A method and device for optimizing AGC control strategy of thermal power unit

Abstract

The present application provides a method and device for optimizing the AGC control strategy of a thermal power unit, which relates to the field of power system control technology, including: receiving the real-time operating status of the thermal power unit and the predicted load in the future time zone; obtaining a reference AGC command signal and a reference power feedback signal through AGC control analysis component processing; receiving the reference signal when the predicted load in the future time zone is triggered; when the first AGC command signal is inconsistent with the reference AGC command signal, correcting the first AGC command signal; when the first power feedback signal is inconsistent with the reference power feedback signal, correcting the first power feedback signal. The present application can solve the technical problem in the prior art that the performance indicators of the AGC of the grid-connected unit have poor adjustment accuracy due to inaccurate adjustment and adjustment in coordinated control, and the remote control terminal continuously adjusts the field control terminal to correct the AGC command and power signal in real time, thereby improving the adjustment accuracy.

Description

Technical Field

[0001] The present application relates to the field of power system control technology, and in particular to a method and device for optimizing an AGC control strategy for a thermal power unit. Background Art

[0002] In modern power systems, thermal power units, as one of the main sources of electricity, undertake important load regulation tasks. In order to cope with the frequent load fluctuations of the power grid, the automatic generation control (AGC) system of thermal power units is widely used to achieve the stability and economy of the grid-connected units supporting the power grid. When the unit is in AGC mode, the power grid evaluates the unit through assessment indicators and makes corresponding compensation, which requires the thermal power unit to have a fast load response speed and control effect. At present, most thermal power units usually improve the assessment indicators by optimizing control strategies and digging deep into the unit's regulation performance, but the accuracy of AGC instructions and power signals has not been solved, that is, the regulation amount and the regulated amount in the coordinated control are inaccurate, resulting in poor regulation accuracy.

[0003] In summary, the prior art has a technical problem that the precision of the AGC command and power signal is not high enough, that is, the regulating quantity and the regulated quantity in the coordinated control are inaccurate, resulting in poor regulation precision of the performance indicators of the AGC of the grid-connected unit. Summary of the invention

[0004] The purpose of this application is to provide a method and device for optimizing the AGC control strategy of a thermal power unit, so as to solve the technical problem in the prior art that the accuracy of the AGC instructions and power signals is not high enough, that is, the regulating quantity and the regulated quantity in the coordinated control are not accurate, resulting in poor regulation accuracy of the performance indicators of the AGC of the grid-connected unit.

[0005] In view of the above problems, the present application provides a method and device for optimizing the AGC control strategy of a thermal power unit.

[0006] In the first aspect, the present application provides a method for optimizing an AGC control strategy of a thermal power unit, which is implemented by an AGC control strategy optimization device for a thermal power unit, wherein the method for optimizing an AGC control strategy of a thermal power unit includes: receiving the real-time operating status of the thermal power unit and the predicted load in the future time zone; sending the real-time operating status of the thermal power unit and the predicted load in the future time zone to an RTU mirror module, and processing them through the AGC control analysis component of the RTU mirror module to obtain a benchmark AGC command signal and a benchmark power feedback signal; when the predicted load in the future time zone is triggered in the future time zone, communicating with a DCS module, receiving a first AGC command signal and a first power feedback signal; when the first AGC command signal is inconsistent with the benchmark AGC command signal, correcting the first AGC command signal according to the benchmark AGC command signal, and when the first power feedback signal is inconsistent with the benchmark power feedback signal, correcting the first power feedback signal according to the benchmark power feedback signal.

[0007] In the second aspect, the present application also provides an AGC control strategy optimization device for a thermal power unit, which is used to execute an AGC control strategy optimization method for a thermal power unit as described in the first aspect, wherein the AGC control strategy optimization device for a thermal power unit includes: a data receiving module, the data receiving module is used to receive the real-time operating status of the thermal power unit and the predicted load in the future time zone; a component processing module, the component processing module is used to send the real-time operating status of the thermal power unit and the predicted load in the future time zone to the RTU mirror module, and obtain a reference AGC command signal and a reference power feedback signal through the AGC control analysis component processing of the RTU mirror module; a signal receiving module, the signal receiving module is used to communicate with the DCS module when the predicted load in the future time zone is triggered in the future time zone, and receive a first AGC command signal and a first power feedback signal; a signal correction module, the signal correction module is used to correct the first AGC command signal according to the reference AGC command signal when the first AGC command signal is inconsistent with the reference AGC command signal, and correct the first power feedback signal according to the reference power feedback signal when the first power feedback signal is inconsistent with the reference power feedback signal.

