Solar power generation prediction method, apparatus, computer device, and storage medium
By modifying solar power generation prediction models with correction coefficients and linear fitting functions, the method addresses low accuracy and interpretability issues, enhancing prediction accuracy and integration with production operations.
Patent Information
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- CHINA THREE GORGES CORPORATION
- Filing Date
- 2024-11-08
- Publication Date
- 2026-05-19
AI Technical Summary
Existing solar power generation prediction methods lack interpretability, leading to difficulty in intuitively analyzing the cause of power prediction results and integrating with actual production operations, while also suffering from low prediction accuracy due to factors like climate differences and dynamic module temperature changes.
A method that modifies solar power generation prediction models using correction coefficients, considering factors like battery temperature, irradiance, and weather conditions, and constructs linear fitting functions to improve prediction accuracy by averaging battery temperatures and accounting for different weather types.
Enhances prediction accuracy by considering various factors affecting solar power generation, such as dust, light attenuation, and surface reflection, and improves model interpretability by linking predictions with actual production scenarios.
Smart Images
Figure 0007862513000024 
Figure 0007862513000025 
Figure 0007862513000026
Abstract
Description
Technical Field
[0001] The present invention relates to the field of computer technology, and specifically to a solar power generation power prediction method, apparatus, computer device, and storage medium.
Background Art
[0002] The utilization of renewable energy is one of the important means to solve the global energy shortage and environmental pollution problems. Solar power generation is the most promising and convenient means in the current new energy development. Since solar power generation is affected by meteorological elements, and further, the process of converting light energy into electrical energy by a solar power generation module is affected by the device itself, it brings strong randomness and variability to solar power generation. With the increase of grid connection capacity, the randomness and variability of solar power generation pose a huge threat to the safe and stable operation of the power grid. Therefore, accurate prediction of solar power generation is of great significance for improving the safety and stability of the power grid.
[0003] In the prior art, a neural network model is usually adopted to predict solar power generation. The neural network model has the characteristics of high prediction accuracy and low data requirements, but due to the low interpretability of the model, it is impossible to intuitively analyze the cause of the power prediction result from the business level, and it is difficult to realize the linkage and penetration with the actual production operation scene. Therefore, there is an urgent need for a solar power generation power prediction method that can interpret the model content and results on the premise of ensuring prediction accuracy, and thus realize the linkage and penetration between the solar power generation power prediction result and the actual production operation scene.
Summary of the Invention
[0004] The technical problem to be solved by the present invention is to provide a solar power generation power prediction method, apparatus, computer device, and storage medium, and solve the problems that the physical model prediction accuracy in related technologies is low, it is impossible to intuitively analyze the cause of the power prediction result from the business level, and it is difficult to realize the linkage and penetration with the actual production operation scene.
[0005] To solve the aforementioned technical problems, the technical solution adopted by the present invention is as follows. A method for predicting solar power generation, including the following: The first solar power generation prediction model is modified based on the correction coefficients to generate a second solar power generation prediction model. The first solar power generation prediction model is constructed based on the battery temperature and irradiance of the solar power generation module. The system determines whether the ambient temperature information of the solar power generation module awaiting prediction matches the pre-set requirement information. If it does not match the pre-set requirement information, the system determines the average battery temperature of the solar power generation module awaiting prediction and a first relationship, which represents the relationship between the battery temperature, ambient temperature, and irradiance of the solar power generation module awaiting prediction. Based on the average battery temperature and the first relationship, the second solar power generation prediction model is modified to generate a third solar power generation prediction model. Using the aforementioned third solar power generation power prediction model, predictions are made for the solar power generation power values of the solar power generation modules awaiting prediction. Based on the weather type of the solar power generation module for which the forecast is pending, the corresponding target weather correction factor is determined from among several weather correction factors.
[0006] Preferably, the target solar power generation value is obtained by adjusting the solar power generation value based on the target weather correction coefficient.
[0007] Preferably, before determining the corresponding target weather correction factor from multiple weather correction factors, the following is included: Prior to the forecast, the aforementioned solar power generation module acquires multiple sets of data for different weather types, and each set of data includes the device capacity, irradiance value, battery temperature value, and actual power generation amount for the corresponding weather type. The device capacity, irradiance value, battery temperature value, and actual power generation amount for the corresponding weather type are input into the correction coefficient prediction model, and the weather correction coefficient for the corresponding weather type is output.
[0008] Preferably, the correction factors include a dust effect coefficient, a light attenuation loss coefficient, and a surface reflection loss coefficient. Based on the correction factors, the first solar power generation prediction model is modified to generate a second solar power generation prediction model, which includes:
number
[0009] Preferably, the second solar power generation prediction model is modified based on the average battery temperature and the first relationship to generate a third solar power generation prediction model, which includes the following: Based on the average battery temperature, the second solar power generation prediction model is subjected to a primary modification. Based on the aforementioned first relationship, a second correction is made to the primary correction result to generate a third solar power generation prediction model.
