New energy grid-connected stability control system based on wind, solar and energy storage joint optimization

Abstract

The present invention discloses a new energy grid-connected stable control system based on wind, photovoltaic and storage joint optimization, which belongs to the technical field of new energy grid-connected. The present invention solves the problem of insufficient practicality of the existing control system, predicts multiple groups of historical electric energy data through a deep network model, and obtains multiple groups of normal operation results and operation failure results; imports real-time electric energy data into the deep network model for prediction, and compares its results with the normal operation results to determine whether it is currently normal; if it is not normal, retrieve the corresponding control scheme according to the fault factor; when obtaining real-time electric energy data, wind, photovoltaic and energy storage data are also obtained, and the minimum critical value of energy storage is preset. When the electric energy reserve of any system in the wind power generation system or the photovoltaic power generation system is lower than the minimum critical value, an alarm message is sent to the client to timely adjust the power supply mode of wind, photovoltaic and energy storage to the power grid system; thereby ensuring the stable operation of new energy after grid connection and improving the practicality of the control system.

Description

Technical Field

[0001] The present invention relates to the technical field of new energy grid-connected technology, and specifically to a new energy grid-connected stable control system based on wind, solar and energy storage joint optimization. Background Art

[0002] In the new era of advocating low-carbon economy, energy conservation and emission reduction, and ecological civilization construction, wind energy, solar energy, etc. have become important new energy sources for building a "resource-saving and environmentally friendly" society; combining wind power generation systems and photovoltaic power generation systems into an organic whole to support the storage, transportation and use of energy can largely meet the huge demand for energy from the population and economy; and it has the advantages of energy conservation and less negative impact on the surrounding ecological environment.

[0003] Grid-connected control refers to the process of effectively connecting and coordinating the operation of renewable energy power generation systems with the power grid, aiming to achieve real-time communication and dispatch between renewable energy power generation systems and the power grid, ensure a stable power supply and store excess power for emergency use. In the grid-connected control of renewable energy power generation systems, the key is to solve two major problems: one is to achieve seamless connection between renewable energy power generation systems and the power grid to ensure the continuity and stability of power supply; the other is to reasonably dispatch and control the operating status of renewable energy power generation systems to optimize energy utilization efficiency.

[0004] However, there are many unstable factors in the operation of existing new energy sources after grid connection, and the instability prediction results are inaccurate, resulting in the lack of practicality of the existing control system.

[0005] Therefore, the existing needs are not met. In response to this, we propose a new energy grid-connected stability control system based on the joint optimization of wind, solar and storage. Summary of the invention

[0006] The purpose of the present invention is to provide a new energy grid-connected stable control system based on wind, solar and storage joint optimization, predict multiple groups of historical electric energy data through a deep network model, and obtain multiple groups of normal operation results and operation fault results; import real-time electric energy data into the deep network model for prediction, and compare its results with the normal operation results to determine whether it is currently normal; if abnormal, retrieve the corresponding control scheme according to the fault factor; when obtaining real-time electric energy data, wind, solar and storage data are also obtained, and the minimum critical value of energy storage is preset. When the electric energy reserve of any system in the wind power generation system or the photovoltaic power generation system is lower than the minimum critical value, an alarm message is sent to the client to timely adjust the power supply mode of wind, solar and storage to the power grid system, ensure the stable operation of new energy after grid connection, and solve the problems raised in the above-mentioned background technology.

[0007] To achieve the above purpose, the present invention provides the following technical solution: a new energy grid-connected stability control system based on wind, solar and energy storage joint optimization, including:

[0008] Stable prediction subsystem for

[0009] According to the deep network model, multiple groups of historical power data after the wind power generation system and the photovoltaic power generation system are connected to the grid are simulated, trained and tested to obtain multiple groups of operation test results after the new energy is connected to the grid; the multiple groups of operation test results include: operation stability results and operation failure results. The operation stability results are used as the critical point data for operation stability after the new energy is connected to the grid, and the deep network model optimized by the test is used as the prediction model;

[0010] Energy storage and collection subsystem for

[0011] Used to collect the power reserve status of wind power generation system and photovoltaic power generation system in real time, and transmit the acquired power reserve status to the human-computer interaction terminal based on wireless transmission technology;

[0012] Stability control subsystem for

[0013] The operation failure results are used as the operation failure simulation phenomenon after the new energy is connected to the grid. According to the operation failure simulation phenomenon, and combined with the power conversion reserve status, a corresponding control plan is established to form a new energy grid connection stability control database;

[0014] Real-time analysis subsystem for

[0015] Collect the power conversion data of wind power generation system and photovoltaic power generation system in real time, and transmit the power conversion data to the stability prediction subsystem and human-computer interaction terminal for prediction and display based on wireless transmission technology; after obtaining the prediction results, retrieve the corresponding control scheme through the new energy grid-connected stability control database;

[0016] Human-computer interaction terminal, used for

[0017] Real-time display of deep network model prediction and analysis results, power reserve status in wind power generation systems and photovoltaic power generation systems, and new energy grid-connected stability control database.

[0018] Furthermore, the stability prediction subsystem includes:

[0019] Data collection module for

[0020] Collect multiple sets of historical power data after the wind power generation system and photovoltaic power generation system are connected to the grid, and clean the multiple sets of historical power data;

[0021] Data partitioning module for

[0022] Divide the multiple groups of historical power data after cleaning into training sets and test sets. The training set is used to confirm the characteristics of the deep network model, and the test set is used to optimize the accuracy of the deep network model prediction.

