Generating capacity prediction method, system and device of distributed photovoltaic equipment and medium

Abstract

The invention relates to the technical field of generating capacity prediction, and provides a generating capacity prediction method, system and device for distributed photovoltaic equipment and a medium, and the method comprises the steps: obtaining historical data of the distributed photovoltaic equipment of a power station, including annual planning and actual generating capacity, generating hours and installed capacity; and setting weights for the related data of the (t-1) th year, and taking the sum of the product as the annual prediction reference electric quantity of the t-th year. Obtaining the actual power generation capacity of the whole year in the first three years, setting a weight to calculate the historical power proportion of a certain month in the tth year, obtaining historical irradiation monthly distribution data, and setting a weight to calculate the monthly comprehensive proportion. And the monthly predicted reference electric quantity is obtained by multiplying the annual predicted reference electric quantity by the monthly comprehensive proportion, so that prediction of the generating capacity of the distributed photovoltaic equipment is realized. The method can accurately predict the future monthly generating capacity.

Description

Technical Field

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

[0002] One of the most critical tasks in the production management of distributed photovoltaic assets is the real-time monitoring and effective management of power generation. This involves not only the continuous tracking of current power generation, but also the accurate prediction of future power generation. The importance of forecasting cannot be ignored, as it is directly related to the operational efficiency and economic benefits of the entire photovoltaic system. Specifically, forecasting work mainly includes two aspects: annual forecast and monthly forecast.

[0003] Annual forecast refers to the estimation of power generation for the whole year, which requires comprehensive consideration of multiple factors, such as seasonal changes, weather conditions, etc. Through in-depth analysis of these factors, a more accurate annual power generation target can be formulated, thus providing a scientific basis for the annual operation plan of the entire photovoltaic system.

[0004] Monthly forecasts are based on annual forecasts and are further refined into monthly power generation estimates. This requires detailed analysis of recent weather forecasts, equipment operation data, etc., so as to adjust the operation strategy in a timely manner to ensure that the power generation each month reaches the expected target. Accurate monthly forecasts can better respond to emergencies, optimize resource allocation, and improve power generation efficiency.

[0005] The existing power generation forecasting method mainly predicts the power generation of the equipment and then the number of power generation hours, and then calculates the predicted power generation according to "total power generation * number of power generation hours = power generation". When predicting the power generation, factors such as equipment attenuation are also considered.

[0006] By predicting the power generation of the equipment, we can further estimate the power generation in the future. However, this method has a significant disadvantage, that is, the accuracy of its prediction results is often not high enough. The main reason for this problem is that the power generation is affected by many factors, including but not limited to the operating status of the equipment, environmental conditions, weather changes, etc.

[0007] In addition, incidental factors also have a significant impact on power generation, such as equipment failures, unexpected weather events, etc. The combined effect of these factors leads to a very large fluctuation in power generation, which results in too many abnormal values, unstable values, and erroneous values ​​in the reference factors during the prediction process, greatly reducing the reliability of the final prediction results. Summary of the invention

[0008] To solve the above problems, the present disclosure provides a method, system, device and medium for predicting power generation of distributed photovoltaic equipment, which uses multiple parameters to calculate monthly power generation and can obtain more accurate prediction results.

[0009] The technology of the present invention includes:

[0010] A method for predicting power generation of distributed photovoltaic equipment, characterized by comprising:

[0011] Obtain the historical data of distributed photovoltaic equipment for a complete cycle of a power station project, including: annual planned power generation, annual actual power generation, annual power generation hours, and installed capacity of the power station;

[0012] Set weights for the annual planned power generation in year t-1, the actual power generation in year t-1, the number of power generation hours in year t-1, and the installed capacity of the power station, and take the sum of the products of the weights and the corresponding variables as the annual forecast benchmark power in year t;

[0013] Obtain the actual annual power generation in the t-1st year, the t-2nd year, and the t-3rd year, and set weights m%, n%, and p% for each year; calculate the historical power generation ratio of a certain month in the tth year, the historical power generation ratio of a certain month = (actual power generation in the month of the t-1st year / actual power generation in the whole year of last year)*m%+(actual power generation in the month of the t-2nd year / actual power generation in the whole year of the t-2nd year)*n%+actual power generation in the month of the t-3rd year / actual power generation in the whole year of the t-3rd year)*P%;

