Photovoltaic power station ultra-short-term power prediction method, system, equipment and medium

Abstract

The invention provides an ultra-short-term power prediction method, system and device for a photovoltaic power station and a medium, and the method comprises the steps: taking a central coordinate of a centralized inverter subarray as a reference point, and obtaining a sun moving trajectory of one day in a set time period under a coordinate system of the reference point; calculating irradiance at a plurality of moments based on the sun moving trajectory in one day; cloud position information at moments corresponding to the multiple moments in the day is obtained through prediction, the irradiance at the corresponding moments is corrected through the obtained cloud position information, and the corrected irradiance is obtained; combining a plurality of corrected irradiances corresponding to the sun moving trajectory in one day to form an irradiance vector in a set time period, and predicting a power vector in the set time period by using the irradiance vector; the accuracy of ultra-short-term power prediction is improved, the stability of a power system is improved, and economic losses caused by power fluctuation can be effectively reduced.

Description

Technical Field

[0001] The present invention belongs to new energy photovoltaic power generation technology, and specifically relates to an ultra-short-term power prediction method, system, equipment and medium for a photovoltaic power station. Background Art

[0002] The ultra-short-term power forecast of photovoltaic power stations is the process of forecasting the active power of photovoltaic power stations by applying technologies and means such as meteorological conditions and statistical laws. It refers to the prediction of power in the next 15 minutes to 4 hours, with a time resolution of 15 minutes. Its importance lies in its direct relationship to the stability of the power system and can effectively reduce the economic losses caused by power fluctuations. With the popularization of renewable energy and the expansion of the scale of photovoltaic power stations, it is particularly important to improve the accuracy of predictions. According to research, for every 1% increase in prediction accuracy, 2% of scheduling costs can be saved. 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 generation prediction involves data collection and preprocessing, feature extraction, time series analysis methods (such as ARI MA model) and the application of machine learning models (such as support vector machines, neural networks, etc.). These methods can further improve the accuracy of power prediction by combining historical meteorological and photovoltaic data. Data cleaning is a basic link, and the accuracy of prediction can be improved by removing outliers and filling missing data.

[0004] However, the uncertainty and randomness of photovoltaic output forecasts caused by weather factors have not yet been fully resolved. In particular, for the Gobi Desert, where there is no problem of component shading, there is currently no effective way to predict the power drop caused by shading due to the randomness of clouds in meteorological phenomena. Summary of the invention

[0005] The purpose of the present invention is to provide an ultra-short-term power prediction method, system, device and medium for photovoltaic power stations, which solves the problem of component shading in open areas of the Gobi Desert, and is an effective prediction method for power drop caused by shading due to the randomness of clouds in meteorological phenomena.

[0006] In order to achieve the above object, the technical solution adopted by the present invention is:

[0007] The present invention provides a method for ultra-short-term power prediction of a photovoltaic power station, comprising the following steps:

[0008] Step 1: Establish a coordinate system with the central coordinate of the centralized inverter subarray as the reference point, and obtain the movement trajectory of the sun in one day under the coordinate system;

[0009] Step 2, calculating the irradiance at multiple times in a set future time period based on the sun's trajectory for the day;

[0010] Step 3, obtaining the current position information of the clouds in the sky in the coordinate system, and using the cloud position information to predict the cloud position information corresponding to multiple moments in the future time period;

[0011] The irradiance obtained in step 2 is corrected using the predicted cloud position information to obtain a corrected irradiance;

[0012] Step 4: Combining the multiple corrected irradiances obtained to form an irradiance vector within a set future time period, and using the irradiance vector to predict the power vector within the set future time period.

[0013] Preferably, in step 1, the obtained sun trajectory for one day 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] Among them, s n is the sun's trajectory curve on the nth day of the year; R is the relative distance radius of the sun; θ n1γ is the horizontal angle of the sun at the γth position point in the running trajectory curve; θ n2γ is the vertical angle of the sun at the γth position point in the running trajectory curve; k=365 / 366.

