A control method, system and readable storage medium based on photovoltaic inverter

Abstract

The present invention provides a control method, system and readable storage medium based on photovoltaic inverters. The present invention senses the temperature data of each photovoltaic module in real time through a temperature sensor, finds out risk photovoltaic modules according to a corresponding evaluation method, and compares the temperature data of risk photovoltaic modules with the threshold value corresponding to the hot spot effect, so as to accurately and effectively identify the hot spot effect, and timely interrupt the control through the photovoltaic inverter when the hot spot effect occurs, so as to avoid affecting the power grid. At the same time, the power grid control device of the present invention is based on the standard Modbus protocol, establishes a diversified data extension library and performs local storage, and can identify the data items and communication protocols extended by the photovoltaic inverter on the standard Modbus protocol through the corresponding extension protocol matching method, so as to realize automatic adaptation to the communication protocols of different photovoltaic inverters for effective communication, and solve the problem of communication failure caused by protocol incompatibility.

Description

Technical Field

[0001] The present invention relates to the field of photovoltaic power generation and temperature measurement technology, and in particular to a control method, system and readable storage medium based on a photovoltaic inverter. Background Art

[0002] Photovoltaic power generation system is composed of solar panels, charging controller, photovoltaic inverter and battery; photovoltaic inverter is also called power regulator, power conditioner, which is an indispensable part of photovoltaic power generation system. The main function of photovoltaic inverter is to convert the direct current generated by solar panels into alternating current used by household appliances. All the electricity generated by solar panels must be processed by inverter before it can be output. The core of photovoltaic inverter is inverter switch circuit, referred to as inverter circuit. This circuit completes the inverter function by turning on and off the power electronic switch. The on and off of power electronic switch devices requires certain driving pulses, which may be adjusted by changing a voltage signal. The circuit that generates and adjusts pulses is usually called control circuit or control loop. The basic structure of photovoltaic inverter, in addition to the above-mentioned inverter circuit and control circuit, also includes protection circuit, output circuit, input circuit, output circuit, etc.

[0003] Under certain conditions, defective areas in photovoltaic modules (such as obstruction, cracks, bubbles, delamination, dirt, internal connection failure, etc.) are treated as loads to consume the energy generated by other areas, resulting in local overheating. This phenomenon is called the "hot spot effect" of photovoltaic modules. The hot spot effect can cause permanent damage such as local burning of batteries to form dark spots, melting of solder joints, and aging of packaging materials. It is an important factor affecting the output power and service life of photovoltaic modules, and may even cause safety hazards. Therefore, how to accurately and effectively identify the hot spot effect and promptly interrupt the control through the photovoltaic inverter when the hot spot effect occurs to avoid affecting the power grid is an urgent problem to be solved.

[0004] At the same time, photovoltaic power generation systems are being integrated into the power grid on a large scale, and a common problem has emerged that needs to be solved urgently: the communication protocol from the photovoltaic inverter to the power grid generally follows the Modbus protocol. Photovoltaic inverters from different manufacturers and even different models of photovoltaic inverters from the same manufacturer will also have their own protocol extensions, which leads to obvious differences in communication protocols. In addition, the power grid company has no authority to constrain photovoltaic inverter manufacturers to adopt a unified communication protocol and data format, resulting in the inability of the two parties to communicate effectively when the power grid control equipment communicates with the photovoltaic inverter to obtain photovoltaic inverter data or issues control instructions to the photovoltaic inverter, and even causes communication failure. Summary of the invention

[0005] In order to solve at least one of the above technical problems, the present invention proposes a control method, system and readable storage medium based on photovoltaic inverters, which can accurately and effectively identify the hot spot effect, and timely interrupt the control through the photovoltaic inverter when the hot spot effect occurs, so as to avoid affecting the power grid. At the same time, it can automatically adapt to the communication protocols of different photovoltaic inverters for effective communication, solving the problem of communication failure caused by protocol incompatibility.

[0006] The first aspect of the present invention provides a control method based on a photovoltaic inverter, the method comprising:

[0007] The preset photovoltaic inverter corresponds to a plurality of photovoltaic modules, a temperature sensor is installed on each photovoltaic module, and the temperature data of the corresponding photovoltaic module is sensed in real time by the temperature sensor;

[0008] The photovoltaic inverter collects the temperature data collected by each temperature sensor on the photovoltaic module and reports it to the grid control equipment;

[0009] The temperature data of each photovoltaic module is calculated separately from the temperature data of other photovoltaic modules to obtain the difference between the two.

[0010] determining whether the difference is greater than a first preset threshold, and if so, marking the former photovoltaic component as an abnormal photovoltaic component;

[0011] After multiple photovoltaic modules corresponding to the photovoltaic inverters are compared with each other, the total number of times each photovoltaic module is marked as an abnormal photovoltaic module is counted;

[0012] Determine whether the total number of times each photovoltaic component is marked as an abnormal photovoltaic component is greater than a second preset threshold, and if so, determine the corresponding photovoltaic component as a risky photovoltaic component;

[0013] It is determined whether the temperature data of the risky photovoltaic assembly exceeds a third preset threshold value. If so, a grid-connection interruption instruction is issued to the photovoltaic inverter, and the grid connection with the photovoltaic inverter is cut off.

[0014] Furthermore, before the photovoltaic inverter collects the temperature data collected by each temperature sensor for the photovoltaic module and reports it to the grid control device, the method also includes:

[0015] A diversified data extension library is established based on the standard Modbus protocol and pre-stored in the local database of the power grid control equipment, wherein the diversified data extension library includes a variety of extended communication protocols based on the standard Modbus protocol;

[0016] Send the first posting information based on the standard Modbus protocol to the photovoltaic inverter;

[0017] Receive the first palindrome information returned by the photovoltaic inverter, and identify therefrom the device identification information of the photovoltaic inverter and the data items extended on the standard Modbus protocol;

[0018] Based on the diversified data extension library, an extended communication protocol of the photovoltaic inverter on the standard Modbus protocol is determined through a preset analytical matching algorithm;

[0019] The extended communication protocol of the photovoltaic inverter on the standard Modbus protocol is associated with the device identification information and stored in a diversified data extension library;

[0020] Based on the extended communication protocol of the photovoltaic inverter on the standard Modbus protocol, a second document information including the control instruction is generated and issued to the photovoltaic inverter.