[0023] Data prediction module for

[0024] The divided training set is imported into the deep network model for training to obtain the power supply operation model; the test set is then imported into the trained neural network model for testing, and the power supply operation prediction result is output; according to the above method, multiple groups of historical electric energy data are successively imported into the deep network model for training and testing to obtain the operation stability result and operation failure result respectively.

[0025] Furthermore, the energy storage collection subsystem includes:

[0026] Energy storage acquisition module for

[0027] Obtain the power collection and storage data of the wind power generation system and the photovoltaic power generation system, and determine the current power reserve status of the wind power generation system and the photovoltaic power generation system;

[0028] Timing transmission module for

[0029] Create a data transmission interval in advance, and after the energy storage acquisition module acquires data, transmit the power reserve data to the human-computer interaction terminal according to the transmission interval;

[0030] Processing storage module for

[0031] The received electric energy reserve data is cleaned, duplicate data and erroneous data are deleted, and the processed electric energy reserve data is stored in time series according to the collection time point.

[0032] Furthermore, the stability control subsystem includes:

[0033] Result filtering module for

[0034] Screening out operation fault results from multiple groups of operation test results, and classifying the operation fault results into wind power generation system operation fault results and photovoltaic power generation system operation fault results;

[0035] Scheme creation module for

[0036] Create corresponding control plans for wind power generation system operation failure results and photovoltaic power generation system operation failure results, and classify and store the control plans in the human-computer interaction terminal to form a new energy grid-connected stable control database;

[0037] Retrieval service module for

[0038] Create control scheme search keywords based on operating fault factors and the type of power generation system to which they belong.

[0039] Furthermore, the real-time analysis subsystem includes:

[0040] Data acquisition module for

[0041] Deploy electric energy collection terminals, collect real-time electric energy supply data from wind power generation systems and photovoltaic power generation systems through the electric energy collection terminals, clean the real-time electric energy supply data and transmit it to the stable prediction subsystem for prediction processing, and transmit the electric energy supply data and prediction results to the human-computer interaction terminal for display;

[0042] Solution retrieval module for

[0043] Based on the human-computer interaction terminal as the solution retrieval interface, the corresponding control solution is retrieved from the new energy grid-connected stability control database according to the prediction results.

[0044] Furthermore, the processing and storage module includes:

[0045] Critical warning unit for

[0046] The minimum critical value of the electric energy reserve data in the wind power generation system and the photovoltaic power generation system is preset, and a warning signal is sent to the human-computer interaction terminal when the electric energy reserve data is lower than the minimum critical value.

[0047] Furthermore, among the multiple groups of operation test results, there are two groups of stable operation results, including: stable operation results of wind power generation system and stable operation results of photovoltaic power generation system; there are no less than four groups of operation failure results, including: no less than two groups of operation failure results of wind power generation system and no less than two groups of operation failure results of photovoltaic power generation system, and the number of groups of control schemes created according to the operation failure results is consistent with the number of groups of operation failure results.

[0048] Furthermore, when the real-time collected power reserve data of the wind power generation system and the photovoltaic power generation system is lower than the minimum critical value, the critical alarm unit sends a warning value number to the human-computer interaction terminal to remind the client to adjust the power supply mode of wind and solar energy storage in time.

[0049] Furthermore, the stability control subsystem includes:

[0050] A reading module, used to read the operation fault result and determine the operation fault data corresponding to the operation fault result;

[0051] A fault type determination module is used to obtain known fault types of the running fault data and use the known fault types of the running fault data as data type labels;

[0052] Data classification module for:

[0053] Construct a data feature identifier corresponding to each data type label based on the data type label;

[0054] Read the data identifier of the running fault data, and calculate the similarity between the data identifier of the running fault data and the data feature identifier corresponding to each data type label;

[0055] Obtain a similarity threshold, and store the target operating fault data corresponding to which the similarity between the data identifier of the operating fault data and the data feature identifier corresponding to each data type label is greater than the similarity threshold in the storage interval corresponding to the corresponding data type label;

[0056] Data analysis module for:

[0057] Reading a target operation fault data set corresponding to a same known fault type in a storage interval, and determining a marginal value of an operation fault occurring in the corresponding known fault type;

[0058] New energy grid-connected stability control decision model building module, used for:

[0059] According to the marginal value of the operation failure corresponding to each known fault type, the operation failure marginal condition of each known fault type is constructed;

[0060] Determine the control scheme corresponding to each known fault type based on the power conversion reserve status, and combine the operating fault edge condition with the control scheme to generate a fault-control pair corresponding to each fault type;

[0061] Each fault type is used as a first learning node, and the fault-control pair corresponding to each fault type is used as a second learning node;

[0062] The first learning node is associated with the second learning node to obtain a learning line, and the first learning node, the second learning node and the learning line are learned, and a new energy grid-connected stability control decision model is constructed according to the learning results;

[0063] The auxiliary decision-making module is used to assist in decision-making and control of operating faults based on the new energy grid-connected control decision model.

[0064] Furthermore, the stability control subsystem also includes power stability control after the new energy is connected to the grid, specifically including:

[0065] The first calculation module is used to obtain the blade area, wind energy conversion efficiency and wind power generator efficiency of the wind power generation, and calculate the output power of the wind power generation according to the blade area, wind energy conversion efficiency and wind power generator efficiency of the wind power generation.

