Method and system for predicting operation and control risks of photovoltaic units

Abstract

The present invention discloses an operation and control risk prediction method and system for photovoltaic units, which are applied to the field of data processing technology. The method comprises: establishing data interaction with photovoltaic units, and extracting the mapping relationship between the illumination intensity and the power generation power of the calibration environment based on the data interaction result, collecting illumination prediction data, and performing real-time power generation power prediction based on the illumination intensity prediction data and the mapping relationship. Obtaining real-time power supply demand data, and performing power supply diversion prediction based on the real-time power supply demand data. Reading pre-control data, performing timing control fitting based on the pre-control data, and generating timing control fitting results. Control evaluation is performed on the timing control fitting results through the diversion prediction control results, and an operation and control risk prediction result is generated. Control management is performed through the operation and control risk prediction results. The technical problem that the power operation and control risk of photovoltaic units in the prior art is difficult to predict, resulting in low power operation and control stability of photovoltaic units is solved.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and in particular to a method and system for predicting operation and control risks of photovoltaic units. Background Art

[0002] Photovoltaic units are generally hybrid photovoltaic systems, which include solar cell modules, power storage modules and load modules. Due to the complex structure of photovoltaic units and the fact that the power allocation of the system is mostly fixed parameter allocation in the process of powering the load, the power operation and control stability of photovoltaic units is low, and the power demand is difficult to guarantee.

[0003] Therefore, in the prior art, the risk of power operation and control of photovoltaic units is difficult to predict, resulting in a technical problem of low stability in power operation and control of photovoltaic units. Summary of the invention

[0004] The present application solves the technical problem in the prior art that the power operation and control risks of photovoltaic units are difficult to predict, resulting in low power operation and control stability of photovoltaic units, by providing a method and system for predicting operation and control risks of photovoltaic units.

[0005] The present application provides an operation and control risk prediction method for a photovoltaic group, the method comprising: establishing data interaction with the photovoltaic group, and extracting a mapping relationship between light intensity and power generation of a calibration environment based on a result of the data interaction; acquiring light prediction data, wherein the light prediction data is acquired through a prediction window, and the light prediction data is light intensity prediction data; performing real-time power generation prediction based on the light intensity prediction data and the mapping relationship, and generating a real-time power prediction result; acquiring real-time power supply demand data, performing power supply diversion prediction based on the real-time power supply demand data, and generating a diversion prediction control result; reading pre-control data of the photovoltaic group, performing timing control fitting based on the pre-control data, and generating a timing control fitting result; performing control evaluation on the timing control fitting result through the diversion prediction control result, and generating an operation and control risk prediction result; and controlling and managing the photovoltaic group through the operation and control risk prediction result.

[0006] The present application also provides an operation and control risk prediction system for a photovoltaic unit, the system comprising: a data interaction module, for establishing data interaction with the photovoltaic unit, and extracting a mapping relationship between the illumination intensity of a calibration environment and the power generation power based on the data interaction result; an illumination prediction module, for acquiring illumination prediction data, wherein the illumination prediction data is acquired through a prediction window, and the illumination prediction data is illumination intensity prediction data; a power prediction module, for performing real-time power generation power prediction based on the illumination intensity prediction data and the mapping relationship, and generating a real-time power prediction result; a shunt prediction module, for acquiring real-time power supply demand data, performing power supply shunt prediction based on the real-time power supply demand data, and generating a shunt prediction control result; a control fitting module, for reading pre-control data of the photovoltaic unit, performing timing control fitting based on the pre-control data, and generating a timing control fitting result; a risk prediction module, for performing control evaluation on the timing control fitting result through the shunt prediction control result, and generating an operation and control risk prediction result; a control management module, for performing control management of the photovoltaic unit through the operation and control risk prediction result.

[0007] The present application also provides an electronic device, including:

[0008] A memory for storing executable instructions;

[0009] The processor is used to implement the operation and control risk prediction method for a photovoltaic unit provided in the present application when executing the executable instructions stored in the memory.

[0010] The present application provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the operation and control risk prediction method for a photovoltaic unit provided by the present application.

