A data model construction method and system for high altitude photovoltaic system

Abstract

The present invention relates to the technical field of photovoltaic system model construction, and specifically to a data model construction method and system for a high-altitude photovoltaic system, the method comprising obtaining first data; starting a photovoltaic power generation system, and measuring a first radiation intensity data sequence, a first output power data sequence, and a first ambient temperature data sequence within a first test time; aggregating a second radiation intensity data sequence, a second output power data sequence, a second ambient temperature data sequence, and a third ambient temperature data sequence to construct a fitting sample set; using a fitting algorithm to calculate a first function; and recording the first function as a photovoltaic system data model. The present invention achieves the construction of a high-altitude photovoltaic system data model by obtaining a functional relationship between the predicted output power of a photovoltaic power generation system and the predicted average value of solar radiation intensity, the predicted average value of ambient temperature, and the predicted discreteness of ambient temperature.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic system model construction, and in particular to a data model construction method and system for a high-altitude photovoltaic system. Background Art

[0002] With the transformation of energy structure and the rapid development of renewable energy, photovoltaic power generation system, as an important part of distributed power source, plays an increasingly important role in energy supply. In order to ensure the safe and stable operation of the power grid, accurate prediction of the output power of photovoltaic system is of great significance to the grid dispatch.

[0003] At present, the output power prediction of photovoltaic systems is mainly achieved by constructing data models. The method commonly used in the prior art is to establish a functional relationship model between the predicted average value of solar radiation intensity, the predicted average value of ambient temperature and the predicted output power of the photovoltaic power generation system, and then predict the output power of the photovoltaic power generation system based on the pre-obtained predicted average value of solar radiation intensity and the predicted average value of ambient temperature. However, for photovoltaic systems in high-altitude areas, the above method has obvious shortcomings. This is because high-altitude areas have the characteristics of large temperature differences and drastic temperature fluctuations. The resistance of the photovoltaic system is not only affected by the average value of the ambient temperature, but also significantly affected by the severity of the temperature fluctuations. When constructing data models for high-altitude photovoltaic systems, the prior art often ignores the important factor of temperature fluctuations, resulting in a large deviation between the prediction results and the actual situation.

[0004] Therefore, there is an urgent need to provide a method for predicting the output power of photovoltaic power generation systems in environments with drastic temperature fluctuations in high-altitude areas. By building a more complete data model, the prediction accuracy can be improved to provide strong support for the grid-connected operation of photovoltaic systems in high-altitude areas. Summary of the invention

[0005] (1) Technical issues to be resolved The purpose of the present invention is to provide a data model construction method and system for a high-altitude photovoltaic system, so as to obtain a functional relationship between the predicted output power of the photovoltaic power generation system and the predicted average value of the solar radiation intensity, the predicted average value of the ambient temperature, and the predicted discreteness of the ambient temperature, so as to realize the data model construction of the high-altitude photovoltaic system.

[0006] (2) Technical solution To achieve the above object, the present invention provides a method for constructing a data model of a high-altitude photovoltaic system, the method comprising the following steps: S1, obtaining first data, wherein the first data includes rated photoelectric conversion efficiency, photovoltaic panel area, rated resistance of photovoltaic power generation system, rated voltage of photovoltaic power generation system, a preset sampling aggregation number, a preset first sampling interval time, and a preset first test time.

[0007] S2, start the photovoltaic power generation system, measure the solar radiation intensity, the output power of the photovoltaic power generation system, and the ambient temperature at the location of the photovoltaic panel at a first sampling interval within a first test time, and obtain a first radiation intensity data sequence, a first output power data sequence, and a first ambient temperature data sequence.

[0008] S3. Aggregate the first radiation intensity data sequence, the first output power data sequence, and the first ambient temperature data sequence according to the sampling aggregation quantity to obtain a second radiation intensity data sequence, a second output power data sequence, a second ambient temperature data sequence, and a third ambient temperature data sequence; and construct a fitting sample set based on the second radiation intensity data sequence, the second output power data sequence, the second ambient temperature data sequence, and the third ambient temperature data sequence.

[0009] S4. According to the fitting sample set, a fitting algorithm is used to calculate a first function, wherein the dependent variable of the first function is the predicted output power of the photovoltaic power generation system, and the independent variables of the first function are the predicted average value of solar radiation intensity, the predicted average value of ambient temperature, and the predicted discreteness of ambient temperature; the first function is recorded as a photovoltaic system data model.

[0010] Furthermore, the method of aggregating the first radiation intensity data sequence, the first output power data sequence, and the first ambient temperature data sequence according to the sampling aggregation quantity to obtain a second radiation intensity data sequence, a second output power data sequence, a second ambient temperature data sequence, and a third ambient temperature data sequence, and constructing a fitting sample set according to the second radiation intensity data sequence, the second output power data sequence, the second ambient temperature data sequence, and the third ambient temperature data sequence includes: According to the first radiation intensity data sequence, the second radiation intensity data sequence is calculated using a radiation intensity aggregation formula; the radiation intensity aggregation formula is: ; in, Indicates the first individual data; Indicates the first radiation intensity data sequence individual data; Indicates the number of sampling aggregations; The value of is greater than 1; The value range is 1 to integer variable of ; The value range is 1 to integer variable of ; Indicates the second length; The calculation formula is: ; in, Indicates the first test time, Indicates the first sampling interval.

[0011] According to the first output power data sequence, a second output power data sequence is calculated using a power aggregation formula; the power aggregation formula is: ; in, Indicates the first individual data; Indicates the first output power data sequence data.

