Photovoltaic power station power prediction method, device and equipment

Abstract

The invention provides a photovoltaic power station power prediction method, device and equipment. The photovoltaic power station power prediction method comprises the steps of obtaining a power real-time value of each photovoltaic module in a current detection period; acquiring an environmental parameter prediction value of each photovoltaic module in the next detection period; based on a temperature real-time value, an illumination intensity real-time value and an inclination angle real-time value in the power real-time values and a temperature predicted value, an illumination intensity predicted value and an inclination angle predicted value in the environmental parameter predicted values, determining a temperature change coefficient, an illumination intensity change coefficient and an inclination angle change coefficient of each corresponding photovoltaic module; according to the method, the temperature change coefficient, the illumination intensity change coefficient, the inclination angle change coefficient and the power real-time value are input to the power prediction model, the power prediction value of the photovoltaic power station in the next detection period is output, and the power prediction accuracy of the photovoltaic power station can be better ensured by accurately obtaining the environmental parameter prediction value and then performing power prediction.

Description

Technical Field

[0001] The present invention relates to the technical field of power prediction, and in particular to a method, device and equipment for predicting power of a photovoltaic power station. Background Art

[0002] With the large-scale access of photovoltaic power stations, the impact on the operation of the power grid is becoming increasingly significant. It is very important to predict the power of photovoltaic power stations, which is an important link to ensure the stable operation of the power system and the optimization of power dispatch. Photovoltaic power station power prediction refers to the prediction of the active power of photovoltaic power stations based on meteorological conditions, statistical laws and other technologies and means, which helps to achieve intelligent management and optimal utilization of photovoltaic power generation and improve energy efficiency.

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

[0004] Therefore, how to accurately predict the power of a photovoltaic power station has become a technical problem that technicians in this field urgently need to solve. Summary of the invention

[0005] The present invention provides a photovoltaic power station power prediction method, device and equipment, which are used to solve the defect of poor accuracy of photovoltaic power station power prediction in the prior art.

[0006] In a first aspect, the present invention provides a method for predicting power of a photovoltaic power station, wherein the photovoltaic power station comprises a plurality of photovoltaic modules connected in series, and the method comprises:

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

[0008] Obtaining environmental parameter prediction values ​​of each photovoltaic module in the next detection cycle, wherein the environmental parameter prediction values ​​include temperature prediction values, light intensity prediction values, and tilt angle prediction values;

[0009] Determine the temperature variation coefficient, the light intensity variation coefficient and the tilt angle variation coefficient of each corresponding photovoltaic module based on the temperature real-time value, the light intensity real-time value, the tilt angle real-time value, the temperature prediction value, the light intensity prediction value and the tilt angle prediction value;

[0010] The temperature variation coefficient, the light intensity variation coefficient, the tilt angle variation coefficient and the real-time power value are input into a power prediction model, and a power prediction value of the photovoltaic power station in the next detection cycle is output.

[0011] According to a photovoltaic power station power prediction method provided by the present invention, the formula for the power prediction value of the photovoltaic module in the next detection cycle is:

[0012] P i,j+1 =P i,j ×(1+λ i,j -η i,j -σ i,j );

[0013]

[0014] Among them, 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 power value of the ith photovoltaic module in the jth detection cycle, λ i,j is the light intensity variation coefficient of the ith photovoltaic module in the jth detection cycle, G i,j+1 is the predicted value of the light intensity of the ith photovoltaic module in the j+1th detection cycle, G i,j is the real-time value of the light intensity of the ith photovoltaic module in the jth detection cycle, η i,j is the tilt angle variation coefficient of the i-th photovoltaic module in the j-th detection cycle, Z i,j+1 is the predicted value of the tilt angle of the ith photovoltaic module in the j+1th detection cycle, where the tilt angle is 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 temperature value of the i-th photovoltaic module in the j-th detection cycle;

[0015] The power prediction model is:

[0016]

[0017] Among them, P total_j+1 is the total power prediction value of the photovoltaic power station in the j+1th detection cycle, i is the serial number of the photovoltaic module, and n is the number of the photovoltaic modules.