[0021] Furthermore, based on the diversified data extension library, the extended communication protocol of the photovoltaic inverter on the standard Modbus protocol is determined by a preset analytical matching algorithm, specifically including:

[0022] Build a simulated network conversation model;

[0023] The simulated network dialogue model is trained and optimized through sample data to obtain an optimized simulated network dialogue model;

[0024] Inputting the first posting information into the simulated network dialogue model for prediction to obtain first palindrome prediction information;

[0025] According to the device identification information of the photovoltaic inverter, finding out from the diversified data extension library whether there is an extended communication protocol associated therewith;

[0026] If not, performing corresponding protocol parsing on the first palindrome information by each extended communication protocol of the diversified data extension library to obtain corresponding first palindrome parsing information;

[0027] Calculate the difference between the first palindrome parsing information and the first palindrome prediction information corresponding to each extended communication protocol to obtain a first difference;

[0028] Determining whether the first difference is less than a fourth preset threshold, and if so, adding the corresponding extended communication protocol to the pre-selected protocol library;

[0029] Generate first verification information, and respectively use each extended communication protocol of the pre-selected protocol library to perform protocol encapsulation on the first verification information to obtain first verification posting information;

[0030] Sending the first verification document information to the photovoltaic inverter;

[0031] Receiving the second verification palindrome information returned by the photovoltaic inverter, and performing protocol parsing using the corresponding extended communication protocol in the preselected protocol library to obtain the second verification information;

[0032] It is determined whether the second verification information matches the first verification information. If they match, it is determined that the corresponding extended communication protocol is the extended communication protocol of the photovoltaic inverter based on the standard Modbus protocol.

[0033] Further, after generating a second posting message including a control instruction based on an extended communication protocol of the photovoltaic inverter on the standard Modbus protocol and issuing the second posting message to the photovoltaic inverter, the method further includes:

[0034] The photovoltaic inverter parses the second published information based on an extended communication protocol on the standard Modbus protocol to obtain a control instruction;

[0035] The photovoltaic inverter executes the control instructions obtained by the analysis;

[0036] After the execution is completed, the photovoltaic inverter generates a second palindrome message including the control result based on the extended communication protocol on the standard Modbus protocol, and reports it to the power grid control device;

[0037] The power grid control device receives the second palindrome information and obtains device identification information about the second palindrome information;

[0038] The power grid control device finds the extended communication protocol associated with the second palindrome information from the diversified data extension library according to the device identification information of the second palindrome information;

[0039] The power grid control device parses the second palindrome information based on the extended communication protocol to obtain the control result.

[0040] Furthermore, after determining the extended communication protocol of the photovoltaic inverter on the standard Modbus protocol based on the diversified data extension library and through a preset analytical matching algorithm, the method further includes:

[0041] Based on the extended communication protocol, the attribute information of the photovoltaic module corresponding to the current moment and the photovoltaic environment data at the current moment are obtained from the photovoltaic inverter, wherein the attribute information at least includes the number of photovoltaic modules, the photovoltaic panel area of ​​each photovoltaic module and the photovoltaic absorption energy efficiency, and the photovoltaic environment data includes spatiotemporal data and weather data, wherein the spatiotemporal data at least includes geographic data and time data, and the weather data at least includes temperature value and light intensity;

[0042] Build a photovoltaic power generation prediction model and perform training optimization using photovoltaic power generation sample data;

[0043] Based on the attribute information of multiple photovoltaic modules and the photovoltaic environment data at the current moment, the photovoltaic predicted power generation at the next moment is predicted through the photovoltaic power generation prediction model;

[0044] Obtaining grid user information and current load environment data, wherein the grid user information includes at least the number of grid users and the type of electricity consumption of each grid user, and the load environment data includes at least time data and grid user operation status;

[0045] Build a grid load prediction model and perform training optimization using grid load sample data;

[0046] Based on the grid user information and the current load environment data, the grid load prediction model is used to predict the grid load value at the next moment.

[0047] Determine the difference between the photovoltaic power generation predicted from the current moment to the next moment and the grid load predicted from the current moment to the next moment;

[0048] According to the difference relationship, the joint grid-connected power transmission control instructions of photovoltaic power generation and photovoltaic batteries are formulated, and sent to the photovoltaic inverter for execution based on the extended communication protocol.

[0049] Furthermore, after predicting the photovoltaic power generation forecast at the next moment based on the property information of the plurality of photovoltaic modules and the photovoltaic environment data at the current moment through the photovoltaic power generation forecast model, the method further includes:

[0050] Acquire multiple historical photovoltaic power generation data, each historical photovoltaic power generation data at least includes attribute information of the photovoltaic component corresponding to the historical moment, photovoltaic environment data at the historical moment, and actual photovoltaic power generation at the next moment of the historical moment, wherein the photovoltaic environment data at the historical moment includes spatiotemporal data at the historical moment and weather data at the historical moment, and the spatiotemporal data at least includes geographic data and time data, and the weather data at least includes temperature value and light intensity;

[0051] Perform characteristic calculation on the photovoltaic environment data at each historical moment in the historical photovoltaic power generation data to obtain the photovoltaic environment characteristic value of the photovoltaic module corresponding to the historical moment;

[0052] Perform characteristic calculation on the photovoltaic environment data at the current moment to obtain the photovoltaic environment characteristic value of the photovoltaic module at the current moment;

[0053] Based on each historical photovoltaic power generation data, the photovoltaic environment characteristic value of the photovoltaic module corresponding to the historical moment and the photovoltaic environment characteristic value of the photovoltaic module corresponding to the current moment are calculated for similarity;

[0054] Determining whether the calculated similarity is greater than a fifth preset threshold, and if so, entering the corresponding historical photovoltaic power generation data into a similar feature database;

[0055] Based on each historical photovoltaic power generation data in the similar feature database, the attribute information of the photovoltaic components corresponding to the historical moment and the photovoltaic environment data at the historical moment are predicted through the photovoltaic power generation prediction model to obtain the photovoltaic predicted power generation at the next moment of the historical moment;

[0056] Based on each historical photovoltaic power generation data in the similar feature database, the photovoltaic actual power generation at the next historical moment is subtracted from the photovoltaic predicted power generation at the next historical moment to obtain the power generation vector difference;

[0057] The power generation vector differences calculated based on each historical photovoltaic power generation data in the similar feature database are added to obtain the sum of the power generation vector differences, and the sum of the power generation vector differences is divided by the amount of historical photovoltaic power generation data in the similar feature database to obtain the average value of the power generation vector differences;

[0058] The photovoltaic predicted power generation at the next moment and the average value of the power generation vector difference are vector summed to obtain the corrected photovoltaic predicted power generation at the next moment from the current moment.

[0059] The present invention further proposes a photovoltaic inverter-based control system, comprising a memory and a processor, wherein the memory comprises a photovoltaic inverter-based control method program, and when the photovoltaic inverter-based control method program is executed by the processor, the following steps are implemented:

[0060] The preset photovoltaic inverter corresponds to a plurality of photovoltaic modules, a temperature sensor is installed on each photovoltaic module, and the temperature data of the corresponding photovoltaic module is sensed in real time by the temperature sensor;

[0061] The photovoltaic inverter collects the temperature data collected by each temperature sensor on the photovoltaic module and reports it to the grid control equipment;

[0062] The temperature data of each photovoltaic module is calculated separately from the temperature data of other photovoltaic modules to obtain the difference between the two.