[0010] Preferably, the average battery temperature of the solar power generation module awaiting prediction is determined, and the following is included: The system obtains all battery temperature values for the aforementioned solar power generation modules within a predetermined time period. From all the aforementioned battery temperature values, exclude the battery temperature values where the irradiance is less than a preset threshold. The average battery temperature is determined by the remaining battery temperature value. Based on the average battery temperature, the second solar power generation prediction model is subjected to a primary modification, which includes the following:
number
[0011] Preferably, the first relationship is a linear fitting function. The first relationship of the solar power generation module awaiting prediction is determined and includes the following: The aforementioned solar power generation module, which is waiting for a prediction, acquires multiple battery temperature values within a predetermined time interval, multiple ambient temperature values corresponding to each of the multiple battery temperature values, and multiple irradiance values corresponding to each of the multiple battery temperature values. Based on the aforementioned plurality of battery temperature values, the plurality of ambient temperature values, and the plurality of irradiance values, a linear fitting function is obtained to show that the difference between the battery temperature value and the ambient temperature value exhibits a linear relationship with the irradiance.
number
number
[0012] Preferably, the solar power generation prediction device includes a first model modification module, which is used to modify a first solar power generation prediction model based on a modification coefficient and generate a second solar power generation prediction model. The first solar power generation prediction model is configured based on the battery temperature and irradiance of the solar power generation module. It includes an information judgment module and is used to determine whether the ambient temperature information of a solar power generation module awaiting prediction matches pre-set requirement information. The data confirmation module is included, and if it does not match the pre-set request information, it is used to determine the average battery temperature of the solar power generation module awaiting prediction and a first relationship, the first relationship which displays the relationship between the battery temperature of the solar power generation module awaiting prediction, the ambient temperature and the irradiance. It includes a second model modification module, which is used to modify the second solar power generation prediction model based on the average battery temperature and the first relationship, and to generate a third solar power generation prediction model. It includes a solar power generation power value prediction module and is used to make predictions for the solar power generation power values of the solar power generation module awaiting prediction using the third solar power generation power prediction model.
[0013] Preferably, the computer device includes a memory and a processor. The memory and the processor are communicatively connected to each other. Computer instructions are stored in the memory, and the processor executes the computer instructions to execute any one of the solar power generation power prediction methods.
[0014] Preferably, it is a computer-readable storage medium in which computer instructions are stored, and the computer instructions are used to cause a computer to execute any one of the solar power generation power prediction methods.
[0015] The beneficial effects of the solar power generation power prediction method, device, computer device and storage medium provided by the present invention are as follows. 1. The solar power generation power prediction method provided by the present invention selects a corresponding target weather correction coefficient according to the weather type, and adjusts the solar power generation power value based on the target weather correction coefficient to obtain the target solar power generation power value, so that different weather factors can be fully considered for the influence on the solar power generation module, thereby greatly improving the accuracy of solar power generation power prediction. 2. The solar power generation power prediction method provided by the present invention inputs the device capacity, irradiance value, battery temperature value and actual power generation amount of the corresponding weather type into the correction coefficient prediction model to output the weather correction coefficient of the corresponding weather type, and determines the weather correction coefficients of different weather types with the correction coefficient prediction model and the related data information of different weather types, so that the solar power generation power status of the solar power generation module in different weather conditions can be effectively predicted. 3. The solar power generation power prediction method provided by the present invention modifies the first solar power generation power prediction model by the correction coefficient, considers various factors affecting solar power generation power, namely the dust influence coefficient, the light attenuation loss coefficient in the initial state, and the surface reflection loss coefficient, and can improve the prediction accuracy of solar power generation power. 4. The solar power generation power prediction method provided by the present invention combines two methods: averaging the measured battery temperature of the solar power generation module and linear fitting the battery temperature and irradiance of the solar power generation module. Together, these methods can improve the accuracy of the solar power generation power prediction results for power plants. 5. The solar power generation power prediction method provided by the present invention removes battery temperature values where the irradiance is less than a preset threshold from all battery temperature values. This allows for sufficient consideration of the problem that the accuracy of solar power generation values predicted under the aforementioned conditions is relatively low due to climate differences arising from geographical location differences and the constant dynamic changes in the module temperature of solar power generation modules in accordance with environmental changes, thereby achieving a technical effect that improves prediction accuracy. Furthermore, by averaging the measured battery temperatures of the solar power generation modules, the accuracy of the solar power generation power prediction results for the power plant can be further improved. 6. The solar power generation prediction method provided by the present invention can more accurately reflect the relationship between battery temperature and irradiance by constructing a linear fitting function that displays the correlation between battery temperature and irradiance, and can further improve the accuracy of solar power generation prediction by fully considering that irradiance and battery temperature are major factors that affect solar power generation. The present invention will be further described below in conjunction with the attached drawings and embodiments. [Brief explanation of the drawing]