[0066]

[0067] Among them, P windrepresents the output power of wind power generation; ρ represents the air density; S1 represents the blade area; v represents the wind speed; η1 represents the wind energy conversion efficiency; η2 represents the wind power generation motor efficiency;

[0068] The second computing module is used for:

[0069] Obtain the area of ​​the photovoltaic panel, solar radiation intensity, photovoltaic conversion efficiency and inverter efficiency during photovoltaic power generation;

[0070] The photovoltaic power generation output power is calculated according to the area of ​​the photovoltaic panel, the solar radiation intensity, the photovoltaic conversion efficiency and the inverter efficiency during photovoltaic power generation;

[0071] P 光伏 =S2*G sun *η3*η4;

[0072] Among them, P 光伏 represents the photovoltaic power output power; S2 represents the photovoltaic panel area; G sun represents the solar radiation intensity; η3 represents the photovoltaic conversion efficiency; η4 represents the inverter efficiency;

[0073] A power balance control function building module is used to build a power balance control function based on the wind power generation output power and the photovoltaic power generation output power;

[0074] f(P balance )=P balance ;

[0075]

[0076] Among them, f(P balance ) represents the power balance control function; P balance Indicates balanced power; P demand represents the total required power; min(·) represents the minimum value; Indicates the maximum energy storage discharge power; P stored represents the stored energy; Indicates the minimum state of charge value; η5 indicates the efficiency of the energy storage system; Indicates the maximum energy storage charging power; P available Indicates the available energy storage power; P discharge Indicates the energy storage discharge power;

[0077] Balance control module for:

[0078] The power balance control function is learned, a power balance control model is constructed, and the wind power generation output power and photovoltaic power generation output power of the wind power generation system after the new energy is connected to the grid are monitored in real time, and the output power is input into the power balance control model for analysis, and the power balance control instruction is output;

[0079] The power balance of the system after the new energy is connected to the grid is controlled based on the power balance control instruction.

[0080] Compared with the prior art, the present invention has the following beneficial effects:

[0081] The present invention predicts multiple groups of historical electric energy data through a deep network model, thereby obtaining multiple groups of operation status prediction results. Since the multiple groups of data include normal operation data and fault data, the multiple groups of results also include normal operation results and operation fault results; the real-time electric energy data is imported into the deep network model for prediction and the prediction results are obtained, which are compared with the normal operation results to determine whether the current prediction results are normal; if abnormal, the corresponding control scheme is retrieved according to the fault factor, thereby ensuring the stable operation of the new energy after the grid is connected; secondly, when obtaining the real-time electric energy data of the wind and solar systems, the wind and solar energy storage data is also obtained, and the minimum critical value of the energy storage is preset. When the electric energy reserve of any system in the wind power generation system or the photovoltaic power generation system is lower than the minimum critical value, an alarm message is sent to the client so that the client can adjust the power supply mode of the wind and solar energy storage to the power grid system in time; thereby further ensuring the stable operation of the new energy after the grid is connected, and improving the practicality of the existing control system.

[0082] By reading the operation fault result, the operation fault data corresponding to the operation fault result is determined, and the operation fault data can be effectively classified through the known fault type of the operation fault data, so that by storing it in the corresponding storage interval, the effective reading of the target operation fault data set in the same fault type can be improved, and by determining the first learning node and the second learning node and the learning line and learning, the construction of the new energy grid-connected control decision model can be effectively realized, so as to realize auxiliary decision-making control of the operation fault based on the new energy grid-connected control decision model, which effectively improves the intelligence, effectiveness and accuracy of the new energy grid-connected stable control.

[0083] By accurately calculating the output power of wind power generation and photovoltaic power generation, the power balance control function based on wind power generation and photovoltaic power generation can be effectively constructed. By learning the power balance control function, the construction of the power balance control model can be effectively realized. Then, the power balance control instructions can be effectively generated through the power balance control model, thereby realizing the power balance control of the system after the new energy is connected to the grid, effectively ensuring the stable operation of the new energy after the grid is connected, and improving the practicability of the existing control system. BRIEF DESCRIPTION OF THE DRAWINGS

[0084] Figure 1 This is a composition diagram of the new energy grid-connected stability control system based on wind, solar and energy storage joint optimization of the present invention;

[0085] Figure 2This is a detailed diagram of the new energy grid-connected stability control system based on wind, solar and storage joint optimization of the present invention. DETAILED DESCRIPTION

[0086] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0087] In order to solve the technical problem that there are many unstable factors in the operation of existing new energy after grid connection, the unstable prediction results are inaccurate, resulting in the lack of practicality of the existing control system, please refer to Figure 1-Figure 2 This embodiment provides the following technical solution

[0088] In this embodiment, for example, a power system needs to predict its operating status after the wind power generation system and the photovoltaic power generation system are connected to the grid to ensure the stable operation of the power system after the new energy is connected to the grid, and ensure that the power supply of the new energy always meets the power demand of the power system.

[0089] The new energy grid-connected stability control system based on wind, solar and energy storage joint optimization includes:

[0090] Stable prediction subsystem for

[0091] According to the deep network model, multiple groups of historical electric energy data after the wind power generation system and the photovoltaic power generation system were connected to the grid were simulated and trained and tested, and multiple groups of operation test results after the new energy was connected to the grid were obtained; the multiple groups of operation test results included: operation stability results and operation failure results. The operation stability results were used as the critical point data for the operation stability after the new energy was connected to the grid, and the deep network model after test optimization was used as the prediction model; specifically, in order to ensure the accuracy of the operation prediction after the new energy was connected to the grid, the collection of electric energy data in the early stage is no longer a single collection of data under normal conditions, but the collection of operation stability data and operation failure data for prediction, thereby enriching the feature set of the deep network model and ensuring the accuracy of the deep network model prediction.