[0063] determining whether the difference is greater than a first preset threshold, and if so, marking the former photovoltaic component as an abnormal photovoltaic component;

[0064] After multiple photovoltaic modules corresponding to the photovoltaic inverters are compared with each other, the total number of times each photovoltaic module is marked as an abnormal photovoltaic module is counted;

[0065] Determine whether the total number of times each photovoltaic component is marked as an abnormal photovoltaic component is greater than a second preset threshold, and if so, determine the corresponding photovoltaic component as a risky photovoltaic component;

[0066] It is determined whether the temperature data of the risky photovoltaic assembly exceeds a third preset threshold value. If so, a grid-connection interruption instruction is issued to the photovoltaic inverter, and the grid connection with the photovoltaic inverter is cut off.

[0067] Furthermore, before the photovoltaic inverter collects the temperature data collected by each temperature sensor for the photovoltaic module and reports it to the power grid control device, the photovoltaic inverter-based control method program further implements the following steps when executed by the processor:

[0068] A diversified data extension library is established based on the standard Modbus protocol and pre-stored in the local database of the power grid control equipment, wherein the diversified data extension library includes a variety of extended communication protocols based on the standard Modbus protocol;

[0069] Send the first posting information based on the standard Modbus protocol to the photovoltaic inverter;

[0070] Receive the first palindrome information returned by the photovoltaic inverter, and identify therefrom the device identification information of the photovoltaic inverter and the data items extended on the standard Modbus protocol;

[0071] Based on the diversified data extension library, an extended communication protocol of the photovoltaic inverter on the standard Modbus protocol is determined through a preset analytical matching algorithm;

[0072] The extended communication protocol of the photovoltaic inverter on the standard Modbus protocol is associated with the device identification information and stored in a diversified data extension library;

[0073] Based on the extended communication protocol of the photovoltaic inverter on the standard Modbus protocol, a second document information including the control instruction is generated and issued to the photovoltaic inverter.

[0074] Furthermore, based on the diversified data extension library, the extended communication protocol of the photovoltaic inverter on the standard Modbus protocol is determined by a preset analytical matching algorithm, specifically including:

[0075] Build a simulated network conversation model;

[0076] The simulated network dialogue model is trained and optimized through sample data to obtain an optimized simulated network dialogue model;

[0077] Inputting the first posting information into the simulated network dialogue model for prediction to obtain first palindrome prediction information;

[0078] According to the device identification information of the photovoltaic inverter, finding out from the diversified data extension library whether there is an extended communication protocol associated therewith;

[0079] If not, performing corresponding protocol parsing on the first palindrome information by each extended communication protocol of the diversified data extension library to obtain corresponding first palindrome parsing information;

[0080] Calculate the difference between the first palindrome parsing information and the first palindrome prediction information corresponding to each extended communication protocol to obtain a first difference;

[0081] Determining whether the first difference is less than a fourth preset threshold, and if so, adding the corresponding extended communication protocol to the pre-selected protocol library;

[0082] Generate first verification information, and respectively use each extended communication protocol of the pre-selected protocol library to perform protocol encapsulation on the first verification information to obtain first verification posting information;

[0083] Sending the first verification document information to the photovoltaic inverter;

[0084] Receiving the second verification palindrome information returned by the photovoltaic inverter, and performing protocol parsing using the corresponding extended communication protocol in the preselected protocol library to obtain the second verification information;

[0085] It is determined whether the second verification information matches the first verification information. If they match, it is determined that the corresponding extended communication protocol is the extended communication protocol of the photovoltaic inverter based on the standard Modbus protocol.

[0086] The present invention also proposes a computer-readable storage medium, which includes a control method program based on a photovoltaic inverter. When the control method program based on a photovoltaic inverter is executed by a processor, the steps of the control method based on a photovoltaic inverter as described above are implemented.

[0087] The present invention proposes a control method, system and readable storage medium based on a photovoltaic inverter, which can accurately and effectively identify the hot spot effect, and timely interrupt the control through the photovoltaic inverter when the hot spot effect occurs, so as to avoid affecting the power grid. At the same time, it can automatically adapt to the communication protocols of different photovoltaic inverters for effective communication, solving the problem of communication failure caused by protocol incompatibility.

[0088] Additional aspects and advantages of the present invention will be given in part in the following description, and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0089] Figure 1 A flow chart of a control method based on a photovoltaic inverter of the present invention is shown;

[0090] Figure 2 A flow chart showing the communication based on the extended communication protocol of the photovoltaic inverter of the present invention is shown;

[0091] Figure 3 A block diagram of a photovoltaic inverter-based control system of the present invention is shown. DETAILED DESCRIPTION

[0092] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0093] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0094] Figure 1 A flow chart of a control method based on a photovoltaic inverter of the present invention is shown.

[0095] like Figure 1 As shown, the first aspect of the present invention proposes a control method based on a photovoltaic inverter, the method comprising:

[0096] S102, presetting a photovoltaic inverter to correspond to a plurality of photovoltaic modules, installing a temperature sensor on each photovoltaic module, and sensing temperature data of the corresponding photovoltaic module in real time through the temperature sensor;

[0097] S104, the photovoltaic inverter collects the temperature data collected by each temperature sensor for the photovoltaic module and reports it to the power grid control device;

[0098] S106, calculating the difference between the temperature data of each photovoltaic module and the temperature data of other photovoltaic modules one by one to obtain the difference between the two;

[0099] S108, determining whether the difference is greater than a first preset threshold, and if so, marking the former photovoltaic component as an abnormal photovoltaic component;

[0100] S110, after multiple photovoltaic modules corresponding to the photovoltaic inverter are compared with each other, the total number of times each photovoltaic module is marked as an abnormal photovoltaic module is counted;

[0101] S112, determining whether the total number of times each photovoltaic component is marked as an abnormal photovoltaic component is greater than a second preset threshold, and if so, determining the corresponding photovoltaic component as a risky photovoltaic component;

[0102] S114, determining whether the temperature data of the risky photovoltaic assembly exceeds a third preset threshold value, and if so, issuing a grid-connection interruption instruction to the photovoltaic inverter, and cutting off the grid connection with the photovoltaic inverter.

