New energy station avc voltage target value optimization method and system based on voltage prediction, and medium

Abstract

The embodiment of the application discloses a new energy station AVC voltage target value optimization method and system based on voltage prediction, and a medium, the method comprises the following steps: acquiring real-time operation data of the new energy station in a preset time window, including real-time voltage, power generation power, load data and reactive power compensation device adjustment capacity; a comprehensive prediction model is built based on historical operation data and a neural network algorithm, and the prediction values of voltage, power generation power and load are output; the weight coefficients of real-time voltage data, predicted operation data and real-time adjustment data are determined according to the current state of the power grid, and the initial value of AVC voltage is calculated through linear weighted summation; finally, the initial value is checked and corrected according to the allowable range of the grid voltage, and the optimized AVC voltage target value is obtained, effectively solving the problem of voltage control under the dynamic change of the high-voltage power grid, realizing accurate prediction and regulation of the voltage, guaranteeing the stable operation of the power grid, and improving the overall benefit of the power system.

Description

Technical Field

[0001] This invention relates to the field of new energy power generation technology, and in particular to a method, system and medium for optimizing the target value of AVC voltage in new energy power plants based on voltage prediction. Background Technology

[0002] In the current power system, the power output of renewable energy power plants (such as wind farms and photovoltaic power plants) fluctuates significantly, posing a challenge to the stable operation of the power system. To ensure the safe and stable operation of the power grid, it is necessary to adjust the reactive power of renewable energy power plants in a timely manner to maintain a reasonable voltage level.

[0003] Traditional voltage regulation methods rely on manual monitoring and adjustment, which is not only inefficient but also susceptible to human error. Furthermore, traditional voltage data acquisition methods involve data collection at the beginning of an AVC command cycle. For example, when an AVC command cycle begins, the system triggers the data acquisition process, at which point the SCADA system transmits the collected voltage data from the renewable energy power plant to the AVC master station. Then, at fixed intervals (usually 5 minutes), the voltage target value is issued to the renewable energy power plant. After receiving the command, the AVC substation, based on its local control strategy, decomposes the voltage target value into specific reactive power regulation equipment, such as adjusting the reactive power of wind turbines and photovoltaic inverters, controlling the switching and output of reactive power compensation devices like SVCs and SVGs, and adjusting the tap positions of the main transformer, thereby achieving voltage control of the renewable energy power plant. Because voltage data acquisition occurs at the beginning of the command cycle, a considerable time has passed since the data acquisition time when the AVC command is actually issued. This time difference causes a significant deviation between the issued voltage target value and the real-time grid voltage. Taking a certain renewable energy power station as an example, during periods of rapid load change, the bus voltage may fluctuate by ±5% or even more within 1.5 minutes due to factors such as changes in renewable energy output and grid load fluctuations. This results in the voltage target value calculated based on the voltage data at the beginning of the command cycle being far from the actual voltage, failing to accurately reflect the actual demand of the current power grid for voltage regulation. Summary of the Invention

[0004] Based on this, it is necessary to propose a method, system, and medium for optimizing the target value of AVC voltage in new energy power plants based on voltage prediction, in order to address the above problems.

[0005] A voltage prediction-based AVC (Automatic Voltage Optimization) method for renewable energy power plants, the method comprising: Within a preset time window, real-time operating data of the new energy power station is acquired. The real-time operating data includes real-time voltage data, real-time power generation data, real-time load data, and real-time adjustment data of reactive power compensation equipment in the new energy power station. Based on historical operating data of new energy power plants and combined with neural network algorithms, a comprehensive prediction model is built. The comprehensive prediction model includes a voltage prediction model, a power generation prediction model, and a load prediction model. The historical operating data includes historical voltage data, historical power generation data, and historical load data. The real-time operating data is input into the comprehensive prediction model to output predicted operating data, which includes: voltage prediction value, power generation prediction value, and load prediction value. The weighting coefficients of the real-time voltage data, predicted operating data, and real-time adjustment data are determined based on the current state of the power grid. The initial value of AVC voltage is determined by linearly weighting and summing the real-time voltage data, predicted operating data, and real-time adjustment data according to the weighting coefficients. The target value of AVC voltage is determined by comparing the initial value of AVC voltage with the preset allowable range of grid voltage.

