Method and apparatus for power prediction of photovoltaic power station, and device

Abstract

The present invention provides a method and apparatus for power prediction of a photovoltaic power station, and a device. The method comprises: acquiring a real-time power value of each photovoltaic module in a current detection cycle; acquiring an environmental parameter predicted value of each photovoltaic module in the next detection cycle; on the basis of a real-time temperature value, real-time light intensity value and real-time tilt angle value in the real-time power value and a temperature predicted value, light intensity predicted value and tilt angle predicted value in the environmental parameter predicted value, determining a temperature variation coefficient, a light intensity variation coefficient, and a tilt angle variation coefficient of each corresponding photovoltaic module; inputting the temperature variation coefficient, the light intensity variation coefficient, the tilt angle variation coefficient, and the real-time power value into a power prediction model, and outputting a power predicted value of a photovoltaic power station in the next detection cycle. By accurately obtaining an environmental parameter predicted value and then performing power prediction, the accuracy of the power prediction of the photovoltaic power station can be guaranteed better.

Description

Photovoltaic power plant power prediction methods, devices and equipment Technical Field

[0001] This invention relates to the field of power prediction technology, and in particular to a method, apparatus and equipment for predicting the power of a photovoltaic power plant. Background Technology

[0002] With the large-scale integration of photovoltaic (PV) power plants, their impact on power grid operation is becoming increasingly significant. Therefore, power forecasting for PV power plants is crucial, serving as a vital link in ensuring stable power system operation and optimized power dispatch. PV power plant power forecasting refers to predicting the active power of PV power plants based on meteorological conditions, statistical laws, and other technical methods. This helps to achieve intelligent management and optimized utilization of PV power generation, thereby improving energy efficiency.

[0003] Existing photovoltaic power plant power prediction methods still have many problems in practical applications, such as: 1) Photovoltaic power generation is affected by a variety of meteorological factors such as solar radiation, temperature, and cloud cover. The uncertainty and variability of these factors make accurate prediction difficult; 2) Models trained at specific locations may not be able to generalize well to other geographical locations or environmental conditions; 3) Local meteorological conditions at the location of photovoltaic power plants, such as terrain and building shading, have a significant impact on photovoltaic power, and these factors have not been effectively considered in existing prediction models.

[0004] Therefore, how to accurately predict the power output of photovoltaic power plants has become a technical problem that urgently needs to be solved by professionals in this field. Summary of the Invention

[0005] This invention provides a method, apparatus, and equipment for predicting the power of photovoltaic power plants, thereby addressing the shortcomings of poor accuracy in predicting the power of photovoltaic power plants in existing technologies.

[0006] In a first aspect, the present invention provides a method for predicting the power output of a photovoltaic power plant, wherein the photovoltaic power plant includes multiple photovoltaic modules connected in series, and the method includes:

[0007] Obtain the real-time power value of each photovoltaic module in the current detection cycle, the real-time power value including the real-time temperature value, the real-time light intensity value and the real-time tilt angle value;

[0008] Obtain the predicted environmental parameters for each photovoltaic module in the next detection cycle. The predicted environmental parameters include predicted temperature, predicted light intensity, and predicted tilt angle.

[0009] Based on the real-time temperature value, the real-time light intensity value, the real-time tilt angle value, the predicted temperature value, the predicted light intensity value, and the predicted tilt angle value, the corresponding temperature change coefficient, light intensity change coefficient, and tilt angle change coefficient for each photovoltaic module are determined.

[0010] Input the temperature change coefficient, the light intensity change coefficient, the tilt angle change coefficient, and the real-time power value into the power prediction model, and output the power prediction value of the photovoltaic power station in the next detection cycle.

[0011] According to a photovoltaic power plant power prediction method provided by the present invention, the formula for the predicted power value of the photovoltaic module in the next detection cycle is: P i,j+1 =P i,j ×(1+λ i,j -η i,j -σ i,j );

