A photovoltaic power generation box-type transformer output power prediction method and system

Abstract

The application discloses a box-type transformer output power prediction method and system for photovoltaic power generation, and belongs to the technical field of photovoltaic power generation. The method comprises the following steps: acquiring the latitude and longitude information of the position of the box-type transformer for photovoltaic power generation; acquiring the hourly weather forecast information of the location of the box-type transformer for photovoltaic power generation in a prediction time period; inputting the latitude and longitude information, the hourly weather forecast information and the date to which the prediction time period belongs into a trained neural network model to obtain the hourly total radiation of the inclined surface of the photovoltaic array in the prediction time period; and calculating the hourly alternating current power generation of the box-type transformer for photovoltaic power generation in the prediction time period based on the hourly total radiation of the inclined surface of the photovoltaic array in the prediction time period. In the process of predicting the output power of photovoltaic power generation, not only the influence of latitude and longitude and seasons on the continuity of illumination is considered, but also the random influence of weather conditions on illumination is considered, so that the accuracy of solar radiation prediction is improved, and the accuracy of photovoltaic power generation output power prediction is improved.

Description

Technical Field

[0001] This invention relates to the field of photovoltaic power generation technology, and in particular to a method and system for predicting the output power of a box-type transformer used in photovoltaic power generation. Background Technology

[0002] To maximize the power generation efficiency of photovoltaic systems and optimize grid dispatch, it is necessary to predict the output power of the photovoltaic power generation box transformer. Based on the comparison between the predicted output power and the actual output power, certain decisions are made (e.g., maintenance decisions and optimized dispatch decisions for photovoltaic power generation box transformers). However, due to the randomness of photovoltaic power generation output power, the prediction results are inaccurate. Summary of the Invention

[0003] The purpose of this invention is to provide a method and system for predicting the output power of a box-type transformer used in photovoltaic power generation, so as to improve the accuracy of predicting the output power of the box-type transformer used in photovoltaic power generation.

[0004] To achieve the above objectives, the present invention provides the following solution:

[0005] This invention provides a method for predicting the output power of a box-type transformer for photovoltaic power generation. The box-type transformer for photovoltaic power generation includes a photovoltaic array, a rectifier, a grid-connected inverter, and a grid-connected transformer connected in sequence. The method includes the following steps:

[0006] Obtain the latitude and longitude information of the location of the box-type transformer used for photovoltaic power generation;

[0007] Obtain hourly weather forecast information for the location of the photovoltaic power generation box-type transformer within the predicted time period;

[0008] The latitude and longitude information, the hourly weather forecast information, and the date of the predicted time period are input into the trained neural network model to obtain the hourly total radiation of the photovoltaic array tilt surface within the predicted time period.

[0009] The hourly AC power generation of the box-type transformer for photovoltaic power generation is calculated based on the hourly total radiation of the tilted surface of the photovoltaic array within the predicted time period.

[0010] Optionally, the neural network model includes an input gate, a hidden layer, and an output gate.

[0011] Optionally, the calculation of the hourly AC power generation of the photovoltaic power generation box-type transformer within the predicted time period based on the hourly total radiation of the photovoltaic array tilt surface within the predicted time period specifically includes:

[0012] Based on the hourly total radiation of the tilted surface of the photovoltaic array within the predicted time period, the hourly plate temperature of the photovoltaic array within the predicted time period is calculated as follows:

[0013] Tc =T0 + b × Q;

[0014] Where Tc is the hourly panel temperature of the photovoltaic array during the prediction period, Q is the hourly total solar radiation on the tilted surface, T0 is the current panel temperature of the photovoltaic array, and b is the panel temperature variation coefficient due to solar radiation.