[0092] Stable prediction subsystem, including:

[0093] Data collection module for

[0094] Collect multiple groups of historical power data after the wind power generation system and the photovoltaic power generation system are connected to the grid, and clean the multiple groups of historical power data; in this embodiment, such as: after collecting multiple groups of historical power data after the wind power generation system and the photovoltaic power generation system are connected to the grid, first classify the data according to the system category, and divide it into wind power data and photovoltaic data, and then classify the two major types of data in detail, and divide the wind power data into normal wind power data and wind power fault data, and divide the photovoltaic data into normal photovoltaic data and photovoltaic fault data; after classifying the data, delete the repeatedly transmitted data and the erroneous or missing data in the multiple groups of data to ensure the validity of the data.

[0095] Data partitioning module for

[0096] The multiple groups of historical electric energy data after cleaning are divided into training sets and test sets, the training set is used to confirm the characteristics of the deep network model, and the test set is used to optimize the accuracy of the deep network model prediction; Continuing with the above embodiment, such as: after classifying and cleaning the multiple groups of data, the valid data in the wind power data and photovoltaic data are divided into wind power training sets and wind power test sets as well as photovoltaic training sets and photovoltaic test sets in turn, so as to distinguish the usage direction of each data.

[0097] Data prediction module for

[0098] The divided training set is imported into the deep network model for training to obtain the power supply operation model; the test set is then imported into the trained neural network model for testing, and the power supply operation prediction result is output; according to the above method, multiple groups of historical electric energy data are successively imported into the deep network model for training and testing to obtain the operation stability result and the operation failure result respectively; following the above embodiment, such as: after classifying and cleaning multiple groups of data, four groups of wind power training sets and wind power test sets and four groups of photovoltaic training sets and photovoltaic test sets are obtained, the four groups of wind power training sets and wind power test sets include two groups of operation data and two groups of operation failure data, each group of operation data and operation failure data includes a training set and a test set, and the same is true for the four groups of photovoltaic training sets and photovoltaic test sets; therefore, the above eight The training set and the test set are sequentially imported into the deep network model for prediction, thereby outputting eight groups of prediction results. The four groups of stable operation results output by the four groups of normal operating data are classified into one category, and the data are compared for consistency; if they are consistent, it indicates that the prediction results of the deep network model are accurate; if they are inconsistent, it indicates that the prediction results of the deep network model are inaccurate, and the parameters of the deep network model need to be adjusted, and the test verification is performed again until the data of the four groups of stable operation results are consistent; then the four groups of operation fault results output by the four groups of normal fault data are analyzed, and corresponding adjustment and control plans are formulated for the fault factors of the four groups of results, and the control plans and fault factors are stored in the human-computer interaction terminal correspondingly, so as to provide a reference for the operation fault in the future.

[0099] Energy storage and collection subsystem for

[0100] It is used to collect the real-time energy reserve status of wind power generation systems and photovoltaic power generation systems, and transmit the acquired energy reserve status to the human-computer interaction terminal at regular intervals based on wireless transmission technology; specifically, by collecting the amount of wind and solar energy storage, it is convenient to understand the current status of wind and solar energy storage, and then facilitate early warning of the operating status after the new energy is connected to the grid.

[0101] Energy storage collection subsystem, including:

[0102] Energy storage acquisition module for

[0103] Obtain the electric energy collection and storage data in the wind power generation system and the photovoltaic power generation system, and determine the current electric energy reserve status of the wind power generation system and the photovoltaic power generation system; Continuing with the above embodiment, for example: obtaining the electric energy collection and storage data in the wind power generation system and the photovoltaic power generation system can be obtained by collecting the electric power of the reserve power source in the generator, thereby understanding the real-time data of wind and solar energy storage.

[0104] Timing transmission module for

[0105] Create a data transmission interval in advance, and after the energy storage acquisition module acquires the data, transmit the electric energy reserve data to the human-computer interaction terminal according to the transmission interval. Specifically, since the collection method for wind and solar energy storage is real-time collection, the time can be set for interval transmission within the collection time range during transmission, which ensures that the wind and solar energy storage data can be obtained normally while reducing the pressure on system operation.

[0106] Processing storage module for

[0107] Clean the received electric energy reserve data, delete duplicate data and erroneous data, and store the processed electric energy reserve data in time series according to the collection time point;

[0108] Processing storage modules, including:

[0109] Critical warning unit for

[0110] The minimum critical value of the electric energy reserve data in the wind power generation system and the photovoltaic power generation system is pre-set, and a warning signal is sent to the human-computer interaction terminal when the electric energy reserve data is lower than the minimum critical value; when the electric energy reserve data in the wind power generation system and the photovoltaic power generation system collected in real time is lower than the minimum critical value, a warning value signal is sent to the human-computer interaction terminal through the critical alarm unit to remind the client to adjust the power supply mode of wind and solar energy storage in time; Continuing with the above embodiment: For example, the amount of wind power storage energy depends on the capacity of the wind power plant and the choice of energy storage technology; Generally speaking, the amount of electricity that can be stored in one round of wind power generation is between 10-30%, so the wind power storage critical value is set to The value is 10%, and then the critical value is set according to the actual number of photovoltaic panels and the illumination time. In this scheme, the critical value of photovoltaic energy storage is set to 15%; when the power energy storage of the wind turbine in the wind power generation system is obtained to be between 10-30%, it indicates that the wind power energy storage is normal, and the normal operation of the power grid can be guaranteed after it is connected to the grid; when the power energy storage of the wind turbine is below 10%, it indicates that the wind power storage is reduced, and the normal operation of the power grid cannot be guaranteed after it is connected to the grid, and the power supply source of the power grid needs to be switched in time. The wind power supply channel can be closed and the photovoltaic power supply can be connected to the power grid line; similarly, the critical value of photovoltaic energy storage is consistent with the above-mentioned wind power system.