[0011] The operation and control risk prediction method and system for photovoltaic units proposed in this application are intended to establish data interaction with photovoltaic units, extract the mapping relationship between the illumination intensity and the power generation power of the calibration environment based on the data interaction results, collect and obtain illumination prediction data, and perform real-time power generation power prediction based on the illumination intensity prediction data and the mapping relationship. Obtain real-time power supply demand data, and perform power supply diversion prediction based on the real-time power supply demand data. Read pre-control data, perform timing control fitting based on the pre-control data, and generate timing control fitting results. Control and evaluate the timing control fitting results through the diversion prediction control results, and generate operation and control risk prediction results. Control and manage through the operation and control risk prediction results. The prediction of the power operation and control risks of photovoltaic units is realized, and control and management are performed based on the prediction results, thereby improving the power operation and control stability of photovoltaic units. The technical problem that the power operation and control risks of photovoltaic units in the prior art are difficult to predict, resulting in low power operation and control stability of photovoltaic units, is solved.

[0012] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following briefly introduces the drawings of the embodiments of the present disclosure. Obviously, the drawings described below only relate to some embodiments of the present disclosure, and are not intended to limit the present disclosure.

[0014] Figure 1 A schematic diagram of a flow chart of a method for predicting operation and control risks of a photovoltaic unit provided in an embodiment of the present application;

[0015] Figure 2 A schematic diagram of a flow chart of compensation for real-time power prediction results of a method for predicting operation and control risks of photovoltaic units provided in an embodiment of the present application;

[0016] Figure 3 A schematic diagram of a flow chart for optimizing the collection of illumination prediction data in a method for predicting the operation and control risks of a photovoltaic unit provided in an embodiment of the present application;

[0017] Figure 4 A schematic diagram of the structure of a system for predicting the operation and control risk of a photovoltaic unit provided in an embodiment of the present application;

[0018] Figure 5 A schematic diagram of the structure of a system electronic device for a method for predicting operation and control risks of a photovoltaic unit provided by an embodiment of the present invention.

[0019] Explanation of the accompanying drawings: data interaction module 11, illumination prediction module 12, power prediction module 13, diversion prediction module 14, control fitting module 15, risk prediction module 16, control management module 17, processor 31, memory 32, input device 33, output device 34. DETAILED DESCRIPTION

[0020] Embodiment 1

[0021] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application.

[0022] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0023] In the following description, the terms "first\second\third" involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It can be understood that "first\second\third" can be interchanged with a specific order or sequence where permitted, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0024] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application.

[0025] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, the modules are illustrative only, and different aspects of the system and method may use different modules.

[0026] Flowcharts are used in the present application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps may be processed in reverse order or simultaneously as required. At the same time, other operations may also be added to these processes, or a certain step or several steps of operations may be removed from these processes.

[0027] like Figure 1 As shown, the embodiment of the present application provides a method for predicting operation and control risks of a photovoltaic unit, the method comprising:

[0028] Establish data interaction with the photovoltaic unit, and extract the mapping relationship between the light intensity and power generation of the calibration environment based on the data interaction results;

[0029] Acquire illumination prediction data, wherein the illumination prediction data is acquired through the prediction window, and the illumination prediction data is illumination intensity prediction data;

[0030] Perform real-time power generation prediction based on the light intensity prediction data and the mapping relationship to generate a real-time power prediction result;

[0031] Acquire real-time power supply demand data, perform power supply diversion prediction based on the real-time power supply demand data, and generate diversion prediction control results;

[0032] Photovoltaic units are generally hybrid photovoltaic systems, which include solar cell components, energy storage components and load components. Due to the complex structure of photovoltaic units and the fact that the power allocation of the system is mostly fixed parameter allocation during the power supply process to the load, the power control stability of the photovoltaic unit is low, and the power demand is difficult to be guaranteed. By establishing data interaction with the photovoltaic unit, the data of the data interaction includes the temperature adjustment data of the photovoltaic unit. Based on the data interaction results, the mapping relationship between the light intensity and the power generation of the calibration environment is extracted, wherein the calibration environment is a pre-calibrated environment category under different light intensities, and there is a corresponding relationship between the light intensity and the power generation of different calibration environments. The light prediction data is collected and obtained, that is, the light intensity prediction data is collected and obtained through the weather software, wherein the light prediction data is obtained through the prediction window, and the light prediction data is the light intensity prediction data. Based on the light intensity prediction data and the mapping relationship, real-time power generation prediction is performed to generate a real-time power prediction result, that is, based on the light intensity prediction data, the mapping relationship between the light intensity and the power generation of the calibration environment is predicted to obtain real-time power prediction, and the real-time power prediction result is obtained. Real-time power supply demand data, i.e., real-time power supply demand data, is acquired, power supply diversion prediction is performed based on the real-time power supply demand data, and diversion prediction control results are generated.