[0012] Among them, P i,j+1 P is the predicted power value of the i-th photovoltaic module in the (j+1)-th detection period. i,j Let λ be the real-time power value of the i-th photovoltaic module in the j-th detection cycle. i,j G is the light intensity variation coefficient of the i-th photovoltaic module in the j-th detection period. i,j+1 G represents the predicted light intensity of the i-th photovoltaic module in the (j+1)-th detection period. i,j η is the real-time value of the light intensity of the i-th photovoltaic module in the j-th detection period. i , j is the tilt angle change coefficient of the i-th photovoltaic module in the j-th detection cycle, Z i,j+1 Z is the predicted tilt angle of the i-th photovoltaic module in the (j+1)-th detection cycle, where the tilt angle is the angle between the line connecting the sun and the photovoltaic module and the numerical direction. i,j σ is the real-time value of the tilt angle of the i-th photovoltaic module in the j-th detection cycle. i,j Let T be the temperature change coefficient of the i-th photovoltaic module in the j-th detection cycle. i,j+1 T is the predicted temperature value of the i-th photovoltaic module in the (j+1)-th detection cycle. i,j The real-time temperature value of the i-th photovoltaic module in the j-th detection cycle;

[0013] The power prediction model is as follows:

[0014] Among them, P total_j+1Let i be the total predicted power of the photovoltaic power station in the (j+1)th detection cycle, i be the serial number of the photovoltaic module, and n be the number of the photovoltaic modules.

[0015] According to a photovoltaic power plant power prediction method provided by the present invention, determining the temperature change coefficient of each photovoltaic module includes:

[0016] The real-time temperature value of each photovoltaic module in the current detection cycle is compared with a preset temperature threshold.

[0017] If the real-time temperature value is less than the preset temperature threshold, then the temperature change coefficient is determined to be 0.

[0018] If the real-time temperature value is greater than or equal to the preset temperature threshold, then the temperature change coefficient is determined based on the real-time temperature value of each photovoltaic module in the current detection cycle and the predicted temperature value in the next detection cycle.

[0019] The photovoltaic power plant power prediction method provided by the present invention further includes:

[0020] Obtain the predicted surface shading rate of the photovoltaic module, including the predicted surface shading rate for the next detection cycle and the real-time surface shading rate for the current detection cycle;

[0021] The surface shading rate change coefficient is determined based on the predicted surface shading rate, the real-time surface shading rate, and the formula for determining the surface shading rate change coefficient.

[0022] The formula for determining the surface shading rate variation coefficient is:

[0023] Where, θ i,j S is the coefficient of variation of the surface shading rate. i,j+1 S is the predicted surface shading value of the i-th photovoltaic module in the (j+1)-th detection cycle. i,j The real-time value of the surface shadow of the i-th photovoltaic module in the j-th detection cycle;

[0024] Correspondingly, the formula for the predicted power value of the photovoltaic module in the next detection cycle is: P i,j+1 =P i,j ×(1+λ i,j -η i,j -σ i,j -θ i,j ).

[0025] According to the photovoltaic power plant power prediction method provided by the present invention, the photovoltaic power plant further includes: a plurality of image acquisition components corresponding one-to-one with the photovoltaic modules;

[0026] The step of obtaining the predicted value of the surface shading rate of the photovoltaic module includes:

[0027] The image acquisition component acquires a first image region and a second image region on the surface of the photovoltaic module within the current detection period. The first image region is the brightness region on the upper surface of the photovoltaic module when sunlight is normally shining, and the second image region is the brightness region on the upper surface of the photovoltaic module when sunlight is blocked.

[0028] Based on the first image region and the second image region, the proportion of the second image region to the upper surface of the photovoltaic module is determined, and the real-time value of the surface shading rate of the photovoltaic module is obtained.

[0029] Obtain a preset number of historical values ​​of the surface shading rate of the photovoltaic module within previous detection cycles, and combine them with the real-time value of the surface shading rate of the photovoltaic module to determine the predicted value of the surface shading rate of the photovoltaic module in the next detection cycle.

[0030] According to a photovoltaic power plant power prediction method provided by the present invention, the formula for calculating the predicted surface shading rate of the photovoltaic module in the next detection cycle is as follows:

[0031] S i,j+1 =τ0S i,j +τ1S i,j-1 +τ2S i,j-2 +…+τ m-1 S i,j-m+1 +τ m S i,j-m ;

[0032] Among them, S i,j+1 S is the predicted surface shading rate of the photovoltaic module in the next detection cycle. i,j τ0 is the real-time value of the surface shading rate of the photovoltaic module in the current detection period. i,j S is the weighting coefficient for the real-time value of the surface shading rate of the photovoltaic module in the current detection period. i,j-m τ is the historical value of the surface shading rate of the photovoltaic module in the previous m-th detection cycle. m The weighting coefficient is the historical value of the surface shading rate of the photovoltaic module in the first m-th detection cycle.