[0015] Based on the hourly total radiation of the tilted surface of the photovoltaic array and the hourly plate temperature of the photovoltaic array during the prediction period, the hourly DC power generation of the photovoltaic array during the prediction period is calculated as follows:

[0016] Edc=ηs×[1-α(Tc-25℃)]×Q×S×K1 / 3.6;

[0017] Where Edc is the hourly DC power generation of the photovoltaic array, ηs is the photoelectric conversion efficiency under standard test conditions, α is the temperature coefficient of the photovoltaic array, S is the effective area of ​​the photovoltaic module, and K1 is the loss coefficient of the photovoltaic array.

[0018] The hourly DC power generation of the photovoltaic array is predicted within the specified time period. The hourly AC power generation of the photovoltaic power generation box-type transformer within the same time period is then calculated as follows:

[0019] Eac = Edc × η × K2;

[0020] Where Eac is the hourly AC power generation of the photovoltaic power generation box transformer during the predicted time period, η is the grid-connected inverter conversion efficiency, and K2 is the AC circuit line loss coefficient.

[0021] Optionally, the step of calculating the hourly AC power generation of the photovoltaic power generation box-type transformer within the prediction time period based on the hourly total radiation of the photovoltaic array tilt surface within the prediction time period further includes:

[0022] Calculate the difference between the hourly AC power generation of the photovoltaic power generation box-type transformer during the predicted period and the actual hourly AC power generation of the photovoltaic power generation box-type transformer during the predicted period.

[0023] When the difference is greater than a preset threshold, the photovoltaic power generation box transformer is maintained.

[0024] A photovoltaic power generation box-type transformer output power prediction system, wherein the system is applied to the above-mentioned method, and the system includes:

[0025] The latitude and longitude information acquisition module is used to acquire the latitude and longitude information of the location of the box-type transformer for photovoltaic power generation;

[0026] The hourly weather forecast information acquisition module is used to acquire hourly weather forecast information for the location of the photovoltaic power generation box-type transformer within the forecast period.

[0027] The total radiation prediction module is used to input the latitude and longitude information, the hourly weather forecast information and the date to which the prediction time period belongs into the trained neural network model to obtain the hourly total radiation of the photovoltaic array tilt surface within the prediction time period;

[0028] The hourly AC power generation calculation module is used to calculate the hourly AC power generation of the photovoltaic power generation box transformer within the predicted time period based on the hourly total radiation of the photovoltaic array tilt surface within the predicted time period.

[0029] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method described above.

[0030] A computer-readable storage medium storing a computer program that, when executed, implements the above-described method.

[0031] According to specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0032] This invention provides a method and system for predicting the output power of a photovoltaic (PV) power generation box-type transformer. The method includes the following steps: obtaining the latitude and longitude information of the location of the PV power generation box-type transformer; obtaining hourly weather forecast information for the location of the PV power generation box-type transformer within a predicted time period; inputting the latitude and longitude information, the hourly weather forecast information, and the date of the predicted time period into a trained neural network model to obtain the hourly total radiation of the PV array tilt surface within the predicted time period; and calculating the hourly AC power generation of the PV power generation box-type transformer within the predicted time period based on the hourly total radiation of the PV array tilt surface within the predicted time period. This invention, in the process of predicting the output power of PV power generation, not only considers the continuous influence of latitude and longitude and season on sunlight, but also the random influence of weather conditions on sunlight, improving the accuracy of solar radiation prediction and thus improving the accuracy of PV power generation output prediction.

[0033] Furthermore, this invention calculates the power generation based on the predicted total radiation and the relevant parameters of the photovoltaic array and grid-connected transformer, taking into account the impact of the relevant parameters of the photovoltaic array and grid-connected transformer on the power generation, thus further improving the accuracy of photovoltaic power generation output prediction. Attached Figure Description

[0034] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0035] Figure 1 A flowchart illustrating a method for predicting the output power of a box-type transformer for photovoltaic power generation, provided as an embodiment of the present invention. Detailed Implementation

[0036] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0037] The purpose of this invention is to provide a method and system for predicting the output power of a box-type transformer used in photovoltaic power generation, so as to improve the accuracy of predicting the output power of the box-type transformer used in photovoltaic power generation.