[0033] like Figure 2 As shown, the method provided in the embodiment of the present application also includes:

[0034] Establishing a temperature adjustment parameter set of the temperature control unit, wherein each adjustment parameter in the temperature adjustment parameter set corresponds to a temperature control result, and the temperature adjustment parameter set is obtained through the data interaction result;

[0035] The control strategy of the temperature control unit is extracted through the pre-control data, and the heating fitting of the photovoltaic unit is performed through the light intensity prediction data to generate a heating fitting result;

[0036] Inputting the heating fitting result, the control strategy extraction result and the temperature adjustment parameter set into the temperature control evaluation network to generate a temperature control evaluation result;

[0037] The real-time power prediction result is compensated by the temperature control evaluation result.

[0038] A temperature adjustment parameter set of a temperature control unit is established, wherein each adjustment parameter in the temperature adjustment parameter set corresponds to a temperature control result, and the temperature adjustment parameter set is obtained through the data interaction result, that is, the temperature adjustment parameter of the photovoltaic unit, that is, the real-time temperature data, is obtained through the data interaction result, and each adjustment parameter corresponds to a temperature control result, that is, a temperature control target, and the temperature control target includes a temperature change parameter per unit time. Subsequently, the control strategy of the temperature control unit is extracted through the pre-control data, wherein the pre-control data is the control data corresponding to the pre-set different temperature adjustment parameters. And the heating fitting of the photovoltaic unit is performed through the light intensity prediction data to generate a heating fitting result. When performing the heating fitting, the corresponding historical temperature rise data is obtained based on the light intensity, wherein the temperature rise data is the temperature increase or decrease in unit time, and the heating fitting result is generated by obtaining the historical temperature rise data corresponding to the current light intensity. The heating fitting result, the control strategy extraction result and the temperature adjustment parameter set are input into the temperature control evaluation network to generate a temperature control evaluation result. The real-time power prediction result is compensated by the temperature control evaluation result.

[0039] The method provided in the embodiment of the present application also includes:

[0040] After the heating fitting result, the control strategy extraction result and the temperature adjustment parameter set are input into the temperature control evaluation network, the temperature trigger control fitting of heating is performed through the balance subnetwork to obtain the equilibrium temperature point of temperature control;

[0041] The equilibrium temperature point is synchronized to the delay evaluation subnetwork, the response delay is output through the delay evaluation subnetwork, and the equilibrium temperature point and the response delay are used as the temperature control evaluation result.

[0042] After the heating fitting result, control strategy extraction result and temperature adjustment parameter set are input into the temperature control evaluation network, the temperature trigger control fitting of heating is performed through the balance sub-network to obtain the equilibrium temperature point of temperature control. Among them, the balance sub-network is constructed based on the neural network model, and the model is supervised and trained by obtaining the historical heating fitting result, the historical control strategy extraction result and the historical temperature adjustment parameter set and the corresponding temperature control equilibrium temperature point as training data, until the equilibrium temperature point of temperature control output by the model meets the preset accuracy to obtain the balance sub-network. The heating fitting result, the control strategy extraction result and the temperature adjustment parameter set are used to perform temperature trigger control fitting to obtain the equilibrium temperature point of temperature control. Since the equilibrium temperature point of temperature control under different light intensity is consistent for different temperature adjustment parameter sets, the response delay to reach the equilibrium temperature point is also consistent. The response delay database is constructed by obtaining the response delay corresponding to the equilibrium temperature point reached by different temperature adjustment parameter sets under different light intensity. The response delay database is used as the query database of the delay evaluation sub-network to obtain the response delay. Finally, the equilibrium temperature point is synchronized to the delay evaluation subnetwork, and the response delay, i.e., the time to reach the equilibrium temperature point, is output by the delay evaluation subnetwork. The equilibrium temperature point and the response delay are used as the temperature control evaluation result.