[0014] Obtain historical monthly irradiation distribution data; set the monthly irradiation weight and the historical electricity consumption proportion of a certain month to X% and Y% respectively; and calculate the monthly comprehensive ratio, which is the monthly comprehensive ratio = monthly irradiation weight * X% + historical electricity consumption proportion of a certain month * Y%;

[0015] Calculate the monthly forecast benchmark electricity: monthly forecast benchmark electricity = annual forecast benchmark electricity * monthly comprehensive ratio.

[0016] Further,

[0017] The calculation formula for the annual forecast benchmark electricity volume in year t is:

[0018] Annual forecast benchmark electricity in year t = annual planned power generation in year t-1 * x% + actual power generation in year t-1 * y% + number of power generation hours in year t-1 * installed capacity * z%.

[0019] Further,

[0020] The obtaining of historical monthly irradiation distribution data includes:

[0021] It is calculated based on Meteosat satellite remote sensing data, combined with cloud index and snowfall index from Meteosat and GOES, water vapor data from the GFS database, atmospheric optical thickness data from the MACC database, snow thickness data from GFS and CSFR, and digital terrain data from SRTM-3.

[0022] Further,

[0023] The obtaining of annual power generation hours includes:

[0024] Obtain the number of power generation hours A in the first year, and use the number of power generation hours A at the end of the first year as the number of power generation hours at the beginning of the second year;

[0025] Obtain the annual attenuation rate of the equipment in the second year, multiply the number of generating hours at the beginning of the second year by the annual attenuation rate, and obtain the number of generating hours B in the second year.

[0026] Further,

[0027] The complete cycle of a project is 20-25 years.

[0028] Further,

[0029] The historical monthly irradiation distribution data is analyzed using the Solargis database, and the analysis results are given.

[0030] Further,

[0031] It also includes calculating the predicted power generation for the remaining days, using the following formula:

[0032] The predicted power consumption in the remaining days = [the average power generation in the last 10 days * K% + the average actual power consumption in this month last year * L%] * the remaining days

[0033] Among them, K% refers to the weight of power generation in the last 10 days; L% refers to the weight of power generation in the same period of this month last year.

[0034] A distributed photovoltaic power generation prediction system, characterized by comprising:

[0035] The annual power forecast module is used to obtain the historical data of distributed photovoltaic equipment for a complete cycle of a power station project. The historical data includes: annual planned power generation, annual actual power generation, annual power generation hours, and installed capacity of the power station;

[0036] Set weights for the annual planned power generation in year t-1, the actual power generation in year t-1, the number of power generation hours in year t-1, and the installed capacity of the power station, and take the sum of the products of the weights and the corresponding variables as the annual forecast benchmark power in year t;

[0037] Monthly historical electricity proportion calculation module is used to obtain the actual annual power generation in the t-1st year, the t-2nd year, and the t-3rd year, and set weights m%, n%, and p% for each year; calculate the historical electricity proportion of a certain month in the tth year, and the historical electricity proportion of a certain month = (actual power generation in the month of the t-1st year / actual power generation in the whole year of last year)*m%+(actual power generation in the month of the t-2nd year / actual power generation in the whole year of the t-2nd year)*n%+actual power generation in the month of the t-3rd year / actual power generation in the whole year of the t-3rd year)*P%;

[0038] Monthly comprehensive ratio calculation module, used to obtain historical irradiation monthly distribution data; set the monthly irradiation weight and the historical electricity proportion of a certain month to X% and Y% respectively; and calculate the monthly comprehensive ratio, monthly comprehensive ratio = monthly irradiation weight * X% + historical electricity proportion of a certain month * Y%;

[0039] The monthly forecast benchmark electricity calculation module is used to calculate the monthly forecast benchmark electricity. The monthly forecast benchmark electricity = annual forecast benchmark electricity * monthly comprehensive ratio.