[0012] According to the first ambient temperature data sequence, a second ambient temperature data sequence is calculated using a second temperature aggregation formula; the second temperature aggregation formula is: ; in, Indicates the first individual data; Indicates the first ambient temperature data sequence data.

[0013] According to the first ambient temperature data sequence, a third ambient temperature data sequence is calculated using a third temperature aggregation formula; the third temperature aggregation formula is: ; in, Indicates the third ambient temperature data sequence data.

[0014] A fitting sample set is constructed according to the second radiation intensity data sequence, the second output power data sequence, the second ambient temperature data sequence, and the third ambient temperature data sequence; the fitting sample set is expressed as: ; in, represents the fitting sample set; represents the first samples; It is expressed as: .

[0015] Furthermore, the method of calculating a first function using a fitting algorithm based on the fitting sample set, wherein the dependent variable of the first function is the predicted output power of the photovoltaic power generation system, and the independent variables of the first function are the predicted average value of solar radiation intensity, the predicted average value of ambient temperature, and the predicted discreteness of ambient temperature includes: The first fitting equation is constructed according to the rated photoelectric conversion efficiency, the photovoltaic panel area, and the rated resistance of the photovoltaic power generation system; the first fitting equation is expressed as: ; in, represents the photovoltaic panel area, Indicates the rated photoelectric conversion efficiency, Indicates the rated voltage of the photovoltaic power generation system. Indicates the rated resistance of the photovoltaic power generation system. Indicates the preset reference temperature. represents the first resistance temperature coefficient, represents the second resistance temperature coefficient, Indicates Remaining power.

[0016] A first objective function is constructed according to the fitting sample set and the first fitting equation; and a first constraint condition is constructed according to the fitting sample set and the first fitting equation.

[0017] Taking the minimum value of the first objective function as the goal, the first constraint condition as the constraint, the first resistance temperature coefficient and the second resistance temperature coefficient as the optimization variables, the particle swarm optimization algorithm is used to calculate the optimal value of the first resistance temperature coefficient and the optimal value of the second resistance temperature coefficient, which are respectively recorded as the first optimization coefficients , the second optimization coefficient .

[0018] The first optimized residual power is calculated using the residual value formula To Optimizing remaining power ; The residual value formula is: ; in, Indicates Optimize remaining power.

[0019] According to the first optimization coefficient , the second optimization coefficient , First optimize the remaining power To Optimizing remaining power The first optimization equation is obtained; the first optimization equation is expressed as: ; in, represents the predicted output power of the photovoltaic power generation system, represents the average value of solar radiation intensity predicted in advance, represents the predicted average ambient temperature obtained in advance, Indicates the predicted dispersion of the ambient temperature obtained in advance.

[0020] According to the first optimization equation, the functional relationship between the predicted output power of the photovoltaic power generation system and the predicted average value of the solar radiation intensity, the predicted average value of the ambient temperature, and the predicted dispersion of the ambient temperature is obtained, which is recorded as the first function; the first function is expressed as: .

[0021] Furthermore, the method of constructing a first objective function according to the fitting sample set and the first fitting equation includes: According to the fitting sample set and the first fitting equation, a first objective function is constructed. , the first objective function is expressed as: .

[0022] Furthermore, the method of constructing the first constraint condition according to the fitting sample set and the first fitting equation includes: According to the fitting sample set and the first fitting equation, a first constraint condition is constructed, and the first constraint condition is expressed as: ; in, Represents the pre-set upper limit of the residual volatility constraint.

[0023] Based on the same inventive concept, on the other hand, the present invention also provides a data model building system for a high-altitude photovoltaic system, the system comprising: The data reading module is used to obtain first data, wherein the first data includes rated photoelectric conversion efficiency, photovoltaic panel area, rated resistance of photovoltaic power generation system, rated voltage of photovoltaic power generation system, a preset sampling aggregation number, a preset first sampling interval time, and a preset first test time.

[0024] The data measurement module is connected to the data reading module and is used to start the photovoltaic power generation system, measure the solar radiation intensity, the output power of the photovoltaic power generation system, and the ambient temperature at the location of the photovoltaic panel at a first sampling interval within a first test time, and obtain a first radiation intensity data sequence, a first output power data sequence, and a first ambient temperature data sequence.

[0025] A sample construction module is connected to the data measurement module, and is used to aggregate the first radiation intensity data sequence, the first output power data sequence, and the first ambient temperature data sequence according to the sampling aggregation quantity to obtain a second radiation intensity data sequence, a second output power data sequence, a second ambient temperature data sequence, and a third ambient temperature data sequence, and to construct a fitting sample set based on the second radiation intensity data sequence, the second output power data sequence, the second ambient temperature data sequence, and the third ambient temperature data sequence.

[0026] The data model construction module is connected to the sample construction module, and is used to calculate the first function according to the fitting sample set using a fitting algorithm, wherein the dependent variable of the first function is the predicted output power of the photovoltaic power generation system, and the independent variables of the first function are the predicted average value of the solar radiation intensity, the predicted average value of the ambient temperature, and the predicted discreteness of the ambient temperature; the first function is recorded as the photovoltaic system data model.

[0027] Furthermore, the sample construction module includes: The second radiation intensity data sequence construction module is used to calculate the second radiation intensity data sequence using the radiation intensity aggregation formula according to the first radiation intensity data sequence; the radiation intensity aggregation formula is: ; in, Indicates the first individual data; Indicates the first radiation intensity data sequence individual data; Indicates the number of sampling aggregations; The value of is greater than 1; The value range is 1 to integer variable of ; The value range is 1 to integer variable of ; Indicates the second length; The calculation formula is: ; in, Indicates the first test time, Indicates the first sampling interval.