[0043] The method provided in the embodiment of the present application also includes:

[0044] Establishing a delay node through the response delay, and dividing the real-time power prediction result through the delay node to determine a steady-state power region and a control power region;

[0045] Performing power compensation on the steady-state power region through the equilibrium temperature point to obtain a first compensation result;

[0046] Calling the initial temperature according to the control start node, performing weighted temperature analysis of the control power area according to the initial temperature, the equilibrium temperature point and the response delay, and generating a second compensation result;

[0047] The real-time power prediction result is compensated by using the first compensation result and the second compensation result.

[0048] A delay node is established through the response delay, and the real-time power prediction result is divided through the delay node to determine the steady-state power area and the control power area, wherein the steady-state power area is the power area of ​​the photovoltaic unit when the temperature adjustment parameter is adjusted, and the control power area is the power area when the temperature is adjusted, that is, within the response delay interval. Since the power parameters under different temperature environments are different, the steady-state power area is compensated for power through the equilibrium temperature point, wherein the power compensation value is the difference between the power of the temperature adjustment parameter point, that is, the initial temperature, and the power of the equilibrium temperature point, to obtain the first compensation result. Subsequently, the initial temperature is called according to the control start node, and the weighted temperature analysis of the control power area is performed according to the initial temperature, the equilibrium temperature point and the response delay to generate the second compensation result. Since the process of reaching the equilibrium temperature point from the initial temperature during temperature adjustment can be approximated as the operation of the photovoltaic unit under different time weights at the initial temperature and the equilibrium temperature point, the specific weight parameters can be set based on professional and technical personnel, and the total power data of the operation under different time weights at the initial temperature and the equilibrium temperature point is further obtained, and the second compensation result is generated based on the ratio of the total power to the response delay. Finally, the real-time power prediction result is compensated by the first compensation result and the second compensation result, wherein the first compensation result is used to compensate for the real-time power prediction result when the equilibrium temperature point is reached, and the second compensation result is used to compensate for the real-time power prediction result in response delay.

[0049] Reading pre-control data of the photovoltaic group, performing timing control fitting based on the pre-control data, and generating a timing control fitting result;

[0050] Performing control evaluation on the timing control fitting result through the diversion prediction control result to generate an operation control risk prediction result;

[0051] The photovoltaic units are controlled and managed based on the operation and control risk prediction results.

[0052] Read the pre-control data of the photovoltaic unit, wherein the pre-control data of the photovoltaic unit is the power supply shunt control data pre-set by the photovoltaic unit, perform timing control fitting through the pre-control data, and generate a timing control fitting result. Perform control evaluation on the timing control fitting result through the shunt prediction control result, and generate an operation and control risk prediction result, that is, evaluate whether the control of the shunt prediction control result and the timing control fitting result are consistent. If they are consistent, the operation and control risk is low, and the photovoltaic unit is controlled and managed according to the timing control fitting result. If they are inconsistent, the corresponding operation and control risk is high, and the photovoltaic unit is controlled and managed according to the evaluation shunt prediction control result. Finally, the photovoltaic unit is controlled and managed according to the operation and control risk prediction result. The prediction of the power operation and control risk of the photovoltaic unit is realized, and control management is performed based on the prediction result, thereby improving the power operation and control stability of the photovoltaic unit.

[0053] The method provided in the embodiment of the present application also includes:

[0054] Performing a power steady-state mark on the real-time power prediction result;

[0055] Perform supply and demand balance analysis through the power steady-state identifier and real-time power supply demand data to determine the reserve control node of the battery;

[0056] A fitting comparison of the timing control fitting result is performed through the preliminary control node, and a control evaluation is completed based on the fitting comparison result.