[0040] Compared with the prior art, the present invention has the following advantages:

[0041] The present invention improves the accuracy of power generation forecast by integrating multi-dimensional data. It is no longer limited to the power generation of equipment and the number of hours of power generation, but incorporates data such as historical power generation and monthly distribution of irradiation. The historical power generation data covers many years and sets weights to consider the impact of different years on the forecast; the monthly distribution of irradiation integrates information from multiple satellites and databases to reflect the actual situation of solar irradiation.

[0042] By setting and adjusting weights for different data factors, the contribution of each factor to the forecast results can be optimized according to the actual situation. The annual and monthly forecast benchmark electricity is calculated in stages to make the forecast more detailed and accurate, avoiding the inaccuracy caused by factors such as large fluctuations in power generation.

[0043] Other features and advantages of the present disclosure will be described in the following description, and partly become apparent from the description, or be understood by implementing the present disclosure. The purpose and other advantages of the present disclosure can be realized and obtained by the structures pointed out in the description, claims and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0045] Figure 1 A schematic diagram of the method of the present invention is shown;

[0046] Figure 2 Shown is the overall flow chart of the present invention;

[0047] Figure 3 A schematic diagram of the parameter structure of the present invention is shown. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0049] The business scenario involved in the present invention is distributed photovoltaics, which has significant differences in asset characteristics compared to centralized photovoltaics, including that the installation locations of power stations are relatively scattered and cross-regional; the installed capacity is relatively small, generally ranging from a few kilowatts to several megawatts; the number of power stations is large; and the operation and maintenance work is relatively simple, but relatively complicated.

[0050] The actual business demand solved by the present invention is the prediction of monthly / annual power generation by the management department of distributed photovoltaic power stations, which is generally used for production planning management and budget management. The management department generally predicts the power generation of the power station at the beginning of the month, the end of the month, the beginning of the year, and the end of the year, and compares the power generation target set by the company for the power station, so as to adjust the operation strategy and maintenance plan in time. It is more ideal to be able to accurately predict the power generation of the month, so as to better arrange power sales, charge and discharge plans of energy storage equipment, and respond to changes in grid demand. Through more accurate power forecasting, the economic benefits and energy efficiency of distributed photovoltaic systems can be maximized.

[0051] The power generation forecast of distributed photovoltaic power stations refers to the prediction of power generation in a future period at a certain point in time. The influencing factors generally involved include weather conditions, solar radiation intensity, equipment operating status, and whether there are obstructions.

[0052] Weather conditions involve basic classifications such as sunny, cloudy, and rainy days. Changes in solar radiation intensity directly affect the power generation efficiency of photovoltaic panels, while the equipment status involves the cleanliness, aging, and integrity of electrical connections of photovoltaic panels. In addition, shading by buildings or other objects can also have a significant impact on power generation.

[0053] The main purpose of the power generation prediction method described in the present invention is to realize online statistical analysis of many influencing factors such as historical power generation, weather conditions, irradiation data, regional power generation data, etc. through digital system application, and ultimately more accurately predict the power generation data of the specified period in the future.

[0054] Figure 1 , Figure 2 A schematic diagram of the method according to the present invention is shown, and the specific implementation details of the present invention include:

[0055] Calculate the annual forecast base electricity volume:

[0056] 1. Step 1: Configure economic calculation data factors

[0057] Step 1.1: Based on the project-related planning and feasibility study, adopt the annual forecast of power generation for the complete project cycle (generally 20-25 years);

[0058] Step 1.2: The system automatically detects and checks for abnormal values.

[0059] 2. Step 2: Configure equipment efficiency data factors

[0060] Step 2.1, according to the equipment conditions, configure the power at the beginning of the first year of the project, the annual attenuation rate, and the power at the end of the year. The system verifies the logic rationality, "power at the end of this year = power at the beginning of the year - annual attenuation rate";

[0061] Step 2.2, based on the project-related planning and feasibility study, obtain the annual power generation hours for the complete project cycle (generally 20-25 years);

[0062] Obtaining annual power generation hours, including:

[0063] Obtain the number of power generation hours A in the first year, and use the number of power generation hours A at the end of the first year as the number of power generation hours at the beginning of the second year;

[0064] Obtain the annual attenuation rate of the equipment in the second year, multiply the number of generating hours at the beginning of the second year by the annual attenuation rate, and obtain the number of generating hours B in the second year.