[0018] According to a photovoltaic power station power prediction method provided by the present invention, the determining of the temperature variation coefficient of each corresponding photovoltaic module includes:

[0019] Compare the real-time temperature value of each photovoltaic module in the current detection cycle with a preset temperature threshold;

[0020] If the real-time temperature value is less than the preset temperature threshold, determining the temperature variation coefficient to be 0;

[0021] 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 component in the current detection cycle and the predicted temperature value in the next detection cycle.

[0022] A photovoltaic power station power prediction method provided by the present invention also includes:

[0023] Obtaining a predicted value of the surface shadow rate of the photovoltaic module, including a predicted value of the surface shadow rate in the next detection cycle and a real-time value of the surface shadow in the current detection cycle;

[0024] Determine a surface shadow rate variation coefficient based on the surface shadow rate prediction value, the surface shadow real-time value and a surface shadow rate variation coefficient determination formula;

[0025] The surface shadow rate variation coefficient is determined by the formula:

[0026]

[0027] Among them, θ i,j is the surface shadow rate variation coefficient, S i,j+1 is the surface shadow prediction value of the ith photovoltaic module in the j+1th detection cycle, S i,j is the real-time value of the surface shadow of the i-th photovoltaic module in the j-th detection cycle;

[0028] Correspondingly, the formula for the power prediction value of the photovoltaic module in the next detection cycle is:

[0029] P i,j+1 =P i,j ×(1+λ i,j -η i,j -σ i,j -θ i,j ).

[0030] According to a photovoltaic power station power prediction method provided by the present invention, the photovoltaic power station further comprises: a plurality of image acquisition components corresponding one-to-one to the photovoltaic components;

[0031] The obtaining of the predicted value of the shadow rate of the photovoltaic module surface includes:

[0032] Acquire a first image area and a second image area of ​​the surface of the photovoltaic module in a current detection cycle through the image acquisition component, wherein the first image area is a brightness area of ​​the upper surface of the photovoltaic module when sunlight is normally irradiated, and the second image area is a brightness area of ​​the upper surface of the photovoltaic module when sunlight is blocked;

[0033] Based on the first image area and the second image area, determining a ratio of the second image area to the upper surface of the photovoltaic assembly, and obtaining a real-time value of the shadow rate of the photovoltaic assembly surface;

[0034] A preset number of historical values ​​of the photovoltaic module surface shadow rate in previous detection cycles are obtained, and a predicted value of the photovoltaic module surface shadow rate in the next detection cycle is determined in combination with the real-time value of the photovoltaic module surface shadow rate.

[0035] According to a photovoltaic power station power prediction method provided by the present invention, the calculation formula of the predicted value of the surface shadow rate of the photovoltaic module in the next detection cycle is:

[0036] 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 ;

[0037] Among them, S i,j+1 is the predicted value of the surface shadow rate of the photovoltaic module in the next detection cycle, S i,j is the real-time value of the surface shadow rate of the photovoltaic module in the current detection cycle, τ0 is S i,j is the weight coefficient of the real-time value of the surface shadow rate of the photovoltaic module in the current detection cycle, S i,j-m is the historical value of the surface shading rate of the photovoltaic module in the previous m-th detection cycle, τ m is the weight coefficient of the historical value of the surface shading rate of the photovoltaic module in the previous m-th detection cycle.