[0103] It can be understood that in the operation of photovoltaic power stations, due to the presence of foreign objects, bird droppings, sunlight blocking and other factors, the hot spot effect is formed, causing the output power of individual photovoltaic modules to drop seriously, and causing the temperature of photovoltaic modules to rise. The hot spot effect of photovoltaic modules refers to the fact that under certain conditions, the blocked or defective areas in the series branches of photovoltaic modules in the power generation state are treated as loads, consuming the energy generated by other areas, resulting in local overheating. This phenomenon is called the "hot spot effect" of photovoltaic modules. In the current photovoltaic power generation system, the dry photovoltaic panel cells are connected in parallel to form an array, so the output power drop of individual photovoltaic modules will be amplified, causing the power generation of the entire array to drop, even to less than half of the nominal power, and become a load to consume power generation energy, and also cause the temperature of the backplane of the photovoltaic module to rise, causing major safety hazards. The power grid control device of the present invention obtains the temperature of each photovoltaic module to check the abnormal photovoltaic module, and promptly cuts off the power grid connection with the photovoltaic inverter after discovering the risk photovoltaic module, thereby effectively avoiding the safety hazards caused by the hot spot effect of the photovoltaic module, and further avoiding the impact on the overall power grid system.

[0104] It can be understood that only excessively high temperatures of local photovoltaic modules are the cause of the hot spot effect of photovoltaic modules. If the temperatures of all photovoltaic modules are high, it may be caused by the overall weather temperature. At this time, the hot spot effect of photovoltaic modules can be ruled out.

[0105] It can be understood that the third preset threshold may be a high temperature threshold corresponding to the hot spot effect.

[0106] According to an embodiment of the present invention, Figure 2 As shown, before the photovoltaic inverter collects the temperature data collected by each temperature sensor for the photovoltaic component and reports it to the grid control device, the method also includes:

[0107] S202, establishing a diversified data extension library based on the standard Modbus protocol and pre-storing it in a local database of the power grid control device, wherein the diversified data extension library includes a plurality of extended communication protocols based on the standard Modbus protocol;

[0108] S204, sending a first publishing message based on a standard Modbus protocol to the photovoltaic inverter;

[0109] S206, receiving the first palindrome information returned by the photovoltaic inverter, and identifying therefrom the device identification information of the photovoltaic inverter and the data items extended on the standard Modbus protocol;

[0110] S208, based on the diversified data extension library, and through a preset analytical matching algorithm, determining an extended communication protocol of the photovoltaic inverter on the standard Modbus protocol;

[0111] S210, associating the extended communication protocol of the photovoltaic inverter on the standard Modbus protocol with the device identification information and storing them in a diversified data extension library;

[0112] S212: Generate second publishing information including control instructions based on the extended communication protocol of the photovoltaic inverter on the standard Modbus protocol, and issue the second publishing information to the photovoltaic inverter.

[0113] It can be understood that the device identification information at least includes device ID, model and brand, but is not limited thereto.

[0114] It can be understood that the control method based on photovoltaic inverters of the present invention is that the control equipment of the power grid company establishes a diversified data extension library based on the standard Modbus protocol and stores it in the power grid control equipment. When communicating with the photovoltaic inverter, based on the data type and format replied by the photovoltaic inverter, after establishing communication once or multiple times, the data items extended by the photovoltaic inverter on the standard Modbus protocol can be automatically identified. In combination with the control instructions issued by the power grid control equipment and the control results returned by the photovoltaic inverter, the power grid control equipment can automatically combine and generate the communication protocol and its extension items adapted to the photovoltaic inverter, and record the device ID, model and brand of the photovoltaic inverter at the same time. The present invention can automatically adapt to the communication protocols of different photovoltaic inverters for effective communication, solving the problem of communication failure caused by protocol incompatibility.

[0115] According to an embodiment of the present invention, based on the diversified data extension library, the extended communication protocol of the photovoltaic inverter on the standard Modbus protocol is determined by a preset analytical matching algorithm, specifically including:

[0116] Build a simulated network conversation model;

[0117] The simulated network dialogue model is trained and optimized through sample data to obtain an optimized simulated network dialogue model;

[0118] Inputting the first posting information into the simulated network dialogue model for prediction to obtain first palindrome prediction information;

[0119] According to the device identification information of the photovoltaic inverter, finding out from the diversified data extension library whether there is an extended communication protocol associated therewith;

[0120] If not, performing corresponding protocol parsing on the first palindrome information by each extended communication protocol of the diversified data extension library to obtain corresponding first palindrome parsing information;

[0121] Calculate the difference between the first palindrome parsing information and the first palindrome prediction information corresponding to each extended communication protocol to obtain a first difference;

[0122] Determining whether the first difference is less than a fourth preset threshold, and if so, adding the corresponding extended communication protocol to the pre-selected protocol library;

[0123] Generate first verification information, and respectively use each extended communication protocol of the pre-selected protocol library to perform protocol encapsulation on the first verification information to obtain first verification posting information;

[0124] Sending the first verification document information to the photovoltaic inverter;

[0125] Receiving the second verification palindrome information returned by the photovoltaic inverter, and performing protocol parsing using the corresponding extended communication protocol in the preselected protocol library to obtain the second verification information;

[0126] It is determined whether the second verification information matches the first verification information. If they match, it is determined that the corresponding extended communication protocol is the extended communication protocol of the photovoltaic inverter based on the standard Modbus protocol.

[0127] In a specific embodiment, for example, in a conversation, the first posting information may be: "Please reply with your device name and identification number?" Then, by simulating the network conversation model, the first posting information can be simulated and predicted to obtain the first palindrome prediction information as: "My device name is XX, and the identification number is IDXXXX". If the first palindrome parsing information is "My output voltage is XXX, and the output current is XXX" after the first palindrome information is parsed based on a certain extended communication protocol of the diversified data extension library, it means that the first palindrome parsing information corresponding to the extended communication protocol and the first palindrome prediction information are quite different. By comparing the difference, most irrelevant extended communication protocols can be eliminated from the diversified data extension library.

[0128] In a specific embodiment, for example, the first verification information is: "Please fill in the missing characters in the string 2_45_7", if the second verification information is: "3 and 6", it means that the verification is passed, and it is determined that the corresponding extended communication protocol is the extended communication protocol of the photovoltaic inverter on the standard Modbus protocol.

[0129] According to an embodiment of the present invention, after generating a second posting message including a control instruction based on an extended communication protocol of the photovoltaic inverter on the standard Modbus protocol and issuing the second posting message to the photovoltaic inverter, the method further includes:

[0130] The photovoltaic inverter parses the second published information based on an extended communication protocol on the standard Modbus protocol to obtain a control instruction;

[0131] The photovoltaic inverter executes the control instructions obtained by the analysis;

[0132] After the execution is completed, the photovoltaic inverter generates a second palindrome message including the control result based on the extended communication protocol on the standard Modbus protocol, and reports it to the power grid control device;

[0133] The power grid control device receives the second palindrome information and obtains device identification information about the second palindrome information;

[0134] The power grid control device finds the extended communication protocol associated with the second palindrome information from the diversified data extension library according to the device identification information of the second palindrome information;

[0135] The power grid control device parses the second palindrome information based on the extended communication protocol to obtain the control result.