[0065] 3. Step 3:

[0066] Step 3.1, initialize the weights of annual planned power generation, historical power generation, and power generation hours*installed capacity to x%, y%, and z% respectively;

[0067] Step 3.2, as the accuracy of the subsequent final prediction data increases, the factors are adjusted appropriately to continuously improve the accuracy.

[0068] 4. Step 4: Calculate the annual forecast base electricity

[0069] Annual forecast base electricity quantity = economic data*x%+historical electricity quantity*y%+generating hours*installed capacity*z%. (Parameter structure as Figure 3 (shown)

[0070] Calculate the monthly forecast base electricity consumption:

[0071] 1. Step 1: Reference historical power consumption ratio

[0072] Step 1.1, select the forecast target year;

[0073] Step 1.2, the system retrieves the completeness of power generation in the target year t-1, t-2, and t-3;

[0074] Step 1.3, configure the proportion coefficients of the corresponding years as m%, n%, and p% according to the power generation completeness.

[0075] 2. Step 2: Configure monthly proportion

[0076] Step 2.1, reference the monthly irradiance distribution configured in the annual parameters;

[0077] Step 2.2, calculate the historical electricity consumption ratio based on the above year ratio coefficient. The specific formula is:

[0078] The historical electricity proportion of a certain month = (actual power generation of the same month last year / actual power generation of the whole year last year) * m% + (actual power generation of the same month in the t-1st year / actual power generation of the whole year in the t-1st year) * n% + actual power generation of the same month in the t-2nd year / actual power generation of the whole year in the t-2nd year) * P%

[0079] Step 2.3: Configure the monthly manual adjustment ratio based on historical forecasts.

[0080] 3. Step 3: Configure monthly irradiation distribution

[0081] Step 3.1, the irradiation data analysis is performed using the Solargis database, and the analysis results are given. The radiation data used by SolarGIS is based on Meteosat satellite remote sensing data, combined with cloud index and snowfall index from Meteosat and GOES, water vapor data from the GFS database, atmospheric optical thickness data from the MACC database, GFS and CSFR and snow thickness data, and digital terrain data from SRTM-3, and the final calculation is obtained.

[0082] Step 3.2: The user configures the monthly distribution ratio based on the above results.

[0083] Monthly irradiation distribution data is data that reflects the distribution of solar irradiation at different times of the month. It integrates information from multiple satellites and databases to calculate the monthly comprehensive ratio and then predict the power generation of distributed photovoltaic equipment.

[0084] Data example: The monthly distribution data of irradiation may show a trend that the irradiation is relatively low in January, gradually increases with the change of seasons, reaches a high level in summer, and then gradually decreases in autumn. For example, the monthly irradiation may account for 8.5% in January, 8.7% in February, and may reach a maximum value of about 15% in July, and then drop to a lower level of about 7% in December (the data is only for example, the actual data will vary according to the specific region and year). These data can reflect the changes in solar irradiation intensity in different months and provide an important basis for the prediction of power generation of distributed photovoltaic equipment.

[0085] 4. Step 4: Configure monthly factor weights

[0086] Step 4.1, set the weights of monthly irradiation weight, monthly proportion of historical electricity consumption, and manual adjustment proportion to X%, Y%, and Z%, respectively.

[0087] 5. Step 5: Calculate the monthly comprehensive ratio

[0088] Step 5.1, monthly comprehensive ratio = monthly radiation ratio * X% + actual monthly historical electricity ratio * Y% + adjustment ratio * Z%.

[0089] 6. Step 6: Calculate the monthly forecast base electricity

[0090] Monthly benchmark electricity = annual benchmark electricity * monthly comprehensive ratio.

[0091] The predicted electricity consumption in the remaining days = [the average power generation in the last 10 days * K% + the average actual electricity consumption in this month last year * L%] * the number of remaining days.