[0016] [Figure 1] This is a flowchart of a solar power generation power prediction method according to an embodiment of the present invention. [Figure 2] This is a flowchart of another solar power generation prediction method according to an embodiment of the present invention. [Figure 3] This is a flowchart of another solar power generation prediction method according to an embodiment of the present invention. [Figure 4] This is a flowchart of another solar power generation prediction method according to an embodiment of the present invention. [Figure 5] This is a flowchart of another solar power generation prediction method according to an embodiment of the present invention. [Figure 6] This is a schematic diagram showing the output of weather correction coefficients using a linear regression model in an embodiment of the present invention. [Figure 7] This is a schematic diagram of a model representation classified by weather in an embodiment of the present invention. [Figure 8] This is a schematic diagram showing the output of weather correction coefficients using a linear regression model in an embodiment of the present invention. [Figure 9] This is a block diagram of the configuration of a solar power generation power prediction device according to an embodiment of the present invention. [Figure 10] This is a hardware configuration diagram of a computer device according to an embodiment of the present invention. [Modes for carrying out the invention]
[0017] Example 1 As shown in Figure 1, the method for predicting solar power generation includes the following: The first solar power generation prediction model is modified based on the correction coefficients to generate a second solar power generation prediction model. The first solar power generation prediction model is constructed based on the battery temperature and irradiance of the solar power generation module. The system determines whether the ambient temperature information of the solar power generation module awaiting prediction matches the pre-set requirement information. If it does not match the pre-set requirement information, the system determines the average battery temperature of the solar power generation module awaiting prediction and a first relationship, which represents the relationship between the battery temperature, ambient temperature, and irradiance of the solar power generation module awaiting prediction. Based on the average battery temperature and the first relationship, the second solar power generation prediction model is modified to generate a third solar power generation prediction model. Using the aforementioned third solar power generation power prediction model, predictions are made for the solar power generation power values of the solar power generation modules awaiting prediction. Based on the weather type of the solar power generation module for which the forecast is pending, the corresponding target weather correction factor is determined from among several weather correction factors.
[0018] Preferably, the target solar power generation value is obtained by adjusting the solar power generation value based on the target weather correction coefficient.
[0019] Preferably, before determining the corresponding target weather correction factor from multiple weather correction factors, the following is included: Multiple sets of data for different weather types of the aforementioned solar power generation module are obtained in advance, and each set of data includes the device capacity, irradiance value, battery temperature value, and actual power generation amount for the corresponding weather type. The device capacity, irradiance value, battery temperature value, and actual power generation amount for the corresponding weather type are input into the correction coefficient prediction model, and the weather correction coefficient for the corresponding weather type is output.
[0020] Preferably, the correction factor includes a dust effect coefficient, an optical attenuation loss coefficient, and a surface reflection loss coefficient. Based on the correction coefficient, the first solar power generation forecast model is modified to generate a second solar power generation forecast model, which includes:
number
[0021] Preferably, the second solar power generation prediction model is modified based on the average battery temperature and the first relationship to generate a third solar power generation prediction model, which includes the following: Based on the average battery temperature, the second solar power generation prediction model is subjected to a primary modification. Based on the aforementioned first relationship, a second correction is made to the primary correction result to generate a third solar power generation prediction model.
[0022] Preferably, the average battery temperature of the solar power generation module awaiting prediction is determined, and the following is included: The system obtains all battery temperature values for the aforementioned solar power generation modules within a predetermined time period. From all the aforementioned battery temperature values, exclude the battery temperature values where the irradiance is less than a preset threshold. The average battery temperature is determined by the remaining battery temperature value. Based on the average battery temperature, the second solar power generation prediction model is subjected to a primary modification, which includes the following:
number
[0023] Preferably, the first relationship is a linear fitting function. The first relationship of the solar power generation module awaiting prediction is determined and includes the following: The aforementioned solar power generation module, which is waiting for a prediction, acquires multiple battery temperature values within a predetermined time interval, multiple ambient temperature values corresponding to each of the multiple battery temperature values, and multiple irradiance values corresponding to each of the multiple battery temperature values. Based on the aforementioned plurality of battery temperature values, the plurality of ambient temperature values, and the plurality of irradiance values, a linear fitting function is obtained to show that the difference between the battery temperature value and the ambient temperature value exhibits a linear relationship with the irradiance.
number
number
[0024] Preferably, the solar power generation prediction device includes a first model modification module, which is used to modify a first solar power generation prediction model based on a modification coefficient and generate a second solar power generation prediction model. The first solar power generation prediction model is configured based on the battery temperature and irradiance of the solar power generation module. It includes an information judgment module and is used to determine whether the ambient temperature information of a solar power generation module awaiting prediction matches pre-set requirement information. The data confirmation module is included, and if it does not match the pre-set request information, it is used to determine the average battery temperature of the solar power generation module awaiting prediction and a first relationship, the first relationship which displays the relationship between the battery temperature of the solar power generation module awaiting prediction, the ambient temperature and the irradiance. It includes a second model modification module, which is used to modify the second solar power generation prediction model based on the average battery temperature and the first relationship, and to generate a third solar power generation prediction model. It includes a solar power generation power value prediction module and is used to make predictions for the solar power generation power values of the solar power generation module awaiting prediction using the third solar power generation power prediction model.
[0025] Preferably, a computer device, the computer device including memory and a processor. The memory and the processor are connected to each other in communication, computer commands are stored in the memory, and the processor executes any one of the solar power generation prediction methods by executing the computer commands.