[0006] The step of comparing and verifying the initial AVC voltage value with the allowable range of the mains voltage to obtain the target AVC voltage value further includes: Determine the voltage adjustment command corresponding to the current state; Adjust the voltage of the new energy power station according to the voltage adjustment command, and obtain the adjusted feedback voltage data; If the absolute value of the difference between the feedback voltage data and the target AVC voltage value meets the preset allowable deviation range, the adjustment is considered effective.

[0007] Specifically, determining the voltage adjustment command corresponding to the current state includes: If the current state is an emergency state, the voltage regulation command is to adjust the output of the reactive power compensation equipment and reduce the active power at the same time; If the current state is stable, the voltage regulation command is to optimize the distribution of reactive power, rotate the operation of reactive power equipment, and adjust the voltage to the optimal mode that ensures the minimum network loss or the maximum voltage stability margin.

[0008] Specifically, determining the weighting coefficients for the real-time voltage data, predicted operating data, and real-time adjustment data based on the current state of the power grid includes: If the real-time voltage data is less than or equal to the first preset threshold, and the power grid is in an emergency state, then weight coefficients are assigned to the real-time voltage data, predicted operating data, and real-time adjustment data according to the preset first weight allocation rule. If the real-time voltage data is greater than the first preset threshold and less than the second preset threshold, and the current state of the power grid is stable, then weight coefficients are assigned to the real-time voltage data, predicted operating data, and real-time adjustment data according to the preset second weight allocation rule.

[0009] Specifically, determining the initial value of the AVC voltage by linearly weighting and summing the real-time voltage data, predicted operating data, and real-time adjustment data according to the weighting coefficients includes: according to ; in, The weighting coefficients for real-time voltage data. For real-time voltage data, The weighting coefficients for the voltage prediction values. This is the predicted voltage value. The weighting coefficients for the predicted power generation values. The dimension conversion factor for the predicted power generation value. This is the predicted power generation value. The dimension conversion factor for the load forecast value. This is the load forecast value. To adjust the dimension conversion coefficients of the data in real time, To adjust the data in real time.

[0010] Specifically, determining the target AVC voltage value based on a comparison between the initial AVC voltage value and a preset allowable range for the mains voltage includes: If the initial value of the AVC voltage is less than the minimum voltage value within the preset allowable range of the mains voltage, then according to Determine the target value of the AVC voltage, where, The target value for AVC voltage. This is the minimum voltage value; If the initial value of the AVC voltage is greater than the maximum voltage value within the preset allowable range of the mains voltage, then according to Determine the target value of the AVC voltage, where, The target value for AVC voltage. This is the maximum voltage value; If the initial value of the AVC voltage is within the preset allowable range of the mains voltage, then the initial value of the AVC voltage is the target value of the AVC voltage.

[0011] Before inputting the real-time operational data into the comprehensive prediction model to output the predicted operational data, the method further includes: The real-time running data is denoised using the Kalman filter algorithm, and missing data is supplemented using the Lagrange interpolation method to obtain preprocessed real-time running data.

[0012] A voltage prediction-based AVC voltage target value optimization system for renewable energy power plants, the system comprising: The data acquisition module is used to acquire real-time operating data of the new energy power station within a preset time window. The real-time operating data includes real-time voltage data, real-time power generation data, real-time load data, and real-time adjustment data of reactive power compensation equipment in the new energy power station. The predictive operation data acquisition module is used to build a comprehensive prediction model based on the historical operation data of the new energy power station and a neural network algorithm. The comprehensive prediction model includes a voltage prediction model, a power generation prediction model, and a load prediction model. The historical operation data includes historical voltage data, historical power generation data, and historical load data. The module inputs the real-time operation data into the comprehensive prediction model to output predicted operation data, which includes predicted voltage values, predicted power generation values, and predicted load values. The weighting coefficient determination module is used to determine the weighting coefficients of the real-time voltage data, predicted operation data, and real-time adjustment data based on the current state of the power grid. The AVC voltage initial value determination module is used to perform linear weighted summation of the real-time voltage data, predicted operation data and real-time adjustment data according to the weighting coefficient to determine the initial value of the AVC voltage. The AVC voltage target value determination module is used to determine the AVC voltage target value based on a comparison between the initial AVC voltage value and a preset allowable range of grid voltage.