[0038] According to a photovoltaic power station power prediction method provided by the present invention, after obtaining the real-time value of the shadow rate of the photovoltaic module surface, the method further includes:

[0039] Obtaining historical values ​​of the surface shading rate of the current date and real-time values ​​of the surface shading rate of the current date of a plurality of the photovoltaic modules in a preset number of previous detection cycles on the current date;

[0040] Compare the historical value of the surface shadow rate on the current date, the real-time value of the surface shadow rate on the current date with the corresponding data of the corresponding period of yesterday respectively;

[0041] If the comparison result shows that the change trends are the same, the historical value of the photovoltaic module surface shadow rate in the corresponding period yesterday is selected as the predicted value of the photovoltaic module surface shadow rate in the next detection cycle today.

[0042] According to a photovoltaic power station power prediction method provided by the present invention, the comparison result is the same change trend, including:

[0043] The difference between the historical values ​​of the photovoltaic component surface shadow rate in the detection cycle of today's photovoltaic component and the corresponding detection cycle of yesterday's photovoltaic component is less than the preset ratio value.

[0044] In a second aspect, the present invention provides a photovoltaic power station power prediction device, comprising:

[0045] An acquisition module is used to acquire the real-time power value of each photovoltaic component in the current detection cycle, wherein the real-time power value includes the real-time temperature value, the real-time light intensity value, and the real-time tilt angle value; and to acquire the predicted environmental parameter value of each photovoltaic component in the next detection cycle, wherein the predicted environmental parameter value includes the predicted temperature value, the predicted light intensity value, and the predicted tilt angle value;

[0046] A determination module, for determining the temperature variation coefficient, the light intensity variation coefficient and the tilt angle variation coefficient of each corresponding photovoltaic module based on the temperature real-time value, the light intensity real-time value, the tilt angle real-time value, the temperature prediction value, the light intensity prediction value and the tilt angle prediction value;

[0047] The prediction module is used to input the temperature variation coefficient, the light intensity variation coefficient, the tilt angle variation 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.

[0048] In a third aspect, the present invention further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a photovoltaic power station power prediction method as described above is implemented.

[0049] In a fourth aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the photovoltaic power station power prediction methods described above.

[0050] In a fifth aspect, the present invention further provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the photovoltaic power station power prediction method as described above is implemented.

[0051] The present invention provides a photovoltaic power station power prediction method, device and equipment, including obtaining the real-time power value of each photovoltaic component 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 component 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; based on the real-time temperature value, the real-time light intensity value, the real-time tilt angle value, the temperature prediction value, the light intensity prediction value and the tilt angle prediction value, determining the temperature variation coefficient, the light intensity variation coefficient and the tilt angle variation coefficient of each corresponding photovoltaic component; 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, outputting the power prediction value of the photovoltaic power station in the next detection cycle, and by accurately obtaining the environmental parameter prediction value and then performing power prediction, the accuracy of the power prediction of the photovoltaic power station can be better guaranteed. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0053] Figure 1 is a schematic diagram of the flow of the photovoltaic power station power prediction method provided in this embodiment;

[0054] Figure 2 is a schematic diagram of the structure of the photovoltaic power station power prediction device provided in this embodiment;

[0055] Figure 3 It is a schematic diagram of the structure of the electronic device provided in this embodiment. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0057] Figure 1 It is a flow chart of the photovoltaic power station power prediction method provided in this embodiment.

[0058] like Figure 1As shown, the photovoltaic power station power prediction method provided by the embodiment of the present invention, the photovoltaic power station includes a plurality of photovoltaic modules connected in series, and the method mainly includes the following steps:

[0059] 101. Obtain the real-time power value of each photovoltaic module in the current detection cycle, where the real-time power value includes the real-time temperature value, the real-time light intensity value, and the real-time tilt angle value.

[0060] In a specific implementation process, the real-time value of temperature, real-time value of light intensity and real-time value of tilt angle can be obtained through sensors or other methods as long as they can be accurately collected. The current detection cycle refers to the cycle of the current time period.

[0061] 102. Obtain environmental parameter prediction values ​​of each photovoltaic module in the next detection cycle, where the environmental parameter prediction values ​​include temperature prediction values, light intensity prediction values, and tilt angle prediction values.