[0026] Preferably, a computer-readable storage medium is used to cause a computer to execute any one of the solar power generation prediction methods, wherein computer commands are stored in the computer-readable storage medium, and the computer commands are used to cause a computer to execute any one of the solar power generation prediction methods.
[0027] Example 2 The solar power generation prediction method based on the examples includes the following steps. Step S101: The first solar power generation forecast model is modified based on the correction coefficients, and a second solar power generation forecast model is generated. Specifically, the first solar power generation prediction model is constructed based on the cell temperature and irradiance of the solar power generation module, as shown in the following equation.
number
[0028] Specifically, the second solar power generation prediction model is obtained by modifying the first solar power generation prediction model using various correction factors, such as the dust effect coefficient, the initial state light attenuation loss coefficient, and the surface reflection loss coefficient, as shown in the following equation.
number
[0029] This invention improves the accuracy of predicting solar power generation by modifying the first solar power generation power prediction model and substituting the effects of dust, the initial state of light attenuation of solar power generation modules, and the module surface reflection loss into the solar power generation power prediction process.
[0030] Process S102 determines whether the ambient temperature information of the solar power generation module awaiting prediction matches the pre-set required information. Specifically, the technologies related to solar power generation forecasting do not take into account climate differences due to differences in the geographical location of solar power plants, and the fact that the module temperature of solar power generation modules constantly undergoes dynamic changes in accordance with environmental changes. As a result, the accuracy of the solar power generation values obtained by forecasting under these conditions is relatively low. For example, the deviation of the predicted solar power generation value is larger in locations where the ambient temperature is relatively low. To solve the above problem, the present invention first needs to determine whether the ambient temperature information of the solar power generation modules awaiting forecasting matches the pre-set required information. For example, the average ambient temperature of the solar power generation modules awaiting forecasting is smaller than a pre-set temperature threshold, and the pre-set temperature threshold can be set to a corresponding temperature value depending on the difference in location, but is not specifically limited thereto.
[0031] In process S103, if the pre-set request information does not match, the average battery temperature of the solar power generation module awaiting prediction is determined as the first relationship. Specifically, when the average ambient temperature of a solar power generation module awaiting prediction is lower than a preset temperature threshold, it is necessary to determine the average battery temperature and the first relationship for the solar power generation module awaiting prediction. The average battery temperature can be understood as the average battery temperature within a preset time interval. The first relationship is the relationship between the battery temperature, ambient temperature, and irradiance of the solar power generation module awaiting prediction, and this relationship can be understood as a chart and / or linear fitting function used to display the linear relationship between the battery temperature, ambient temperature, and irradiance.
[0032] Process S104 modifies the second solar power prediction model based on the average battery temperature and the first relationship to generate a third solar power prediction model. The present invention combines two methods—averaging the measured battery temperature of the photovoltaic module and linearly fitting the battery temperature and irradiance of the photovoltaic module—to improve the accuracy of the power generation forecast results for a power plant.
[0033] Process S105: Using the third solar power prediction model, a prediction is made for the solar power values of the solar power generation modules awaiting prediction. Specifically, by inputting the irradiance of the solar power generation modules awaiting prediction into the third solar power generation power prediction model, the solar power generation value of the said solar power generation modules can be output. Here, the irradiance is the average value of the irradiance, for example, the average value of the irradiance per minute.
[0034] This embodiment provides a method for predicting solar power generation, the process comprising the following steps. In step S201, the first solar power generation prediction model is modified based on the correction coefficients to generate a second solar power generation prediction model. The first solar power generation prediction model is constructed based on the battery temperature and irradiance of the solar power generation module. Details are omitted here and should be seen in step S101 of the embodiment shown in Figure 1. In step S202, it is determined whether the ambient temperature information of the solar power generation module awaiting prediction matches the pre-set required information. For details, please refer to step S102 of the embodiment shown in Figure 1, and the details are omitted here. In step S203, if the data does not match the pre-set request information, the average battery temperature of the solar power generation module awaiting prediction and a first relationship are determined. The first relationship represents the relationship between the battery temperature of the solar power generation module awaiting prediction, the ambient temperature, and the irradiance. For details, please refer to step S103 of the embodiment shown in Figure 1, and the details are omitted here. In step S204, the second solar power generation prediction model is modified based on the average battery temperature and the first relationship to generate a third solar power generation prediction model.
[0035] Step S204 specifically includes steps S2041-S2042, as shown in Figure 2. Process S2041: The second solar power generation prediction model is modified based on the average battery temperature. Specifically, as shown in Figure 3, it is necessary to determine the average battery temperature of the solar power generation module before process S2041, which includes the following processes a1-a3. Process a1: Obtain all battery temperature values for the solar power generation module within a predetermined time period. The predetermined time period can be set according to actual conditions and is not specifically limited thereto. Process a2: From all the aforementioned battery temperature values, exclude the battery temperature values in which the radiant temperature is less than a preset threshold. Specifically, the solar power generation module is subject to solar radiation of 120 W / m². 2 Under lower conditions, the sunlight absorbed by the module surface belongs to a diffuse reflection state, the direction of photon motion is disordered, the module cannot perform the photovoltaic effect, and there is no power output. Therefore, the preset threshold is set to 120 W / m 2 It can be installed. Process a3: The average battery temperature is determined based on the remaining battery temperature values.