[0057] The real-time power prediction result is marked with a power steady state, that is, the real-time power prediction result is marked when it reaches the power steady state and the corresponding real-time power prediction result. Subsequently, a supply and demand balance analysis is performed using the power steady state mark and the real-time power supply demand data, that is, a supply and demand balance analysis is performed based on the real-time power prediction result and the real-time power supply demand data to determine the reserve control node of the battery, that is, determine the time node at which the real-time power prediction result cannot meet the real-time power supply demand data, that is, the reserve control node of the battery. Finally, a fitting comparison of the timing control fitting result is performed through the reserve control node, and a control evaluation is completed based on the fitting comparison result, that is, it is determined whether the reserve control node is consistent with the timing control fitting result.

[0058] The method provided in the embodiment of the present application also includes:

[0059] Perform supply and demand balance analysis through the power steady-state identifier and real-time power supply demand data to determine the compensation power;

[0060] Configuring the conversion power loss of the battery, and predicting the total amount of battery compensation by using the conversion power loss and the compensation power, to generate a total amount of compensation prediction result;

[0061] A comparison is performed based on the total compensation amount prediction result and the battery power data, and an operation control risk report is issued based on the comparison result.

[0062] The power steady-state identifier and real-time power supply demand data are used to perform supply and demand balance analysis to determine the compensation power. The conversion power loss of the battery is configured, that is, the conversion power loss of the battery is pre-set, and the total battery compensation amount is predicted through the conversion power loss and the compensation power, wherein the total battery compensation amount is the sum of the conversion power loss and the compensation power, and a total compensation prediction result is generated, wherein the total compensation prediction result is the compensation amount per unit time. Based on the comparison between the total compensation prediction result and the battery power data, the ratio of the battery power data to the total compensation prediction result is obtained, the maximum compensation time is obtained, and the operation control risk is reported through the comparison result, i.e., the maximum compensation time.

[0063] like Figure 3 As shown, the method provided in the embodiment of the present application also includes:

[0064] Record and verify the operation control risk prediction results and generate record verification results;

[0065] Generating a window length and frequency constraint of a prediction window through the record verification result;

[0066] The acquisition optimization of subsequent illumination prediction data is performed through window length and frequency constraints.

[0067] The operation control risk prediction results are recorded and verified to generate a record verification result, wherein the record verification result includes the number of successes and the number of failures. The window length and frequency constraint of the prediction window are generated through the record verification result, that is, the ratio between the number of successes and the number of failures in the record verification result is obtained, and the window length and frequency constraint of the prediction window corresponding to the ratio are set, wherein the window length of the prediction window is used to constrain the prediction interval time, and the frequency constraint is used to constrain the prediction frequency per unit time. The subsequent light prediction data collection optimization is performed through the window length and frequency constraints.

[0068] The technical solution provided by the embodiment of the present invention establishes data interaction with a photovoltaic unit, and extracts the mapping relationship between the illumination intensity and the power generation of the calibration environment based on the data interaction result. The illumination prediction data is collected and obtained, wherein the illumination prediction data is obtained through the prediction window collection, and the illumination prediction data is the illumination intensity prediction data. The real-time power generation power prediction is performed based on the illumination intensity prediction data and the mapping relationship to generate a real-time power prediction result. The real-time power supply demand data is obtained, and the power supply shunt prediction is performed based on the real-time power supply demand data to generate a shunt prediction control result. The pre-control data of the photovoltaic unit is read, and the timing control fitting is performed based on the pre-control data to generate a timing control fitting result. The timing control fitting result is controlled and evaluated based on the shunt prediction control result to generate an operation and control risk prediction result. The photovoltaic unit is controlled and managed based on the operation and control risk prediction result. The prediction of the power operation and control risk of the photovoltaic unit is realized, and the control management is performed based on the prediction result, thereby improving the power operation and control stability of the photovoltaic unit. The technical problem that the power operation and control risk of the photovoltaic unit is difficult to predict in the prior art, resulting in low power operation and control stability of the photovoltaic unit, is solved.