[0062] The next detection cycle refers to the cycle adjacent to the current detection cycle. Therefore, for the relevant parameters in the next detection cycle, it is necessary to predict the environmental parameter prediction values ​​of each photovoltaic module in the next detection cycle. Among them, the temperature prediction value, light intensity prediction value and tilt angle prediction value correspond to the relevant values ​​in the current detection cycle. The prediction method can be through weather forecasting or other methods.

[0063] 103. 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, determine the temperature variation coefficient, the light intensity variation coefficient and the tilt angle variation coefficient of each corresponding photovoltaic module.

[0064] The variation coefficient of each photovoltaic component is determined by the real-time temperature value and the predicted temperature value. Specifically, the real-time temperature value of each photovoltaic component in the current detection cycle is compared with the 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 component in the current detection cycle and the predicted temperature value in the next detection cycle.

[0065] Similarly, the illumination intensity variation coefficient of each photovoltaic module can be determined by the illumination intensity real-time value and illumination intensity prediction value. The tilt angle variation coefficient can be determined by the tilt angle real-time value and tilt angle prediction value.

[0066] 104. Input the temperature variation coefficient, the light intensity variation coefficient, the tilt angle variation 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.

[0067] After obtaining the temperature variation coefficient, light intensity variation coefficient, and tilt angle variation coefficient, the real-time temperature value, light intensity value, and tilt angle value are combined and input into the power prediction model, and the power prediction value of the photovoltaic power station in the next detection cycle can be accurately output. The photovoltaic power station includes multiple photovoltaic modules, that is, the sum of the power prediction values ​​of the multiple photovoltaic modules in the next detection cycle is output.

[0068] The power generated by a photovoltaic power station is affected by its own temperature. When the temperature is higher than the preset temperature threshold, the above influence is relatively obvious. Therefore, when the real-time temperature value is less than the preset temperature threshold, the temperature change is relatively small, and the temperature change coefficient can be set to 0 to ignore the influence of the photovoltaic module temperature on the power calculation; when the real-time temperature value is higher than the preset temperature threshold, the influence of temperature change on the photovoltaic module power is relatively large. The temperature change coefficient is obtained according to the above calculation method and used to calculate the power prediction value of the photovoltaic module in the next detection cycle, ensuring the accuracy and scientificity of the power prediction value.

[0069] The formulas for the power prediction value of the PV module in the next detection cycle are (1)(2)(3) and (4):

[0070] P i,j+1 =P i,j ×(1+λ i,j -η i,j -σ i,j ) (1);

[0071]

[0072] Among them, P i,j+1 is the power prediction value of the ith PV module in the j+1th detection cycle, P i,j is the real-time power value of the i-th PV module in the j-th detection cycle, λ i,j is the light intensity variation coefficient of the i-th photovoltaic module in the j-th detection cycle, G i,j+1 is the predicted value of the light intensity of the i-th photovoltaic module in the j+1-th detection cycle, G i,j is the real-time value of the light intensity of the i-th photovoltaic module in the j-th detection cycle, η i,j is the tilt angle variation coefficient of the i-th PV module in the j-th detection cycle, Z i,j+1 is the predicted value of the tilt angle of the i-th photovoltaic module in the j+1-th detection cycle. The tilt angle is the angle between the line connecting the sun and the photovoltaic module and the numerical direction. i,j is the real-time value of the tilt angle of the i-th PV module in the j-th detection cycle, σ i,j is the temperature variation coefficient of the ith PV module in the jth detection cycle, Ti,j+1 is the predicted temperature value of the ith PV module in the j+1th detection cycle, T i,j is the real-time temperature value of the i-th photovoltaic module in the j-th detection cycle;

[0073] The power prediction model is formula (5):

[0074]

[0075] Among them, P total_j+1 is the total power prediction value of the PV power station in the j+1th detection cycle, i is the PV module serial number, and n is the number of PV modules.