[0136] According to an embodiment of the present invention, after determining the extended communication protocol of the photovoltaic inverter on the standard Modbus protocol based on the diversified data extension library and through a preset analytical matching algorithm, the method further includes:

[0137] Based on the extended communication protocol, the attribute information of the photovoltaic module corresponding to the current moment and the photovoltaic environment data at the current moment are obtained from the photovoltaic inverter, wherein the attribute information at least includes the number of photovoltaic modules, the photovoltaic panel area of ​​each photovoltaic module and the photovoltaic absorption energy efficiency, and the photovoltaic environment data includes spatiotemporal data and weather data, wherein the spatiotemporal data at least includes geographic data and time data, and the weather data at least includes temperature value and light intensity;

[0138] Build a photovoltaic power generation prediction model and perform training optimization using photovoltaic power generation sample data;

[0139] Based on the attribute information of multiple photovoltaic modules and the photovoltaic environment data at the current moment, the photovoltaic predicted power generation at the next moment is predicted through the photovoltaic power generation prediction model;

[0140] Obtaining grid user information and current load environment data, wherein the grid user information includes at least the number of grid users and the type of electricity consumption of each grid user, and the load environment data includes at least time data and grid user operation status;

[0141] Build a grid load prediction model and perform training optimization using grid load sample data;

[0142] Based on the grid user information and the current load environment data, the grid load prediction model is used to predict the grid load value at the next moment.

[0143] Determine the difference between the photovoltaic power generation predicted from the current moment to the next moment and the grid load predicted from the current moment to the next moment;

[0144] According to the difference relationship, the joint grid-connected power transmission control instructions of photovoltaic power generation and photovoltaic batteries are formulated, and sent to the photovoltaic inverter for execution based on the extended communication protocol.

[0145] It is understandable that the type of electricity consumption may be industrial electricity consumption, residential electricity consumption, etc., but is not limited thereto.

[0146] It can be understood that if the photovoltaic power generation predicted from the current moment to the next moment is greater than the grid load predicted from the current moment to the next moment, part of the photovoltaic power generation will be incorporated into the grid, and the other part will be charged to the photovoltaic battery. If the photovoltaic power generation predicted from the current moment to the next moment is less than the grid load predicted from the current moment to the next moment, all the photovoltaic power generation will be incorporated into the grid, and the remaining shortfall will be compensated by the photovoltaic battery. If the photovoltaic power generation predicted from the current moment to the next moment is equal to the grid load predicted from the current moment to the next moment, all the photovoltaic power generation will be incorporated into the grid, and no photovoltaic battery is required for compensation.

[0147] According to an embodiment of the present invention, after predicting the photovoltaic predicted power generation at the next moment from the current moment through a photovoltaic power generation prediction model based on the attribute information of multiple photovoltaic components and the photovoltaic environment data at the current moment, the method further includes:

[0148] Acquire multiple historical photovoltaic power generation data, each historical photovoltaic power generation data at least includes attribute information of the photovoltaic component corresponding to the historical moment, photovoltaic environment data at the historical moment, and actual photovoltaic power generation at the next moment of the historical moment, wherein the photovoltaic environment data at the historical moment includes spatiotemporal data at the historical moment and weather data at the historical moment, and the spatiotemporal data at least includes geographic data and time data, and the weather data at least includes temperature value and light intensity;

[0149] Perform characteristic calculation on the photovoltaic environment data at each historical moment in the historical photovoltaic power generation data to obtain the photovoltaic environment characteristic value of the photovoltaic module corresponding to the historical moment;

[0150] Perform characteristic calculation on the photovoltaic environment data at the current moment to obtain the photovoltaic environment characteristic value of the photovoltaic module at the current moment;

[0151] Based on each historical photovoltaic power generation data, the photovoltaic environment characteristic value of the photovoltaic module corresponding to the historical moment and the photovoltaic environment characteristic value of the photovoltaic module corresponding to the current moment are calculated for similarity;

[0152] Determining whether the calculated similarity is greater than a fifth preset threshold, and if so, entering the corresponding historical photovoltaic power generation data into a similar feature database;

[0153] Based on each historical photovoltaic power generation data in the similar feature database, the attribute information of the photovoltaic components corresponding to the historical moment and the photovoltaic environment data at the historical moment are predicted through the photovoltaic power generation prediction model to obtain the photovoltaic predicted power generation at the next moment of the historical moment;

[0154] Based on each historical photovoltaic power generation data in the similar feature database, the photovoltaic actual power generation at the next historical moment is subtracted from the photovoltaic predicted power generation at the next historical moment to obtain the power generation vector difference;

[0155] The power generation vector differences calculated based on each historical photovoltaic power generation data in the similar feature database are added to obtain the sum of the power generation vector differences, and the sum of the power generation vector differences is divided by the amount of historical photovoltaic power generation data in the similar feature database to obtain the average value of the power generation vector differences;

[0156] The photovoltaic predicted power generation at the next moment and the average value of the power generation vector difference are vector summed to obtain the corrected photovoltaic predicted power generation at the next moment from the current moment.

[0157] It can be understood that the present invention obtains a correction value of the prediction model based on the analysis and calculation of multiple historical photovoltaic power generation data, and corrects the predicted photovoltaic power generation from the current moment to the next moment through the correction value, thereby predicting a more accurate photovoltaic power generation, which further facilitates the precise control of the photovoltaic inverter.

[0158] According to a specific embodiment of the present invention, feature calculation is performed for photovoltaic environment data at a historical moment in each historical photovoltaic power generation data to obtain photovoltaic environment feature values ​​of photovoltaic modules corresponding to the historical moment; feature calculation is performed for photovoltaic environment data at the current moment to obtain photovoltaic environment feature values ​​of photovoltaic modules corresponding to the current moment; based on each historical photovoltaic power generation data, similarity calculation is performed between the photovoltaic environment feature values ​​of photovoltaic modules corresponding to the historical moment and the photovoltaic environment feature values ​​of photovoltaic modules corresponding to the current moment, specifically including:

[0159] Extract the spatiotemporal data of the historical moment from the photovoltaic environment data of the historical moment in each historical photovoltaic power generation data, and calculate the positional relationship between the geographical location of the photovoltaic module corresponding to the historical moment and the sun based on the geographic data and time data in the spatiotemporal data of the historical moment and the law of the earth's revolution and rotation, so as to serve as the spatiotemporal characteristic value of the photovoltaic module corresponding to the historical moment;

[0160] Extract weather data at a historical moment from photovoltaic environment data at a historical moment in each historical photovoltaic power generation data, multiply the temperature value in the weather data at a historical moment by the light intensity, and obtain the weather characteristic value of the photovoltaic module corresponding to the historical moment;