[0111] Stability control subsystem for

[0112] The operation failure results are used as the operation failure simulation phenomenon after the new energy is connected to the grid. According to the operation failure simulation phenomenon and combined with the power conversion reserve status, the corresponding control plan is established to form a new energy grid-connected stable control database.

[0113] Stability control subsystem, including:

[0114] Result filtering module for

[0115] The operation fault results are screened out from multiple groups of operation test results, and the operation fault results are classified into wind power generation system operation fault results and photovoltaic power generation system operation fault results; specifically, after the operation fault results are classified according to the above description, the aesthetics of the interface of the new energy grid-connected stability control database is improved, and the efficiency of data query is improved.

[0116] Scheme creation module for

[0117] Corresponding control schemes are created for the operation failure results of the wind power generation system and the operation failure results of the photovoltaic power generation system, and the control schemes are classified and stored in the human-computer interaction terminal to form a new energy grid-connected stable control database; wherein, there are two groups of stable operation results in the multiple groups of operation test results, including: stable operation results of the wind power generation system and stable operation results of the photovoltaic power generation system; therefore, the operation failure results are four or more groups, including: no less than two groups of operation failure results of the wind power generation system and no less than two groups of operation failure results of the photovoltaic power generation system, and the number of groups of control schemes created according to the operation failure results is consistent with the number of groups of operation failure results; following the above embodiment: such as: pouring the wind power system data and the photovoltaic system data into the deep network model for prediction respectively; when a fault warning appears in the wind power system prediction result, a control scheme can be formulated according to the phenomenon, such as: closing the wind power supply channel and connecting the photovoltaic power supply to the power grid line; otherwise, closing the photovoltaic power supply channel and connecting the wind power supply to the power grid line.

[0118] Retrieval service module for.

[0119] Create control scheme search keywords based on operating fault factors and the category of the power generation system to which it belongs; continuing with the above embodiment, for example, words with certain factors such as "wind power generation", "wind power failure", "photovoltaic power generation", "photovoltaic failure" can be created as search keywords to improve the search efficiency of the scheme.

[0120] Real-time analysis subsystem for

[0121] The power conversion data of the wind power generation system and the photovoltaic power generation system are collected in real time, and based on the wireless transmission technology, the power conversion data are transmitted to the stability prediction subsystem and the human-computer interaction terminal for prediction and display; after the prediction results are obtained, the corresponding control scheme is retrieved through the new energy grid-connected stability control database; specifically, the power conversion data of the wind power generation system and the photovoltaic power generation system are: the voltage data of the wind power generation system and the photovoltaic power generation system connected to the power supply network, by obtaining the real-time voltage data of the two types of new energy after grid connection, and importing the real-time voltage data into the deep network model for training and testing, thereby outputting the current new energy grid-connected operation prediction results, so that when a prediction failure occurs, the operation mode of the new energy after grid connection can be adjusted in time.

[0122] Real-time analysis subsystem, including:

[0123] Data acquisition module for

[0124] An electric energy collection terminal is deployed, and real-time electric energy supply data from the wind power generation system and the photovoltaic power generation system are collected according to the electric energy collection terminal. The real-time electric energy supply data is cleaned and then transmitted to the stable prediction subsystem for prediction processing, and the electric energy supply data and the prediction result are transmitted to the human-computer interaction terminal for display; Continuing with the above embodiment, for example: the electric energy collection terminal is a voltage sensor, and the voltage sensor is respectively deployed on the electric wires connecting the wind turbine and the photovoltaic generator to the power supply system, so that the voltage data transmitted by the wind power system and the photovoltaic system can be collected in real time, thereby providing effective data for system operation prediction.

[0125] Solution retrieval module for

[0126] Based on the human-computer interaction terminal as the solution retrieval interface, the corresponding control solution is retrieved in the new energy grid-connected stability control database according to the prediction results; in the above embodiments, such as: "wind power generation", "wind power failure", "photovoltaic power generation", "photovoltaic failure", etc. have been created. When searching, the predicted failure factors can be combined with the above but not limited to the above keywords to obtain the required control solution, and implement it according to the existing control solution, or implement the existing control solution in combination with the actual situation.

[0127] Human-computer interaction terminal, used for

[0128] Real-time display of deep network model prediction and analysis results, power reserve status in wind power generation systems and photovoltaic power generation systems, and new energy grid-connected stability control database.

[0129] The beneficial effects achieved by the above content are as follows: through the above method, the output normal operation results are used as the critical point reference data of the prediction results, the operation fault results are used as the fault simulation site, and the corresponding control plan is established according to the fault factors; thereby improving the accuracy of the system prediction and ensuring the stable operation of the new energy after the grid connection; secondly, the reserve amount of wind, solar and energy storage is warned to prevent the normal power supply from being affected by too low energy storage, further ensuring the stable operation of the new energy after the grid connection, and improving the practicability of the existing control system.