[0017] Preferably, in step 2, the irradiance at multiple moments in a set future time period is calculated based on the sun's trajectory for the day, and the specific method is:

[0018] Cal_t1=C(R,θ n11 ,θ n21 )

[0019] Among them, Cal_t1 is the irradiance corresponding to time t1; C is the standard irradiance function; (R,θ n11 ,θ n21 ) is the sun position point corresponding to time t1 in the sun trajectory curve of the nth day of the 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 cloud position information consists 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] Among them, P u is the set of boundary points of the u-th cloud that are not connected to each other; p um is the coordinate of the mth boundary point of the uth cloud that is not connected to each other; D is the relative distance radius of the cloud; α 11j is the horizontal angle; α 12j is the vertical angle.

[0025] Preferably, in step 3, the irradiance at the corresponding moment is corrected using the cloud position information to obtain the corrected irradiance, and the specific method is:

[0026] Determine whether the sun at a set time is blocked by clouds at the corresponding time, where:

[0027] If the sun at a set time is blocked by clouds at the corresponding time, the irradiance is corrected using the following formula:

[0028] Cal′_t1=ω·Cal_t1

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

[0030] Cal′_t1=Cal_t1

[0031] In the above formula, ω is the correction factor, Cal′_t1 is the corrected irradiation at time t1; Cal_t1 is the irradiance corresponding to time t1.

[0032] Preferably, the specific method for determining whether the sun at a set time is blocked by clouds at a corresponding time is:

[0033] If the sun position point at the set time is located within the range covered by u unconnected clouds in the sky at the corresponding time, it is determined that the sun at the set time is blocked by the clouds at the corresponding time; otherwise, it is determined that the sun at the set time is not blocked by the clouds at the corresponding time.

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

[0035] W=μ·Cal=μ[Cal′_t1, Cal′_t2, Cal′_t3,…,Cal′_t 16 ]

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

[0037] An ultra-short-term power prediction system for a photovoltaic power station, comprising:

[0038] The solar trajectory curve calculation module is used to establish a coordinate system with the central coordinates of the centralized inverter subarray as the reference point to obtain the solar trajectory of one day in the coordinate system;

[0039] The cloud position information monitoring module is used to obtain the position information of clouds in the sky at the current moment in the coordinate system, and use the cloud position information to predict the cloud position information corresponding to multiple moments in the future time period;

[0040] The power prediction module is used to calculate the irradiance at multiple times in a set future time period based on the sun's trajectory for the day, and to correct the obtained irradiance using the predicted cloud position information to obtain the corrected irradiance, and:

[0041] The obtained multiple corrected irradiances are combined to form an irradiance vector within a set future time period, and the irradiance vector is used to predict the power vector within the set future time period.

[0042] A computer device comprising:

[0043] a processor suitable for executing a computer program;

[0044] A computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the method described is performed.

[0045] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described above is implemented.

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

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

[0048] In summary, the present invention is applicable to ultra-short-term power prediction and correction of photovoltaic power stations, and has broad application prospects and social benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION

[0050] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

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

[0052] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0053] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0054] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0055] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0056] Example 1

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

[0058] Step 1: Get the trajectory curve set of the sun and the cloud position information of the reference point

[0059] S11, taking the central coordinate of the centralized inverter subarray (denoted as subarray #1) as the reference point, calculating the trajectory curve set S of the sun's movement at the reference point;

[0060] The set of trajectory curves S of the sun's motion at this reference point refers to the set of sun trajectory curves for each day of the year, namely:

[0061] S=[s1,s2,…,s k ]

[0062] k = 365 / 366

[0063] Among them, s1,s2,…,s k These are the trajectory curves of the sun's movement on each day of the year, k = 365 for an ordinary year, and k = 366 for a leap year;