[0069] Embodiment 2

[0070] Based on the same inventive concept as the method for predicting the operation and control risks of photovoltaic units in the aforementioned embodiment, the present invention also provides a system for predicting the operation and control risks of photovoltaic units. The system can be implemented in hardware and / or software, and can generally be integrated into an electronic device to execute the method provided by any embodiment of the present invention. Figure 4 As shown, the system comprises:

[0071] The data interaction module 11 is used to establish data interaction with the photovoltaic unit and extract the mapping relationship between the light intensity and the power generation of the calibration environment based on the data interaction result;

[0072] An illumination prediction module 12 is used to collect and obtain illumination prediction data, wherein the illumination prediction data is obtained through the prediction window, and the illumination prediction data is illumination intensity prediction data;

[0073] A power prediction module 13, configured to perform real-time power generation prediction based on the light intensity prediction data and the mapping relationship, and generate a real-time power prediction result;

[0074] A shunt prediction module 14 is used to obtain real-time power supply demand data, perform power supply shunt prediction based on the real-time power supply demand data, and generate a shunt prediction control result;

[0075] A control fitting module 15 is used to read pre-control data of the photovoltaic unit, perform timing control fitting based on the pre-control data, and generate a timing control fitting result;

[0076] A risk prediction module 16, configured to perform control evaluation on the timing control fitting result through the diversion prediction control result to generate an operation control risk prediction result;

[0077] The control management module 17 is used to control and manage the photovoltaic unit based on the operation and control risk prediction results.

[0078] Furthermore, the power prediction module 13 is also used for:

[0079] Establishing a temperature adjustment parameter set of the temperature control unit, wherein each adjustment parameter in the temperature adjustment parameter set corresponds to a temperature control result, and the temperature adjustment parameter set is obtained through the data interaction result;

[0080] The control strategy of the temperature control unit is extracted through the pre-control data, and the heating fitting of the photovoltaic unit is performed through the light intensity prediction data to generate a heating fitting result;

[0081] Inputting the heating fitting result, the control strategy extraction result and the temperature adjustment parameter set into the temperature control evaluation network to generate a temperature control evaluation result;

[0082] The real-time power prediction result is compensated by the temperature control evaluation result.

[0083] Furthermore, the power prediction module 13 is also used for:

[0084] After the heating fitting result, the control strategy extraction result and the temperature adjustment parameter set are input into the temperature control evaluation network, the temperature trigger control fitting of heating is performed through the balance subnetwork to obtain the equilibrium temperature point of temperature control;

[0085] The equilibrium temperature point is synchronized to the delay evaluation subnetwork, the response delay is output through the delay evaluation subnetwork, and the equilibrium temperature point and the response delay are used as the temperature control evaluation result.

[0086] Furthermore, the power prediction module 13 is also used for:

[0087] Establishing a delay node through the response delay, and dividing the real-time power prediction result through the delay node to determine a steady-state power region and a control power region;

[0088] Performing power compensation on the steady-state power region through the equilibrium temperature point to obtain a first compensation result;

[0089] Calling the initial temperature according to the control start node, performing weighted temperature analysis of the control power area according to the initial temperature, the equilibrium temperature point and the response delay, and generating a second compensation result;

[0090] The real-time power prediction result is compensated by using the first compensation result and the second compensation result.

[0091] Furthermore, the risk prediction module 16 is also used for:

[0092] Performing a power steady-state mark on the real-time power prediction result;

[0093] Perform supply and demand balance analysis through the power steady-state identifier and real-time power supply demand data to determine the reserve control node of the battery;

[0094] A fitting comparison of the timing control fitting result is performed through the preliminary control node, and a control evaluation is completed based on the fitting comparison result.

[0095] Furthermore, the risk prediction module 16 is also used for:

[0096] Perform supply and demand balance analysis through the power steady-state identifier and real-time power supply demand data to determine the compensation power;

[0097] Configuring the conversion power loss of the battery, and predicting the total amount of battery compensation by using the conversion power loss and the compensation power, to generate a total amount of compensation prediction result;

[0098] A comparison is performed based on the total compensation amount prediction result and the battery power data, and an operation control risk report is issued based on the comparison result.

[0099] Furthermore, the control management module 17 is also used for:

[0100] Record and verify the operation control risk prediction results and generate record verification results;

[0101] Generating a window length and frequency constraint of a prediction window through the record verification result;

[0102] The acquisition optimization of subsequent illumination prediction data is performed through window length and frequency constraints.