[0008] In a third aspect, the present application further provides an electronic device, including:

[0009] at least one processor;

[0010] a memory communicatively coupled to the at least one processor;

[0011] Wherein, the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the steps of a method for optimizing the AGC control strategy of a thermal power unit described in any one of the first aspects above.

[0012] In a fourth aspect, a computer-readable storage medium stores a computer program, and when the computer program is executed, the computer program implements the steps of the method for optimizing the AGC control strategy of a thermal power unit described in any one of the first aspects.

[0013] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0014] By receiving the real-time operating status of the thermal power unit and the predicted load in the future time zone; sending the real-time operating status of the thermal power unit and the predicted load in the future time zone to the RTU mirror module, and processing through the AGC control analysis component of the RTU mirror module to obtain the reference AGC command signal and the reference power feedback signal; when the predicted load in the future time zone is triggered in the future time zone, the communication DCS module receives the first AGC command signal and the first power feedback signal; when the first AGC command signal is inconsistent with the reference AGC command signal, the first AGC command signal is corrected according to the reference AGC command signal, and when the first power feedback signal is inconsistent with the reference power feedback signal, the first power feedback signal is corrected according to the reference power feedback signal. In other words, the remote control terminal continuously adjusts the field control terminal, uses the RTU mirror module to analyze the AGC command and power feedback, and corrects the inconsistent command and feedback signals, thereby improving the adjustment accuracy of the AGC.

[0015] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0017] Figure 1 A schematic diagram of a flow chart of an AGC control strategy optimization method for a thermal power unit in this application;

[0018] Figure 2 This is a schematic diagram of the structure of an AGC control strategy optimization device for a thermal power unit in this application;

[0019] Figure 3 This is a schematic diagram of the structure of an exemplary electronic device of the present application.

[0020] Explanation of the reference numerals: data receiving module 11 , component processing module 12 , signal receiving module 13 , signal correction module 14 , bus 300 , receiver 301 , processor 302 , transmitter 303 , memory 304 , bus interface 305 . DETAILED DESCRIPTION

[0021] The present application provides a method and device for optimizing the AGC control strategy of a thermal power unit, which solves the technical problem in the prior art that the precision of the AGC command and power signal is not high enough, that is, the adjustment amount and the adjusted amount in the coordinated control are not accurate, resulting in poor adjustment precision of the performance indicators of the AGC of the grid-connected unit. The remote control end continuously adjusts the field control end, uses the RTU mirror module to analyze the AGC command and power feedback, and corrects the inconsistent command and feedback signals, thereby improving the adjustment precision of the AGC.

[0022] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0023] For example, please refer to the attached Figure 1 The present application provides a method for optimizing an AGC control strategy of a thermal power plant, wherein the method for optimizing an AGC control strategy of a thermal power plant is applied to an AGC control strategy optimization device of a thermal power plant, and the method for optimizing an AGC control strategy of a thermal power plant specifically comprises the following steps:

[0024] Step 1: Receive the real-time operating status of thermal power units and the predicted load in future time zones.

[0025] Specifically, sensors and monitoring equipment are used to monitor the operating status of thermal power units in real time, including key parameters such as power generation, temperature, pressure, and efficiency. The target area where the thermal power units should supply power is matched, and the power load data corresponding to the current cycle in the future time zone is regularly collected. Statistical analysis methods, such as concentrated value analysis, are used to predict power demand in the future. Combining real-time data with forecast data can optimize power distribution and ensure stable power supply in various power grid areas.

[0026] Step 2: Send the real-time operating status of the thermal power unit and the predicted load in the future time zone to the RTU mirror module, and process them through the AGC control analysis component of the RTU mirror module to obtain a reference AGC command signal and a reference power feedback signal.

[0027] Specifically, the real-time operating status of the thermal power unit and the predicted load information of the future time zone are sent to the RTU mirror module. The RTU mirror module is a data acquisition and processing system that simulates the functions of the actual RTU and is used to receive and process the data of the thermal power unit. The AGC control analysis component is a part of the RTU mirror module, which is specifically used to analyze the AGC command signal and power feedback signal. The received data is processed by the AGC control analysis component, including data cleaning, engineering quantity conversion, statistical analysis, etc., to generate a benchmark AGC command signal and a benchmark power feedback signal. The RTU mirror module intercepts the position field according to the rules defined in the configuration file, parses the intercepted data, and performs engineering quantity conversion. The processed data will be written to the database and returned to the RTU mirror module to ensure the accuracy and integrity of the data. Through the automatic data acquisition and processing of the RTU mirror module, the data processing speed is accelerated and the system response efficiency is improved. By sending real-time data and predicted load to the RTU mirror module for processing, the AGC control strategy of the thermal power unit can more accurately generate a benchmark AGC command signal and a benchmark power feedback signal, thereby optimizing power distribution and scheduling.