[0064] The trajectory curves of the sun's movement every day of the year are s1, s2, ..., s k The following coordinate relationship is 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 is the trajectory curve of the sun's movement on the nth day of a year, the curve includes γ position points, and the analytical expression of each position point can be composed of the relative distance radius R, the horizontal angle of the sun, and the vertical angle of the sun, and is a single variable function of time t; wherein, in this application, the relative distance radius R is set to remain unchanged within a day;

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

[0069] S12, real-time acquisition of cloud position information in the sky (i.e., taking the reference point as the origin of the spherical coordinates, within the range of the spherical coordinate radius D, the azimuth angle (0-2π) and the elevation angle (0-π)), wherein the cloud position information is composed 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 means that there are u unconnected clouds in the sky at the current moment, P1, P2, ...P u are the boundary point sets of u unconnected clouds at the current moment in the coordinate system with the central coordinate of the centralized inverter subarray as the reference point; 11 ,p 12 ,…,p 1j …,p 1m are the coordinates of each boundary point of cloud #1, p 1j is a point in it, and the analytical expression of this point can be obtained by the cloud relative distance radius D, horizontal angle α 11j , vertical angle α 12j Similarly, in this application, the cloud relative distance radius D is set to remain unchanged within a day.

[0079] Step 3: According to the trajectory curve of the sun's movement on that day, the current cloud and astronomical monitoring module information, and the wind speed and direction forecast information for the next 4 hours, the power forecast result of the #1 sub-array for the next 4 hours is predicted.

[0080] S21, take the nth day of the year as an example, and the rest of the days are the same; on that day, the trajectory curve of the sun's movement is s n is a single variable function at time t, starting from the first trajectory point (R, α n11 ,α n21 ), that is, starting from time t1, first calculate the irradiance Cal_t1 at the current time (i.e., the moment when the sun first rises 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 They are the relative distance radius R, the horizontal angle of the sun, and the vertical angle of the sun at time t1;

[0083] S22, obtain the position information of the clouds in the sky at time t1 in real time. Suppose there are u unconnected clouds in the sky at time t1, P1, P2, ...P u are the boundary point sets of u unconnected clouds at the current moment in the spherical coordinate system with the central coordinate of the centralized inverter subarray as the reference point;11 ,p 12 ,…,p 1j …,p 1m are the coordinates of each boundary point of cloud #1, p 1j is a point in it, and the analytical expression of this point can be obtained by the cloud relative distance radius D, horizontal angle α 11j , vertical angle α 12j Uniquely determined; then the boundary point analytical expressions of all u-blocks of unconnected clouds are unique; carry out the following judgment:

[0084] If, (R,θ n11 ,θ n21 ) is located within the range covered by u unconnected clouds in the sky at time t1, that is, the sun is blocked by clouds at this moment. Correct Cal_t1 as follows:

[0085] Cal′_t1=ω·Cal_t1

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

[0087] If, (R,θ n11 ,θ n21 ) is not located within the range of u unconnected clouds in the sky at time t1, that is, the sun is not blocked by clouds at this moment, and Cal_t1 is not corrected:

[0088] Cal′_t1=Cal_t1

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

[0090] Preferably, the process of the K-means clustering method here is as 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 angle and vertical angle of the cloud in the spherical coordinate system respectively; since the relative distance radius R remains unchanged, the cluster center in the spherical coordinate system can be transformed into (x1, y1); the cluster vector from each point in the P1 point set to the cluster center in the spherical coordinate system is:

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

[0093] in,

[0094] (R,θ n11 ,θ n21 ) and the distance from the cluster center is

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

[0096] If the result is no, continue to determine P2, ...P u , until all analysis is 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 They are the relative distance radius R, the horizontal angle of the sun, and the vertical angle of the sun at time t2 respectively;

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

[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] The Bidirectional Long Short-Term Memory (Bi-LSTM) algorithm is used to build an initial model for predicting cloud location information;

[0111] The cloud location information prediction model is trained using cloud change data from historical meteorology to obtain a cloud location information prediction model, so that the prediction results and actual change results meet the confidence interval of 95%;