[0028] The second output power data sequence construction module is connected to the second radiation intensity data sequence construction module and is used to calculate the second output power data sequence using a power aggregation formula according to the first output power data sequence; the power aggregation formula is: ; in, Indicates the first individual data; Indicates the first output power data sequence data.

[0029] The second ambient temperature data sequence construction module is connected to the second output power data sequence construction module and is used to calculate the second ambient temperature data sequence using the second temperature aggregation formula according to the first ambient temperature data sequence; the second temperature aggregation formula is: ; in, Indicates the first individual data; Indicates the first ambient temperature data sequence data.

[0030] The third ambient temperature data sequence construction module is connected to the second ambient temperature data sequence construction module and is used to calculate the third ambient temperature data sequence using the third temperature aggregation formula according to the first ambient temperature data sequence; the third temperature aggregation formula is: ; in, Indicates the third ambient temperature data sequence data.

[0031] The fitting sample set generation module is connected to the third ambient temperature data sequence construction module, and is used to construct a fitting sample set according to the second radiation intensity data sequence, the second output power data sequence, the second ambient temperature data sequence, and the third ambient temperature data sequence; the fitting sample set is expressed as: ; in, represents the fitting sample set; represents the first samples; It is expressed as: .

[0032] Furthermore, the data model building module includes: The first fitting equation construction module is used to construct a first fitting equation according to the rated photoelectric conversion efficiency, the photovoltaic panel area, and the rated resistance of the photovoltaic power generation system; the first fitting equation is expressed as: ; in, represents the photovoltaic panel area, Indicates the rated photoelectric conversion efficiency, Indicates the rated voltage of the photovoltaic power generation system. Indicates the rated resistance of the photovoltaic power generation system. Indicates the preset reference temperature. represents the first resistance temperature coefficient, represents the second resistance temperature coefficient, Indicates Remaining power.

[0033] The optimization model construction module is connected to the first fitting equation construction module, and is used to construct a first objective function according to the fitting sample set and the first fitting equation; and to construct a first constraint condition according to the fitting sample set and the first fitting equation.

[0034] The optimization calculation module is connected to the optimization model building module, and is used to take the minimum value of the first objective function as the goal, the first constraint condition as the constraint, the first resistance temperature coefficient and the second resistance temperature coefficient as the optimization variables, and use the particle swarm optimization algorithm to calculate the optimal value of the first resistance temperature coefficient and the optimal value of the second resistance temperature coefficient, which are respectively recorded as the first optimization coefficients , the second optimization coefficient .

[0035] The optimized residual power calculation module is connected to the optimized calculation module and is used to calculate the first optimized residual power using the residual value formula To Optimizing remaining power ; The residual value formula is: ; in, Indicates Optimize remaining power.

[0036] The first optimization equation building module is connected to the optimization residual power calculation module and is used to calculate the residual power according to the first optimization coefficient. , the second optimization coefficient , First optimize the remaining power To Optimizing remaining power The first optimization equation is obtained; the first optimization equation is expressed as: ; in, represents the predicted output power of the photovoltaic power generation system obtained in advance, represents the average value of solar radiation intensity predicted in advance, represents the predicted average ambient temperature obtained in advance, Indicates the predicted dispersion of the ambient temperature obtained in advance.

[0037] The first function construction module is connected to the first optimization equation construction module, and is used to solve the functional relationship between the predicted output power of the photovoltaic power generation system and the predicted average value of the solar radiation intensity, the predicted average value of the ambient temperature, and the predicted dispersion of the ambient temperature according to the first optimization equation, which is recorded as the first function; the first function is expressed as: .

[0038] Furthermore, the optimization model building module includes: The first objective function construction module is used to construct the first objective function according to the fitting sample set and the first fitting equation. , the first objective function is expressed as: .

[0039] Furthermore, the optimization model building module also includes: The first constraint condition construction module is used to construct a first constraint condition according to the fitting sample set and the first fitting equation. The first constraint condition is expressed as: ; in, Represents the pre-set upper limit of the residual volatility constraint.

[0040] (3) Beneficial effects Compared with the prior art, the present invention has the following beneficial effects: According to the fitting sample set, the fitting algorithm is used to calculate the functional relationship between the predicted output power of the photovoltaic power generation system and the predicted average value of solar radiation intensity, the predicted average value of ambient temperature, and the predicted discreteness of ambient temperature, so as to realize the construction of the high-altitude photovoltaic system data model. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 This is a flowchart of a method for constructing a data model for a high-altitude photovoltaic system according to Embodiment 1 of the present invention; Figure 2 This is a schematic diagram of the module composition of a data model building system for a high-altitude photovoltaic system according to Embodiment 2 of the present invention. DETAILED DESCRIPTION

[0042] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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.

[0043] Before giving examples, it is necessary to explain the application scenarios conceived by the present invention. The present invention is applied to obtain the functional relationship between the predicted output power of the photovoltaic power generation system and the predicted average value of the solar radiation intensity, the predicted average value of the ambient temperature, and the predicted discreteness of the ambient temperature in an environment with drastic fluctuations at high altitudes, thereby realizing the construction of a high-altitude photovoltaic system data model.

[0044] Example 1: Figure 1 As shown, this embodiment provides a method for constructing a data model of a high-altitude photovoltaic system, the method comprising the following steps: S1, obtaining first data, wherein the first data includes rated photoelectric conversion efficiency, photovoltaic panel area, rated resistance of photovoltaic power generation system, rated voltage of photovoltaic power generation system, a preset sampling aggregation number, a preset first sampling interval time, and a preset first test time.

