A distributed photovoltaic power generation power prediction system and method

Abstract

The present invention discloses a distributed photovoltaic power generation prediction system and method, which belongs to the field of electric energy technology. The present invention selects a number of similar scenes, imports the operation damage data of the photovoltaic power station at the corresponding position of the acquired historical meteorological data into the operation damage judgment strategy to construct a meteorological damage judgment model, imports the selected several similar scene data and the historical operation power data corresponding to the similar scenes into the power generation prediction strategy to make a preliminary prediction of the power generation, imports the power generation obtained by the preliminary prediction into the power generation prediction value calculation formula to finally derive the power generation prediction value, based on the acquisition of similar scenes and the construction of the meteorological damage judgment model, avoids the interference of irrelevant data, and improves the prediction accuracy of photovoltaic power generation under complex weather conditions.

Description

Technical Field

[0001] The present invention belongs to the technical field of electric energy, and specifically relates to a distributed photovoltaic power generation power prediction system and method. Background Art

[0002] At present, distributed photovoltaic power generation prediction refers to the prediction of the power generation of distributed photovoltaic power generation systems in the future through certain methods and technologies. This prediction is helpful for grid dispatching, power system management and the optimal operation of photovoltaic power generation equipment. Distributed photovoltaic power generation prediction mainly depends on the characteristics of photovoltaic power generation systems and meteorological factors, such as solar irradiance, temperature, humidity, etc.

[0003] For example, a Chinese patent with publication number CN116667318A discloses a photovoltaic power generation power prediction method, which belongs to the field of electric power energy technology. It includes the following steps: obtaining the original meteorological data and photovoltaic output data of the photovoltaic power station; calculating the mean, standard deviation, skewness coefficient and kurtosis of the historical power data in the original meteorological data and photovoltaic output data of the photovoltaic power station as input factors of the improved K-means algorithm, using the improved K-means algorithm to perform cluster analysis on the input factors, and calculating the correlation between meteorological data and power generation in different clustering categories; using meteorological data with a correlation with power generation greater than 0.6 as input factors of the prediction model into the Attention-LSTM model, training the model to obtain the optimal parameters, and outputting the final prediction results. Based on the improved K-means clustering and Attention-LSTM network model, the accuracy of photovoltaic power prediction can be greatly improved, which has engineering application value;

[0004] At the same time, for example, a Chinese patent with publication number CN114825328A provides a short-term photovoltaic power prediction method and system, including: obtaining an original meteorological data sequence and a photovoltaic power data sequence, and normalizing the original meteorological data sequence; decomposing the photovoltaic power data sequence to obtain N groups of intrinsic mode function components and residual components; normalizing the N groups of intrinsic mode function components and residual components, and then inputting the normalized processing results of the N groups of intrinsic mode function components and residual components and the normalized processing results of the original meteorological data sequence into the trained BiGRU model to obtain a prediction result of short-term photovoltaic power. The method and system can accurately predict short-term photovoltaic power.

[0005] The above patents all have the problems raised by this background technology: the prior art usually collects and analyzes the previous operating data of photovoltaic power generation when predicting photovoltaic power generation. The prior art cannot quickly and accurately clean and screen a large amount of data, and the prediction accuracy of photovoltaic power generation under harsh environments (such as strong winds) is not high. The above problems exist in the prior art. In order to solve these problems, this application designs a distributed photovoltaic power generation power prediction system and method. Summary of the invention

[0006] In view of the deficiencies in the prior art, the present invention proposes a distributed photovoltaic power generation power prediction system and method. The present invention obtains historical operating power data and historical meteorological data during the operation of historical photovoltaic power stations, and simultaneously obtains operating damage data of photovoltaic power stations at locations corresponding to the historical meteorological data, imports the acquired historical operating power data and historical meteorological data into a data screening strategy to screen similar scenes, screens out several similar scenes, imports the operating damage data of photovoltaic power stations at locations corresponding to the acquired historical meteorological data into an operating damage judgment strategy to construct a meteorological damage judgment model, imports the screened several similar scene data and the historical operating power data corresponding to the similar scenes into a power generation prediction strategy to perform a preliminary prediction of the power generation, imports the power generation obtained by the preliminary prediction into a power generation prediction value calculation formula to finally derive the power generation prediction value, based on the acquisition of similar scenes and the construction of a meteorological damage judgment model, avoids interference from irrelevant data, and improves the prediction accuracy of photovoltaic power generation under complex weather conditions.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A distributed photovoltaic power generation power prediction method comprises the following specific steps:

[0009] S1. Obtain historical operating power data and historical meteorological data during the operation of the historical photovoltaic power station, and at the same time obtain the operating damage data of the photovoltaic power station at the location corresponding to the historical meteorological data;

[0010] S2. Import the acquired historical operating power data and historical meteorological data into the data screening strategy to screen similar scenes, and screen out several similar scenes;

[0011] S3, importing the photovoltaic power station operation damage data corresponding to the location of the acquired historical meteorological data into the operation damage judgment strategy to construct a meteorological damage judgment model;

[0012] S4, importing the selected data of several similar scenarios and the historical operating power data corresponding to the similar scenarios into the power generation prediction strategy to perform a preliminary prediction of the power generation;

[0013] S5. The generated power obtained by the preliminary prediction is introduced into the generated power prediction value calculation formula to finally derive the generated power prediction value.

[0014] Specifically, S1 includes the following specific steps:

[0015] S11, collecting historical meteorological data of the photovoltaic power station area through a meteorological collection module, wherein the meteorological data includes irradiance, wind force, precipitation, temperature and humidity, and obtaining historical operating power data of the photovoltaic power station at the corresponding historical moment;

[0016] S12. Extracting operation damage data of the photovoltaic power station at the corresponding location under the influence of historical meteorological data through the operation records of equipment maintenance, where the operation damage data includes the number of damaged photovoltaic power generation modules;

[0017] S13. Use historical meteorological data as the first-dimensional vector form, historical operating power data as the second-dimensional vector form, and historical operating damage data as the third-dimensional vector form, and store and transmit historical meteorological data, historical operating power data, and historical operating damage data in the form of three-dimensional vectors.

[0018] Specifically, the specific content of the data screening strategy in S2 is as follows:

[0019] S21, set the monitoring time interval, obtain the stored historical meteorological data and historical operating power data, extract the irradiance, temperature and humidity data of each monitoring time interval in the historical meteorological data, and extract the irradiance, temperature and humidity data in the weather data of the weather forecast in this time interval, and obtain the historical operating power data of each monitoring time in the corresponding historical meteorological data;

[0020] S22, the irradiance, temperature and humidity data of each monitoring time interval in the historical meteorological data and the irradiance, temperature and humidity data in the weather data of the weather forecast in this time interval are introduced into the difference value calculation formula to calculate the difference value, and the difference value calculation formula is: Among them, a i is the proportion coefficient of the ith item in the irradiance, temperature and humidity data in the weather data, k i is the ith item of the irradiance, temperature and humidity data at each monitoring time interval in the historical meteorological data, k i ′ is the ith item of the irradiance, temperature and humidity data in the weather data of the weather forecast in this time interval, where,

[0021] S23, extract the calculated difference value of each historical monitoring time interval and compare it with the set difference threshold, set the monitoring scene of the corresponding historical monitoring time interval whose difference value is less than or equal to the set difference threshold as a similar scene, and set the monitoring scene of the corresponding historical monitoring time interval whose difference value is greater than the set difference threshold as not a similar scene, where a i The process of selecting the difference threshold is to select 500 monitoring scenarios with a corresponding historical monitoring time interval that differs from the rated output power by 5%, substitute the data of the monitoring scenarios into the difference value calculation formula to calculate the difference value, substitute it into the fitting software to fit the data, and obtain a that meets the accuracy rate. i and the difference threshold value.