[0076] Therefore, by accurately obtaining the predicted values ​​of environmental parameters, including temperature predicted values, light intensity predicted values ​​and tilt angle predicted values, as the accurate prediction of the main environmental factors affecting the performance of the photovoltaic system, the output power of the photovoltaic power station can be predicted more accurately, which will help grid operators optimize power dispatching and energy management, reduce energy waste caused by inaccurate predictions, and improve the operating efficiency of the entire power system.

[0077] Furthermore, based on the above-mentioned embodiments, the environmental parameter prediction value in this embodiment also includes the surface shadow rate of the photovoltaic module. Correspondingly, the surface shadow rate variation coefficient of each photovoltaic module is obtained, including: obtaining the surface shadow rate prediction value of the photovoltaic module, including the surface shadow rate prediction value of the next detection cycle and the surface shadow real-time value of the current detection cycle; determining the surface shadow rate variation coefficient based on the surface shadow rate prediction value, the surface shadow real-time value and the surface shadow rate variation coefficient determination formula.

[0078] The formula for determining the surface shadow rate variation coefficient is (6):

[0079]

[0080] Among them, θ i,j is the surface shadow rate variation coefficient, S i,j+1 is the surface shadow prediction value of the i-th PV module in the j+1-th detection cycle, S i,j is the real-time value of the surface shadow of the i-th PV module in the j-th detection cycle.

[0081] Correspondingly, the formula for the power prediction value of the photovoltaic module in the next detection cycle is (7):

[0082] P i,j+1 =P i,j ×(1+λ i,j -η i,j -σ i,j -θ i,j ) (7);

[0083] By considering the shading of the upper surface of photovoltaic modules by environmental factors, which can be occasional shading, such as clouds or animals or vehicles passing by briefly, or periodic shading, such as fixed buildings and plants in the surrounding environment, the accuracy of the final power prediction can be effectively improved.

[0084] Furthermore, the photovoltaic power station also includes: a plurality of image acquisition components corresponding to the photovoltaic components one by one. The acquisition of the predicted value of the shadow rate of the photovoltaic component surface in this embodiment includes: acquiring the first image area and the second image area of ​​the photovoltaic component surface in the current detection cycle through the image acquisition component, the first image area is the brightness area of ​​the upper surface of the photovoltaic component when the sunlight is normally irradiated, and the second image area is the brightness area of ​​the upper surface of the photovoltaic component when the sunlight is blocked; based on the first image area and the second image area, determining the proportion of the second image area to the upper surface of the photovoltaic component, and obtaining the real-time value of the shadow rate of the photovoltaic component surface; obtaining a preset number of historical values ​​of the shadow rate of the photovoltaic component surface in the previous detection cycle, and determining the predicted value of the shadow rate of the photovoltaic component surface in the next detection cycle in combination with the real-time value of the shadow rate of the photovoltaic component surface.

[0085] Specifically, in the process of determining the predicted value of the surface shadow rate, the normal brightness area and the blocked area on the surface of the photovoltaic module are detected. By detecting the brightness of the two areas, the proportion of the blocked area to the overall area of ​​the upper surface of the photovoltaic module is obtained to obtain the surface shadow rate of the photovoltaic module. The surface shadow rate of the previous multiple detection cycles is then combined with the surface shadow rates of the previous multiple detection cycles and the weight coefficients of the surface shadow rates of the previous multiple detection cycles when predicting the surface shadow rate of the next detection cycle, to obtain the predicted result of the surface shadow rate of the photovoltaic module.

[0086] The calculation formula for the predicted value of the surface shadow rate of the photovoltaic module in the next detection cycle is (8):

[0087] 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);

[0088] Among them, S i,j+1 is the predicted value of the surface shadow rate of the photovoltaic module in the next detection cycle, S i,j is the real-time value of the surface shadow rate of the photovoltaic module in the current detection cycle, τ0 is S i,j is the weight coefficient of the real-time value of the surface shadow rate of the photovoltaic module in the current detection cycle, S i,j-m is the historical value of the surface shadow rate of the PV module in the previous m-th detection cycle, τ mis the weight coefficient of the historical value of the surface shading rate of the PV module in the previous m-th detection cycle.