[0045] Exemplarily, the rated photoelectric conversion efficiency, photovoltaic panel area, rated resistance of the photovoltaic power generation system, and rated voltage of the photovoltaic power generation system are obtained by reading the design manual of the photovoltaic power generation system. The rated photoelectric conversion efficiency is 17.8%, the photovoltaic panel area is 39.6 square meters, the rated resistance of the photovoltaic power generation system is 0.3 ohms, the rated voltage of the photovoltaic power generation system is 220 volts, the pre-set sampling aggregation number is 60, the pre-set first sampling interval time is 60 seconds, and the pre-set first test time is 360,000 seconds.

[0046] S2, start the photovoltaic power generation system, measure the solar radiation intensity, the output power of the photovoltaic power generation system, and the ambient temperature at the location of the photovoltaic panel at a first sampling interval within a first test time, and obtain a first radiation intensity data sequence, a first output power data sequence, and a first ambient temperature data sequence.

[0047] Exemplarily, the photovoltaic power generation system is turned on, and the solar radiation intensity at the location of the photovoltaic panel, the output power of the photovoltaic power generation system, and the ambient temperature are measured at intervals of 60 seconds within 360,000 seconds to obtain a first radiation intensity data sequence, a first output power data sequence, and a first ambient temperature data sequence. The unit of the solar radiation intensity at the location of the photovoltaic panel is watts per square meter, which is measured by a solar irradiance meter; the unit of the output power of the photovoltaic power generation system is watts, which is measured by a power meter; the unit of the ambient temperature is degrees Celsius, which is measured by a thermometer. The lengths of the first radiation intensity data sequence, the first output power data sequence, and the first ambient temperature data sequence are all 6000.

[0048] S3. Aggregate the first radiation intensity data sequence, the first output power data sequence, and the first ambient temperature data sequence according to the sampling aggregation quantity to obtain a second radiation intensity data sequence, a second output power data sequence, a second ambient temperature data sequence, and a third ambient temperature data sequence; and construct a fitting sample set based on the second radiation intensity data sequence, the second output power data sequence, the second ambient temperature data sequence, and the third ambient temperature data sequence.

[0049] Exemplarily, the first radiation intensity data sequence, the first output power data sequence, and the first ambient temperature data sequence are aggregated according to the sampling aggregation quantity to obtain the second radiation intensity data sequence, the second output power data sequence, the second ambient temperature data sequence, and the third ambient temperature data sequence. The lengths of the second radiation intensity data sequence, the second output power data sequence, the second ambient temperature data sequence, and the third ambient temperature data sequence are all 100. A fitting sample set is constructed based on the second radiation intensity data sequence, the second output power data sequence, the second ambient temperature data sequence, and the third ambient temperature data sequence, and the number of samples in the sample set is 100.

[0050] S4. According to the fitting sample set, a fitting algorithm is used to calculate a first function, wherein the dependent variable of the first function is the predicted output power of the photovoltaic power generation system, and the independent variables of the first function are the predicted average value of solar radiation intensity, the predicted average value of ambient temperature, and the predicted discreteness of ambient temperature; the first function is recorded as a photovoltaic system data model.

[0051] Furthermore, the method of aggregating the first radiation intensity data sequence, the first output power data sequence, and the first ambient temperature data sequence according to the sampling aggregation quantity to obtain a second radiation intensity data sequence, a second output power data sequence, a second ambient temperature data sequence, and a third ambient temperature data sequence, and constructing a fitting sample set according to the second radiation intensity data sequence, the second output power data sequence, the second ambient temperature data sequence, and the third ambient temperature data sequence includes: According to the first radiation intensity data sequence, the second radiation intensity data sequence is calculated using a radiation intensity aggregation formula; the radiation intensity aggregation formula is: ; in, Indicates the first individual data; Indicates the first radiation intensity data sequence individual data; Indicates the number of sampling aggregations; The value of is greater than 1; The value range is 1 to integer variable of ; The value range is 1 to integer variable of ; Indicates the second length; The calculation formula is: ; in, Indicates the first test time, Indicates the first sampling interval.

[0052] For example, Second, Second, , so we can calculate Calculated to .by , For example, The calculation formula is: Watt per square meter; The calculation formula is: Watt per square meter; By analogy, we can calculate to .Will to The second radiation intensity data sequence is obtained by combining.

[0053] According to the first output power data sequence, a second output power data sequence is calculated using a power aggregation formula; the power aggregation formula is: ; in, Indicates the first individual data; Indicates the first output power data sequence data.

[0054] For example, , For example, The calculation formula is: watt; The calculation formula is: watt; By analogy, we can calculate to .Will to The second output power data sequence is obtained by combining.

[0055] According to the first ambient temperature data sequence, a second ambient temperature data sequence is calculated using a second temperature aggregation formula; the second temperature aggregation formula is: ; in, Indicates the first individual data; Indicates the first ambient temperature data sequence data.

[0056] For example, , For example, The calculation formula is: Celsius; The calculation formula is: Celsius; By analogy, we can calculate to .Will to The second ambient temperature data sequence is obtained by combining.

[0057] According to the first ambient temperature data sequence, a third ambient temperature data sequence is calculated using a third temperature aggregation formula; the third temperature aggregation formula is: ; in, Indicates the third ambient temperature data sequence data.

[0058] For example, , For example, The calculation formula is: ; The calculation formula is: ; By analogy, we can calculate to .Will to The third ambient temperature data sequence is obtained by combination.

[0059] A fitting sample set is constructed according to the second radiation intensity data sequence, the second output power data sequence, the second ambient temperature data sequence, and the third ambient temperature data sequence; the fitting sample set is expressed as: ; in, represents the fitting sample set; represents the first samples; It is expressed as: .

[0060] Exemplarily, the fitting sample set is obtained: .