[0022] Specifically, the specific content of the damage judgment strategy in S3 is:

[0023] The wind force data and duration data in the historical meteorological data and the operation damage data of the photovoltaic power station at the corresponding location are obtained, and the wind force data and duration data in the historical meteorological data and the operation damage data of the photovoltaic power station at the corresponding location are substituted into the damage judgment formula to construct a meteorological damage judgment model, where the damage judgment formula is: Among them, Q is the meteorological damage judgment data, Q1 is the meteorological damage judgment data corresponding to the historical meteorological data, t1 is the duration of exceeding the set wind force in the historical meteorological data, t is the duration of exceeding the set wind force in the current meteorological data, F1 is the average wind force in the historical meteorological data, F is the average wind force in the current meteorological data, V1 is the maximum wind force in the historical meteorological data, V is the maximum wind force in the current meteorological data, λ1 is the duration ratio, λ2 is the average wind force ratio, λ3 is the maximum wind force ratio, and among them, λ1+λ2+λ3=1.

[0024] Specifically, the power generation prediction strategy in S4 includes the following specific steps:

[0025] S41, obtaining a plurality of screened similar scene data and historical operating power data corresponding to the similar scenes, wherein the similar scene data includes radiance, temperature and humidity data, and constructing a deep learning neural network model whose input is radiance, temperature and humidity data and whose output is operating power data;

[0026] S42, dividing the extracted data of several similar scenes and the historical operating power data corresponding to the similar scenes into 70% parameter training sets and 30% parameter test sets; inputting 70% parameter training sets into the deep learning neural network model for training to obtain an initial deep learning neural network model; using 30% parameter test sets to test the initial deep learning neural network model, and outputting the optimal initial deep learning neural network model that meets the accuracy of the operating power data as the deep learning neural network model, wherein the output strategy formula of a specific neuron in the deep learning neural network model is:

[0027] in is the output of n-layer s-term neurons, is the connection weight between the n-1th layer neuron I and the nth layer s-term neuron, represents the output of neuron I in the n-1th layer, represents the bias of the linear relationship between the n-1th layer neuron I and the nth layer s-item neuron, σ() represents the Sigmoid activation function, and m is the number of items in the n-1 layer neuron;

[0028] S43. Obtain the current meteorological data and import it into the constructed deep learning neural network model to output a preliminary predicted value W of the generated power.

[0029] Specifically, S5 includes the following specific contents:

[0030] The wind force data and duration data in the meteorological data are obtained and imported into the meteorological damage judgment model to calculate the meteorological damage judgment data. The calculated meteorological damage judgment data and the preliminary predicted value of the power generation are imported into the power generation predicted value calculation formula to calculate the predicted value. The power generation predicted value calculation formula is: Among them, Q Z is the total number of photovoltaic modules in the photovoltaic power station at the corresponding location.

[0031] Specifically, a distributed photovoltaic power generation prediction system is implemented based on the above-mentioned distributed photovoltaic power generation prediction method, and specifically includes: a data acquisition module, a similar scene judgment module, a meteorological damage judgment model construction module, a power generation preliminary prediction module, a power generation output module and a control module. The data acquisition module is used to obtain historical operating power data and historical meteorological data during the operation of historical photovoltaic power stations, and at the same time obtain the photovoltaic power station operation damage data at the corresponding position of the historical meteorological data. The similar scene judgment module is used to import the acquired historical operating power data and historical meteorological data into the data screening strategy to screen similar scenes, and screen out several similar scenes. The meteorological damage judgment model construction module is used to import the acquired photovoltaic power station operation damage data at the corresponding position of the historical meteorological data into the operation damage judgment strategy to construct a meteorological damage judgment model.

[0032] Specifically, the preliminary power generation prediction module is used to import the screened similar scene data and the historical operating power data corresponding to the similar scenes into the power generation prediction strategy to perform a preliminary prediction of the power generation; the power generation output module is used to import the preliminary predicted power generation into the power generation prediction value calculation formula to finally derive the power generation prediction value; the control module is used to control the operation of the data acquisition module, the similar scene judgment module, the meteorological damage judgment model construction module, the preliminary power generation prediction module, and the power generation output module.