[0038] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0039] Example 1

[0040] Embodiment 1 of the present invention provides a method for predicting the output power of a box-type transformer for photovoltaic power generation. The box-type transformer for photovoltaic power generation includes a photovoltaic array, a rectifier, a grid-connected inverter, and a grid-connected transformer connected in sequence. Figure 1 As shown, the method includes the following steps:

[0041] Step 101: Obtain the latitude and longitude information of the location of the box-type transformer for photovoltaic power generation.

[0042] Step 102: Obtain hourly weather forecast information for the location of the photovoltaic power generation box-type transformer within the predicted time period.

[0043] Step 103: Input the latitude and longitude information, the hourly weather forecast information, and the date to which the predicted time period belongs into the trained neural network model to obtain the hourly total radiation of the photovoltaic array tilt surface within the predicted time period.

[0044] The efficiency of solar energy conversion into electrical energy is mainly affected by solar radiation and the temperature of solar photovoltaic panels. Solar radiation is influenced by geographical and meteorological factors, exhibiting significant discontinuity and uncertainty, with marked annual, seasonal, and diurnal variations. Atmospheric physicochemical conditions such as cloud cover, humidity, atmospheric transparency, and aerosol concentration also affect the intensity of solar radiation. Geographical conditions show clear patterns; the annual trajectory of the sun can be calculated based on local latitude and longitude, and combined with the parameters of the photovoltaic array itself, an overall trend of solar energy variation can be calculated. Meteorological conditions have the most direct impact on solar radiation and panel temperature. Hourly weather forecasts published by local meteorological departments can be obtained, accurately reflecting the changes in solar energy over several hours or even days, allowing for the calculation of solar energy trends. In this embodiment of the invention, the hourly total radiation of the tilted surface of the photovoltaic array is predicted by comprehensively considering latitude and longitude information, the date of the prediction period, and hourly weather forecast information. Latitude and longitude information and date information characterize the influence of the sun's relative trajectory to the Earth on solar radiation, while weather changes characterize the impact of cloud and rain obstruction on solar radiation.

[0045] The neural network model provided in this embodiment of the invention includes an input gate, hidden layers, and an output gate. The input gate has 5 input nodes, the hidden layers have 2 hidden nodes, and the output gate has 1 output node. Once the network structure is determined, the connection weights and thresholds of each neuron in each layer can be repeatedly adjusted using known samples until the cost function is maximized. For example, the cost function can be selected as the absolute value of the difference between the predicted hourly total radiation of the photovoltaic array tilt surface and the measured hourly total radiation of the photovoltaic array tilt surface, until the absolute value of this difference is less than a certain threshold or no longer changes.

[0046] Step 104: Calculate the hourly AC power generation of the photovoltaic power generation box transformer during the predicted time period based on the hourly total radiation of the photovoltaic array tilt surface during the predicted time period.

[0047] A grid-connected photovoltaic power generation system includes two stages: photoelectric conversion and DC / AC inverter.

[0048] The fundamental physical principle of solar photovoltaic (PV) power generation is the photovoltaic effect. In the photoelectric conversion stage, the efficiency of a PV array in converting solar energy into direct current (DC) is mainly affected by solar radiation and panel temperature. Aging, array configuration, dust accumulation, and DC line losses are also factors that need to be considered. The expression for the hourly DC power generation (kWh) of a PV array is:

[0049] Edc = η s ×[1-α(Tc-25℃)]×Q×S×K1 / 3.6 (1)

[0050] In the formula:

[0051] η s Photoelectric conversion efficiency under standard test conditions;

[0052] α is the temperature coefficient (°C) -1 This relates to solar cell materials;

[0053] Q represents the total solar radiation per hour on the inclined surface (MJ / m²). 2 );

[0054] Tc is the array plate temperature (°C), T c =T0 + b × Q;

[0055] S represents the effective area of ​​the photovoltaic module (m²). 2 );

[0056] K1 is the loss factor of the photovoltaic array due to aging, mismatch, dust obstruction, DC circuit, etc.