[0061] by , For example: ; .

[0062] Furthermore, the method of calculating a first function using a fitting algorithm based on the fitting sample set, wherein the dependent variable of the first function is the predicted output power of the photovoltaic power generation system, and the independent variables of the first function are the predicted average value of solar radiation intensity, the predicted average value of ambient temperature, and the predicted discreteness of ambient temperature includes: The first fitting equation is constructed according to the rated photoelectric conversion efficiency, the photovoltaic panel area, and the rated resistance of the photovoltaic power generation system; the first fitting equation is expressed as: ; in, represents the photovoltaic panel area, Indicates the rated photoelectric conversion efficiency, Indicates the rated voltage of the photovoltaic power generation system. Indicates the rated resistance of the photovoltaic power generation system. Indicates the preset reference temperature. represents the first resistance temperature coefficient, represents the second resistance temperature coefficient, Indicates Remaining power.

[0063] For example, the preset reference temperature The unit of the first resistance temperature coefficient is ohm per degree Celsius, and the unit of the second resistance temperature coefficient is ohm.

[0064] A first objective function is constructed according to the fitting sample set and the first fitting equation; and a first constraint condition is constructed according to the fitting sample set and the first fitting equation.

[0065] Taking the minimum value of the first objective function as the goal, the first constraint condition as the constraint, the first resistance temperature coefficient and the second resistance temperature coefficient as the optimization variables, the particle swarm optimization algorithm is used to calculate the optimal value of the first resistance temperature coefficient and the optimal value of the second resistance temperature coefficient, which are respectively recorded as the first optimization coefficients , the second optimization coefficient .

[0066] Exemplarily, the first optimization coefficient is calculated , the second optimization coefficient .

[0067] The first optimized residual power is calculated using the residual value formula To Optimizing remaining power ; The residual value formula is: ; in, Indicates Optimize remaining power.

[0068] For example, , For example, the calculation is: watt; watt; Using the same method, the first optimized residual power is calculated Optimize remaining power to 100th .

[0069] According to the first optimization coefficient , the second optimization coefficient , First optimize the remaining power To Optimizing remaining power The first optimization equation is obtained; the first optimization equation is expressed as: ; in, represents the predicted output power of the photovoltaic power generation system, represents the average value of solar radiation intensity predicted in advance, represents the predicted average ambient temperature obtained in advance, Indicates the predicted dispersion of the ambient temperature obtained in advance.

[0070] Exemplarily, the first optimization equation characterizes the relationship between the predicted output power of the photovoltaic power generation system and the predicted average value of solar radiation intensity, the predicted average value of ambient temperature, and the predicted dispersion of ambient temperature. Substituting the predicted average value of solar radiation intensity, the predicted average value of ambient temperature, and the predicted dispersion of ambient temperature into the first optimization equation, the predicted output power of the photovoltaic power generation system can be obtained.

[0071] According to the first optimization equation, the functional relationship between the predicted output power of the photovoltaic power generation system and the predicted average value of the solar radiation intensity, the predicted average value of the ambient temperature, and the predicted dispersion of the ambient temperature is obtained, which is recorded as the first function; the first function is expressed as: .

[0072] Furthermore, the method of constructing a first objective function according to the fitting sample set and the first fitting equation includes: According to the fitting sample set and the first fitting equation, a first objective function is constructed. , the first objective function is expressed as: .

[0073] Furthermore, the method of constructing the first constraint condition according to the fitting sample set and the first fitting equation includes: According to the fitting sample set and the first fitting equation, a first constraint condition is constructed, and the first constraint condition is expressed as: ; in, Represents the pre-set upper limit of the residual volatility constraint.

[0074] Exemplarily, the preset upper limit of the residual fluctuation constraint is 2.

[0075] Embodiment 2: Based on the same inventive concept, Figure 2 As shown, this embodiment also provides a data model building system for a high altitude photovoltaic system, the system comprising: The data reading module is used to obtain first data, wherein the first data includes rated photoelectric conversion efficiency, photovoltaic panel area, rated resistance of photovoltaic power generation system, rated voltage of photovoltaic power generation system, a preset sampling aggregation number, a preset first sampling interval time, and a preset first test time.

[0076] The data measurement module is connected to the data reading module and is used to start the photovoltaic power generation system, measure the solar radiation intensity, the output power of the photovoltaic power generation system, and the ambient temperature at the location of the photovoltaic panel at a first sampling interval within a first test time, and obtain a first radiation intensity data sequence, a first output power data sequence, and a first ambient temperature data sequence.

[0077] A sample construction module is connected to the data measurement module, and is used to aggregate the first radiation intensity data sequence, the first output power data sequence, and the first ambient temperature data sequence according to the sampling aggregation quantity to obtain a second radiation intensity data sequence, a second output power data sequence, a second ambient temperature data sequence, and a third ambient temperature data sequence, and to construct a fitting sample set based on the second radiation intensity data sequence, the second output power data sequence, the second ambient temperature data sequence, and the third ambient temperature data sequence.

[0078] The data model construction module is connected to the sample construction module, and is used to calculate the first function according to the fitting sample set using a fitting algorithm, wherein the dependent variable of the first function is the predicted output power of the photovoltaic power generation system, and the independent variables of the first function are the predicted average value of the solar radiation intensity, the predicted average value of the ambient temperature, and the predicted discreteness of the ambient temperature; the first function is recorded as the photovoltaic system data model.