[0033] Specifically, an electronic device includes: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;

[0034] The processor executes the above-mentioned distributed photovoltaic power generation power prediction method by calling the computer program stored in the memory.

[0035] Specifically, a computer-readable storage medium stores instructions, and when the instructions are executed on a computer, the computer executes a distributed photovoltaic power generation power prediction method as described above.

[0036] Compared with the prior art, the present invention has the following beneficial effects:

[0037] The present invention obtains historical operating power data and historical meteorological data during the operation of historical photovoltaic power stations, and simultaneously obtains operating damage data of photovoltaic power stations at positions corresponding to the historical meteorological data, imports the acquired historical operating power data and historical meteorological data into a data screening strategy to screen similar scenes, screens out a number of similar scenes, imports the operating damage data of photovoltaic power stations at positions corresponding to the acquired historical meteorological data into an operating damage judgment strategy to construct a meteorological damage judgment model, imports the screened several similar scene data and the historical operating power data corresponding to the similar scenes into a power generation prediction strategy to perform a preliminary prediction of the power generation, imports the power generation power obtained by the preliminary prediction into a power generation prediction value calculation formula to finally derive the power generation prediction value, and based on the acquisition of similar scenes and the construction of a meteorological damage judgment model, avoids interference from irrelevant data and improves the prediction accuracy of photovoltaic power generation under complex weather conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 A schematic diagram of a distributed photovoltaic power generation power prediction method according to the present invention;

[0039] Figure 2 This is a schematic diagram of a specific process of step S1 of a distributed photovoltaic power generation prediction method of the present invention;

[0040] Figure 3 This is a schematic diagram of a specific process of step S4 of a distributed photovoltaic power generation prediction method of the present invention;

[0041] Figure 4 The present invention is a schematic diagram of a distributed photovoltaic power generation power prediction system architecture. DETAILED DESCRIPTION

[0042] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0043] Example 1

[0044] See also Figure 1-Figure 3 The present invention provides an embodiment: a distributed photovoltaic power generation power prediction method, which includes the following specific steps:

[0045] S1. Obtain historical operating power data and historical meteorological data during the operation of the historical photovoltaic power station, and at the same time obtain the operating damage data of the photovoltaic power station at the location corresponding to the historical meteorological data;

[0046] In this embodiment, S1 includes the following specific steps:

[0047] S11, collecting historical meteorological data of the photovoltaic power station area through a meteorological collection module, wherein the meteorological data includes irradiance, wind force, precipitation, temperature and humidity, and obtaining historical operating power data of the photovoltaic power station at the corresponding historical moment;

[0048] The following is a simple C language code example, which is used to collect the historical meteorological data of the photovoltaic power station area and the historical operating power data of the photovoltaic power station through the meteorological collection module. Please note that this code is only for demonstration purposes and may need to be adjusted according to actual needs and data formats in actual applications;

[0049]

[0050]

[0051]

[0052] This code defines two structures, one for storing weather data and the other for storing PV power plant operation data. The 'getWeatherData' function is used to obtain weather data, and the 'getPowerData' function is used to obtain PV power plant operation data. In the 'main' function, these two functions are called to obtain data and print them to the console. In actual applications, these two functions need to be adjusted according to the data source and format to read data from the corresponding data source (such as a file, database, or network request);

[0053] S12. Extracting operation damage data of the photovoltaic power station at the corresponding location under the influence of historical meteorological data through the operation records of equipment maintenance, where the operation damage data includes the number of damaged photovoltaic power generation modules;

[0054] S13, taking the historical meteorological data as the first dimensional vector form, the historical operating power data as the second dimensional vector form, and the historical operating damage data as the third dimensional vector form, and storing and transmitting the historical meteorological data, the historical operating power data, and the historical operating damage data in the form of three-dimensional vectors;

[0055] S2. Import the acquired historical operating power data and historical meteorological data into the data screening strategy to screen similar scenes, and screen out several similar scenes;

[0056] In this embodiment, the specific content of the data screening strategy in S2 is as follows:

[0057] S21, set the monitoring time interval, obtain the stored historical meteorological data and historical operating power data, extract the irradiance, temperature and humidity data of each monitoring time interval in the historical meteorological data, and extract the irradiance, temperature and humidity data in the weather data of the weather forecast in this time interval, and obtain the historical operating power data of each monitoring time in the corresponding historical meteorological data;

[0058] S22, the irradiance, temperature and humidity data of each monitoring time interval in the historical meteorological data and the irradiance, temperature and humidity data in the weather data of the weather forecast in this time interval are introduced into the difference value calculation formula to calculate the difference value, and the difference value calculation formula is: Among them, a i is the proportion coefficient of the ith item in the irradiance, temperature and humidity data in the weather data, k i is the ith item of the irradiance, temperature and humidity data at each monitoring time interval in the historical meteorological data, k i ′ is the ith item of the irradiance, temperature and humidity data in the weather data of the weather forecast in this time interval, where,

[0059] S23, extract the calculated difference value of each historical monitoring time interval and compare it with the set difference threshold, set the monitoring scene of the corresponding historical monitoring time interval whose difference value is less than or equal to the set difference threshold as a similar scene, and set the monitoring scene of the corresponding historical monitoring time interval whose difference value is greater than the set difference threshold as not a similar scene, where a i The process of selecting the difference threshold is to select 500 monitoring scenarios with a corresponding historical monitoring time interval that differs from the rated output power by 5%, substitute the data of the monitoring scenarios into the difference value calculation formula to calculate the difference value, substitute it into the fitting software to fit the data, and obtain a that meets the accuracy rate. i and the value of the difference threshold;

[0060] S3, importing the photovoltaic power station operation damage data corresponding to the location of the acquired historical meteorological data into the operation damage judgment strategy to construct a meteorological damage judgment model;

[0061] In this embodiment, the specific content of the damage judgment strategy in S3 is:

[0062] The wind force data and duration data in the historical meteorological data and the operation damage data of the photovoltaic power station at the corresponding location are obtained, and the wind force data and duration data in the historical meteorological data and the operation damage data of the photovoltaic power station at the corresponding location are substituted into the damage judgment formula to construct a meteorological damage judgment model, where the damage judgment formula is: Wherein, Q is the meteorological damage judgment data, Q1 is the meteorological damage judgment data corresponding to the historical meteorological data, t1 is the duration of exceeding the set wind force in the historical meteorological data, t is the duration of exceeding the set wind force in the current meteorological data, F1 is the average wind force in the historical meteorological data, F is the average wind force in the current meteorological data, V1 is the maximum wind force in the historical meteorological data, V is the maximum wind force in the current meteorological data, λ1 is the duration ratio, λ2 is the average wind force ratio, λ3 is the maximum wind force ratio, wherein, λ1+λ2+λ3=1;

[0063] S4, importing the selected data of several similar scenarios and the historical operating power data corresponding to the similar scenarios into the power generation prediction strategy to perform a preliminary prediction of the power generation;

[0064] In this embodiment, the power generation prediction strategy in S4 includes the following specific steps:

[0065] S41, obtaining a plurality of screened similar scene data and historical operating power data corresponding to the similar scenes, wherein the similar scene data includes radiance, temperature and humidity data, and constructing a deep learning neural network model whose input is radiance, temperature and humidity data and whose output is operating power data;

[0066] S42, dividing the extracted data of several similar scenes and the historical operating power data corresponding to the similar scenes into 70% parameter training sets and 30% parameter test sets; inputting 70% parameter training sets into the deep learning neural network model for training to obtain an initial deep learning neural network model; using 30% parameter test sets to test the initial deep learning neural network model, and outputting the optimal initial deep learning neural network model that meets the accuracy of the operating power data as the deep learning neural network model, wherein the output strategy formula of a specific neuron in the deep learning neural network model is:

[0067] in is the output of n-layer s-term neurons, is the connection weight between the n-1th layer neuron I and the nth layer s-term neuron, represents the output of neuron I in layer n-1, represents the bias of the linear relationship between the n-1th layer neuron I and the nth layer s-item neuron, σ() represents the Sigmoid activation function, and m is the number of items in the n-1 layer neuron;