[0033] According to a photovoltaic power plant power prediction method provided by the present invention, after obtaining the real-time value of the surface shading rate of the photovoltaic module, the method further includes:

[0034] Obtain the historical surface shading rate values ​​and real-time surface shading rate values ​​of multiple photovoltaic modules in a preset number of prior detection cycles within the current date;

[0035] The historical value of the surface shading rate for the current date, the real-time value of the surface shading rate for the current date, and the corresponding data for the corresponding time period yesterday are compared respectively.

[0036] If the comparison results show the same trend, then the historical value of the photovoltaic module surface shading rate for the corresponding period yesterday will be selected as the predicted value of the photovoltaic module surface shading rate for the next testing cycle today.

[0037] According to the photovoltaic power plant power prediction method provided by the present invention, the comparison result is that the trend of change is the same, including: the difference between the historical values ​​of the surface shading rate of each photovoltaic module in today's detection cycle and the corresponding yesterday's detection cycle is less than a preset ratio value.

[0038] In a second aspect, the present invention provides a photovoltaic power plant power prediction device, comprising:

[0039] The acquisition module is used to acquire the real-time power value of each photovoltaic module in the current detection cycle, the real-time power value including the real-time temperature value, the real-time light intensity value and the real-time tilt angle value; and to acquire the predicted environmental parameters of each photovoltaic module in the next detection cycle, the predicted environmental parameters including the predicted temperature value, the predicted light intensity value and the predicted tilt angle value.

[0040] The determination module is used to determine the temperature change coefficient, light intensity change coefficient, and tilt angle change coefficient of each photovoltaic module based on the real-time temperature value, the real-time light intensity value, the real-time tilt angle value, the predicted temperature value, the predicted light intensity value, and the predicted tilt angle value.

[0041] The prediction module is used to input the temperature change coefficient, the light intensity change coefficient, the tilt angle change coefficient, and the real-time power value into the power prediction model, and output the power prediction value of the photovoltaic power station in the next detection cycle.

[0042] Thirdly, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the photovoltaic power plant power prediction method as described above.

[0043] Fourthly, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the photovoltaic power plant power prediction method as described above.

[0044] Fifthly, the present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the photovoltaic power plant power prediction method as described above.

[0045] This invention provides a photovoltaic power plant power prediction method, apparatus, and equipment, including: acquiring the real-time power value of each photovoltaic module in the current testing cycle, the real-time power value including real-time temperature, real-time irradiance, and real-time tilt angle; acquiring the predicted environmental parameters of each photovoltaic module in the next testing cycle, the predicted environmental parameters including predicted temperature, predicted irradiance, and predicted tilt angle; determining the corresponding temperature variation coefficient, irradiance variation coefficient, and tilt angle variation coefficient for each photovoltaic module based on the real-time temperature, irradiance, and tilt angle; inputting the temperature variation coefficient, irradiance variation coefficient, tilt angle variation coefficient, and real-time power value into the power prediction model, and outputting the predicted power value of the photovoltaic power plant in the next testing cycle. By accurately acquiring the predicted environmental parameters and then performing power prediction, the accuracy of photovoltaic power plant power prediction can be better guaranteed. Attached Figure Description

[0046] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0047] Figure 1 is a flowchart illustrating the photovoltaic power plant power prediction method provided in this embodiment;

[0048] Figure 2 is a schematic diagram of the photovoltaic power plant power prediction device provided in this embodiment;

[0049] Figure 3 is a schematic diagram of the structure of the electronic device provided in this embodiment. Detailed Implementation

[0050] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0051] Figure 1 is a flowchart illustrating the photovoltaic power plant power prediction method provided in this embodiment.

[0052] As shown in Figure 1, the photovoltaic power plant power prediction method provided in this embodiment of the invention includes multiple photovoltaic modules connected in series in the photovoltaic power plant. The method mainly includes the following steps:

[0053] 101. Obtain the real-time power value of each photovoltaic module in the current detection cycle. The real-time power value includes the real-time temperature value, the real-time light intensity value, and the real-time tilt angle value.

[0054] In a specific implementation, the real-time values ​​of temperature, light intensity, and tilt angle can be obtained through sensors or other methods, as long as they can be accurately acquired. The current detection period refers to the period of the current time segment.

[0055] 102. Obtain the predicted environmental parameters for each photovoltaic module in the next testing cycle. The predicted environmental parameters include the predicted temperature, the predicted light intensity, and the predicted tilt angle.

