of a photovoltaic system; The power vector for a given time period; This is the irradiance vector.

5. A photovoltaic power plant ultra-short-term power prediction system, characterized in that, The prediction method based on claim 1 includes: The solar trajectory curve calculation module is used to establish a coordinate system with the center coordinates of the centralized inverter subarray as the reference point, and to obtain the solar trajectory in that coordinate system over a day. The cloud location information monitoring module is used to obtain the current location information of clouds in the sky in this coordinate system, and use this cloud location information to predict the cloud location information corresponding to multiple times in the future time period. The power prediction module is used to calculate the irradiance at multiple times within a set future time period based on the sun's trajectory on a given day, and to correct the irradiance using the predicted cloud location information, resulting in the corrected irradiance. The obtained multiple corrected irradiance values ​​are combined to form an irradiance vector for a set future time period, and this irradiance vector is used to predict the power vector for the set future time period.

6. A computer device, characterized in that, include: A processor is used to execute computer programs; A computer-readable storage medium storing a computer program that, when executed by the processor, performs the method as described in any one of claims 1-4.

7. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1-4.

Images