[0013] The system also includes: The instruction issuance and closed-loop control module is used to determine the voltage adjustment instruction corresponding to the current state; adjust the voltage of the new energy power station according to the voltage adjustment instruction, and obtain the adjusted feedback voltage data; if the absolute value of the difference between the feedback voltage data and the AVC voltage target value meets the preset allowable deviation range, the adjustment is considered effective.

[0014] A computer-readable storage medium storing a computer program that, when executed by a processor, causes the processor to perform the steps of the method described above.

[0015] The embodiments of the present invention have the following beneficial effects: This invention acquires real-time operational data, meteorological data, and real-time adjustment data of reactive power compensation equipment in renewable energy power plants within a preset time window. The real-time operational data is input into a preset data prediction model, which outputs predicted operational data. The preset data prediction model comprehensively analyzes the real-time operational data of the renewable energy power plants to obtain accurate predicted operational data.

[0016] Furthermore, by dynamically adjusting the weights of real-time voltage data, predicted operating data, and real-time adjustment data based on the current state of the power grid, it can better adapt to the real-time operating state of the power grid, accurately adjust the initial value of AVC voltage under different levels of urgency, flexibly respond to various operating scenarios, and improve the accuracy and stability of voltage regulation.

[0017] Finally, based on the comparison between the initial value of the AVC voltage and the preset allowable range of the grid voltage, the target value of the AVC voltage is determined, which effectively solves the problem of voltage control under dynamic changes in the high-voltage grid, realizes accurate voltage prediction and regulation, ensures the stable operation of the grid, and improves the overall efficiency of the power system. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] in: Figure 1 This is a flowchart illustrating an embodiment of the voltage prediction-based AVC voltage optimization method for new energy power plants provided by the present invention. Figure 2 A flowchart illustrating another embodiment of the voltage prediction-based AVC voltage optimization method for new energy power plants provided by the present invention; Figure 3 A schematic diagram of an embodiment of the voltage prediction-based AVC voltage optimization system for new energy power plants provided by the present invention; Figure 4 A schematic diagram of the structure of an embodiment of the medium provided by the present invention. Detailed Implementation

[0020] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0021] like Figure 1 As shown, Figure 1 This is a flowchart illustrating an embodiment of the voltage prediction-based AVC voltage optimization method for renewable energy power plants provided by the present invention. The method includes: S101: Within a preset time window, acquire real-time operating data of the new energy power station. The real-time operating data includes real-time voltage data, real-time power generation data, real-time load data, and real-time adjustment data of reactive power compensation equipment in the new energy power station.

[0022] For example, within a preset time window, such as a very short period of time before the instruction is issued (e.g., 10-20 seconds), real-time operating data of the new energy power station is collected every 1-2 seconds. The real-time operating data includes real-time voltage data, real-time power generation data, real-time load data, and real-time adjustment data of reactive power compensation equipment in the new energy power station.

[0023] The Kalman filter algorithm is used to denoise the real-time operating data, removing abnormal data caused by electromagnetic interference, equipment noise, and other factors, thereby improving the accuracy and reliability of the data. Simultaneously, by combining data interpolation algorithms, such as Lagrange interpolation, any missing data can be supplemented, ensuring data integrity.

[0024] S102: Based on the historical operating data of new energy power plants and combined with neural network algorithms, a comprehensive prediction model is built. The comprehensive prediction model includes a voltage prediction model, a power generation prediction model, and a load prediction model. The historical operating data includes historical voltage data, historical power generation data, and historical load data.

[0025] S103: Input real-time operating data into the comprehensive prediction model to output predicted operating data, which includes: voltage prediction value, power generation prediction value, and load prediction value.

[0026] For example, based on historical operating data of new energy power plants, historical operating data includes historical voltage data, historical power generation data, and historical load data, as well as meteorological data (such as solar irradiance, wind speed, temperature, etc. For wind power plants, wind speed data can be obtained through an anemometer installed near the wind turbine, with an accuracy of up to 0.1 m / s; for photovoltaic power plants, solar irradiance data can be collected through professional solar sensors, with an accuracy of up to 1 Lux), and other multi-source data. For historical operating data, linear interpolation is used to fill in missing values. Outliers are identified and replaced using the 3σ principle. All data are normalized and mapped to the [0,1] interval. After data preprocessing, features that are strongly correlated with voltage changes are selected according to the type of new energy power station. A time series feature matrix is ​​constructed using the sliding window method to clarify the correspondence between input features and output voltage.