[0112] p 11 ,p 12 ,…,p 1j …,p 1m are the coordinates of each boundary point of cloud #1, p 1j is a point in it, and the analytical expression of this point can be obtained by the cloud relative distance radius D, horizontal angle α 11j , vertical angle α 12j Uniquely determined; then the boundary point analytical expressions of all y-blocks of clouds that are not connected to each other are unique; carry out the following judgment:

[0113] If, (R,θ n12 ,θ n22 ) is located within the range covered by u unconnected clouds in the sky at time t2, that is, the sun is blocked by clouds at this moment. Correct Cal_t2 as follows;

[0114] Cal′_t2=ω·Cal_t2

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

[0116] If, (R,θ n12 ,θ n22 ) is not located within the range of u unconnected clouds in the sky at time t2, that is, the sun is not blocked by clouds at this moment, and Cal_t2 is not corrected;

[0117] Cal′_t2=Cal_t2

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

[0119] S25, repeat S23, S24, and obtain Cal′_t3, Cal′_t4, Cal′_t5,…,Cal′_t 16 , together with cal′_t1 and Cal′_t2, form the vector Cal. Then the vector Cal is the irradiance vector in 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 station ultra-short-term power prediction system, including:

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

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

[0128] The power prediction module is used to calculate the irradiance at multiple times based on the sun's trajectory during the day, and to correct the irradiance at the corresponding time using the cloud position information to obtain the corrected irradiance, as well as:

[0129] A plurality of corrected irradiances corresponding to the sun's trajectory for the day are combined to form an irradiance vector within a set time period, and the irradiance vector is used to predict the power vector within 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 implementing the steps of a computer method when executing the computer program.

[0132] When the processor executes the computer program, the steps of the above computer method are implemented.

[0133] Alternatively, the processor implements the functions of each module in the above system when executing the computer program, and the computer device may be a computing device such as a desktop computer, a notebook, a PDA, and a cloud server. The computer device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the above are examples of computer devices and do not constitute a limitation on computer devices, and may include more components than the above, or a combination of certain components, or different components. For example, the computer device may also include input and output devices, network access devices, buses, etc.

[0134] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the computer device, and uses various interfaces and lines to connect various parts of the entire computer device.

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

[0136] The memory may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (SmartMediaCard, SMC), a secure digital (SecureDigital, SD) card, a flash card (FlashCard), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0137] Example 4

[0138] This embodiment 4 also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps of the method described are implemented.

[0139] If the module / unit integrated in the computer system is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium.

[0140] Based on such understanding, the present invention implements all or part of the processes in the above method, and can also be completed by instructing related hardware through a computer program, and the computer program can be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the above computer method can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or preset intermediate form, etc.

[0141] The computer-readable storage medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, 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 can 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, computer-readable storage media do not include electrical carrier signals and telecommunication signals.

[0143] Example 5

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

[0145] It should be noted that a person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing related hardware through a computer program. The program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods.

[0146] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for ultra-short-term power prediction of a photovoltaic power station, characterized in that: The following steps are involved: Step 1: Establish a coordinate system with the central coordinate of the centralized inverter subarray as the reference point, and obtain the movement trajectory of the sun in one day in the coordinate system; Step 2, calculating the irradiance at multiple times in a set future time period based on the sun's trajectory for the day; Step 3, obtaining the current position information of the clouds in the sky in the coordinate system, and using the cloud position information to predict the cloud position information corresponding to multiple moments in the future time period; The irradiance obtained in step 2 is corrected using the predicted cloud position information to obtain a corrected irradiance; Step 4: Combining the multiple corrected irradiances obtained to form an irradiance vector within a set future time period, and using the irradiance vector to predict the power vector within the set future time period.