[0092] Among them, K% refers to the weight of power generation in the last 10 days; L% refers to the weight of power generation in the same period of this month last year.

[0093] Based on the method of the present invention, the embodiment of the present disclosure also provides a prediction system corresponding to the above method, which includes:

[0094] The annual power forecast module is used to obtain the historical data of distributed photovoltaic equipment for a complete cycle of a power station project. The historical data includes: annual planned power generation, annual actual power generation, annual power generation hours, and installed capacity of the power station;

[0095] Set weights for the annual planned power generation in year t-1, the actual power generation in year t-1, the number of power generation hours in year t-1, and the installed capacity of the power station, and take the sum of the products of the weights and the corresponding variables as the annual forecast benchmark power in year t;

[0096] Monthly historical electricity proportion calculation module is used to obtain the actual annual power generation in the t-1st year, the t-2nd year, and the t-3rd year, and set weights m%, n%, and p% for each year; calculate the historical electricity proportion of a certain month in the tth year, and the historical electricity proportion of a certain month = (actual power generation in the month of the t-1st year / actual power generation in the whole year of last year)*m%+(actual power generation in the month of the t-2nd year / actual power generation in the whole year of the t-2nd year)*n%+actual power generation in the month of the t-3rd year / actual power generation in the whole year of the t-3rd year)*P%;

[0097] Monthly comprehensive ratio calculation module, used to obtain historical irradiation monthly distribution data; set the monthly irradiation weight and the historical electricity proportion of a certain month to X% and Y% respectively; and calculate the monthly comprehensive ratio, monthly comprehensive ratio = monthly irradiation weight * X% + historical electricity proportion of a certain month * Y%;

[0098] The monthly forecast benchmark electricity calculation module is used to calculate the monthly forecast benchmark electricity. The monthly forecast benchmark electricity = annual forecast benchmark electricity * monthly comprehensive ratio.

[0099] To sum up: the present invention adopts a power generation prediction method involving multi-dimensional factors such as solar radiation, weather conditions, power attenuation, historical data, and installed capacity. Compared with other prediction methods, it avoids the problem of low prediction accuracy caused by large fluctuations in equipment power and many abnormal values, and effectively helps asset managers improve the management efficiency of power plants.

[0100] Based on the same inventive concept as the above disclosed content, an embodiment of the present disclosure also provides a prediction device corresponding to the above method, which includes at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the above method.

[0101] It should be noted that the electrical connection between the above-mentioned units does not necessarily mean the connection between lines. An indirect connection method can be applied to the embodiments of the present disclosure as long as the purpose of the present disclosure is achieved.

[0102] Based on the same inventive concept, the present disclosure also provides a computer storage medium on which executable instructions are stored. When the instructions are executed by a processor, the processor performs the above method.

[0103] Although the present disclosure has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure.

Claims

1. A method for predicting power generation of distributed photovoltaic equipment, characterized in that: include: Obtain the historical data of distributed photovoltaic equipment for a complete cycle of a power station project, including: annual planned power generation, annual actual power generation, annual power generation hours, and installed capacity of the power station; Set weights for the annual planned power generation in year t-1, the actual power generation in year t-1, the number of power generation hours in year t-1, and the installed capacity of the power station, and take the sum of the products of the weights and the corresponding variables as the annual forecast benchmark power in year t; Obtain the actual annual power generation in the t-1st year, the t-2nd year, and the t-3rd year, and set weights m%, n%, and p% for each year; calculate the historical power generation ratio of a certain month in the tth year, the historical power generation ratio of a certain month = (actual power generation in the month of the t-1st year / actual power generation in the whole year of last year)*m%+(actual power generation in the month of the t-2nd year / actual power generation in the whole year of the t-2nd year)*n%+actual power generation in the month of the t-3rd year / actual power generation in the whole year of the t-3rd year)*P%; Obtain historical monthly irradiation distribution data; set the monthly irradiation weight and the historical electricity consumption proportion of a certain month to X% and Y% respectively; and calculate the monthly comprehensive ratio, which is the monthly comprehensive ratio = monthly irradiation weight * X% + historical electricity consumption proportion of a certain month * Y%; Calculate the monthly forecast benchmark electricity: monthly forecast benchmark electricity = annual forecast benchmark electricity * monthly comprehensive ratio.