[0027] Furthermore, neural network algorithms, such as Long Short-Term Memory (LSTM) networks, are used to build a comprehensive forecasting model, which includes a voltage forecasting model, a power generation forecasting model, and a load forecasting model. LSTM models can effectively handle long-term dependencies in time series data and are suitable for forecasting data with dynamic characteristics.

[0028] Furthermore, historical operational data is used to train the model. This data is divided into training, validation, and test sets according to a certain ratio, such as 70% for training, 20% for validation, and 10% for testing. During training, the backpropagation algorithm is used to adjust the model parameters to minimize the error between predicted and actual values, such as mean squared error (MSE). Simultaneously, adaptive learning rate adjustment strategies, such as Adagrad and Adadelta algorithms, are used to dynamically adjust the learning rate, accelerating model convergence and improving training effectiveness. Based on the latest real-time data, the model is regularly updated and optimized, such as updating it daily in the early morning when the grid load is low and the data is relatively stable, to adapt to the dynamic changes in the grid's operating status and improve prediction accuracy.

[0029] Furthermore, real-time operational data is input into the comprehensive prediction model to output predicted operational data, which includes: voltage prediction, power generation prediction, and load prediction.

[0030] S104: Determine the weighting coefficients for real-time voltage data, predicted operating data, and real-time adjustment data based on the current state of the power grid.

[0031] For example, based on the real-time operating status of the power grid, the weight coefficients of each factor are dynamically allocated (the sum of the weights satisfies Σw_i=1, i=1,2,3,4,5), and the specific rules are as follows: If the real-time voltage data is less than or equal to a first preset threshold, and the power grid is currently in an emergency state, then weighting coefficients are assigned to the real-time voltage data, predicted operating data, and real-time adjustment data according to a preset first weighting allocation rule. Specifically, in an emergency state (such as when the voltage drops rapidly to a certain threshold), weighting coefficients are assigned to the real-time voltage data, predicted operating data, and real-time adjustment data. , (Rated voltage): Prioritize voltage stability and set weighting coefficients for real-time voltage data. Weighting coefficient of voltage prediction value Weighting coefficient of power generation forecast Weighting coefficients of load forecast values Adjusting the weighting coefficients of the data in real time .

[0032] If the real-time voltage data is greater than a first preset threshold and less than a second preset threshold, and the power grid is currently in a stable state, then weight coefficients are assigned to the real-time voltage data, predicted operating data, and real-time adjustment data according to a preset second weight allocation rule. Specifically, in a stable state (such as...), To balance network loss optimization and equipment lifespan, a weighting factor for real-time voltage data is set. Weighting coefficient of voltage prediction value Weighting coefficient of power generation forecast Weighting coefficients of load forecast values Adjusting the weighting coefficients of the data in real time ; The formula for dynamically adjusting the weighting coefficients is: ; in, Let be the dynamic weight of the i-th factor at time t. The baseline weight for the i-th factor (the weight coefficients under the above emergency / stable conditions). The baseline state index ( =0.95), S(t) is the power grid operation status evaluation index at time t, reflecting the degree of voltage deviation from the rated value, as shown in the following formula: .

[0033] S105: Perform a linear weighted summation of the real-time voltage data, predicted operating data, and real-time adjustment data based on the weighting coefficients to determine the initial value of the AVC voltage.

[0034] For example, the initial value of the AVC voltage is determined according to the following formula: ; in, The weighting coefficients for real-time voltage data. For real-time voltage data, The weighting coefficients for the voltage prediction values. This is the predicted voltage value. The weighting coefficients for the predicted power generation values. The dimension conversion factor for the predicted power generation value. This is the predicted power generation value. The dimension conversion factor for the load forecast value. This is the load forecast value. To adjust the dimension conversion coefficients of the data in real time, To adjust the data in real time.

[0035] S106: Determine the target value of AVC voltage based on the comparison between the initial value of AVC voltage and the preset allowable range of grid voltage.

[0036] For example, the preset allowable range of mains voltage is: ,in, This is the initial value of the AVC voltage. This is the minimum voltage value within the preset allowable range of mains voltage. This is the maximum voltage value within the preset allowable range of grid voltage.