[0161] Extract the spatiotemporal data at the current moment from the photovoltaic environment data at the current moment, and calculate the positional relationship between the geographical location of the photovoltaic component at the current moment and the sun based on the geographic data and time data in the spatiotemporal data at the current moment and the laws of the earth's revolution and rotation, so as to serve as the spatiotemporal characteristic value of the photovoltaic component at the current moment;

[0162] Extract the weather data at the current moment from the photovoltaic environment data at the current moment, multiply the temperature value in the weather data at the current moment by the light intensity, and obtain the weather characteristic value corresponding to the photovoltaic module at the current moment;

[0163] Based on each historical photovoltaic power generation data, the spatiotemporal characteristic value of the photovoltaic module corresponding to each historical moment is similar to the spatiotemporal characteristic value of the photovoltaic module corresponding to the current moment, so as to obtain the spatiotemporal characteristic similarity based on each historical photovoltaic power generation data;

[0164] Based on each historical photovoltaic power generation data, a similarity calculation is performed between the weather characteristic value of the photovoltaic module corresponding to each historical moment and the weather characteristic value of the photovoltaic module corresponding to the current moment, so as to obtain the weather characteristic similarity based on each historical photovoltaic power generation data;

[0165] The preset time and space and weather have different influence weights on determining whether the photovoltaic environment of the photovoltaic module corresponding to the historical moment is similar to the photovoltaic environment of the photovoltaic module corresponding to the current moment;

[0166] Based on each historical photovoltaic power generation data, the corresponding spatiotemporal feature similarity is multiplied by the spatiotemporal influence weight to obtain the spatiotemporal feature weight similarity, and the corresponding weather feature similarity is multiplied by the weather influence weight to obtain the weather feature weight similarity;

[0167] Based on each historical photovoltaic power generation data, the corresponding spatiotemporal feature weight similarity and the corresponding weather feature weight similarity are added to obtain a first intermediate value;

[0168] Add the influence weight of time and space to the influence weight of weather to obtain a second intermediate value;

[0169] Based on each historical photovoltaic power generation data, the first intermediate value is divided by the second intermediate value to obtain the similarity between the photovoltaic environment characteristic value of the photovoltaic component corresponding to the historical moment and the photovoltaic environment characteristic value of the photovoltaic component corresponding to the current moment.

[0170] Figure 3 A block diagram of a photovoltaic inverter-based control system of the present invention is shown.

[0171] like Figure 3As shown, the present invention further proposes a photovoltaic inverter-based control system 3, comprising a memory 31 and a processor 32, wherein the memory comprises a photovoltaic inverter-based control method program, and when the photovoltaic inverter-based control method program is executed by the processor, the following steps are implemented:

[0172] The preset photovoltaic inverter corresponds to a plurality of photovoltaic modules, a temperature sensor is installed on each photovoltaic module, and the temperature data of the corresponding photovoltaic module is sensed in real time by the temperature sensor;

[0173] The photovoltaic inverter collects the temperature data collected by each temperature sensor on the photovoltaic module and reports it to the grid control equipment;

[0174] The temperature data of each photovoltaic module is calculated separately from the temperature data of other photovoltaic modules to obtain the difference between the two.

[0175] determining whether the difference is greater than a first preset threshold, and if so, marking the former photovoltaic component as an abnormal photovoltaic component;

[0176] After multiple photovoltaic modules corresponding to the photovoltaic inverters are compared with each other, the total number of times each photovoltaic module is marked as an abnormal photovoltaic module is counted;

[0177] Determine whether the total number of times each photovoltaic component is marked as an abnormal photovoltaic component is greater than a second preset threshold, and if so, determine the corresponding photovoltaic component as a risky photovoltaic component;

[0178] It is determined whether the temperature data of the risky photovoltaic assembly exceeds a third preset threshold value. If so, a grid-connection interruption instruction is issued to the photovoltaic inverter, and the grid connection with the photovoltaic inverter is cut off.

[0179] According to an embodiment of the present invention, before the photovoltaic inverter collects the temperature data collected by each temperature sensor for the photovoltaic assembly and reports it to the power grid control device, the photovoltaic inverter-based control method program further implements the following steps when executed by the processor:

[0180] A diversified data extension library is established based on the standard Modbus protocol and pre-stored in the local database of the power grid control equipment, wherein the diversified data extension library includes a variety of extended communication protocols based on the standard Modbus protocol;

[0181] Send the first posting information based on the standard Modbus protocol to the photovoltaic inverter;

[0182] Receive the first palindrome information returned by the photovoltaic inverter, and identify therefrom the device identification information of the photovoltaic inverter and the data items extended on the standard Modbus protocol;

[0183] Based on the diversified data extension library, an extended communication protocol of the photovoltaic inverter on the standard Modbus protocol is determined through a preset analytical matching algorithm;

[0184] The extended communication protocol of the photovoltaic inverter on the standard Modbus protocol is associated with the device identification information and stored in a diversified data extension library;

[0185] Based on the extended communication protocol of the photovoltaic inverter on the standard Modbus protocol, a second document information including the control instruction is generated and issued to the photovoltaic inverter.

[0186] According to an embodiment of the present invention, based on the diversified data extension library, the extended communication protocol of the photovoltaic inverter on the standard Modbus protocol is determined by a preset analytical matching algorithm, specifically including:

[0187] Build a simulated network conversation model;

[0188] The simulated network dialogue model is trained and optimized through sample data to obtain an optimized simulated network dialogue model;

[0189] Inputting the first posting information into the simulated network dialogue model for prediction to obtain first palindrome prediction information;

[0190] According to the device identification information of the photovoltaic inverter, finding out from the diversified data extension library whether there is an extended communication protocol associated therewith;

[0191] If not, performing corresponding protocol parsing on the first palindrome information by each extended communication protocol of the diversified data extension library to obtain corresponding first palindrome parsing information;

[0192] Calculate the difference between the first palindrome parsing information and the first palindrome prediction information corresponding to each extended communication protocol to obtain a first difference;

[0193] Determining whether the first difference is less than a fourth preset threshold, and if so, adding the corresponding extended communication protocol to the pre-selected protocol library;

[0194] Generate first verification information, and respectively use each extended communication protocol of the pre-selected protocol library to perform protocol encapsulation on the first verification information to obtain first verification posting information;

[0195] Sending the first verification document information to the photovoltaic inverter;

[0196] Receiving the second verification palindrome information returned by the photovoltaic inverter, and performing protocol parsing using the corresponding extended communication protocol in the preselected protocol library to obtain the second verification information;

[0197] It is determined whether the second verification information matches the first verification information. If they match, it is determined that the corresponding extended communication protocol is the extended communication protocol of the photovoltaic inverter based on the standard Modbus protocol.

[0198] The present invention also proposes a computer-readable storage medium, which includes a control method program based on a photovoltaic inverter. When the control method program based on a photovoltaic inverter is executed by a processor, the steps of the control method based on a photovoltaic inverter as described above are implemented.