2. The method for predicting power generation of distributed photovoltaic equipment according to claim 1, characterized in that: The calculation formula for the annual forecast benchmark electricity volume in year t is: Annual forecast benchmark electricity in year t = annual planned power generation in year t-1 * x% + actual power generation in year t-1 * y% + number of power generation hours in year t-1 * installed capacity * z%.

3. The method for predicting power generation of distributed photovoltaic equipment according to claim 1, characterized in that: The obtaining of historical monthly irradiation distribution data includes: It is calculated based on Meteosat satellite remote sensing data, combined with cloud index and snowfall index from Meteosat and GOES, water vapor data from the GFS database, atmospheric optical thickness data from the MACC database, snow thickness data from GFS and CSFR, and digital terrain data from SRTM-3.

4. The method for predicting power generation of distributed photovoltaic equipment according to claim 1, characterized in that: The obtaining of annual power generation hours includes: Obtain the number of power generation hours A in the first year, and use the number of power generation hours A at the end of the first year as the number of power generation hours at the beginning of the second year; Obtain the annual attenuation rate of the equipment in the second year, multiply the number of generating hours at the beginning of the second year by the annual attenuation rate, and obtain the number of generating hours B in the second year.

5. The method for predicting power generation of distributed photovoltaic equipment according to claim 4, characterized in that: The complete cycle of a project is 20-25 years.

6. The method for predicting power generation of distributed photovoltaic equipment according to claim 1, characterized in that: The historical monthly irradiation distribution data is analyzed using the Solargis database, and the analysis results are given.

7. The method for predicting power generation of distributed photovoltaic equipment according to claim 1, characterized in that: It also includes calculating the predicted power generation for the remaining days, using the following formula: The predicted power consumption in the remaining days = [the average power generation in the last 10 days * K% + the average actual power consumption in this month last year * L%] * the remaining days Among them, K% refers to the weight of power generation in the last 10 days; L% refers to the weight of power generation in the same period of this month last year.

8. A distributed photovoltaic power generation prediction system, characterized in that: include: The annual power forecast module is used to obtain the historical data of distributed photovoltaic equipment for a complete cycle of a power station project. The historical data includes: annual planned power generation, annual actual power generation, annual power generation hours, and installed capacity of the power station; Set weights for the annual planned power generation in year t-1, the actual power generation in year t-1, the number of power generation hours in year t-1, and the installed capacity of the power station, and take the sum of the products of the weights and the corresponding variables as the annual forecast benchmark power in year t; Monthly historical electricity proportion calculation module is used to obtain the actual annual power generation in the t-1st year, the t-2nd year, and the t-3rd year, and set weights m%, n%, and p% for each year; calculate the historical electricity proportion of a certain month in the tth year, and the historical electricity proportion of a certain month = (actual power generation in the month of the t-1st year / actual power generation in the whole year of last year)*m%+(actual power generation in the month of the t-2nd year / actual power generation in the whole year of the t-2nd year)*n%+actual power generation in the month of the t-3rd year / actual power generation in the whole year of the t-3rd year)*P%; Monthly comprehensive ratio calculation module, used to obtain historical irradiation monthly distribution data; set the monthly irradiation weight and the historical electricity proportion of a certain month to X% and Y% respectively; and calculate the monthly comprehensive ratio, monthly comprehensive ratio = monthly irradiation weight * X% + historical electricity proportion of a certain month * Y%; The monthly forecast benchmark electricity calculation module is used to calculate the monthly forecast benchmark electricity. The monthly forecast benchmark electricity = annual forecast benchmark electricity * monthly comprehensive ratio.

9. A distributed photovoltaic device power generation prediction device, comprising: at least one processor; And a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the power generation prediction method of the distributed photovoltaic equipment described in any one of claims 1 to 7.

10. A computer storage medium having executable instructions stored thereon, wherein when the instructions are executed by a processor, the processor is enabled to implement the method according to any one of claims 1 to 7.

Images