[0028] Step 3: When the future time zone predicted load is triggered in the future time zone, the communication DCS module receives the first AGC command signal and the first power feedback signal.

[0029] Specifically, the predicted future time zone load is triggered in the actual future time zone, which means that the system's load demand has reached the preset standard. When the predicted load reaches or exceeds a certain threshold, it can be regarded as a trigger condition. The DCS module is an automation system for controlling and managing industrial processes. It consists of multiple distributed control units that are connected through a network and jointly manage the entire production process and are responsible for receiving and processing control signals. Communicate with the DCS (distributed control system) module, use the modbus program to collect the first AGC command signal and the first power feedback signal from the DCS, realize the collection of DCS data, and reflect the current power generation status of the thermal power unit. By communicating with the DCS module when the future time zone load is triggered and receiving the latest AGC command signal and power feedback signal, the AGC control strategy of the thermal power unit can more accurately adjust the power generation and maintain the frequency stability of the power grid.

[0030] Step 4: When the first AGC command signal is inconsistent with the reference AGC command signal, the first AGC command signal is corrected according to the reference AGC command signal; when the first power feedback signal is inconsistent with the reference power feedback signal, the first power feedback signal is corrected according to the reference power feedback signal.

[0031] Specifically, the first AGC command signal and the first power feedback signal collected from the DCS are compared and analyzed with the reference AGC command signal and the reference power feedback signal collected from the RTU mirror image to determine whether there are differences, identify and correct any deviations or errors, and obtain the analysis results. When the first AGC command signal is inconsistent with the reference AGC command signal, it means that there is a difference between the current AGC command signal and the ideal command signal. The analysis result is sent to the DCS through the AO module, and the first AGC command signal is corrected according to the reference AGC command signal, including replacement, adjustment of parameters or application of correction algorithms. When the first power feedback signal is inconsistent with the reference power feedback signal, it means that there is a difference between the actual output power and the expected power, and the first power feedback signal is corrected according to the reference power feedback signal. When correcting the AGC signal, it is necessary to consider the time synchronization problem between the RTU and DCS systems, because if the time of the two systems is not synchronized, it will cause signal delay or inconsistency, thereby affecting the overall control effect. Through real-time monitoring and adjustment, the accuracy of the AGC command and power feedback signals of the thermal power unit is ensured, and the regulation ability and response speed of the system are improved.

[0032] Furthermore, step one of this application includes:

[0033] According to the location number of the thermal power unit, the power supply target area is matched; with a 7-day period, the power load cross-section data of the future time zone is collected; the concentrated value analysis of the power load cross-section data of the same period is performed to obtain the predicted load of the future time zone; the thermal power unit is communicated to receive the real-time operating status of the thermal power unit.

[0034] Specifically, according to the bit number of the thermal power unit, the power plant and the specific unit to which it belongs are identified. According to the dispatching rules of the power grid and the power supply capacity of the unit, the thermal power unit is matched with a specific power supply target area to determine the target area to which the unit should supply power. The bit number is a unique identifier of the thermal power unit in the power grid system, usually including a combination of numbers and letters. The power supply target area refers to a specific area in the power grid, which has specific requirements and characteristics for power supply. In the SCADA system (supervisory control and data acquisition) or other load monitoring system of the power grid, the power load data corresponding to the current cycle in the future time zone is collected every 7 days. The future time zone refers to the time period after a specific time point. The cross-sectional data of the power load in the same period refers to the total power load in the power grid at a specific time point or time period, that is, the power load data in the same time period (for example, the same hour of each day).

[0035] Conduct concentrated value analysis on the cross-sectional data of power load in the same period, including calculating statistics such as mean, median, standard deviation, and identifying typical patterns and changing trends of load. By conducting concentrated value analysis on the cross-sectional data of power load in the same period, a representative value can be obtained to reflect the average power load in the time period. Using the results of concentrated value analysis, the power load in future time zones can be predicted through time series analysis, machine learning models or other prediction technologies. Establish a communication system, which can be wireless or wired, for data exchange with thermal power units and receiving the real-time operating status of thermal power units, including various parameters of thermal power units, such as output power, temperature, pressure, etc. The real-time operating status is collected in real time and is usually obtained through sensors and monitoring equipment. By accurately matching thermal power units and power supply target areas, the problem of uneven power distribution is solved, and concentrated value analysis using historical data is used to improve the accuracy of load forecasting. Real-time reception of the operating status of thermal power units helps to quickly respond to changes in power grid load.