[0056] The next testing cycle refers to the cycle adjacent to the current testing cycle. Therefore, it is necessary to predict the relevant parameters for the next testing cycle, specifically the predicted environmental parameters for each photovoltaic module in the next testing cycle. Among these, the predicted values ​​for temperature, irradiance, and tilt angle correspond to the relevant values ​​within the current testing cycle. Prediction can be made using weather forecasts or other methods.

[0057] 103. Based on the real-time temperature value, real-time light intensity value, real-time tilt angle value, predicted temperature value, predicted light intensity value, and predicted tilt angle value, determine the corresponding temperature change coefficient, light intensity change coefficient, and tilt angle change coefficient for each photovoltaic module.

[0058] The temperature variation coefficient for each photovoltaic module is determined by using real-time temperature values ​​and predicted temperature values. Specifically, the real-time temperature value of each photovoltaic module in the current testing cycle is compared with a preset temperature threshold. If the real-time temperature value is less than the preset temperature threshold, the temperature variation coefficient is determined to be 0. If the real-time temperature value is greater than or equal to the preset temperature threshold, the temperature variation coefficient is determined based on the real-time temperature value of each photovoltaic module in the current testing cycle and the predicted temperature value in the next testing cycle.

[0059] Similarly, the illuminance variation coefficient for each photovoltaic module can be determined using the real-time and predicted illuminance values. The tilt angle variation coefficient can be determined using the real-time and predicted tilt angle values.

[0060] 104. Input the temperature change coefficient, light intensity change coefficient, tilt angle change coefficient, and real-time power value into the power prediction model, and output the power prediction value of the photovoltaic power station in the next detection cycle.

[0061] After obtaining the temperature change coefficient, irradiance change coefficient, and tilt angle change coefficient, these are combined with real-time temperature, irradiance, and tilt angle values ​​and input into the power prediction model. This allows for the accurate output of the photovoltaic power plant's power prediction value for the next monitoring cycle. The photovoltaic power plant comprises multiple photovoltaic modules; therefore, the output is the sum of the power prediction values ​​for all photovoltaic modules in the next monitoring cycle.

[0062] The power generated by a photovoltaic (PV) power station is affected by its own temperature. When the temperature is higher than a preset temperature threshold, the above-mentioned effects are relatively significant. Therefore, when the real-time temperature value is lower than the preset temperature threshold, the temperature change is relatively small, and the temperature change coefficient can be set to 0, ignoring the impact of PV module temperature on power calculation. However, when the real-time temperature value is higher than the preset temperature threshold, the impact of temperature change on PV module power is relatively large. The temperature change coefficient is obtained according to the above calculation method and used to calculate the predicted power value of the PV module in the next testing cycle, ensuring the accuracy and scientific nature of the power prediction value.

[0063] The formulas for the predicted power of the photovoltaic module in the next detection cycle are (1), (2), (3), and (4): P i,j+1 =P i,j ×(1+λ i,j -η i,j -σ i,j (1);

[0064] Among them, P i,j+1 Let P be the predicted power value of the i-th photovoltaic module in the (j+1)-th detection period. i,j Let λ be the real-time power value of the i-th photovoltaic module in the j-th detection period. i,j Let G be the light intensity variation coefficient of the i-th photovoltaic module in the j-th detection period. i,j+1 Let G be the predicted light intensity value of the i-th photovoltaic module in the (j+1)-th detection period. i,j Let η be the real-time value of the light intensity of the i-th photovoltaic module in the j-th detection period. i,j Z is the tilt angle change coefficient of the i-th photovoltaic module in the j-th detection period. i,j+1 Z represents the predicted tilt angle of the i-th photovoltaic module in the (j+1)-th detection cycle, where the tilt angle is the angle between the line connecting the sun and the photovoltaic module and the numerical direction. i,j Let σ be the real-time value of the tilt angle of the i-th photovoltaic module in the j-th detection cycle. i,j Let T be the temperature change coefficient of the i-th photovoltaic module in the j-th detection cycle. i,j+1 Let T be the predicted temperature value of the i-th photovoltaic module in the (j+1)-th detection cycle. i,j Let be the real-time temperature value of the i-th photovoltaic module in the j-th detection cycle;

[0065] The power prediction model is given by formula (5):

[0066] Among them, P total_j+1 Let i be the total predicted power of the photovoltaic power station in the (j+1)th detection cycle, where i is the serial number of the photovoltaic module and n is the number of photovoltaic modules.