[0068] S43, obtaining the current meteorological data, and importing the constructed deep learning neural network model to output a preliminary predicted value W of the generated power;

[0069] S5, importing the generated power obtained by the preliminary prediction into the generated power prediction value calculation formula to finally derive the generated power prediction value;

[0070] In this embodiment, S5 includes the following specific contents:

[0071] The wind force data and duration data in the meteorological data are obtained and imported into the meteorological damage judgment model to calculate the meteorological damage judgment data. The calculated meteorological damage judgment data and the preliminary predicted value of the power generation are imported into the power generation predicted value calculation formula to calculate the predicted value. The power generation predicted value calculation formula is: Among them, Q Z is the total number of photovoltaic modules in the photovoltaic power station at the corresponding location.

[0072] Through this embodiment, it can be achieved that: the present invention obtains historical operating power data and historical meteorological data during the operation of historical photovoltaic power stations, and simultaneously obtains operating damage data of photovoltaic power stations at positions corresponding to the historical meteorological data, imports the obtained historical operating power data and historical meteorological data into the data screening strategy to screen similar scenes, screens out several similar scenes, imports the operating damage data of photovoltaic power stations at positions corresponding to the obtained historical meteorological data into the operating damage judgment strategy to construct a meteorological damage judgment model, imports the screened several similar scene data and the historical operating power data corresponding to the similar scenes into the power generation power prediction strategy to make a preliminary prediction of the power generation power, imports the power generation power obtained by the preliminary prediction into the power generation power prediction value calculation formula to finally derive the power generation power prediction value, based on the acquisition of similar scenes and the construction of the meteorological damage judgment model, the interference of irrelevant data is avoided, and the prediction accuracy of photovoltaic power generation power under complex weather conditions is improved.

[0073] Example 2

[0074] like Figure 4As shown, a distributed photovoltaic power generation power prediction system is implemented based on the above-mentioned distributed photovoltaic power generation power prediction method, which specifically includes: a data acquisition module, a similar scene judgment module, a meteorological damage judgment model construction module, a power generation preliminary prediction module, a power generation output module and a control module. The data acquisition module is used to obtain the historical operating power data and historical meteorological data during the operation of the historical photovoltaic power station, and at the same time obtain the photovoltaic power station operation damage data at the location corresponding to the historical meteorological data. The similar scene judgment module is used to import the acquired historical operating power data and historical meteorological data into the data screening strategy to screen similar scenes, and screen out several similar scenes. The meteorological damage judgment model The model construction module is used to import the operation damage data of the photovoltaic power station at the corresponding position of the historical meteorological data into the operation damage judgment strategy to construct the meteorological damage judgment model; the preliminary power generation prediction module is used to import the screened similar scene data and the historical operation power data corresponding to the similar scenes into the power generation prediction strategy to make a preliminary prediction of the power generation; the power generation output module is used to import the power generation obtained by the preliminary prediction into the power generation prediction value calculation formula to finally derive the power generation prediction value; the control module is used to control the operation of the data acquisition module, the similar scene judgment module, the meteorological damage judgment model construction module, the power generation preliminary prediction module, and the power generation output module.

[0075] Example 3

[0076] This embodiment provides an electronic device, including: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;

[0077] The processor executes the above-mentioned distributed photovoltaic power generation power prediction method by calling the computer program stored in the memory.

[0078] The electronic device may have relatively large differences due to different configurations or performances, and may include one or more processors (Central Processing Units, CPU) and one or more memories, wherein the memory stores at least one computer program, which is loaded and executed by the processor to implement a distributed photovoltaic power generation power prediction method provided by the above method embodiment. The electronic device may also include other components for implementing the functions of the device, for example, the electronic device may also have components such as a wired or wireless network interface and an input and output interface to input and output data. This embodiment will not be described in detail here.

[0079] Example 4

[0080] This embodiment provides a computer-readable storage medium having a rewritable computer program stored thereon;

[0081] When the computer program runs on a computer device, the computer device executes the above-mentioned distributed photovoltaic power generation power prediction method.