[0037] If the initial value of the AVC voltage is less than the minimum voltage value within the preset allowable range of the mains voltage, then the target value of the AVC voltage is determined according to the following formula: ; in, The target value for AVC voltage. This is the minimum voltage value; If the initial value of the AVC voltage is greater than the maximum voltage value within the preset allowable range of the mains voltage, then the target value of the AVC voltage is determined according to the following formula: ; in, The target value for AVC voltage. This is the maximum voltage value; If the initial value of the AVC voltage is within the preset allowable range of the mains voltage, then the initial value of the AVC voltage is the target value of the AVC voltage.

[0038] As described above, this invention acquires real-time operational data, meteorological data, and real-time adjustment data of reactive power compensation equipment in new energy power plants within a preset time window. The real-time operational data is input into a preset data prediction model, which outputs predicted operational data. The preset data prediction model comprehensively analyzes the real-time operational data of the new energy power plants to obtain accurate predicted operational data.

[0039] Furthermore, by dynamically adjusting the weights of real-time voltage data, predicted operating data, and real-time adjustment data based on the current state of the power grid, it can better adapt to the real-time operating state of the power grid, accurately adjust the initial value of AVC voltage under different levels of urgency, flexibly respond to various operating scenarios, and improve the accuracy and stability of voltage regulation.

[0040] Finally, based on the comparison between the initial value of the AVC voltage and the preset allowable range of the grid voltage, the target value of the AVC voltage is determined, which effectively solves the problem of voltage control under dynamic changes in the high-voltage grid, realizes accurate voltage prediction and regulation, ensures the stable operation of the grid, and improves the overall efficiency of the power system.

[0041] like Figure 2 As shown, Figure 2 This is a flowchart illustrating another embodiment of the voltage prediction-based AVC voltage optimization method for renewable energy power plants provided by the present invention. A voltage prediction-based AVC voltage optimization method for renewable energy power plants includes: S201: Within a preset time window, acquire real-time operating data of the new energy power station. The real-time operating data includes real-time voltage data, real-time power generation data, real-time load data, and real-time adjustment data of reactive power compensation equipment in the new energy power station.

[0042] S202: Based on the historical operating data of the new energy power station and combined with the neural network algorithm, a comprehensive prediction model is built. The comprehensive prediction model includes a voltage prediction model, a power generation prediction model, and a load prediction model. The historical operating data includes historical voltage data, historical power generation data, and historical load data.

[0043] S203: Input real-time operating data into the comprehensive prediction model to output predicted operating data, which includes: voltage prediction, power generation prediction, and load prediction.

[0044] S204: Determine the weighting coefficients for real-time voltage data, predicted operating data, and real-time adjustment data based on the current state of the power grid.

[0045] S205: Based on the weighting coefficients, perform a linear weighted summation of the real-time voltage data, predicted operating data, and real-time adjustment data to determine the initial value of the AVC voltage.

[0046] S206: Determine the target value of AVC voltage based on the comparison between the initial value of AVC voltage and the preset allowable range of grid voltage.

[0047] It should be noted that steps S201-S206 are in Figure 1 The implementation scenarios shown have been discussed in detail and will not be repeated here.

[0048] S207: Determine the voltage regulation command corresponding to the current state.

[0049] For example, if the current state is an emergency state, the voltage regulation command adjusts the output of the reactive power compensation device in the direction of preventing the emergency state from continuing to expand or worsen (e.g., if the voltage is low, the reactive power compensation device will generate capacitive reactive power; if the voltage is high, the reactive power compensation device will generate inductive reactive power; the specific adjustment amount is determined according to the dynamic voltage regulation coefficient at each moment), while limiting the further increase of active power or reducing active power.

[0050] If the current state is stable, the voltage regulation command is to optimize the distribution of reactive power according to the principle of hierarchical and zoned local balance, rotate the operation of reactive power equipment, and adjust the voltage to the optimal mode that ensures the minimum network loss or the maximum voltage stability margin.

[0051] S208: Adjusts the voltage of the new energy power station according to the voltage regulation command and obtains the adjusted feedback voltage data.

[0052] S209: If the absolute value of the difference between the feedback voltage data and the AVC voltage target value meets the preset allowable deviation range, the adjustment is considered effective.