[0067] Therefore, by accurately obtaining predicted environmental parameters, including temperature, light intensity, and tilt angle, as the main environmental factors affecting the performance of photovoltaic systems, the output power of photovoltaic power plants can be predicted more accurately. This helps grid operators optimize power dispatch and energy management, reduces energy waste caused by inaccurate predictions, and improves the overall operating efficiency of the power system.

[0068] Furthermore, based on the above embodiments, the environmental parameter prediction values ​​in this embodiment also include the surface shading rate of the photovoltaic module. Correspondingly, obtaining the surface shading rate change coefficient for each photovoltaic module includes: obtaining the predicted surface shading rate value of the photovoltaic module, including the predicted surface shading rate value for the next detection cycle and the real-time surface shading value for the current detection cycle; and determining the surface shading rate change coefficient based on the predicted surface shading rate value, the real-time surface shading value, and the formula for determining the surface shading rate change coefficient. The formula for determining the surface shading rate change coefficient is (6):

[0069] Where, θ i,j S is the coefficient of variation of surface shading rate. i,j+1 S is the predicted surface shading value of the i-th photovoltaic module in the (j+1)-th detection cycle. i,j Let be the real-time value of the surface shadow of the i-th photovoltaic module in the j-th detection cycle.

[0070] Correspondingly, the formula for the predicted power value of the photovoltaic module in the next detection cycle is (7): P i,j+1 =P i,j ×(1+λ i,j -η i,j -σ i,j -θ i,j (7);

[0071] By taking into account environmental factors that shade the upper surface of photovoltaic modules—which can be occasional, such as clouds or passing animals or vehicles, or periodic, such as fixed buildings or vegetation in the surrounding environment—the accuracy of the final power prediction can be effectively improved.

[0072] Furthermore, the photovoltaic power station also includes multiple image acquisition components that correspond one-to-one with each photovoltaic module. In this embodiment, obtaining the predicted surface shading rate of the photovoltaic module includes: acquiring a first image region and a second image region on the surface of the photovoltaic module within the current detection period using the image acquisition components. The first image region is the brightness region of the upper surface of the photovoltaic module when sunlight is normally shining, and the second image region is the brightness region of the upper surface of the photovoltaic module when sunlight is blocked. Based on the first and second image regions, determining the proportion of the second image region to the upper surface of the photovoltaic module yields the real-time value of the surface shading rate of the photovoltaic module. Obtaining a preset number of historical surface shading rate values ​​of the photovoltaic module within previous detection periods, and combining these with the real-time surface shading rate values, determines the predicted surface shading rate value of the photovoltaic module in the next detection period.

[0073] Specifically, in determining the predicted value of the surface shading rate, the normal brightness area and the shading area on the surface of the photovoltaic module are detected. By detecting the brightness of the two areas, the proportion of the shading area to the total area of ​​the upper surface of the photovoltaic module is obtained, and the surface shading rate of the photovoltaic module is obtained. Then, combined with the surface shading rate of the previous multiple detection cycles, and referring to the weight coefficient of the surface shading rate of the previous multiple detection cycles in predicting the surface shading rate of the next detection cycle, the predicted result of the surface shading rate of the photovoltaic module can be obtained.

[0074] The formula for calculating the predicted surface shading rate of the photovoltaic module in the next testing cycle is (8): S i,j+1 =τ0S i,j +τ1S i,j-1 +τ2S i,j-2 +…+τ m-1 S i,j-m+1 +τ m S i,j-m (8);

[0075] Among them, S i,j+1 S is the predicted surface shading rate of the photovoltaic module in the next inspection cycle. i,j τ0 represents the real-time surface shading rate of the photovoltaic module during the current testing period. i,j S is the weighting coefficient for the real-time value of the surface shading rate of the photovoltaic module in the current testing period. i,j-m τ represents the historical surface shading rate of the photovoltaic module in the previous m-th detection cycle. m This is the weighting coefficient for the historical surface shading rate of the photovoltaic module in the first m-th detection cycle.

[0076] Furthermore, based on the above embodiments, after obtaining the real-time value of the surface shading rate of the photovoltaic module in this embodiment, the method further includes: obtaining the historical value of the surface shading rate of the current date and the real-time value of the surface shading rate of the current date for a preset number of photovoltaic modules in previous detection periods within the current date; comparing the historical value of the surface shading rate of the current date and the real-time value of the surface shading rate of the current date with the corresponding data of the corresponding time period yesterday; if the comparison result shows that the trend is the same, then selecting the historical value of the surface shading rate of the photovoltaic module in the corresponding time period yesterday as the predicted value of the surface shading rate of the photovoltaic module for the next detection period today.