[0079] Furthermore, the sample construction module includes: The second radiation intensity data sequence construction module is used to calculate the second radiation intensity data sequence using the radiation intensity aggregation formula according to the first radiation intensity data sequence; the radiation intensity aggregation formula is: ; in, Indicates the first individual data; Indicates the first radiation intensity data sequence individual data; Indicates the number of sampling aggregations; The value of is greater than 1; The value range is 1 to integer variable of ; The value range is 1 to integer variable of ; Indicates the second length; The calculation formula is: ; in, Indicates the first test time, Indicates the first sampling interval.

[0080] The second output power data sequence construction module is connected to the second radiation intensity data sequence construction module and is used to calculate the second output power data sequence using a power aggregation formula according to the first output power data sequence; the power aggregation formula is: ; in, Indicates the first individual data; Indicates the first output power data sequence data.

[0081] The second ambient temperature data sequence construction module is connected to the second output power data sequence construction module and is used to calculate the second ambient temperature data sequence using the second temperature aggregation formula according to the first ambient temperature data sequence; the second temperature aggregation formula is: ; in, Indicates the first individual data; Indicates the first ambient temperature data sequence data.

[0082] The third ambient temperature data sequence construction module is connected to the second ambient temperature data sequence construction module and is used to calculate the third ambient temperature data sequence using the third temperature aggregation formula according to the first ambient temperature data sequence; the third temperature aggregation formula is: ; in, Indicates the third ambient temperature data sequence data.

[0083] The fitting sample set generation module is connected to the third ambient temperature data sequence construction module, and is used to construct a fitting sample set according to the second radiation intensity data sequence, the second output power data sequence, the second ambient temperature data sequence, and the third ambient temperature data sequence; the fitting sample set is expressed as: ; in, represents the fitting sample set; represents the first samples; It is expressed as: .

[0084] Furthermore, the data model building module includes: The first fitting equation construction module is used to construct a first fitting equation according to the rated photoelectric conversion efficiency, the photovoltaic panel area, and the rated resistance of the photovoltaic power generation system; the first fitting equation is expressed as: ; in, represents the photovoltaic panel area, Indicates the rated photoelectric conversion efficiency, Indicates the rated voltage of the photovoltaic power generation system. Indicates the rated resistance of the photovoltaic power generation system. Indicates the preset reference temperature. represents the first resistance temperature coefficient, represents the second resistance temperature coefficient, Indicates Remaining power.

[0085] The optimization model construction module is connected to the first fitting equation construction module, and is used to construct a first objective function according to the fitting sample set and the first fitting equation; and to construct a first constraint condition according to the fitting sample set and the first fitting equation.

[0086] The optimization calculation module is connected to the optimization model building module, and is used to take the minimum value of the first objective function as the goal, the first constraint condition as the constraint, the first resistance temperature coefficient and the second resistance temperature coefficient as the optimization variables, and use the particle swarm optimization algorithm to calculate the optimal value of the first resistance temperature coefficient and the optimal value of the second resistance temperature coefficient, which are respectively recorded as the first optimization coefficients , the second optimization coefficient .

[0087] The optimized residual power calculation module is connected to the optimized calculation module and is used to calculate the first optimized residual power using the residual value formula To Optimizing remaining power ; The residual value formula is: ; in, Indicates Optimize remaining power.

[0088] The first optimization equation building module is connected to the optimization residual power calculation module and is used to calculate the residual power according to the first optimization coefficient. , the second optimization coefficient , First optimize the remaining power To Optimizing remaining power The first optimization equation is obtained; the first optimization equation is expressed as: ; in, represents the predicted output power of the photovoltaic power generation system obtained in advance, represents the average value of solar radiation intensity predicted in advance, represents the predicted average ambient temperature obtained in advance, Represents the predicted discreteness of the ambient temperature obtained in advance.

[0089] The first function construction module is connected to the first optimization equation construction module, and is used to solve the functional relationship between the predicted output power of the photovoltaic power generation system and the predicted average value of the solar radiation intensity, the predicted average value of the ambient temperature, and the predicted dispersion of the ambient temperature according to the first optimization equation, which is recorded as the first function; the first function is expressed as: .

[0090] Furthermore, the optimization model building module includes: The first objective function construction module is used to construct the first objective function according to the fitting sample set and the first fitting equation. , the first objective function is expressed as: .

[0091] Furthermore, the optimization model building module also includes: The first constraint condition construction module is used to construct a first constraint condition according to the fitting sample set and the first fitting equation. The first constraint condition is expressed as: ; in, Represents the pre-set upper limit of the residual volatility constraint.

[0092] It should be noted that, regarding the system in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0093] Finally, it should be noted that: Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments, or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for constructing a data model for a high altitude photovoltaic system, characterized in that: The method comprises the following steps: S1, obtaining first data, wherein the first data includes rated photoelectric conversion efficiency, photovoltaic panel area, rated resistance of photovoltaic power generation system, rated voltage of photovoltaic power generation system, a preset sampling aggregation number, a preset first sampling interval time, and a preset first test time; S2, start the photovoltaic power generation system, and measure the solar radiation intensity, the output power of the photovoltaic power generation system, and the ambient temperature at the location of the photovoltaic panel within a first test time and at a first sampling interval, to obtain a first radiation intensity data sequence, a first output power data sequence, and a first ambient temperature data sequence; S3, aggregating the first radiation intensity data sequence, the first output power data sequence, and the first ambient temperature data sequence according to the sampling aggregation quantity to obtain a second radiation intensity data sequence, a second output power data sequence, a second ambient temperature data sequence, and a third ambient temperature data sequence, and constructing a fitting sample set according to the second radiation intensity data sequence, the second output power data sequence, the second ambient temperature data sequence, and the third ambient temperature data sequence; S4. According to the fitting sample set, a fitting algorithm is used to calculate a first function, wherein the dependent variable of the first function is the predicted output power of the photovoltaic power generation system, and the independent variables of the first function are the predicted average value of solar radiation intensity, the predicted average value of ambient temperature, and the predicted discreteness of ambient temperature; the first function is recorded as a photovoltaic system data model.