[0053] For example, if the absolute value of the difference between the feedback voltage data and the AVC voltage target value meets the preset allowable deviation range... like If the adjustment is successful, it is considered effective, a valid tag is added, and the same strategy is used to generate the voltage adjustment command for the next cycle; if the preset allowable deviation range is not met, i.e. If an adjustment is deemed invalid, it is labeled as invalid. If a certain number of consecutive or cumulative invalid adjustments occur (the number of invalid labels exceeds a certain amount in a short period of time or cumulatively), an alarm is issued and the function is deactivated. The model is then put back into verification after manual verification and optimization, so that the model can be continuously improved. Ultimately, this ensures that the number of invalid adjustments decreases within the statistical period, thereby achieving precise control of the operating voltage of new energy power stations by the dispatching end.

[0054] like Figure 3 As shown, Figure 3 This is a schematic diagram of an embodiment of the AVC voltage optimization system for renewable energy power plants based on voltage prediction provided by the present invention. A voltage prediction-based AVC voltage target value optimization system 10 for renewable energy power plants includes: The data acquisition module 11 is used to acquire real-time operating data of the new energy power station within a preset time window. The real-time operating data includes real-time voltage data, real-time power generation data, real-time load data, and real-time adjustment data of reactive power compensation equipment in the new energy power station.

[0055] The predictive operation data acquisition module 12 is used to build a comprehensive prediction model based on the historical operation data of the new energy power station and the neural network algorithm. The comprehensive prediction model includes a voltage prediction model, a power generation prediction model, and a load prediction model. The historical operation data includes historical voltage data, historical power generation data, and historical load data. The module inputs real-time operation data into the comprehensive prediction model and outputs predicted operation data, which includes voltage prediction value, power generation prediction value, and load prediction value.

[0056] The weighting coefficient determination module 13 is used to determine the weighting coefficients of real-time voltage data, predicted operation data, and real-time adjustment data based on the current state of the power grid.

[0057] The AVC voltage initial value determination module 14 is used to determine the initial value of AVC voltage by performing a linear weighted summation of the real-time voltage data, predicted operating data, and real-time adjustment data according to the weighting coefficients.

[0058] The AVC voltage target value determination module 15 is used to determine the AVC voltage target value based on the comparison between the initial AVC voltage value and the preset allowable range of the mains voltage.

[0059] For example, in the data acquisition module 11, real-time operating data of the new energy power station is acquired within a preset time window. This real-time operating data includes real-time voltage data, real-time power generation data, real-time load data, and real-time adjustment data of the reactive power compensation equipment in the new energy power station. The real-time operating data is denoised using a Kalman filter algorithm, and missing data is supplemented using Lagrange interpolation to obtain preprocessed real-time operating data. In the predictive operating data acquisition module 12, a comprehensive prediction model is built based on the historical operating data of the new energy power station combined with a neural network algorithm. This comprehensive prediction model includes a voltage prediction model, a power generation prediction model, and a load prediction model. The historical operating data includes historical voltage data, historical power generation data, and historical load data. The real-time operating data is input to the comprehensive prediction model to output predicted operating data, which includes predicted voltage values, predicted power generation values, and predicted load values.

[0060] Furthermore, in the weight coefficient determination module 13, if the real-time voltage data is less than or equal to the first preset threshold, the current state of the power grid is in an emergency state, and weight coefficients are assigned to the real-time voltage data, predicted operating data, and real-time adjustment data according to the preset first weight allocation rule; if the real-time voltage data is greater than the first preset threshold and less than the second preset threshold, the current state of the power grid is in a stable state, and weight coefficients are assigned to the real-time voltage data, predicted operating data, and real-time adjustment data according to the preset second weight allocation rule.

[0061] Furthermore, in the AVC voltage initial value determination module 14, the real-time voltage data, predicted operating data, and real-time adjustment data are linearly weighted and summed according to the weighting coefficients to determine the AVC voltage initial value.