[0077] Specifically, the determination of whether the changing trends are the same is based on the fact that the difference between the surface shading rate of the photovoltaic modules in the current testing cycle, several previous testing cycles, and the corresponding testing cycle of yesterday (or any day before) is less than a preset ratio. If the surface shading rate values ​​obtained in several testing cycles today have the same or very similar changing trends as the corresponding testing cycle of yesterday or any day before, it can be determined that the area of ​​surface shading rate change is consistent, that is, the shading object is a fixed object that appears periodically. Therefore, the predicted value of the surface shading rate of the photovoltaic modules in the next testing cycle today is determined to be the known surface shading rate value of the photovoltaic modules in the corresponding testing cycle of yesterday or any day before.

[0078] Based on the same general inventive concept, this invention also protects a photovoltaic power plant power prediction device. The photovoltaic power plant power prediction device provided by this invention will be described below. The photovoltaic power plant power prediction device described below can be referred to in correspondence with the photovoltaic power plant power prediction method described above.

[0079] Figure 2 is a schematic diagram of the photovoltaic power plant power prediction device provided in this embodiment.

[0080] As shown in Figure 2, this embodiment provides a photovoltaic power plant power prediction device, including:

[0081] The acquisition module 201 is used to acquire the real-time power value of each photovoltaic module in the current detection cycle, including the real-time temperature value, the real-time light intensity value, and the real-time tilt angle value; and to acquire the predicted environmental parameters of each photovoltaic module in the next detection cycle, including the predicted temperature value, the predicted light intensity value, and the predicted tilt angle value.

[0082] The determination module 202 is used to determine the temperature change coefficient, light intensity change coefficient and tilt angle change coefficient of each photovoltaic module based on the real-time temperature value, real-time light intensity value, real-time tilt angle value, predicted temperature value, predicted light intensity value and predicted tilt angle value.

[0083] The prediction module 203 is used to input the temperature change coefficient, light intensity change coefficient, tilt angle change coefficient and real-time power value into the power prediction model, and output the power prediction value of the photovoltaic power station in the next detection cycle.

[0084] Figure 3 is a schematic diagram of the structure of the electronic device provided in this embodiment.

[0085] As shown in Figure 3, the electronic device may include a processor 310, a communication interface 320, a memory 330, and a communication bus 340, wherein the processor 310, the communication interface 320, and the memory 330 communicate with each other through the communication bus 340. The processor 310 can call logic instructions in the memory 330 to execute a photovoltaic power plant power prediction method. This method includes: acquiring the real-time power value of each photovoltaic module in the current detection cycle, the real-time power value including real-time temperature, real-time irradiance, and real-time tilt angle; acquiring the predicted environmental parameters of each photovoltaic module in the next detection cycle, the predicted environmental parameters including predicted temperature, predicted irradiance, and predicted tilt angle; determining the corresponding temperature variation coefficient, irradiance variation coefficient, and tilt angle variation coefficient for each photovoltaic module based on the real-time temperature, irradiance, tilt angle, predicted temperature, predicted irradiance, and predicted tilt angle; inputting the temperature variation coefficient, irradiance variation coefficient, tilt angle variation coefficient, and real-time power value into a power prediction model, and outputting the predicted power value of the photovoltaic power plant in the next detection cycle.

[0086] Furthermore, the logical instructions in the aforementioned memory 330 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium 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 described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0087] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the photovoltaic power plant power prediction method provided by the above methods. The method includes: obtaining the real-time power value of each photovoltaic module in the current detection cycle, the real-time power value including the real-time temperature value, the real-time light intensity value, and the real-time tilt angle value; obtaining the environmental parameter prediction value of each photovoltaic module in the next detection cycle, the environmental parameter prediction value including the temperature prediction value, the light intensity prediction value, and the tilt angle prediction value; determining the temperature change coefficient, the light intensity change coefficient, and the tilt angle change coefficient of each photovoltaic module based on the real-time temperature value, the real-time light intensity value, the real-time tilt angle value, the predicted temperature value, the predicted light intensity value, and the predicted tilt angle value; inputting the temperature change coefficient, the light intensity change coefficient, the tilt angle change coefficient, and the real-time power value into the power prediction model, and outputting the power prediction value of the photovoltaic power plant in the next detection cycle.