[0082] For example, the computer readable storage medium can be a read-only memory (ROM), a random access memory (RAM), a compact disc (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, etc.

[0083] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0084] It should be understood that determining B based on A does not mean determining B only based on A. B can also be determined based on A and / or other information.

[0085] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When a computer instruction or computer program is loaded or executed on a computer, a process or function according to an embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center through a wired network or / and a wireless network. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0086] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0087] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0088] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only one, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0089] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0090] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0091] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0092] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the specific implementation methods of the invention. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A distributed photovoltaic power generation power prediction method, characterized in that: It includes the following specific steps: S1. Obtain historical operating power data and historical meteorological data during the operation of the historical photovoltaic power station, and at the same time obtain the operating damage data of the photovoltaic power station at the location corresponding to the historical meteorological data; S2. Import the acquired historical operating power data and historical meteorological data into the data screening strategy to screen similar scenes, and screen out several similar scenes; S3, importing the photovoltaic power station operation damage data corresponding to the location of the acquired historical meteorological data into the operation damage judgment strategy to construct a meteorological damage judgment model; S4, importing the selected data of several similar scenarios and the historical operating power data corresponding to the similar scenarios into the power generation prediction strategy to perform a preliminary prediction of the power generation; S5, importing the generated power obtained by the preliminary prediction into the generated power prediction value calculation formula to finally derive the generated power prediction value; The specific content of the data screening strategy in S2 is as follows: S21, set the monitoring time interval, obtain the stored historical meteorological data and historical operating power data, extract the irradiance, temperature and humidity data of each monitoring time interval in the historical meteorological data, and extract the irradiance, temperature and humidity data in the weather data of the weather forecast in this time interval, and obtain the historical operating power data of each monitoring time in the corresponding historical meteorological data; S22, the irradiance, temperature and humidity data of each monitoring time interval in the historical meteorological data and the irradiance, temperature and humidity data in the weather data of the weather forecast in this time interval are introduced into the difference value calculation formula to calculate the difference value, and the difference value calculation formula is: Among them, a i is the proportion coefficient of the ith item in the irradiance, temperature and humidity data in the weather data, k i is the ith item of the irradiance, temperature and humidity data at each monitoring time interval in the historical meteorological data, k i ′ is the ith item of the irradiance, temperature and humidity data in the weather data of the weather forecast in this time interval, where, S23, extract the calculated difference value of each historical monitoring time interval and compare it with the set difference threshold, set the monitoring scene of the corresponding historical monitoring time interval whose difference value is less than or equal to the set difference threshold as a similar scene, and set the monitoring scene of the corresponding historical monitoring time interval whose difference value is greater than the set difference threshold as not a similar scene; the specific content of the damage judgment strategy in S3 is: The wind force data and duration data in the historical meteorological data and the operation damage data of the photovoltaic power station at the corresponding location are obtained, and the wind force data and duration data in the historical meteorological data and the operation damage data of the photovoltaic power station at the corresponding location are substituted into the damage judgment formula to construct a meteorological damage judgment model, where the damage judgment formula is: Wherein, Q is meteorological damage judgment data, Q1 is meteorological damage judgment data corresponding to historical meteorological data, t1 is the duration of exceeding the set wind force in historical meteorological data, t is the duration of exceeding the set wind force in this meteorological data, F1 is the average wind force in historical meteorological data, F is the average wind force in this meteorological data, V1 is the maximum wind force in historical meteorological data, V is the maximum wind force in this meteorological data, λ1 is the duration ratio, λ2 is the average wind force ratio, λ3 is the maximum wind force ratio, wherein, λ1+λ2+λ3=1; the power generation prediction strategy in S4 includes the following specific steps: S41, obtaining a plurality of screened similar scene data and historical operating power data corresponding to the similar scenes, wherein the similar scene data includes radiance, temperature and humidity data, and constructing a deep learning neural network model whose input is radiance, temperature and humidity data and whose output is operating power data; S42, dividing the extracted data of several similar scenes and the historical operating power data corresponding to the similar scenes into 70% parameter training sets and 30% parameter test sets; inputting 70% parameter training sets into the deep learning neural network model for training to obtain an initial deep learning neural network model; using 30% parameter test sets to test the initial deep learning neural network model, and outputting the optimal initial deep learning neural network model that meets the accuracy of the operating power data as the deep learning neural network model, wherein the output strategy formula of a specific neuron in the deep learning neural network model is: in is the output of n-layer s-term neurons, is the connection weight between the n-1th layer neuron I and the nth layer s-term neuron, represents the output of neuron I in layer n-1, represents the bias of the linear relationship between the n-1th layer neuron I and the nth layer s-item neuron, σ() represents the Sigmoid activation function, and m is the number of items in the n-1 layer neuron; S43, obtaining the meteorological data of this time, and importing the preliminary predicted value W of the output power into the constructed deep learning neural network model; the said S5 includes the following specific contents: The wind force data and duration data in the meteorological data are obtained and imported into the power generation prediction value calculation formula to calculate the meteorological damage judgment data. The calculated meteorological damage judgment data and the preliminary prediction value of the power generation are imported into the power generation prediction value calculation formula to calculate the prediction value. The power generation prediction value calculation formula is: Among them, Q Z is the total number of photovoltaic modules in the photovoltaic power station at the corresponding location.