[0130] Working principle: Multiple groups of historical electric energy data are predicted through a deep network model, thereby obtaining multiple groups of operation status prediction results. Since the multiple groups of data include normal operation data and fault data, the multiple groups of results also include normal operation results and operation fault results; the real-time electric energy data is imported into the deep network model for prediction and the prediction results are output, which are compared with the normal operation results to determine whether the current prediction results are normal; if not, the corresponding control scheme is retrieved according to the fault factors; secondly, when obtaining the real-time electric energy data of the wind and solar systems, the wind and solar energy storage data is also obtained, and the minimum critical value of energy storage is preset. When the electric energy reserve of any system in the wind power generation system or the photovoltaic power generation system is lower than the minimum critical value, an alarm message is sent to the client so that the client can adjust the power supply method of the wind and solar energy storage to the power grid system in time.

[0131] In one embodiment, the stability control subsystem includes:

[0132] A reading module, used to read the operation fault result and determine the operation fault data corresponding to the operation fault result;

[0133] A fault type determination module is used to obtain known fault types of the running fault data and use the known fault types of the running fault data as data type labels;

[0134] Data classification module for:

[0135] Construct a data feature identifier corresponding to each data type label based on the data type label;

[0136] Read the data identifier of the running fault data, and calculate the similarity between the data identifier of the running fault data and the data feature identifier corresponding to each data type label;

[0137] Obtain a similarity threshold, and store the target operating fault data corresponding to which the similarity between the data identifier of the operating fault data and the data feature identifier corresponding to each data type label is greater than the similarity threshold in the storage interval corresponding to the corresponding data type label;

[0138] Data analysis module for:

[0139] Reading a target operation fault data set corresponding to a same known fault type in a storage interval, and determining a marginal value of an operation fault occurring in the corresponding known fault type;

[0140] New energy grid-connected stability control decision model building module, used for:

[0141] According to the marginal value of the operation failure corresponding to each known fault type, the operation failure marginal condition of each known fault type is constructed;

[0142] Determine the control scheme corresponding to each known fault type based on the power conversion reserve status, and combine the operating fault edge condition with the control scheme to generate a fault-control pair corresponding to each fault type;

[0143] Each fault type is used as a first learning node, and the fault-control pair corresponding to each fault type is used as a second learning node;

[0144] The first learning node is associated with the second learning node to obtain a learning line, and the first learning node, the second learning node and the learning line are learned, and a new energy grid-connected stability control decision model is constructed according to the learning results;

[0145] The auxiliary decision-making module is used to assist in decision-making and control of operating faults based on the new energy grid-connected control decision model.

[0146] In this embodiment, the known fault type can be determined for each situation based on the operating fault results obtained after simulation training and testing of multiple groups of historical power data.

[0147] In this embodiment, the data type label may be used to distinguish known fault types.

[0148] In this embodiment, the storage intervals correspond to the known fault types one by one, wherein the storage intervals store the target operation fault data set corresponding to each known fault type.

[0149] In this embodiment, the similarity threshold may be set in advance to implement classification of the operation fault data.

[0150] In this embodiment, the edge value may be the minimum threshold and the maximum threshold corresponding to the currently known fault type, that is, when the operation data is in the edge value (the interval corresponding to the minimum threshold and the maximum threshold), it is operation fault data.

[0151] In this embodiment, the fault edge condition may be a determination condition corresponding to the occurrence of an operating fault in currently known fault types.

[0152] In this embodiment, the new energy grid-connected stability control decision model may be used to implement an auxiliary decision control strategy corresponding to the operating fault output by the new energy grid-connected stability control decision model when an operating fault occurs.

[0153] In this embodiment, the fault-control pair can be a standard data used for auxiliary decision-making. The control strategy corresponding to different fault types can be determined through the fault-control pair.

[0154] The working principle and beneficial effects of the above technical solution are: by reading the operation fault result, the operation fault data corresponding to the operation fault result is determined, and the operation fault data is effectively classified through the known fault type of the operation fault data, so that by storing it in the corresponding storage interval, the effective reading of the target operation fault data set in the same fault type can be improved, and by determining the first learning node and the second learning node and the learning line and learning, the construction of the new energy grid-connected control decision model can be effectively realized, so as to realize auxiliary decision-making control of the operation fault based on the new energy grid-connected control decision model, and effectively improve the intelligence, effectiveness and accuracy of the new energy grid-connected stable control.

[0155] In one embodiment, the stability control subsystem further includes power stability control after the new energy source is connected to the grid, specifically including:

[0156] The first calculation module is used to obtain the blade area, wind energy conversion efficiency and wind power generator efficiency of the wind power generation, and calculate the output power of the wind power generation according to the blade area, wind energy conversion efficiency and wind power generator efficiency of the wind power generation.