[0036] Specifically, in the process of determining the average battery temperature, multiple identical time intervals can be set first. Then, the average battery temperature within each time interval is calculated based on the remaining battery temperature values and the number of time intervals. For example, if there are five time intervals, the corresponding battery temperature values are y1, y2, y3, y4, and y5. The average battery temperature within each time interval is y1 + y2 + y3 + y4 + y5 / 5.
[0037] In the aforementioned process S2041, the second solar power generation prediction model can be modified using the following formula and the average battery temperature.
number
[0038] This invention performs a primary correction to the second solar power generation prediction model using the average battery temperature, allowing for sufficient consideration of climate differences between different regions, dynamic differences produced by module temperature time in accordance with environmental changes, and the influence of photovoltaic modules on solar power generation, thereby improving the accuracy of solar power generation prediction in the second solar power generation prediction model after the primary correction.
[0039] Process S2042 involves performing a secondary modification on the primary modification result based on the first relationship to generate a third solar power generation prediction model. Specifically, before process S2042, it is necessary to first determine the initial relationship of the solar power generation modules awaiting prediction, which includes the following processes b1-b2. Process b1 involves obtaining a plurality of battery temperature values within a preset time period of the solar power generation module awaiting prediction, a plurality of ambient temperature values that correspond one-to-one with the plurality of battery temperature values, and a plurality of irradiance values that correspond one-to-one with the plurality of battery temperature values. Specifically, the aforementioned pre-set time period can be set according to the actual circumstances and is not specifically limited here; for example, it could be a quarter or a year. The battery temperature value can be the average battery temperature per minute, the irradiance can be the average irradiance per minute, and the ambient temperature value can also be the average ambient temperature per minute. There is a one-to-one correspondence between the three, for example: average ambient temperature 1 - average battery temperature 1 - average irradiance 1, average ambient temperature 2 - average battery temperature 2 - average irradiance 2. More specifically, when acquiring multiple irradiance values that correspond one-to-one with multiple battery temperature values within a predetermined time frame for a solar power generation module awaiting prediction, it is necessary to analyze and screen these irradiance values, that is, to remove data from non-operating conditions, such as power outage maintenance, rainy weather, and 120W / m². 2 These are lower irradiance data. During the process of removing data from non-operating conditions, the irradiance is processed using the box plot method. That is, the power generation is divided into sections, and a box plot is created for the irradiance within each section. The corresponding outliers are identified and filtered out. Using the irradiance data filtered by the box plot, the Cook distance for each irradiance data can be calculated. If the Cook distance is greater than a predetermined multiple of the average distance, the irradiance data is recognized as an outlier and needs to be filtered out.
[0040] Process b2 involves obtaining a linear fitting function that shows that the difference between the battery temperature value and the ambient temperature value exhibits a linear relationship with the irradiance, based on the plurality of battery temperature values, the plurality of ambient temperature values, and the plurality of irradiance values. Specifically, multiple sets of data are acquired, each set of data including battery temperature, irradiance corresponding to the battery temperature, and ambient temperature corresponding to the battery temperature. After filtering and screening, a large number of test samples are fitted using the screened data to obtain the relationship between the three: battery temperature, ambient temperature, and irradiance, i.e., solar power generation battery temperature T cell and ambient temperature T aThe difference exhibits a linear relationship with solar irradiance, which allows us to calculate and obtain the actual operating temperature of the solar cell. Specifically, refer to the following formula.
number
[0041] In the process S2042 described above, a secondary modification is performed on the modification result using the following equation and the first relation to generate a third solar power generation prediction model.
number
[0042] Considering that ambient temperature, irradiance, and battery temperature are major factors influencing solar power generation, the present invention obtains a correlation between ambient temperature, irradiance, and battery temperature by fitting a large number of test samples, and then obtains a second solar power generation prediction model by performing a secondary correction on the primary correction result based on the aforementioned correlation, thereby further improving the accuracy of solar power generation prediction.
[0043] In some arbitrary embodiments, as shown in Figure 4, the method also includes steps c1 and c2. In step c1, a corresponding target weather correction factor is determined from among several weather correction factors, depending on the weather type of the solar power generation module for which the forecast is pending. Specifically, weather types are mainly divided into sunny and cloudy. For example, if the weather includes cloudy, overcast, sunny to cloudy, and rain / snow from cloudy to rain / snow, the weather correction coefficients also include corresponding sunny correction coefficients, cloudy correction coefficients, and rain / snow correction coefficients. The appropriate weather correction coefficient is selected according to the weather type and used to adjust the solar power generation value. Step c2 involves adjusting the solar power generation value based on the target weather correction coefficient to obtain the target solar power generation value. Specifically, by selecting a target weather correction coefficient corresponding to the weather type and adjusting the solar power generation value, the accuracy of the prediction of the output target solar power generation value can be improved.