[0103] The various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other and are not used to limit the scope of protection of the present invention.

[0104] Embodiment 3

[0105] Figure 5 The schematic diagram of the structure of the electronic device provided in the third embodiment of the present invention shows a block diagram of an exemplary electronic device suitable for implementing the implementation mode of the present invention. Figure 5The electronic device shown is only an example and should not limit the functions and scope of use of the embodiments of the present invention. Figure 5 As shown, the electronic device includes a processor 31, a memory 32, an input device 33 and an output device 34; the number of processors 31 in the electronic device can be one or more. Figure 5 Taking a processor 31 as an example, the processor 31, memory 32, input device 33 and output device 34 in the electronic device can be connected through a bus or other means. Figure 5 The example of connecting through bus is taken in the following.

[0106] The memory 32 is a computer-readable storage medium that can be used to store software programs, computer executable programs and modules, such as program instructions / modules corresponding to the operation and control risk prediction method for photovoltaic units in the embodiment of the present invention. The processor 31 executes various functional applications and data processing of the computer device by running the software programs, instructions and modules stored in the memory 32, that is, realizing the above-mentioned operation and control risk prediction method for photovoltaic units.

[0107] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A method for predicting operation and control risks of photovoltaic units, characterized in that: The method comprises: Establish data interaction with the photovoltaic unit, and extract the mapping relationship between the light intensity and power generation of the calibration environment based on the data interaction results; Acquire illumination prediction data, wherein the illumination prediction data is acquired through the prediction window, and the illumination prediction data is illumination intensity prediction data; Perform real-time power generation prediction based on the light intensity prediction data and the mapping relationship to generate a real-time power prediction result; Acquire real-time power supply demand data, perform power supply diversion prediction based on the real-time power supply demand data, and generate diversion prediction control results; Reading pre-control data of the photovoltaic group, performing timing control fitting based on the pre-control data, and generating a timing control fitting result; Performing control evaluation on the timing control fitting result through the diversion prediction control result to generate an operation control risk prediction result; Control and manage photovoltaic units through operation and control risk prediction results; The method further comprises: Establishing a temperature adjustment parameter set of the temperature control unit, wherein each adjustment parameter in the temperature adjustment parameter set corresponds to a temperature control result, and the temperature adjustment parameter set is obtained through the data interaction result; The control strategy of the temperature control unit is extracted through the pre-control data, and the heating fitting of the photovoltaic unit is performed through the light intensity prediction data to generate a heating fitting result; Inputting the heating fitting result, the control strategy extraction result and the temperature adjustment parameter set into the temperature control evaluation network to generate a temperature control evaluation result; Compensating the real-time power prediction result by using the temperature control evaluation result; The method further comprises: After the heating fitting result, the control strategy extraction result and the temperature adjustment parameter set are input into the temperature control evaluation network, the temperature trigger control fitting of heating is performed through the balance subnetwork to obtain the equilibrium temperature point of temperature control; Synchronize the equilibrium temperature point to the delay evaluation subnetwork, output the response delay through the delay evaluation subnetwork, and use the equilibrium temperature point and the response delay as the temperature control evaluation result; The method further comprises: Establishing a delay node through the response delay, and dividing the real-time power prediction result through the delay node to determine a steady-state power region and a control power region; Performing power compensation on the steady-state power region through the equilibrium temperature point to obtain a first compensation result; Calling the initial temperature according to the control start node, performing weighted temperature analysis of the control power area according to the initial temperature, the equilibrium temperature point and the response delay, and generating a second compensation result; Compensating the real-time power prediction result by using the first compensation result and the second compensation result; The method further comprises: Performing a power steady-state mark on the real-time power prediction result; Perform supply and demand balance analysis through the power steady-state identifier and real-time power supply demand data to determine the reserve control node of the battery; Performing a fitting comparison of the timing control fitting result through the preliminary control node, and completing a control evaluation based on the fitting comparison result; The method further comprises: Perform supply and demand balance analysis through the power steady-state identifier and real-time power supply demand data to determine the compensation power; Configuring the conversion power loss of the battery, and predicting the total amount of battery compensation by using the conversion power loss and the compensation power, to generate a total amount of compensation prediction result; A comparison is performed based on the total compensation amount prediction result and the battery power data, and an operation control risk report is issued based on the comparison result.