[0089] Furthermore, on the basis of the above-mentioned embodiments, after obtaining the real-time value of the surface shadow rate of the photovoltaic module in the present embodiment, it also includes: obtaining the current date surface shadow rate historical values ​​and the current date surface shadow rate real-time value of a preset number of multiple photovoltaic modules in the previous detection cycles within the current date; comparing the current date surface shadow rate historical values, the current date surface shadow rate real-time value with the corresponding data of the corresponding time period yesterday; if the comparison result is that the change trend is the same, then selecting the historical value of the surface shadow rate of the photovoltaic module in the corresponding time period yesterday as the predicted value of the surface shadow rate of the photovoltaic module in the next detection cycle today.

[0090] Specifically, the judgment of whether the change trend is the same is based on the difference between the surface shadow rate of the photovoltaic module in the current detection cycle today and the previous several detection cycles and the corresponding detection cycle of yesterday (or any previous day) is less than the preset ratio value. If the surface shadow rate values ​​of several detection cycles obtained today are the same or very similar to the change trend in the corresponding detection cycle of yesterday or any previous day, it can be determined that the surface shadow rate change area is consistent, that is, the obstruction is a fixed obstruction that appears periodically, and then the predicted value of the surface shadow rate of the photovoltaic module in the next detection cycle today is determined to be the known surface shadow rate value of the photovoltaic module in the corresponding detection cycle of yesterday or any previous day.

[0091] Based on the same general inventive concept, the present invention also protects a photovoltaic power station power prediction device. The photovoltaic power station power prediction device provided by the present invention is described below. The photovoltaic power station power prediction device described below and the photovoltaic power station power prediction method described above can be referenced to each other.

[0092] Figure 2 It is a schematic diagram of the structure of the photovoltaic power station power prediction device provided in this embodiment.

[0093] like Figure 2 As shown, this embodiment provides a photovoltaic power station power prediction device, including:

[0094] The acquisition module 201 is used to acquire the real-time power value of each photovoltaic component 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; acquire the environmental parameter prediction value of each photovoltaic component in the next detection cycle, the environmental parameter prediction value includes the temperature prediction value, the light intensity prediction value and the tilt angle prediction value;

[0095] A determination module 202, for determining a temperature variation coefficient, a light intensity variation coefficient, and a tilt angle variation coefficient of each corresponding photovoltaic module based on the temperature real-time value, the light intensity real-time value, the tilt angle real-time value, the temperature prediction value, the light intensity prediction value, and the tilt angle prediction value;

[0096] The prediction module 203 is used to input the temperature variation coefficient, the light intensity variation coefficient, the tilt angle variation 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.

[0097] Figure 3 It is a schematic diagram of the structure of the electronic device provided in this embodiment.

[0098] like Figure 3 As shown, the electronic device may include: a processor (processor) 310, a communication interface (Communications Interface) 320, a memory (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 the logic instructions in the memory 330 to execute the photovoltaic power station power prediction method, which includes: obtaining the real-time power value of each photovoltaic component in the current detection cycle, and the real-time power value includes 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 component in the next detection cycle, and the environmental parameter prediction value includes the temperature prediction value, the light intensity prediction value and the tilt angle prediction value; based on the real-time temperature value, the real-time light intensity value, the real-time tilt angle value, the temperature prediction value, the light intensity prediction value and the tilt angle prediction value, determine the temperature variation coefficient, the light intensity variation coefficient and the tilt angle variation coefficient of each corresponding photovoltaic component; input the temperature variation coefficient, the light intensity variation coefficient, the tilt angle variation 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.