[0062] Finally, in the AVC voltage target value determination module 15, if the initial value of the AVC voltage is less than the minimum voltage value within the preset allowable range of the mains voltage, then according to... Determine the target value of the AVC voltage, where, The target value for AVC voltage. This is the minimum voltage value; if the initial AVC voltage value is greater than the maximum voltage value within the preset allowable range of mains voltage, then according to... Determine the target value of the AVC voltage, where, The target value for AVC voltage. This is the maximum voltage value; like Figure 4 As shown, Figure 4 This is a schematic diagram of the structure of an embodiment of the medium provided by the present invention. The medium 20 stores at least one computer program 21, which is executed by a processor to perform the following... Figure 1 and Figure 2 The method shown is detailed above and will not be repeated here. In one embodiment, the medium 20 can be a storage chip, hard disk, portable hard disk, USB flash drive, optical disk, or other read / write storage device, or even a server, etc.

[0063] Furthermore, the processes depicted in the accompanying drawings do not necessarily have to be performed in the specific or sequential order shown to achieve the desired result. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0064] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments of apparatus, devices, and non-volatile computer-readable storage media are basically similar to the method embodiments, and therefore described more simply; relevant parts can be referred to the descriptions of the method embodiments.

[0065] The apparatus, device, non-volatile computer-readable storage medium and method provided in the embodiments of this specification are corresponding. Therefore, the apparatus, device and non-volatile computer storage medium also have similar beneficial technical effects as the corresponding method. Since the beneficial technical effects of the method have been described in detail above, the beneficial technical effects of the corresponding apparatus, device and non-volatile computer storage medium will not be repeated here.

[0066] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0067] For ease of description, the above apparatus is described by dividing it into various functional units. Of course, in implementing this specification, the functions of each unit can be implemented in one or more software and / or hardware components. Those skilled in the art will understand that the embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, the embodiments of this specification can take the form of computer program products implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0068] This specification is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this specification. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0069] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0070] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0071] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0072] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0073] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0074] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0075] This specification can be described in the general context of computer-executable instructions that are executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. This specification can also be practiced in distributed computing environments, where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0076] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0077] The above description discloses only preferred embodiments of the present invention and should not be construed as limiting the scope of the present invention. Therefore, equivalent variations made in accordance with the claims of the present invention are still within the scope of the present invention.

Claims

1. A voltage optimization method for AVC (Automatic Voltage Control) at renewable energy power plants based on voltage prediction, characterized in that, The method includes: Within a preset time window, real-time operating data of the new energy power station is acquired. The real-time operating data includes real-time voltage data, real-time power generation data, real-time load data, and real-time adjustment data of reactive power compensation equipment in the new energy power station. Based on historical operating data of new energy power plants and combined with neural network algorithms, a comprehensive prediction model is built. The comprehensive prediction model includes a voltage prediction model, a power generation prediction model, and a load prediction model. The historical operating data includes historical voltage data, historical power generation data, and historical load data. The real-time operating data is input into the comprehensive prediction model to output predicted operating data, which includes: voltage prediction value, power generation prediction value, and load prediction value. The weighting coefficients of the real-time voltage data, predicted operating data, and real-time adjustment data are determined based on the current state of the power grid. The initial value of AVC voltage is determined by linearly weighting and summing the real-time voltage data, predicted operating data, and real-time adjustment data according to the weighting coefficients. The target value of AVC voltage is determined by comparing the initial value of AVC voltage with the preset allowable range of grid voltage.

2. The method for optimizing AVC voltage in new energy power plants based on voltage prediction according to claim 1, characterized in that, After comparing and verifying the initial AVC voltage value with the allowable range of the mains voltage to obtain the target AVC voltage value, the process further includes: Determine the voltage adjustment command corresponding to the current state; Adjust the voltage of the new energy power station according to the voltage adjustment command, and obtain the adjusted feedback voltage data; If the absolute value of the difference between the feedback voltage data and the target AVC voltage value meets the preset allowable deviation range, the adjustment is considered effective.

3. The method for optimizing the target value of AVC voltage in new energy power plants based on voltage prediction according to claim 2, characterized in that, The determination of the voltage adjustment command corresponding to the current state specifically includes: If the current state is an emergency state, the voltage regulation command is to adjust the output of the reactive power compensation equipment and reduce the active power at the same time; If the current state is stable, the voltage regulation command is to optimize the distribution of reactive power, rotate the operation of reactive power equipment, and adjust the voltage to the optimal mode that ensures the minimum network loss or the maximum voltage stability margin.