[0057] The conversion efficiency of the DC / AC inverter stage is mainly determined by the inverter device. The expression for the hourly AC power generation (kWh) of a grid-connected inverter is:

[0058] Eac=Edc×η×K2 (2)

[0059] In the formula:

[0060] η is the conversion efficiency of the grid-connected inverter;

[0061] K2 is the line loss factor for AC circuits.

[0062] As an optional implementation, the step of calculating the hourly AC power generation of the photovoltaic power generation box-type transformer within the predicted time period based on the hourly total radiation of the photovoltaic array tilt surface within the predicted time period further includes: calculating the difference between the predicted hourly AC power generation of the photovoltaic power generation box-type transformer within the predicted time period and the actual hourly AC power generation of the photovoltaic power generation box-type transformer within the predicted time period; when the difference is greater than a preset threshold, maintenance is performed on the photovoltaic power generation box-type transformer. The hourly AC power generation predicted in this embodiment can also be applied to power grid optimization scheduling, and the specific method is not described here.

[0063] Example 2

[0064] Embodiment 2 of the present invention provides a photovoltaic power generation box-type transformer output power prediction system, wherein the system is applied to the above-described method, and the system includes:

[0065] The latitude and longitude information acquisition module is used to acquire the latitude and longitude information of the location of the box-type transformer for photovoltaic power generation;

[0066] The hourly weather forecast information acquisition module is used to acquire hourly weather forecast information for the location of the photovoltaic power generation box-type transformer within the forecast period.

[0067] The total radiation prediction module is used to input the latitude and longitude information, the hourly weather forecast information and the date to which the prediction time period belongs into the trained neural network model to obtain the hourly total radiation of the photovoltaic array tilt surface within the prediction time period;

[0068] The hourly AC power generation calculation module is used to calculate the hourly AC power generation of the photovoltaic power generation box transformer within the predicted time period based on the hourly total radiation of the photovoltaic array tilt surface within the predicted time period.

[0069] Example 3

[0070] Embodiment 3 of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-described method.

[0071] Example 4

[0072] Embodiment 4 of the present invention provides a computer-readable storage medium storing a computer program, which, when executed, implements the above-described method.

[0073] According to specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0074] This invention provides a method and system for predicting the output power of a photovoltaic (PV) power generation box-type transformer. The method includes the following steps: obtaining the latitude and longitude information of the location of the PV power generation box-type transformer; obtaining hourly weather forecast information for the location of the PV power generation box-type transformer within a predicted time period; inputting the latitude and longitude information, the hourly weather forecast information, and the date of the predicted time period into a trained neural network model to obtain the hourly total radiation of the PV array tilt surface within the predicted time period; and calculating the hourly AC power generation of the PV power generation box-type transformer within the predicted time period based on the hourly total radiation of the PV array tilt surface within the predicted time period. This invention, in the process of predicting the output power of PV power generation, not only considers the continuous influence of latitude and longitude and season on sunlight, but also the random influence of weather conditions on sunlight, improving the accuracy of solar radiation prediction and thus improving the accuracy of PV power generation output prediction.

[0075] Furthermore, this invention calculates the power generation based on the predicted total radiation and the relevant parameters of the photovoltaic array and grid-connected transformer, taking into account the impact of the relevant parameters of the photovoltaic array and grid-connected transformer on the power generation, thus further improving the accuracy of photovoltaic power generation output prediction.

[0076] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the systems disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple; relevant parts can be referred to the method section.