[0157]

[0158] Among them, P wind represents the output power of wind power generation; ρ represents the air density; S1 represents the blade area; v represents the wind speed; η1 represents the wind energy conversion efficiency; η2 represents the wind power generation motor efficiency;

[0159] The second computing module is used for:

[0160] Obtain the area of ​​the photovoltaic panel, solar radiation intensity, photovoltaic conversion efficiency and inverter efficiency during photovoltaic power generation;

[0161] The photovoltaic power generation output power is calculated according to the area of ​​the photovoltaic panel, the solar radiation intensity, the photovoltaic conversion efficiency and the inverter efficiency during photovoltaic power generation;

[0162] P 光伏 =S2*G sun *η3*η4;

[0163] Among them, P 光伏 represents the photovoltaic power output power; S2 represents the photovoltaic panel area; G sun represents the solar radiation intensity; η3 represents the photovoltaic conversion efficiency; η4 represents the inverter efficiency;

[0164] A power balance control function building module is used to build a power balance control function based on the wind power generation output power and the photovoltaic power generation output power;

[0165] f(Pbalance )=P balance ;

[0166]

[0167] Among them, f(P balance ) represents the power balance control function; P balance Indicates balanced power; P demand represents the total required power; min(·) represents the minimum value; Indicates the maximum energy storage discharge power; P stored represents the stored energy; Indicates the minimum state of charge value; η5 indicates the efficiency of the energy storage system; Indicates the maximum energy storage charging power; P available Indicates the available energy storage power; P discharge Indicates the energy storage discharge power;

[0168] Balance control module for:

[0169] The power balance control function is learned, a power balance control model is constructed, and the wind power generation output power and photovoltaic power generation output power of the wind power generation system after the new energy is connected to the grid are monitored in real time, and the output power is input into the power balance control model for analysis, and the power balance control instruction is output;

[0170] The power balance of the system after the new energy is connected to the grid is controlled based on the power balance control instruction.

[0171] The working principle and beneficial effects of the above technical solution are: by accurately calculating the output power of wind power generation and the output power of photovoltaic power generation, a power balance control function based on wind power generation and photovoltaic power generation is effectively constructed, and by learning the power balance control function, the construction of the power balance control model is effectively realized, and then the power balance control instructions are effectively generated through the power balance control model, thereby realizing the power balance control of the system after the new energy is connected to the grid, effectively ensuring the stable operation of the new energy after the grid is connected, and improving the practicability of the existing control system.

[0172] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0173] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A new energy grid-connected stability control system based on wind, solar and energy storage joint optimization, characterized by: include: Stable prediction subsystem for Based on the deep network model, multiple groups of historical power data after the wind power generation system and photovoltaic power generation system were connected to the grid were simulated and tested to obtain multiple groups of operation test results after the new energy was connected to the grid; Multiple groups of operation test results include: operation stability results and operation failure results. The operation stability results are used as the critical point data for operation stability after the new energy is connected to the grid, and the deep network model optimized by the test is used as the prediction model; Energy storage and collection subsystem for It is used to collect the power reserve status of wind power generation system and photovoltaic power generation system in real time, and transmit the acquired power reserve status to the human-computer interaction terminal based on wireless transmission technology; Stability control subsystem for The operation fault results are used as the operation fault simulation phenomenon after the new energy is connected to the grid. According to the operation fault simulation phenomenon, the corresponding control plan is established in combination with the power conversion reserve status to form a new energy grid connection stability control database; the stability control subsystem includes: A reading module, used to read the operation fault result and determine the operation fault data corresponding to the operation fault result; A fault type determination module is used to obtain known fault types of the running fault data and use the known fault types of the running fault data as data type labels; A data classification module is used to construct a data feature identifier corresponding to each data type label based on the data type label; read the data identifier of the operation fault data, and calculate the similarity between the data identifier of the operation fault data and the data feature identifier corresponding to each data type label; obtain a similarity threshold, and store the target operation fault data corresponding to the data feature identifier corresponding to each data type label whose similarity between the data identifier of the operation fault data and the data feature identifier corresponding to each data type label is greater than the similarity threshold into the storage interval corresponding to the corresponding data type label; A data analysis module, used for reading a target operation fault data set corresponding to a same known fault type in a storage interval, and determining a marginal value of an operation fault occurring in the corresponding known fault type; A new energy grid-connected stable control decision model construction module is used to construct the operating fault edge condition of each known fault type according to the edge value of the operating fault corresponding to each known fault type; determine the control scheme corresponding to each known fault type based on the power conversion reserve status, and combine the operating fault edge condition with the control scheme to generate a fault-control pair corresponding to each fault type; take each fault type as the first learning node, and at the same time, take the fault-control pair corresponding to each fault type as the second learning node; associate the first learning node with the second learning node to obtain a learning line, and learn the first learning node, the second learning node and the learning line, and construct a new energy grid-connected stable control decision model according to the learning results; Auxiliary decision-making module, used to assist in decision-making and control of operating faults based on the new energy grid-connected control decision model; The stability control subsystem also includes power stability control after the new energy is connected to the grid, including: The first calculation module is used to obtain the blade area, wind energy conversion efficiency and wind power generator efficiency of the wind power generation, and calculate the output power of the wind power generation according to the blade area, wind energy conversion efficiency and wind power generator efficiency of the wind power generation: Among them, P wind represents the output power of wind power generation; ρ represents the air density; S1 represents the blade area; v represents the wind speed; η1 represents the wind energy conversion efficiency; η2 represents the wind power generation motor efficiency; The second calculation module is used to obtain the area of ​​the photovoltaic panel, the solar radiation intensity, the photovoltaic conversion efficiency and the inverter efficiency during photovoltaic power generation; and calculate the photovoltaic power generation output power according to the area of ​​the photovoltaic panel, the solar radiation intensity, the photovoltaic conversion efficiency and the inverter efficiency during photovoltaic power generation: P 光伏 =S2*G sun *η3*η4; Among them, P 光伏 represents the photovoltaic power output power; S2 represents the photovoltaic panel area; G sun represents the solar radiation intensity; η3 represents the photovoltaic conversion efficiency; η4 represents the inverter efficiency; The power balance control function building module is used to build a power balance control function based on the wind power output power and the photovoltaic power output power: f(P balance )=P balance ; Among them, f(P balance ) represents the power balance control function; P balance Indicates balanced power; P demand represents the total required power; min(·) represents the minimum value; Indicates the maximum energy storage discharge power; P stored represents the stored energy; Indicates the minimum state of charge value; η5 indicates the efficiency of the energy storage system; Indicates the maximum energy storage charging power; P available Indicates the available energy storage power; P discharge Indicates the energy storage discharge power; The balance control module is used to learn the power balance control function, build a power balance control model, and monitor the wind power output power and photovoltaic power output power of the wind power generation system after the new energy is connected to the grid in real time, and input them into the power balance control model for analysis, output power balance control instructions, and control the power balance of the system after the new energy is connected to the grid based on the power balance control instructions; Real-time analysis subsystem for Collect the power conversion data of wind power generation system and photovoltaic power generation system in real time, and transmit the power conversion data to the stability prediction subsystem and human-computer interaction terminal for prediction and display based on wireless transmission technology; after obtaining the prediction results, retrieve the corresponding control scheme through the new energy grid-connected stability control database; Human-computer interaction terminal, used for Real-time display of deep network model prediction and analysis results, power reserve status in wind power generation systems and photovoltaic power generation systems, and new energy grid-connected stability control database.