4. The method for optimizing the target value of AVC voltage in new energy power plants based on voltage prediction according to claim 1, characterized in that, The determination of weighting coefficients for the real-time voltage data, predicted operating data, and real-time adjustment data based on the current state of the power grid specifically includes: If the real-time voltage data is less than or equal to the first preset threshold, and the power grid is in an emergency state, then weight coefficients are assigned to the real-time voltage data, predicted operating data, and real-time adjustment data according to the preset first weight allocation rule. If the real-time voltage data is greater than the first preset threshold and less than the second preset threshold, and the current state of the power grid is stable, then weight coefficients are assigned to the real-time voltage data, predicted operating data, and real-time adjustment data according to the preset second weight allocation rule.

5. The method for optimizing the target value of AVC voltage in new energy power plants based on voltage prediction according to claim 1, characterized in that, The step of determining the initial value of the AVC voltage by linearly weighting and summing the real-time voltage data, predicted operating data, and real-time adjustment data according to the weighting coefficients specifically includes: according to ； in, The weighting coefficients for real-time voltage data. For real-time voltage data, The weighting coefficients for the voltage prediction values. This is the predicted voltage value. The weighting coefficients for the predicted power generation values. The dimension conversion factor for the predicted power generation value. This is the predicted power generation value. The dimension conversion factor for the load forecast value. This is the load forecast value. To adjust the unit conversion coefficients of the data in real time, To adjust the data in real time.

6. The method for optimizing the target value of AVC voltage in new energy power plants based on voltage prediction according to claim 1, characterized in that, The step of determining the target AVC voltage value based on a comparison between the initial AVC voltage value and a preset allowable range of grid voltage specifically includes: If the initial value of the AVC voltage is less than the minimum voltage value within the preset allowable range of the mains voltage, then according to Determine the target value of the AVC voltage, where, The target value for AVC voltage. This is the minimum voltage value; If the initial value of the AVC voltage is greater than the maximum voltage value within the preset allowable range of the mains voltage, then according to Determine the target value of the AVC voltage, where, The target value for AVC voltage. This is the maximum voltage value; If the initial value of the AVC voltage is within the preset allowable range of the mains voltage, then the initial value of the AVC voltage is the target value of the AVC voltage.

7. The method for optimizing the target value of AVC voltage in new energy power plants based on voltage prediction according to claim 1, characterized in that, Before inputting the real-time operational data into the comprehensive prediction model to output the predicted operational data, the method further includes: The real-time running data is denoised using the Kalman filter algorithm, and missing data is supplemented using the Lagrange interpolation method to obtain preprocessed real-time running data.

8. A system for optimizing the target AVC voltage value of new energy power plants based on voltage prediction, characterized in that, The system includes: The data acquisition module is used to acquire real-time operating data of the new energy power station within a preset time window. The real-time operating data includes real-time voltage data, real-time power generation data, real-time load data, and real-time adjustment data of reactive power compensation equipment in the new energy power station. The predictive operation data acquisition module is used to build a comprehensive prediction model based on the historical operation data of the new energy power station and a neural network algorithm. The comprehensive prediction model includes a voltage prediction model, a power generation prediction model, and a load prediction model. The historical operation data includes historical voltage data, historical power generation data, and historical load data. The module inputs the real-time operation data into the comprehensive prediction model to output predicted operation data, which includes predicted voltage values, predicted power generation values, and predicted load values. The weighting coefficient determination module is used to determine the weighting coefficients of the real-time voltage data, predicted operation data, and real-time adjustment data based on the current state of the power grid. The AVC voltage initial value determination module is used to perform linear weighted summation of the real-time voltage data, predicted operation data and real-time adjustment data according to the weighting coefficient to determine the initial value of the AVC voltage. The AVC voltage target value determination module is used to determine the AVC voltage target value based on a comparison between the initial AVC voltage value and a preset allowable range of grid voltage.

9. A voltage prediction-based AVC voltage target value optimization system for new energy power plants according to claim 8, characterized in that, The system also includes: The instruction issuance and closed-loop control module is used to determine the voltage adjustment instruction corresponding to the current state; adjust the voltage of the new energy power station according to the voltage adjustment instruction, and obtain the adjusted feedback voltage data; if the absolute value of the difference between the feedback voltage data and the AVC voltage target value meets the preset allowable deviation range, the adjustment is considered effective.

10. A computer-readable storage medium storing a computer program that, when executed by a processor, causes the processor to perform the steps of the method as claimed in any one of claims 1 to 7.

Images