[0044] In some arbitrary embodiments, as shown in Figure 5, the method further includes steps d1 to d2 before determining a corresponding target weather correction factor from a plurality of weather correction factors. Step d1 involves acquiring multiple sets of data for different weather types for the aforementioned solar power generation modules awaiting forecast, with each set of data including the device capacity, irradiance value, battery temperature value, and actual power generation for the corresponding weather type. The solar power generation modules awaiting forecast are those that do not have access to centralized control data or whose centralized control data quality does not meet the training requirements. Specifically, the device capacity represents the maximum power that the solar power generation module can continuously output. The irradiance value can be the daily average irradiance, and is determined by the preset time period for acquiring the data set. If the preset time period is daily, the irradiance value is the daily average irradiance; if the preset time period is monthly, the irradiance value is the monthly average irradiance. The battery temperature value may be the maximum battery temperature, the daily average battery temperature, or the monthly average battery temperature. The actual power generation amount is the actual power generation amount of the solar power generation module. Process d2 involves inputting the device capacity, irradiance value, battery temperature value, and actual power generation amount for the corresponding weather type into a correction coefficient prediction model, and outputting a weather correction coefficient for the corresponding weather type. Specifically, the correction coefficient prediction model uses a linear regression model to obtain the corresponding weather correction coefficients using the linear regression method. The correction coefficient prediction model is expressed as follows:
number
[0045] The aforementioned correction coefficient prediction model outputs weather correction coefficients corresponding to weather types, allowing the prediction results to be investigated in conjunction with actual production scenarios, and further improving the accuracy of the model by considering weather conditions. Considering the optimization of the linear model by training it for each weather type, the model representation classified by weather type is shown in Figure 7 and Table 1, classifying the weather into three types of correction coefficients: (1) sunny, (2) cloudy / overcast / sunny then cloudy, and (3) rain / snow / cloudy then rain. From Table 1, it can be seen that the sunny coefficient is high, the cloudy / overcast coefficient is low, and the rain / snow coefficient is the lowest. From Figure 7, it can be seen that the power generation is highest for sunny conditions, lowest for cloudy / overcast conditions, and lowest for rain / snow. It can be seen that by optimizing the linear model using different weather coefficients, the objective of improving the accuracy of the prediction results can be achieved by linking the solar power generation prediction results with actual production operation scenarios, i.e., different weather types. (Model representation classified by weather type) [Table 1]
[0046] In some arbitrary embodiments, as shown in Figure 8, if a solar power module awaiting forecast is a solar power module that can use centralized control data but cannot drive the data with an inverter, the method further includes the following before determining a corresponding target weather correction factor from among a plurality of weather correction factors: Step e1, wherein multiple sets of centralized control data for different weather types of the forecast-awaiting solar power generation module are obtained in advance, and each set of centralized control data includes output power and irradiance for the corresponding weather type. Process e2 involves preprocessing multiple sets of centralized control data and converting the average irradiance per minute into the average irradiance per 10 minutes. The processed output power and irradiance, along with the device capacity and battery temperature, are input into a linear regression model, and the corresponding sunny coefficient k1, cloudy coefficient k2, and rainy coefficient k3 are output. Specifically, when the solar power generation module awaiting prediction is a solar power generation module that can use centralized control data and operates the data using an inverter, the device capacity data should be replaced with the operating capacity of the inverter data, and the other processes are the same as processes e1 and e2 described above.
[0047] A solar power generation forecasting device is also provided in this embodiment, and is a device for realizing the above embodiment and preferred embodiment, and its description is omitted. As used below, the term "module" can realize a combination of software and / or hardware with a predetermined function. The devices described below are preferably realized in software, but are also conceived as hardware, or a combination of software and hardware.
[0048] This embodiment provides a solar power generation prediction device, as shown in Figure 9. It includes a first model modification module and is used to modify the first solar power generation prediction model based on modification coefficients to generate a second solar power generation prediction model. The first solar power generation prediction model is constructed based on the battery temperature and irradiance of the solar power generation module. It includes an information judgment module and is used to determine whether the ambient temperature information of a solar power generation module awaiting prediction matches pre-set requirement information. The data confirmation module is included, and if it does not match the pre-set request information, it is used to determine the average battery temperature of the solar power generation module awaiting prediction and a first relationship, the first relationship which displays the relationship between the battery temperature of the solar power generation module awaiting prediction, the ambient temperature and the irradiance. It includes a second model modification module, which is used to modify the second solar power generation prediction model based on the average battery temperature and the first relationship, and to generate a third solar power generation prediction model. It includes a solar power generation power value prediction module and is used to make predictions for the solar power generation power values of the solar power generation module awaiting prediction using the third solar power generation power prediction model.
[0049] In some select embodiments, the apparatus also includes the following: A target weather correction coefficient determination module is used to determine a corresponding target weather correction coefficient from among multiple weather correction coefficients based on the weather type of the solar power generation module awaiting forecast. A solar power generation power value adjustment module is used to adjust the solar power generation power value based on the target weather correction coefficient and to obtain the target solar power generation power value.