2. A method for constructing a data model for a high altitude photovoltaic system according to claim 1, characterized in that: The method of aggregating the first radiation intensity data sequence, the first output power data sequence, and the first ambient temperature data sequence according to the sampling aggregation quantity to obtain the second radiation intensity data sequence, the second output power data sequence, the second ambient temperature data sequence, and the third ambient temperature data sequence, and constructing a fitting sample set according to the second radiation intensity data sequence, the second output power data sequence, the second ambient temperature data sequence, and the third ambient temperature data sequence comprises: According to the first radiation intensity data sequence, the second radiation intensity data sequence is calculated using a radiation intensity aggregation formula; the radiation intensity aggregation formula is: ； in, Indicates the first individual data; Indicates the first radiation intensity data sequence individual data; Indicates the number of sampling aggregations; The value of is greater than 1; The value range is 1 to integer variable of ; The value range is 1 to integer variable of ; Indicates the second length; The calculation formula is: ； in, Indicates the first test time, Indicates the first sampling interval time; According to the first output power data sequence, a second output power data sequence is calculated using a power aggregation formula; the power aggregation formula is: ； in, Indicates the first individual data; Indicates the first output power data sequence individual data; According to the first ambient temperature data sequence, a second ambient temperature data sequence is calculated using a second temperature aggregation formula; the second temperature aggregation formula is: ； in, Indicates the first individual data; Indicates the first ambient temperature data sequence individual data; According to the first ambient temperature data sequence, a third ambient temperature data sequence is calculated using a third temperature aggregation formula; the third temperature aggregation formula is: ； in, Indicates the third ambient temperature data sequence individual data; A fitting sample set is constructed according to the second radiation intensity data sequence, the second output power data sequence, the second ambient temperature data sequence, and the third ambient temperature data sequence; the fitting sample set is expressed as: ； in, represents the fitting sample set; represents the first samples; It is expressed as: 。 3. A method for constructing a data model for a high altitude photovoltaic system according to claim 2, characterized in that: The method of calculating a first function using a fitting algorithm according to the fitting sample set, wherein the dependent variable of the first function is the predicted output power of the photovoltaic power generation system, and the independent variables of the first function are the predicted average value of solar radiation intensity, the predicted average value of ambient temperature, and the predicted discreteness of ambient temperature includes: The first fitting equation is constructed according to the rated photoelectric conversion efficiency, the photovoltaic panel area, and the rated resistance of the photovoltaic power generation system; the first fitting equation is expressed as: ； in, represents the photovoltaic panel area, Indicates the rated photoelectric conversion efficiency, Indicates the rated voltage of the photovoltaic power generation system. Indicates the rated resistance of the photovoltaic power generation system. Indicates the preset reference temperature. represents the first resistance temperature coefficient, represents the second resistance temperature coefficient, Indicates Residual power; Constructing a first objective function according to the fitting sample set and the first fitting equation; constructing a first constraint condition according to the fitting sample set and the first fitting equation; Taking the minimum value of the first objective function as the goal, the first constraint condition as the constraint, the first resistance temperature coefficient and the second resistance temperature coefficient as the optimization variables, the particle swarm optimization algorithm is used to calculate the optimal value of the first resistance temperature coefficient and the optimal value of the second resistance temperature coefficient, which are respectively recorded as the first optimization coefficients , the second optimization coefficient ; The first optimized residual power is calculated using the residual value formula To Optimizing remaining power ; The residual value formula is: ； in, Indicates Optimize remaining power; According to the first optimization coefficient , the second optimization coefficient , First optimize the remaining power To Optimizing remaining power The first optimization equation is obtained; the first optimization equation is expressed as: ； in, represents the predicted output power of the photovoltaic power generation system, represents the average value of solar radiation intensity predicted in advance, represents the predicted average ambient temperature obtained in advance, Indicates the predicted discreteness of the ambient temperature obtained in advance; According to the first optimization equation, the functional relationship between the predicted output power of the photovoltaic power generation system and the predicted average value of the solar radiation intensity, the predicted average value of the ambient temperature, and the predicted dispersion of the ambient temperature is obtained, which is recorded as the first function; the first function is expressed as: 。 4. A method for constructing a data model for a high altitude photovoltaic system according to claim 3, characterized in that: The method for constructing a first objective function according to the fitting sample set and the first fitting equation includes: According to the fitting sample set and the first fitting equation, a first objective function is constructed. , the first objective function is expressed as: 。 5. A method for constructing a data model for a high altitude photovoltaic system according to claim 4, characterized in that: The method for constructing the first constraint condition according to the fitting sample set and the first fitting equation includes: According to the fitting sample set and the first fitting equation, a first constraint condition is constructed, and the first constraint condition is expressed as: ； in, Represents the pre-set upper limit of the residual volatility constraint.