[0099] In addition, the logic instructions in the above-mentioned memory 330 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0100] On the other hand, the present invention also provides a computer program product, which includes a computer program, which 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 station power prediction method provided by the above methods, the method including: obtaining the real-time power value of each photovoltaic component 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 component 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; based on the real-time temperature value, the real-time light intensity value, the real-time tilt angle value, the temperature prediction value, the light intensity prediction value and the tilt angle prediction value, determine the temperature variation coefficient, the light intensity variation coefficient and the tilt angle variation coefficient of each corresponding photovoltaic component; input the temperature variation coefficient, the light intensity variation coefficient, the tilt angle variation 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.

[0101] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the photovoltaic power station power prediction method provided by the above-mentioned methods, the method comprising: obtaining the real-time power value of each photovoltaic component 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 component 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; based on the real-time temperature value, the real-time light intensity value, the real-time tilt angle value, the temperature prediction value, the light intensity prediction value and the tilt angle prediction value, determining the temperature variation coefficient, the light intensity variation coefficient and the tilt angle variation coefficient of each corresponding photovoltaic component; 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 the power prediction value of the photovoltaic power station in the next detection cycle.

[0102] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0103] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0104] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these 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 invention.

Claims

1. A photovoltaic power station power prediction method, characterized in that: The photovoltaic power station comprises a plurality of photovoltaic modules connected in series, and the method comprises: Acquire the real-time power value of each photovoltaic module in the current detection cycle, wherein the real-time power value includes the real-time temperature value, the real-time light intensity value and the real-time tilt angle value; Obtaining environmental parameter prediction values ​​of each photovoltaic module in the next detection cycle, wherein the environmental parameter prediction values ​​include temperature prediction values, light intensity prediction values, and tilt angle prediction values; Determine the temperature variation coefficient, the light intensity variation coefficient and the tilt angle variation coefficient of each corresponding photovoltaic module based on the temperature real-time value, the light intensity real-time value, the tilt angle real-time value, the temperature prediction value, the light intensity prediction value and the tilt angle prediction value; The temperature variation coefficient, the light intensity variation coefficient, the tilt angle variation coefficient and the real-time power value are input into a power prediction model, and a power prediction value of the photovoltaic power station in the next detection cycle is output.

2. The photovoltaic power station power prediction method according to claim 1, characterized in that: The formula for the power prediction 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 ); Among them, 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 power value of the ith photovoltaic module in the jth detection cycle, λ i,j is the light intensity variation coefficient of the ith photovoltaic module in the jth detection cycle, G i,j+1 is the predicted value of the light intensity of the ith photovoltaic module in the j+1th detection cycle, G i,j is the real-time value of the light intensity of the ith photovoltaic module in the jth detection cycle, η i,j is the tilt angle variation coefficient of the i-th photovoltaic module in the j-th detection cycle, Z i,j+1 is the predicted value of the tilt angle of the ith photovoltaic module in the j+1th detection cycle, where the tilt angle is 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 temperature value of the i-th photovoltaic module in the j-th detection cycle; The power prediction model is: Among them, P total_j+1 is the total power prediction value of the photovoltaic power station in the j+1th detection cycle, i is the serial number of the photovoltaic module, and n is the number of the photovoltaic modules.

3. The photovoltaic power station power prediction method according to claim 1, characterized in that: The determining of the temperature variation coefficient of each corresponding photovoltaic module includes: Compare the real-time temperature value of each photovoltaic module in the current detection cycle with a preset temperature threshold; If the real-time temperature value is less than the preset temperature threshold, determining the temperature variation coefficient 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 component in the current detection cycle and the predicted temperature value in the next detection cycle.