[0050] In some select embodiments, before determining the corresponding target weather correction factor from a plurality of weather correction factors, the apparatus also includes the following: A data acquisition module is used to acquire multiple sets of data for different weather types of the solar power generation module awaiting forecast, with each set of data including the device capacity, irradiance value, battery temperature value, and actual power generation amount for the corresponding weather type. A weather correction coefficient output module is used to input the device capacity, irradiance value, battery temperature value, and actual power generation amount for the corresponding weather type into a correction coefficient prediction model, and to output a weather correction coefficient for the corresponding weather type.
[0051] In some selectable embodiments, the correction factor includes a dust effect factor, an optical attenuation loss factor, and a surface reflection loss factor. Based on the correction coefficient, the first solar power generation forecast model is modified to generate a second solar power generation forecast model, which includes:
number
[0052] In some optional embodiments, the second model modification module includes the following: A primary correction unit is used to perform a primary correction on the second solar power generation prediction model based on the average battery temperature. This is a secondary correction unit used to perform a secondary correction on the primary correction result based on the first relationship and generate a third solar power generation prediction model.
[0053] In some arbitrary embodiments, the data determination module includes the following: A battery temperature value acquisition unit is used to acquire all battery temperature values within a preset time stage of the solar power generation module waiting for prediction. A battery temperature value removal unit is used to remove battery temperature values from all of the aforementioned battery temperature values in which the irradiance is less than a preset threshold. A battery temperature average value determination unit, used to determine the battery temperature average value based on the remaining battery temperature values.
[0054] The primary correction unit includes:
number
[0055] In some arbitrary embodiments, the first relation is a linear fitting function. The data determination module includes the following: A data acquisition unit used to acquire multiple battery temperature values within a preset time stage of the solar power generation module waiting for prediction, multiple ambient temperature values corresponding to each of the multiple battery temperature values, and multiple irradiance values corresponding to each of the multiple battery temperature values. A linear fitting function determination unit obtains a linear fitting function used to indicate that the difference between the battery temperature value and the ambient temperature value exhibits a linear relationship with the irradiance, based on the plurality of battery temperature values, the plurality of ambient temperature values, and the plurality of irradiance values. The aforementioned linear fitting function includes the following:
number
[0056] The secondary correction unit includes:
number
[0057] Further functional descriptions of each module and unit described above are the same as those of the corresponding embodiments described above and are therefore omitted here.
[0058] A computer device having a solar power generation prediction device, as shown in Figure 9 above, is also provided. As shown in Figure 10, this is a schematic diagram of a computer device provided by any embodiment of the present invention, including one or more processors 10, memory 20, and interfaces for connecting components including high-speed and low-speed interfaces. Each component communicates with one another using different buses and can be mounted on a common motherboard or in other ways as needed. The processors can process instructions to be executed within the computer device, including instructions to be stored in or on the memory for displaying the graphical information of the GUI on an external input / output device such as a display device coupled to the interface. In some arbitrary embodiments, multiple processors and / or multiple buses can be used together with multiple memories as needed. Similarly, multiple computer devices can be connected, and each device can provide some of the necessary operations, such as a server array, a set of blade servers, or a multiprocessor system. Figure 10 shows one processor 10 as an example.
[0059] The processor 10 may be a central processor, a network processor, or a combination thereof. The processor 10 may further include a hardware chip. The aforementioned hardware chip may be an application-specific integrated circuit, a programmable logic device, or a combination thereof. The aforementioned programmable logic device may be a composite programmable logic device, a field-programmable logic gate array, a general-purpose array logic, or any combination thereof.
[0060] The memory 20 described above stores instructions that can be executed by at least one processor 10, which are to be executed by at least one processor 10 in order to carry out the method shown in the above embodiment.
[0061] The memory 20 may include an area for storing programs and an area for storing data. The area for storing programs can store an operating system and application programs necessary for at least one function. The area for storing data may store data created in accordance with the use of the computer device, etc. The memory 20 may also include high-speed random access memory and may include non-temporary memory such as at least one magnetic disk storage device, flash memory device, or other non-temporary solid-state storage device. In some arbitrary embodiments, the memory 20 selectively includes memory configured remotely from the processor 10, and these remote memories may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, a corporate intranet, a local area network, a mobile communication network, and combinations thereof.
[0062] Memory 20 may include volatile memory such as random access memory. Memory may also include non-volatile memory such as flash memory, hard disk drives, and solid-state drives. Memory 20 may also include combinations of the above types of memory.
[0063] The computer device also includes a communication interface 30 for communicating with other devices or communication networks.
[0064] Embodiments of the present invention may also provide a computer-readable storage medium that can implement the methods described above in the embodiments of the present invention as computer code stored on a local storage medium, which can be recorded on hardware, firmware, or a storage medium, or stored on a remote storage medium or non-temporary machine-readable storage medium downloaded over a network. Thus, the methods described herein are processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium may be a magnetic disk, an optical disk, a read-only storage memory, a random-access storage memory, a flash memory, a hard disk, or a solid-state drive. Furthermore, the storage medium may further include combinations of the above types of memory. It is understood that a computer, processor, microprocessor controller, or programmable hardware includes a storage component capable of storing or receiving software or computer code, and when the software or computer code is accessed and executed by the computer, processor, or hardware, the methods described in the embodiments above are implemented.