2. A distributed photovoltaic power generation power prediction method as claimed in claim 1, characterized in that: The S1 comprises the following specific steps: S11, collecting historical meteorological data of the photovoltaic power station area through a meteorological collection module, wherein the meteorological data includes irradiance, wind force, precipitation, temperature and humidity, and obtaining historical operating power data of the photovoltaic power station at the corresponding historical moment; S12. Extracting operation damage data of the photovoltaic power station at the corresponding location under the influence of historical meteorological data through the operation records of equipment maintenance, where the operation damage data includes the number of damaged photovoltaic power generation modules; S13. Use historical meteorological data as the first-dimensional vector form, historical operating power data as the second-dimensional vector form, and historical operating damage data as the third-dimensional vector form, and store and transmit historical meteorological data, historical operating power data, and historical operating damage data in the form of three-dimensional vectors.

3. A distributed photovoltaic power generation power prediction system, which is implemented based on the distributed photovoltaic power generation power prediction method according to any one of claims 1-2, characterized in that: The system specifically includes: a data acquisition module, a similar scenario judgment module, a meteorological damage judgment model construction module, a power generation preliminary prediction module, a power generation output module and a control module. The data acquisition module is used to obtain historical operating power data and historical meteorological data during the operation of historical photovoltaic power stations, and at the same time obtain the photovoltaic power station operation damage data at the corresponding position of the historical meteorological data. The similar scenario judgment module is used to import the acquired historical operating power data and historical meteorological data into the data screening strategy to screen similar scenarios and screen out several similar scenarios. The meteorological damage judgment model construction module is used to import the photovoltaic power station operation damage data at the corresponding position of the acquired historical meteorological data into the operation damage judgment strategy to construct a meteorological damage judgment model.

4. A distributed photovoltaic power generation power prediction system as claimed in claim 3, characterized in that: The preliminary power generation prediction module is used to import the screened similar scene data and the historical operating power data corresponding to the similar scenes into the power generation prediction strategy to perform a preliminary prediction of the power generation; the power generation output module is used to import the power generation obtained by the preliminary prediction into the power generation prediction value calculation formula to finally derive the power generation prediction value; the control module is used to control the operation of the data acquisition module, the similar scene judgment module, the meteorological damage judgment model construction module, the preliminary power generation prediction module, and the power generation output module.

5. An electronic device, characterized in that: include: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; The processor executes the distributed photovoltaic power generation power prediction method described in any one of claims 1-2 by calling the computer program stored in the memory.

6. A computer-readable storage medium, characterized in that: Instructions are stored, and when the instructions are executed on a computer, the computer executes a distributed photovoltaic power generation power prediction method as described in any one of claims 1-2.

Images