4. The photovoltaic power station power prediction method according to claim 3, characterized in that: Also includes: Obtaining a predicted value of the surface shadow rate of the photovoltaic module, including a predicted value of the surface shadow rate in the next detection cycle and a real-time value of the surface shadow in the current detection cycle; Determine a surface shadow rate variation coefficient based on the surface shadow rate prediction value, the surface shadow real-time value and a surface shadow rate variation coefficient determination formula; The surface shadow rate variation coefficient is determined by the formula: Among them, θ i,j is the surface shadow rate variation coefficient, S i,j+1 is the surface shadow prediction value of the ith photovoltaic module in the j+1th detection cycle, S i,j is 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 power prediction 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 station power prediction method according to claim 4, characterized in that: The photovoltaic power station further comprises: a plurality of image acquisition components corresponding one-to-one to the photovoltaic components; The obtaining of the predicted value of the shadow rate of the photovoltaic module surface includes: Acquire a first image area and a second image area of ​​the surface of the photovoltaic module in a current detection cycle through the image acquisition component, wherein the first image area is a brightness area of ​​the upper surface of the photovoltaic module when sunlight is normally irradiated, and the second image area is a brightness area of ​​the upper surface of the photovoltaic module when sunlight is blocked; Based on the first image area and the second image area, determining a ratio of the second image area to the upper surface of the photovoltaic assembly, and obtaining a real-time value of the shadow rate of the photovoltaic assembly surface; A preset number of historical values ​​of the photovoltaic module surface shadow rate in previous detection cycles are obtained, and a predicted value of the photovoltaic module surface shadow rate in the next detection cycle is determined in combination with the real-time value of the photovoltaic module surface shadow rate.

6. The photovoltaic power station power prediction method according to claim 5, characterized in that: The calculation formula for the predicted value of the surface shadow 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 +…+t m-1 S i,j-m+1 +t m S i,j-m ; Among them, S i,j+1 is the predicted value of the surface shadow rate of the photovoltaic module in the next detection cycle, S i,j is the real-time value of the surface shadow rate of the photovoltaic module in the current detection cycle, τ0 is S i,j is the weight coefficient of the real-time value of the surface shadow rate of the photovoltaic module in the current detection cycle, S i,j-m is the historical value of the surface shading rate of the photovoltaic module in the previous m-th detection cycle, τ m is the weight coefficient of the historical value of the surface shading rate of the photovoltaic module in the previous m-th detection cycle.

7. The photovoltaic power station power prediction method according to claim 5, characterized in that: After obtaining the real-time value of the shadow rate of the photovoltaic module surface, the method further includes: Obtaining historical values ​​of the surface shading rate of the current date and real-time values ​​of the surface shading rate of the current date of a plurality of the photovoltaic modules in a preset number of previous detection cycles on the current date; Compare the historical value of the surface shadow rate on the current date, the real-time value of the surface shadow rate on the current date with the corresponding data of the corresponding period of yesterday respectively; If the comparison result shows that the change trends are the same, the historical value of the photovoltaic module surface shadow rate in the corresponding period yesterday is selected as the predicted value of the photovoltaic module surface shadow rate in the next detection cycle today.

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

9. A photovoltaic power station power prediction device, characterized in that: include: An acquisition module is used to acquire the real-time power value of each photovoltaic component in the current detection cycle, wherein the real-time power value includes the real-time temperature value, the real-time light intensity value, and the real-time tilt angle value; and to acquire the predicted environmental parameter value of each photovoltaic component in the next detection cycle, wherein the predicted environmental parameter value includes the predicted temperature value, the predicted light intensity value, and the predicted tilt angle value; A determination module, for determining the temperature variation coefficient, the light intensity variation coefficient and the tilt angle variation coefficient of each corresponding photovoltaic module based on the temperature real-time value, the light intensity real-time value, the tilt angle real-time value, the temperature prediction value, the light intensity prediction value and the tilt angle prediction value; The prediction module is used to input the temperature variation coefficient, the light intensity variation coefficient, the tilt angle variation 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, wherein: When the processor executes the program, the photovoltaic power station power prediction method according to any one of claims 1 to 8 is implemented.

Images