2. The new energy grid-connected stability control system based on wind, solar and energy storage joint optimization according to claim 1 is characterized by: The stability prediction subsystem comprises: Data collection module for Collect multiple sets of historical power data after the wind power generation system and photovoltaic power generation system are connected to the grid, and clean the multiple sets of historical power data; Data partitioning module for Divide the multiple groups of historical power data after cleaning into training sets and test sets. The training set is used to confirm the characteristics of the deep network model, and the test set is used to optimize the accuracy of the deep network model prediction. Data prediction module for The divided training set is imported into the deep network model for training to obtain the power supply operation model; the test set is then imported into the trained neural network model for testing, and the power supply operation prediction result is output; according to the above method, multiple groups of historical electric energy data are successively imported into the deep network model for training and testing to obtain the operation stability result and operation failure result respectively.

3. The new energy grid-connected stability control system based on wind, solar and energy storage joint optimization according to claim 1 is characterized by: The energy storage collection subsystem comprises: Energy storage acquisition module for Obtain the power collection and storage data of the wind power generation system and the photovoltaic power generation system, and determine the current power reserve status of the wind power generation system and the photovoltaic power generation system; Timing transmission module for Create a data transmission interval in advance, and after the energy storage acquisition module acquires data, transmit the power reserve data to the human-computer interaction terminal according to the transmission interval; Processing storage module for The received electric energy reserve data is cleaned, duplicate data and erroneous data are deleted, and the processed electric energy reserve data is stored in time series according to the collection time point.

4. The new energy grid-connected stability control system based on wind, solar and energy storage joint optimization according to claim 1 is characterized by: The stability control subsystem comprises: Result filtering module for Screening out operation fault results from multiple groups of operation test results, and classifying the operation fault results into wind power generation system operation fault results and photovoltaic power generation system operation fault results; Scheme creation module for Create corresponding control plans for wind power generation system operation failure results and photovoltaic power generation system operation failure results, and classify and store the control plans in the human-computer interaction terminal to form a new energy grid-connected stable control database; Retrieval service module for Create control scheme search keywords based on operating fault factors and the type of power generation system to which they belong.

5. The new energy grid-connected stability control system based on wind, solar and energy storage joint optimization according to claim 1 is characterized by: The real-time analysis subsystem comprises: Data acquisition module for Deploy electric energy collection terminals, collect real-time electric energy supply data from wind power generation systems and photovoltaic power generation systems through the electric energy collection terminals, clean the real-time electric energy supply data and transmit it to the stable prediction subsystem for prediction processing, and transmit the electric energy supply data and prediction results to the human-computer interaction terminal for display; Solution retrieval module for Based on the human-computer interaction terminal as the solution retrieval interface, the corresponding control solution is retrieved from the new energy grid-connected stability control database according to the prediction results.

6. The new energy grid-connected stability control system based on wind, solar and energy storage joint optimization according to claim 3 is characterized by: The processing and storage module comprises: Critical warning unit for The minimum critical value of the electric energy reserve data in the wind power generation system and the photovoltaic power generation system is preset, and a warning signal is sent to the human-computer interaction terminal when the electric energy reserve data is lower than the minimum critical value.

7. The new energy grid-connected stability control system based on wind, solar and energy storage joint optimization according to claim 4 is characterized by: Among the multiple groups of operation test results, there are two groups of stable operation results, including: stable operation results of wind power generation system and stable operation results of photovoltaic power generation system; there are no less than four groups of operation failure results, including: no less than two groups of operation failure results of wind power generation system and no less than two groups of operation failure results of photovoltaic power generation system, and the number of groups of control schemes created according to the operation failure results is consistent with the number of groups of operation failure results.

8. The new energy grid-connected stability control system based on wind, solar and energy storage joint optimization according to claim 6 is characterized by: When the real-time collected power reserve data in the wind power generation system and photovoltaic power generation system is lower than the minimum critical value, the critical alarm unit sends a warning value number to the human-computer interaction terminal to remind the client to adjust the power supply mode of wind and solar energy storage in time.

Images