[0199] The control method, system and readable storage medium based on the photovoltaic inverter proposed in the present invention can accurately and effectively identify the hot spot effect, and timely interrupt the control through the photovoltaic inverter when the hot spot effect occurs, so as to avoid affecting the power grid. At the same time, it can automatically adapt to the communication protocols of different photovoltaic inverters for effective communication, solving the problem of communication failure caused by protocol incompatibility.

[0200] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0201] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; 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 present embodiment.

[0202] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0203] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: a mobile storage device, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0204] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0205] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A control method based on a photovoltaic inverter, characterized in that: The method comprises: The preset photovoltaic inverter corresponds to a plurality of photovoltaic modules, a temperature sensor is installed on each photovoltaic module, and the temperature data of the corresponding photovoltaic module is sensed in real time by the temperature sensor; The photovoltaic inverter collects the temperature data collected by each temperature sensor on the photovoltaic module and reports it to the grid control equipment; The temperature data of each photovoltaic module is calculated separately from the temperature data of other photovoltaic modules to obtain the difference between the two. determining whether the difference is greater than a first preset threshold, and if so, marking the former photovoltaic component as an abnormal photovoltaic component; After multiple photovoltaic modules corresponding to the photovoltaic inverters are compared with each other, the total number of times each photovoltaic module is marked as an abnormal photovoltaic module is counted; Determine whether the total number of times each photovoltaic component is marked as an abnormal photovoltaic component is greater than a second preset threshold, and if so, determine the corresponding photovoltaic component as a risky photovoltaic component; Determine whether the temperature data of the risky photovoltaic assembly exceeds a third preset threshold value, and if so, issue a grid-connection interruption instruction to the photovoltaic inverter, and cut off the grid connection with the photovoltaic inverter; Before the photovoltaic inverter collects the temperature data collected by each temperature sensor for the photovoltaic component and reports it to the power grid control device, the method further includes: A diversified data extension library is established based on the standard Modbus protocol and pre-stored in the local database of the power grid control equipment, wherein the diversified data extension library includes a variety of extended communication protocols based on the standard Modbus protocol; Send the first posting information based on the standard Modbus protocol to the photovoltaic inverter; Receive the first palindrome information returned by the photovoltaic inverter, and identify therefrom the device identification information of the photovoltaic inverter and the data items extended on the standard Modbus protocol; Based on the diversified data extension library, an extended communication protocol of the photovoltaic inverter on the standard Modbus protocol is determined through a preset analytical matching algorithm; The extended communication protocol of the photovoltaic inverter on the standard Modbus protocol is associated with the device identification information and stored in a diversified data extension library; Based on the extended communication protocol of the photovoltaic inverter on the standard Modbus protocol, a second document information including the control instruction is generated and issued to the photovoltaic inverter.

2. A control method based on a photovoltaic inverter according to claim 1, characterized in that: Based on the diversified data extension library, the extended communication protocol of the photovoltaic inverter on the standard Modbus protocol is determined through a preset analytical matching algorithm, specifically including: Build a simulated network conversation model; The simulated network dialogue model is trained and optimized through sample data to obtain an optimized simulated network dialogue model; Inputting the first posting information into the simulated network dialogue model for prediction to obtain first palindrome prediction information; According to the device identification information of the photovoltaic inverter, finding out from the diversified data extension library whether there is an extended communication protocol associated therewith; If not, performing corresponding protocol parsing on the first palindrome information by each extended communication protocol of the diversified data extension library to obtain corresponding first palindrome parsing information; Calculate the difference between the first palindrome parsing information and the first palindrome prediction information corresponding to each extended communication protocol to obtain a first difference; Determining whether the first difference is less than a fourth preset threshold, and if so, adding the corresponding extended communication protocol to the pre-selected protocol library; Generate first verification information, and respectively use each extended communication protocol of the pre-selected protocol library to perform protocol encapsulation on the first verification information to obtain first verification posting information; Sending the first verification document information to the photovoltaic inverter; Receiving the second verification palindrome information returned by the photovoltaic inverter, and performing protocol parsing using the corresponding extended communication protocol in the preselected protocol library to obtain the second verification information; It is determined whether the second verification information matches the first verification information. If they match, it is determined that the corresponding extended communication protocol is the extended communication protocol of the photovoltaic inverter based on the standard Modbus protocol.

3. A control method based on a photovoltaic inverter according to claim 1, characterized in that: After generating a second posting message including a control instruction based on an extended communication protocol of the photovoltaic inverter on the standard Modbus protocol and issuing the second posting message to the photovoltaic inverter, the method further includes: The photovoltaic inverter parses the second published information based on an extended communication protocol on the standard Modbus protocol to obtain a control instruction; The photovoltaic inverter executes the control instructions obtained by the analysis; After the execution is completed, the photovoltaic inverter generates a second palindrome message including the control result based on the extended communication protocol on the standard Modbus protocol, and reports it to the power grid control device; The power grid control device receives the second palindrome information and obtains device identification information about the second palindrome information; The power grid control device finds the extended communication protocol associated with the second palindrome information from the diversified data extension library according to the device identification information of the second palindrome information; The power grid control device parses the second palindrome information based on the extended communication protocol to obtain the control result.

4. The photovoltaic inverter control method according to claim 1, characterized in that: After determining the extended communication protocol of the photovoltaic inverter on the standard Modbus protocol based on the diversified data extension library and through a preset analytical matching algorithm, the method further includes: Based on the extended communication protocol, the attribute information of the photovoltaic module corresponding to the current moment and the photovoltaic environment data at the current moment are obtained from the photovoltaic inverter, wherein the attribute information at least includes the number of photovoltaic modules, the photovoltaic panel area of ​​each photovoltaic module and the photovoltaic absorption energy efficiency, and the photovoltaic environment data includes spatiotemporal data and weather data, wherein the spatiotemporal data at least includes geographic data and time data, and the weather data at least includes temperature value and light intensity; Build a photovoltaic power generation prediction model and perform training optimization using photovoltaic power generation sample data; Based on the property information of multiple photovoltaic modules and the photovoltaic environment data at the current moment, the photovoltaic predicted power generation at the next moment of the current moment is predicted by a photovoltaic power generation prediction model; Obtaining grid user information and current load environment data, wherein the grid user information includes at least the number of grid users and the type of electricity consumption of each grid user, and the load environment data includes at least time data and grid user operation status; Build a grid load prediction model and perform training optimization using grid load sample data; Based on the grid user information and the load environment data at the current moment, the grid load prediction model is used to predict the grid load value at the next moment after the current moment. Determine the difference between the photovoltaic power generation predicted at the next moment of the current moment and the power grid load predicted at the next moment of the current moment; According to the difference relationship, the joint grid-connected power transmission control instructions of photovoltaic power generation and photovoltaic batteries are formulated, and sent to the photovoltaic inverter for execution based on the extended communication protocol.