2. The method for ultra-short-term power prediction of a photovoltaic power station according to claim 1, characterized in that: In step 1, the sun's trajectory for one day is obtained to satisfy the following coordinate relationship: s n →t[(R,θ n11 ,i n21 ),(R,θ n12 ,i n22 ),…,(R,θ n1γ ,i n2γ )] 1≤n≤k Among them, s n is the sun's trajectory curve on the nth day of the year; R is the relative distance radius of the sun; θ n1γ is the horizontal angle of the sun at the γth position point in the running trajectory curve; θ n2γ is the vertical angle of the sun at the γth position point in the running trajectory curve; k=365 / 366.

3. The method for ultra-short-term power prediction of a photovoltaic power station according to claim 1, characterized in that: In step 2, the irradiance at multiple times in a set future time period is calculated based on the sun's trajectory for the day. The specific method is: Cal_t1=C(R,θ n11 ,i n21 ) Among them, Cal_t1 is the irradiance corresponding to time t1; C is the standard irradiance function; (R,θ n11 ,θ n21 ) is the sun position point corresponding to time t1 in the sun trajectory curve of the nth day of the 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.

4. The method for ultra-short-term power prediction of a photovoltaic power station according to claim 1, characterized in that: In step 3, the obtained cloud location information consists of a series of boundary points and satisfies the following expression: P u =(p u1 ,p u2 ,…,p uj …,p um ) p uj →(D,a u1j ,a u2j ) 1≤j≤m Among them, P u is the set of boundary points of the u-th cloud that are not connected to each other; p um is the coordinate of the mth boundary point of the uth cloud block that is not connected to each other; D is the relative distance radius of the cloud; α 11j is the horizontal angle; α 12j is the vertical angle.

5. The method for ultra-short-term power prediction of a photovoltaic power station according to claim 1, characterized in that: In step 3, the irradiance at the corresponding time is corrected using the cloud position information to obtain the corrected irradiance. The specific method is: Determine whether the sun at a set time is blocked by clouds at the corresponding time, where: If the sun at a set time is blocked by clouds at the corresponding time, the irradiance is corrected using the following formula: Cal′_1=·Cal_t1 If the sun at the set time is not blocked by the clouds at the corresponding time, the irradiance is corrected using the following formula: Cal′_1=al_t1 In the above formula, ω is the correction factor, Cal′_1 is the corrected irradiance at time t1; Cal_t1 is the irradiance corresponding to time t1.

6. A method for ultra-short-term power prediction of a photovoltaic power station according to claim 5, characterized in that: Determine whether the sun at a set time is blocked by clouds at the corresponding time. The specific method is: If the sun position point at the set time is located within the range covered by u unconnected clouds in the sky at the corresponding time, it is determined that the sun at the set time is blocked by the clouds at the corresponding time; otherwise, it is determined that the sun at the set time is not blocked by the clouds at the corresponding time.

7. The method for ultra-short-term power prediction of a photovoltaic power station according to claim 1, characterized in that: In step 4, the irradiance vector is used in combination with the following formula to predict the power vector within the set time period: W=μ·Cal=μ[Cal′_1、Cal′_2、Cal′_3,…,al′_t 16 ] In the above formula, μ is the irradiance conversion power factor of the photovoltaic system; W is the power vector in the set time period; Cal is the irradiance vector.

8. A photovoltaic power station ultra-short-term power prediction system, characterized in that: include: The solar trajectory curve calculation module is used to establish a coordinate system with the central coordinates of the centralized inverter subarray as the reference point to obtain the solar trajectory of one day in the coordinate system; The cloud position information monitoring module is used to obtain the position information of clouds in the sky at the current moment in the coordinate system, and use the cloud position information to predict the cloud position information corresponding to multiple moments in the future time period; The power prediction module is used to calculate the irradiance at multiple times in a set future time period based on the sun's trajectory for the day, and to correct the obtained irradiance using the predicted cloud position information to obtain the corrected irradiance, and: The obtained multiple corrected irradiances are combined to form an irradiance vector within a set future time period, and the irradiance vector is used to predict the power vector within the set future time period.

9. A computer device, characterized in that: include: a processor suitable for executing a computer program; A computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by the processor, the method according to any one of claims 1 to 7 is performed.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images