[0088] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements a photovoltaic power plant power prediction method provided by the methods described above. The method includes: acquiring a real-time power value for each photovoltaic module in the current detection cycle, the real-time power value including a real-time temperature value, a real-time irradiance value, and a real-time tilt angle value; acquiring predicted environmental parameters for each photovoltaic module in the next detection cycle, the predicted environmental parameters including a predicted temperature value, a predicted irradiance value, and a predicted tilt angle value; determining a corresponding temperature variation coefficient, irradiance variation coefficient, and tilt angle variation coefficient for each photovoltaic module based on the real-time temperature value, the real-time irradiance value, the real-time tilt angle value, the predicted temperature value, the predicted irradiance value, and the predicted tilt angle value; inputting the temperature variation coefficient, the irradiance variation coefficient, the tilt angle variation coefficient, and the real-time power value into a power prediction model, and outputting a predicted power value for the photovoltaic power plant in the next detection cycle.

[0089] The device embodiments described above are merely illustrative. 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 modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0090] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0091] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention 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; and these 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 the present invention.

Claims

1. A method for predicting the power output of a photovoltaic power plant, characterized in that, The photovoltaic power station includes multiple photovoltaic modules connected in series, and the method includes: The real-time power value of each photovoltaic module is obtained during the current detection cycle. The real-time power value includes the real-time temperature value, the real-time light intensity value, and the real-time tilt angle value. Obtain the predicted environmental parameters for each photovoltaic module in the next detection cycle. The predicted environmental parameters include predicted temperature, predicted light intensity, and predicted tilt angle. Based on the real-time temperature value, the real-time light intensity value, the real-time tilt angle value, the predicted temperature value, the predicted light intensity value, and the predicted tilt angle value, the corresponding temperature change coefficient, light intensity change coefficient, and tilt angle change coefficient for each photovoltaic module are determined. Input the temperature change coefficient, the light intensity change coefficient, the tilt angle change coefficient, and the real-time power value into the power prediction model, and output the power prediction value of the photovoltaic power station in the next detection cycle.

2. The photovoltaic power plant power prediction method according to claim 1, characterized in that, The formula for the predicted power value of the photovoltaic module in the next detection cycle is: P i,j+1 =P i,j ×(1+λ i,j -η i,j -σ i,j ); P i,j+1 is the power prediction value of the ith photovoltaic module in the j+1th detection cycle, P i,j is the real-time value of the power of the ith photovoltaic module in the jth detection cycle, λ i,j is the illumination intensity variation coefficient of the ith photovoltaic module in the jth detection cycle, G i,j+1 is the illumination intensity prediction value of the ith photovoltaic module in the j+1th detection cycle, G i,j is the real-time value of the illumination intensity of the ith photovoltaic module in the jth detection cycle, η i,j is the tilt angle variation coefficient of the ith photovoltaic module in the jth detection cycle, Z i,j+1 is the tilt angle prediction value of the ith photovoltaic module in the j+1th detection cycle, the tilt angle being the angle between the line connecting the sun and the photovoltaic module and the numerical direction, Z i,j is the real-time value of the tilt angle of the ith photovoltaic module in the jth detection cycle, σ i,j is the temperature variation coefficient of the ith photovoltaic module in the jth detection cycle, T i,j+1 is the temperature prediction value of the ith photovoltaic module in the j+1th detection cycle, T i,j is the real-time value of the temperature of the ith photovoltaic module in the jth detection cycle. The power prediction model is as follows: Among them, P total_j+1 Let i be the total predicted power of the photovoltaic power station in the (j+1)th detection cycle, i be the serial number of the photovoltaic module, and n be the number of the photovoltaic modules.

3. The photovoltaic power plant power prediction method according to claim 1, characterized in that, Determining the temperature change coefficient for each photovoltaic module includes: The real-time temperature value of each photovoltaic module in the current detection cycle is compared with a preset temperature threshold. If the real-time temperature value is less than the preset temperature threshold, then the temperature change coefficient is determined to be 0. If the real-time temperature value is greater than or equal to the preset temperature threshold, then the temperature change coefficient is determined based on the real-time temperature value of each photovoltaic module in the current detection cycle and the predicted temperature value in the next detection cycle.