[0065] While embodiments of the present invention have been described with reference to the drawings, those skilled in the art can make various modifications and variations that fall within the scope defined by the appended claims without departing from the spirit and scope of the invention.
Claims
1. A method for predicting solar power generation, performed by a computer device including a processor, memory, and interface, comprising: Based on the correction coefficient, the first solar power generation prediction model is modified to generate a second solar power generation prediction model, the first solar power generation prediction model being constructed based on the battery temperature and irradiance of the solar power generation module. The system determines whether the ambient temperature information of the solar power generation module awaiting prediction matches the pre-set requirement information. If it does not match the pre-set requirement information, it determines the average battery temperature of the solar power generation module and a first relationship, which represents the relationship between the battery temperature, ambient temperature, and irradiance of the solar power generation module awaiting prediction. Based on the average battery temperature and the first relationship, the second solar power generation prediction model is modified to generate a third solar power generation prediction model. Using the third solar power generation power prediction model, a prediction is made for the solar power generation power values of the solar power generation modules awaiting prediction. A method for predicting solar power generation, characterized by determining a corresponding target weather correction coefficient from among multiple weather correction coefficients based on the weather type of the solar power generation module awaiting prediction.
2. The solar power generation power prediction method according to claim 1, characterized in that an adjustment is made to the solar power generation power value based on the target weather correction coefficient to obtain the target solar power generation power value.
3. Before determining the corresponding target weather correction factor from multiple weather correction factors, include the following: Multiple sets of data for the aforementioned solar power generation module under different weather conditions are obtained in advance, and each set of data includes the device capacity, irradiance value, battery temperature value, and actual power generation amount for the corresponding weather condition. The method for predicting solar power generation according to claim 2, characterized in that the device capacity, irradiance value, battery temperature value, and actual power generation amount for the corresponding weather type are input into a correction coefficient prediction model, and a weather correction coefficient for the corresponding weather type is output.
4. The correction factor includes the dust effect factor, the light attenuation loss factor, and the surface reflection loss factor. Based on the correction coefficient, the first solar power generation forecast model is modified to generate a second solar power generation forecast model, which includes: [Math 1]
5. Based on the average battery temperature and the first relationship, the second solar power generation prediction model is modified to generate a third solar power generation prediction model, which includes the following: Based on the average battery temperature, the second solar power generation prediction model is subjected to a primary modification. The solar power generation power prediction method according to claim 1, characterized in that a secondary modification is made to the primary modification result based on the first relationship described above to generate a third solar power generation power prediction model.
6. The average battery temperature of the aforementioned solar power generation module awaiting prediction is determined, and the following is included: The following steps are performed to obtain all battery temperature values for the aforementioned solar power generation modules within a predetermined time period: From all the aforementioned battery temperature values, exclude the battery temperature values in which the irradiance is less than a preset threshold, The average battery temperature is determined by the remaining battery temperature values. Based on the average battery temperature, the second solar power generation prediction model is subjected to a primary modification, including the following: [Math 2]
7. The aforementioned first relationship is a linear fitting function, and the first relationship of the solar power generation module awaiting prediction is determined, and includes the following: The system obtains multiple battery temperature values within a predetermined time stage of the solar power generation module awaiting prediction, multiple ambient temperature values corresponding to each of the multiple battery temperature values, and multiple irradiance values corresponding to each of the multiple battery temperature values. Based on the aforementioned plurality of battery temperature values, the plurality of ambient temperature values, and the plurality of irradiance values, a linear fitting function is obtained to show that the difference between the battery temperature value and the ambient temperature value exhibits a linear relationship with the irradiance. [Math 3] Based on the aforementioned first relationship, a secondary modification is made to the primary modification result to generate a third solar power generation prediction model, which includes the following: [Math 4]
8. A solar power generation power forecasting device, the device including a first model modification module, which is used to modify a first solar power generation power forecasting model based on a modification coefficient and generate a second solar power generation power forecasting model, the first solar power generation power forecasting model being configured based on the battery temperature and irradiance of the solar power generation module, It includes an information judgment module and is used to determine whether the ambient temperature information of a solar power generation module awaiting prediction matches pre-set requirement information. It includes a data confirmation module, and if it does not match the pre-set request information, it is used to determine the average battery temperature of the solar power generation module awaiting prediction and a first relationship, the first relationship displays the relationship between the battery temperature of the solar power generation module awaiting prediction, the ambient temperature and the irradiance, It includes a second model modification module, which is used to modify the second solar power generation prediction model based on the average battery temperature and the first relationship, and to generate a third solar power generation prediction model. A solar power generation power prediction device, characterized in that it includes a solar power generation power value prediction module and is used to make predictions for the solar power generation power values of the solar power generation module awaiting prediction using the third solar power generation power prediction model.
9. A computer device, including memory and a processor, A computer device characterized in that the memory and the processor are connected to each other in communication, computer commands are stored in the memory, and the processor executes the solar power generation power prediction method according to any one of claims 1 to 7 by executing the computer commands.
10. A computer-readable storage medium, A computer-readable storage medium characterized in that computer commands are stored in the computer-readable storage medium, and the computer commands are used to cause a computer to execute the solar power generation power prediction method described in any one of claims 1 to 7.