2. The method according to claim 1, characterized in that The method further comprises: Record and verify the operation control risk prediction results and generate record verification results; Generating a window length and frequency constraint of a prediction window through the record verification result; The acquisition optimization of subsequent illumination prediction data is performed through window length and frequency constraints.

3. The operation and control risk prediction system for photovoltaic units is characterized by: The system comprises: A data interaction module is used to establish data interaction with the photovoltaic unit and extract the mapping relationship between the light intensity of the calibration environment and the power generation based on the data interaction result; An illumination prediction module, used for collecting and obtaining illumination prediction data, wherein the illumination prediction data is obtained through collection of a prediction window, and the illumination prediction data is illumination intensity prediction data; A power prediction module, used to perform real-time power generation prediction based on the light intensity prediction data and the mapping relationship, and generate a real-time power prediction result; A shunt prediction module is used to obtain real-time power supply demand data, perform power supply shunt prediction based on the real-time power supply demand data, and generate a shunt prediction control result; A control fitting module is used to read the pre-control data of the photovoltaic group, perform timing control fitting based on the pre-control data, and generate a timing control fitting result; A risk prediction module, used to perform control evaluation on the timing control fitting result through the diversion prediction control result to generate an operation control risk prediction result; The control management module is used to control and manage the photovoltaic units based on the operation and control risk prediction results; The power prediction module is also used for: Establishing a temperature adjustment parameter set of the temperature control unit, wherein each adjustment parameter in the temperature adjustment parameter set corresponds to a temperature control result, and the temperature adjustment parameter set is obtained through the data interaction result; The control strategy of the temperature control unit is extracted through the pre-control data, and the heating fitting of the photovoltaic unit is performed through the light intensity prediction data to generate a heating fitting result; Inputting the heating fitting result, the control strategy extraction result and the temperature adjustment parameter set into the temperature control evaluation network to generate a temperature control evaluation result; Compensating the real-time power prediction result by using the temperature control evaluation result; After the heating fitting result, the control strategy extraction result and the temperature adjustment parameter set are input into the temperature control evaluation network, the temperature trigger control fitting of heating is performed through the balance subnetwork to obtain the equilibrium temperature point of temperature control; Synchronize the equilibrium temperature point to the delay evaluation subnetwork, output the response delay through the delay evaluation subnetwork, and use the equilibrium temperature point and the response delay as the temperature control evaluation result; Establishing a delay node through the response delay, and dividing the real-time power prediction result through the delay node to determine a steady-state power region and a control power region; Performing power compensation on the steady-state power region through the equilibrium temperature point to obtain a first compensation result; Calling the initial temperature according to the control start node, performing weighted temperature analysis of the control power area according to the initial temperature, the equilibrium temperature point and the response delay, and generating a second compensation result; Compensating the real-time power prediction result by using the first compensation result and the second compensation result; The risk prediction module is also used for: Performing a power steady-state mark on the real-time power prediction result; Perform supply and demand balance analysis through the power steady-state identifier and real-time power supply demand data to determine the reserve control node of the battery; Performing a fitting comparison of the timing control fitting result through the preliminary control node, and completing a control evaluation based on the fitting comparison result; The risk prediction module is also used for: Perform supply and demand balance analysis through the power steady-state identifier and real-time power supply demand data to determine the compensation power; Configuring the conversion power loss of the battery, and predicting the total amount of battery compensation by using the conversion power loss and the compensation power, to generate a total amount of compensation prediction result; A comparison is performed based on the total compensation amount prediction result and the battery power data, and an operation control risk report is issued based on the comparison result.

4. An electronic device, characterized in that: The electronic device comprises: A memory for storing executable instructions; The processor is used to implement the operation and control risk prediction method for a photovoltaic unit as described in any one of claims 1 to 2 when executing the executable instructions stored in the memory.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for predicting operation and control risks of a photovoltaic unit as described in any one of claims 1-2 is implemented.

Images