4. The photovoltaic power plant power prediction method according to claim 3, characterized in that, Also includes: Obtain the predicted surface shading rate of the photovoltaic module, including the predicted surface shading rate for the next detection cycle and the real-time surface shading rate for the current detection cycle; The surface shading rate change coefficient is determined based on the predicted surface shading rate, the real-time surface shading rate, and the formula for determining the surface shading rate change coefficient. The formula for determining the surface shading rate variation coefficient is: Where, θ i,j S is the coefficient of variation of the surface shading rate. i,j+1 S is the predicted surface shading value of the i-th photovoltaic module in the (j+1)-th detection cycle. i,j The real-time value of the surface shadow of the i-th photovoltaic module in the j-th detection cycle; Correspondingly, the formula for the predicted power value of the photovoltaic module in the next detection cycle is: P i,j+1 =P i,j ×(1+λ i,j -or i,j -s i,j -θ i,j )。 5. The photovoltaic power plant power prediction method according to claim 4, characterized in that, The photovoltaic power station further includes: multiple image acquisition components corresponding one-to-one with the photovoltaic modules; the acquisition of the predicted surface shading rate value of the photovoltaic modules includes: The image acquisition component acquires a first image region and a second image region on the surface of the photovoltaic module within the current detection period. The first image region is the brightness region on the upper surface of the photovoltaic module when sunlight is normally shining, and the second image region is the brightness region on the upper surface of the photovoltaic module when sunlight is blocked. Based on the first image region and the second image region, the proportion of the second image region to the upper surface of the photovoltaic module is determined to obtain the real-time value of the surface shading rate of the photovoltaic module; a preset number of historical values ​​of the surface shading rate of the photovoltaic module within the previous detection period are obtained, and the predicted value of the surface shading rate of the photovoltaic module in the next detection period is determined by combining the real-time value of the surface shading rate of the photovoltaic module.

6. The photovoltaic power plant power prediction method according to claim 5, characterized in that, The formula for calculating the predicted surface shading rate of the photovoltaic module in the next detection cycle is: S i,j+1 =τ0S i,j +τ1S i,j-1 +τ2S i,j-2 +…+τ m-1 S i,j-m+1 +τ m S i,j-m ; Among them, S i,j+1 S is the predicted surface shading rate of the photovoltaic module in the next detection cycle. i,j τ0 is the real-time value of the surface shading rate of the photovoltaic module in the current detection period. i,j S is the weighting coefficient for the real-time value of the surface shading rate of the photovoltaic module in the current detection period. i,j-m τ is the historical value of the surface shading rate of the photovoltaic module in the previous m-th detection cycle. m The weighting coefficient is the historical value of the surface shading rate of the photovoltaic module in the first m-th detection cycle.

7. The photovoltaic power plant power prediction method according to claim 5, characterized in that, After obtaining the real-time value of the shading rate on the surface of the photovoltaic module, the method further includes: Obtain the historical surface shading rate values ​​and real-time surface shading rate values ​​of multiple photovoltaic modules in a preset number of prior detection cycles within the current date; The historical value of the surface shading rate for the current date, the real-time value of the surface shading rate for the current date, and the corresponding data for the corresponding time period yesterday are compared respectively. If the comparison results show the same trend, then the historical value of the photovoltaic module surface shading rate for the corresponding period yesterday will be selected as the predicted value of the photovoltaic module surface shading rate for the next testing cycle today.

8. The photovoltaic power plant power prediction method according to claim 7, characterized in that, The comparison results show that the trends of change are the same, including: The difference between the historical values ​​of the surface shading rate of each photovoltaic module in today's testing cycle and the corresponding historical values ​​in yesterday's testing cycle is less than a preset ratio value.

9. A photovoltaic power plant power prediction device, characterized in that, include: The acquisition module is used to acquire the real-time power value of each photovoltaic module in the current detection cycle, the real-time power value including the real-time temperature value, the real-time light intensity value and the real-time tilt angle value; and to acquire the predicted environmental parameters of each photovoltaic module in the next detection cycle, the predicted environmental parameters including the predicted temperature value, the predicted light intensity value and the predicted tilt angle value. The determination module is used to determine the temperature change coefficient, light intensity change coefficient, and tilt angle change coefficient of each photovoltaic module based on the real-time temperature value, the real-time light intensity value, the real-time tilt angle value, the predicted temperature value, the predicted light intensity value, and the predicted tilt angle value. The prediction module is used to input the temperature change coefficient, the light intensity change coefficient, the tilt angle change coefficient, and the real-time power value into the power prediction model, and output the power prediction value of the photovoltaic power station in the next detection cycle.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the photovoltaic power plant power prediction method as described in any one of claims 1 to 8.

Images