5. A control method based on a photovoltaic inverter according to claim 4, characterized in that: After predicting the photovoltaic power generation at the next moment after the current moment based on the property information of the plurality of photovoltaic modules and the photovoltaic environment data at the current moment through the photovoltaic power generation prediction model, the method further includes: Acquire multiple historical photovoltaic power generation data, each historical photovoltaic power generation data at least includes attribute information of the photovoltaic component corresponding to the historical moment, photovoltaic environment data at the historical moment, and actual photovoltaic power generation at the next moment of the historical moment, wherein the photovoltaic environment data at the historical moment includes spatiotemporal data at the historical moment and weather data at the historical moment, and the spatiotemporal data at least includes geographic data and time data, and the weather data at least includes temperature value and light intensity; Perform characteristic calculation on the photovoltaic environment data at each historical moment in the historical photovoltaic power generation data to obtain the photovoltaic environment characteristic value of the photovoltaic module corresponding to the historical moment; Perform characteristic calculation on the photovoltaic environment data at the current moment to obtain the photovoltaic environment characteristic value of the photovoltaic module at the current moment; Based on each historical photovoltaic power generation data, the photovoltaic environment characteristic value of the photovoltaic module corresponding to the historical moment and the photovoltaic environment characteristic value of the photovoltaic module corresponding to the current moment are calculated for similarity; Determining whether the calculated similarity is greater than a fifth preset threshold, and if so, entering the corresponding historical photovoltaic power generation data into a similar feature database; Based on each historical photovoltaic power generation data in the similar feature database, the attribute information of the photovoltaic components corresponding to the historical moment and the photovoltaic environment data at the historical moment are predicted through the photovoltaic power generation prediction model to obtain the photovoltaic predicted power generation at the next moment of the historical moment; Based on each historical photovoltaic power generation data in the similar feature database, the photovoltaic actual power generation at the next moment of the historical moment is subtracted from the photovoltaic predicted power generation at the next moment of the historical moment to obtain the power generation vector difference; The power generation vector differences calculated based on each historical photovoltaic power generation data in the similar feature database are added to obtain the sum of the power generation vector differences, and the sum of the power generation vector differences is divided by the amount of historical photovoltaic power generation data in the similar feature database to obtain the average value of the power generation vector differences; The photovoltaic predicted power generation at the next moment after the current moment is vector-sum-calculated with the average value of the power generation vector difference to obtain the corrected photovoltaic predicted power generation at the next moment after the current moment.

6. A control system based on a photovoltaic inverter, characterized in that: The invention comprises a memory and a processor, wherein the memory comprises a photovoltaic inverter-based control method program, and the photovoltaic inverter-based control method program implements the following steps when executed by the processor: The preset photovoltaic inverter corresponds to a plurality of photovoltaic modules, a temperature sensor is installed on each photovoltaic module, and the temperature data of the corresponding photovoltaic module is sensed in real time by the temperature sensor; The photovoltaic inverter collects the temperature data collected by each temperature sensor on the photovoltaic module and reports it to the grid control equipment; The temperature data of each photovoltaic module is calculated separately from the temperature data of other photovoltaic modules to obtain the difference between the two. determining whether the difference is greater than a first preset threshold, and if so, marking the former photovoltaic component as an abnormal photovoltaic component; After multiple photovoltaic modules corresponding to the photovoltaic inverters are compared with each other, the total number of times each photovoltaic module is marked as an abnormal photovoltaic module is counted; Determine whether the total number of times each photovoltaic component is marked as an abnormal photovoltaic component is greater than a second preset threshold, and if so, determine the corresponding photovoltaic component as a risky photovoltaic component; Determine whether the temperature data of the risky photovoltaic assembly exceeds a third preset threshold value, and if so, issue a grid-connection interruption instruction to the photovoltaic inverter, and cut off the grid connection with the photovoltaic inverter; Before the photovoltaic inverter collects the temperature data collected by each temperature sensor for the photovoltaic module and reports it to the power grid control device, the photovoltaic inverter-based control method program further implements the following steps when executed by the processor: A diversified data extension library is established based on the standard Modbus protocol and pre-stored in the local database of the power grid control equipment, wherein the diversified data extension library includes a variety of extended communication protocols based on the standard Modbus protocol; Send the first posting information based on the standard Modbus protocol to the photovoltaic inverter; Receive the first palindrome information returned by the photovoltaic inverter, and identify therefrom the device identification information of the photovoltaic inverter and the data items extended on the standard Modbus protocol; Based on the diversified data extension library, an extended communication protocol of the photovoltaic inverter on the standard Modbus protocol is determined through a preset analytical matching algorithm; The extended communication protocol of the photovoltaic inverter on the standard Modbus protocol is associated with the device identification information and stored in a diversified data extension library; Based on the extended communication protocol of the photovoltaic inverter on the standard Modbus protocol, a second document information including the control instruction is generated and issued to the photovoltaic inverter.

7. A photovoltaic inverter-based control system according to claim 6, characterized in that: Based on the diversified data extension library, the extended communication protocol of the photovoltaic inverter on the standard Modbus protocol is determined through a preset analytical matching algorithm, specifically including: Build a simulated network conversation model; The simulated network dialogue model is trained and optimized through sample data to obtain an optimized simulated network dialogue model; Inputting the first posting information into the simulated network dialogue model for prediction to obtain first palindrome prediction information; According to the device identification information of the photovoltaic inverter, finding out from the diversified data extension library whether there is an extended communication protocol associated therewith; If not, performing corresponding protocol parsing on the first palindrome information by each extended communication protocol of the diversified data extension library to obtain corresponding first palindrome parsing information; Calculate the difference between the first palindrome parsing information and the first palindrome prediction information corresponding to each extended communication protocol to obtain a first difference; Determining whether the first difference is less than a fourth preset threshold, and if so, adding the corresponding extended communication protocol to the pre-selected protocol library; Generate first verification information, and respectively use each extended communication protocol of the pre-selected protocol library to perform protocol encapsulation on the first verification information to obtain first verification posting information; Sending the first verification document information to the photovoltaic inverter; Receiving the second verification palindrome information returned by the photovoltaic inverter, and performing protocol parsing using the corresponding extended communication protocol in the preselected protocol library to obtain the second verification information; It is determined whether the second verification information matches the first verification information. If they match, it is determined that the corresponding extended communication protocol is the extended communication protocol of the photovoltaic inverter based on the standard Modbus protocol.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a photovoltaic inverter-based control method program. When the photovoltaic inverter-based control method program is executed by a processor, the steps of a photovoltaic inverter-based control method according to any one of claims 1 to 5 are implemented.

Images