[0077] This document uses specific examples to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. Furthermore, those skilled in the art will recognize that, based on the ideas of the present invention, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for predicting the output power of a box-type transformer for photovoltaic power generation, characterized in that, The photovoltaic power generation box-type transformer includes a photovoltaic array, a rectifier, a grid-connected inverter, and a grid-connected transformer connected in sequence. The method includes the following steps: Obtain the latitude and longitude information of the location of the box-type transformer used for photovoltaic power generation; Obtain hourly weather forecast information for the location of the photovoltaic power generation box-type transformer within the predicted time period; The latitude and longitude information, the hourly weather forecast information, and the date of the predicted time period are input into the trained neural network model to obtain the hourly total radiation of the photovoltaic array tilt surface within the predicted time period. The hourly AC power generation of the box-type transformer for photovoltaic power generation is calculated based on the hourly total radiation of the tilted surface of the photovoltaic array within the predicted time period. The calculation of the hourly AC power generation of the photovoltaic power generation box-type transformer within the predicted time period based on the hourly total radiation of the photovoltaic array tilt surface within the predicted time period specifically includes: Based on the hourly total radiation of the tilted surface of the photovoltaic array within the predicted time period, the hourly plate temperature of the photovoltaic array within the predicted time period is calculated as follows: ； in, To predict the hourly panel temperature of the photovoltaic array over a period of time, The total solar radiation on the inclined surface is measured hourly. Let be the current temperature of the photovoltaic array, and b be the coefficient of temperature variation due to solar radiation. Based on the hourly total radiation of the tilted surface of the photovoltaic array and the hourly plate temperature of the photovoltaic array during the prediction period, the hourly DC power generation of the photovoltaic array during the prediction period is calculated as follows: Edc=η s ×[1-α(T c -25℃)]×Q×S×K1 / 3.6; Where Edc is the hourly DC power generation of the photovoltaic array, and η s The photoelectric conversion efficiency is given under standard test conditions, α is the temperature coefficient of the photovoltaic array, S is the effective area of ​​the photovoltaic module, and K1 is the loss coefficient of the photovoltaic array. Based on the hourly DC power generation of the photovoltaic array within the predicted time period, the hourly AC power generation of the box-type transformer used for photovoltaic power generation within the predicted time period is calculated as follows: Eac = Edc × η × K2; Where Eac is the hourly AC power generation of the box-type transformer for photovoltaic power generation during the predicted time period, η is the conversion efficiency of the grid-connected inverter, and K2 is the AC circuit line loss coefficient. The calculation of the hourly AC power generation of the photovoltaic power generation box-type transformer within the predicted time period based on the hourly total radiation of the photovoltaic array tilt surface within the predicted time period, and the subsequent steps include: Calculate the difference between the hourly AC power generation of the photovoltaic power generation box-type transformer during the predicted period and the actual hourly AC power generation of the photovoltaic power generation box-type transformer during the predicted period. When the difference is greater than a preset threshold, the photovoltaic power generation box transformer is maintained.

2. The method for predicting the output power of a box-type transformer for photovoltaic power generation according to claim 1, characterized in that, The neural network model includes an input gate, hidden layers, and an output gate.

3. A photovoltaic power generation box-type transformer output power prediction system, characterized in that, The system is applied to the method according to any one of claims 1-2, the system comprising: The latitude and longitude information acquisition module is used to acquire the latitude and longitude information of the location of the box-type transformer for photovoltaic power generation; The hourly weather forecast information acquisition module is used to acquire hourly weather forecast information for the location of the photovoltaic power generation box-type transformer within the forecast period. The total radiation prediction module is used to input the latitude and longitude information, the hourly weather forecast information and the date to which the prediction time period belongs into the trained neural network model to obtain the hourly total radiation of the photovoltaic array tilt surface within the prediction time period; The hourly AC power generation calculation module is used to calculate the hourly AC power generation of the photovoltaic power generation box transformer within the predicted time period based on the hourly total radiation of the photovoltaic array tilt surface within the predicted time period.

4. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the method as described in any one of claims 1 to 2.

5. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, which, when executed, implements the method as described in any one of claims 1 to 2.

Images