6. A data model building system for a high altitude photovoltaic system, characterized in that: The system comprises: A data reading module, used to obtain first data, wherein the first data includes a rated photoelectric conversion efficiency, a photovoltaic panel area, a rated resistance of a photovoltaic power generation system, a rated voltage of a photovoltaic power generation system, a preset sampling aggregation number, a preset first sampling interval time, and a preset first test time; The data measurement module is connected to the data reading module and is used to start the photovoltaic power generation system, measure the solar radiation intensity, the output power of the photovoltaic power generation system, and the ambient temperature at the location of the photovoltaic panel at a first sampling interval within a first test time, and obtain a first radiation intensity data sequence, a first output power data sequence, and a first ambient temperature data sequence; a sample construction module connected to the data measurement module, and configured to aggregate the first radiation intensity data sequence, the first output power data sequence, and the first ambient temperature data sequence according to the sampling aggregation quantity to obtain a second radiation intensity data sequence, a second output power data sequence, a second ambient temperature data sequence, and a third ambient temperature data sequence, and to construct a fitting sample set according to the second radiation intensity data sequence, the second output power data sequence, the second ambient temperature data sequence, and the third ambient temperature data sequence; The data model construction module is connected to the sample construction module, and is used to calculate the first function according to the fitting sample set using a fitting algorithm, wherein the dependent variable of the first function is the predicted output power of the photovoltaic power generation system, and the independent variables of the first function are the predicted average value of the solar radiation intensity, the predicted average value of the ambient temperature, and the predicted discreteness of the ambient temperature; the first function is recorded as the photovoltaic system data model.

7. A data model building system for a high altitude photovoltaic system as claimed in claim 6, characterized in that: The sample building blocks include: The second radiation intensity data sequence construction module is used to calculate the second radiation intensity data sequence using the radiation intensity aggregation formula according to the first radiation intensity data sequence; the radiation intensity aggregation formula is: ； in, Indicates the first individual data; Indicates the first radiation intensity data sequence individual data; Indicates the number of sampling aggregations; The value of is greater than 1; The value range is 1 to integer variable of ; The value range is 1 to integer variable of ; Indicates the second length; The calculation formula is: ； in, Indicates the first test time, Indicates the first sampling interval time; The second output power data sequence construction module is connected to the second radiation intensity data sequence construction module and is used to calculate the second output power data sequence using a power aggregation formula according to the first output power data sequence; the power aggregation formula is: ； in, Indicates the first individual data; Indicates the first output power data sequence individual data; The second ambient temperature data sequence construction module is connected to the second output power data sequence construction module and is used to calculate the second ambient temperature data sequence using the second temperature aggregation formula according to the first ambient temperature data sequence; the second temperature aggregation formula is: ； in, Indicates the first individual data; Indicates the first ambient temperature data sequence individual data; The third ambient temperature data sequence construction module is connected to the second ambient temperature data sequence construction module and is used to calculate the third ambient temperature data sequence using the third temperature aggregation formula according to the first ambient temperature data sequence; the third temperature aggregation formula is: ； in, Indicates the third ambient temperature data sequence individual data; The fitting sample set generation module is connected to the third ambient temperature data sequence construction module, and is used to construct a fitting sample set according to the second radiation intensity data sequence, the second output power data sequence, the second ambient temperature data sequence, and the third ambient temperature data sequence; the fitting sample set is expressed as: ； in, represents the fitting sample set; represents the first samples; It is expressed as: 。 8. A data model building system for a high altitude photovoltaic system as claimed in claim 7, characterized in that: The data model building module includes: The first fitting equation construction module is used to construct a first fitting equation according to the rated photoelectric conversion efficiency, the photovoltaic panel area, and the rated resistance of the photovoltaic power generation system; the first fitting equation is expressed as: ； in, represents the photovoltaic panel area, Indicates the rated photoelectric conversion efficiency, Indicates the rated voltage of the photovoltaic power generation system. Indicates the rated resistance of the photovoltaic power generation system. Indicates the preset reference temperature. represents the first resistance temperature coefficient, represents the second resistance temperature coefficient, Indicates Residual power; An optimization model construction module is connected to the first fitting equation construction module, and is used to construct a first objective function according to the fitting sample set and the first fitting equation; and to construct a first constraint condition according to the fitting sample set and the first fitting equation; The optimization calculation module is connected to the optimization model building module, and is used to take the minimum value of the first objective function as the goal, the first constraint condition as the constraint, the first resistance temperature coefficient and the second resistance temperature coefficient as the optimization variables, and use the particle swarm optimization algorithm to calculate the optimal value of the first resistance temperature coefficient and the optimal value of the second resistance temperature coefficient, which are respectively recorded as the first optimization coefficients , the second optimization coefficient ; The optimized residual power calculation module is connected to the optimized calculation module and is used to calculate the first optimized residual power using the residual value formula To Optimizing remaining power ; The residual value formula is: ； in, Indicates Optimize remaining power; The first optimization equation building module is connected to the optimization residual power calculation module and is used to calculate the residual power according to the first optimization coefficient. , the second optimization coefficient , First optimize the remaining power To Optimizing remaining power The first optimization equation is obtained; the first optimization equation is expressed as: ； in, represents the predicted output power of the photovoltaic power generation system obtained in advance, represents the average value of solar radiation intensity predicted in advance, represents the predicted average ambient temperature obtained in advance, Indicates the predicted discreteness of the ambient temperature obtained in advance; The first function construction module is connected to the first optimization equation construction module, and is used to solve the functional relationship between the predicted output power of the photovoltaic power generation system and the predicted average value of the solar radiation intensity, the predicted average value of the ambient temperature, and the predicted dispersion of the ambient temperature according to the first optimization equation, which is recorded as the first function; the first function is expressed as: 。 9. A data model building system for a high altitude photovoltaic system as claimed in claim 8, characterized in that: The optimization model building module includes: The first objective function construction module is used to construct the first objective function according to the fitting sample set and the first fitting equation. , the first objective function is expressed as: 。 10. A data model building system for a high altitude photovoltaic system according to claim 9, characterized in that: The optimization model building module also includes: The first constraint condition construction module is used to construct a first constraint condition according to the fitting sample set and the first fitting equation. The first constraint condition is expressed as: ； in, Represents the pre-set upper limit of the residual volatility constraint.

Images