[0036] Further, step 2 of this application includes:

[0037] Taking the real-time operation status of the thermal power unit and the predicted load in the future time zone as the first-level screening benchmark, the first-level control signals of the thermal power units with the same model and the same service time are collected, wherein the first-level control signals include a first-level AGC command signal and a first-level power feedback signal; taking the operation status of the thermal power unit of the first-level control signal source and the recorded load of the first-level control signal source as the second-level screening benchmark, the second-level control signals of the thermal power units with the same model and the same service time are collected, wherein the second-level control signals include a second-level AGC command signal and a second-level power feedback signal; the first-level AGC command signal and the second-level AGC command signal are integrated to obtain the reference AGC command signal; the first-level power feedback signal and the second-level power feedback signal are integrated to obtain the reference power feedback signal.

[0038] Specifically, the real-time operating status of the thermal power units and the predicted load in the future time zone are used as the first-level screening benchmarks to collect the first-level control signals of the thermal power units of the same model and the same service time, including the first-level AGC command signal and the first-level power feedback signal. The same model refers to the thermal power units with the same design and performance parameters, and the same service time refers to the thermal power units with similar operating time. The real-time operating status and power load records of the thermal power units of the first-level control signal source are used as the second-level screening benchmarks to further collect the second-level control signals of the thermal power units of the same model and the same service time, including the second-level AGC command signal and the second-level power feedback signal. The first-level control signal is the basic control instruction of the thermal power unit, usually including the AGC command signal and the power feedback signal. It is a relatively rough control and is suitable for preliminary adjustment of the stability and power balance of the overall power grid. The second-level control signal is based on the first-level control signal, and is further collected from the thermal power units of the same model and the same service time, based on the operating status and recorded load of the thermal power units of the first-level control signal source, to achieve more refined control of the thermal power units to better adapt to the changes in power grid demand.

[0039] The first-level AGC command signal and the second-level AGC command signal are fused using the GraphSAGE model or other appropriate machine learning models to obtain a benchmark AGC command signal. The first-level power feedback signal and the second-level power feedback signal are also fused using the GraphSAGE model or other machine learning models to obtain a benchmark power feedback signal. GraphSAGE is a deep learning model for graph data. It generates an embedding of a target node by sampling and aggregating the features of neighboring nodes, and uses aggregation functions (such as mean aggregation, pooling aggregation, etc.) to merge the features of the target node and its sampled neighbors. GraphSAGE is particularly suitable for large-scale graphs because it can effectively handle scenarios with a large number of nodes and complex graph structures. The various control signals of the thermal power unit are taken as nodes in the graph, and the relationships between the signals are taken as edges. Using the sampling and aggregation mechanism of the GraphSAGE model, features are extracted from the first-level and second-level control signals to generate embedded representations of the nodes. By aggregating these embedded representations, the fused benchmark AGC command signal and benchmark power feedback signal are obtained. Through hierarchical screening and signal fusion, the control accuracy and response speed of the thermal power unit are effectively improved, which helps to improve the regulation capability of the unit.

[0040] Furthermore, the present application also includes the following steps:

[0041] Collect the operating status, sample recorded load, sample AGC command signal and sample power feedback signal of the same model and the same service time of the thermal power unit; perform deviation analysis based on the real-time operating status of the thermal power unit and the operating status of the sample thermal power unit to obtain a first distance coefficient; perform deviation analysis based on the future time zone predicted load and the sample recorded load to obtain a second distance coefficient; when the first distance coefficient is less than or equal to the first distance coefficient threshold, and the second distance coefficient is less than or equal to the second distance coefficient threshold, add the sample AGC command signal and the sample power feedback signal into the primary control signal, and at the same time add the operating status of the sample thermal power unit into the operating status of the primary control signal source thermal power unit, and add the sample recorded load into the recorded load of the primary control signal source; when the number of sample retrievals that meet the requirements is greater than or equal to 5, output the primary control signal.

[0042] Specifically, the operating status, recorded load, AGC command signal and power feedback signal of the sample thermal power units of the same model and service time are collected from the thermal power units. The operating status of the sample thermal power units includes the real-time operating parameters of other units of the same model and service time as the target thermal power unit, such as output power, temperature, pressure, etc.; the sample recorded load refers to the grid load data in the same time period as the target thermal power unit; the sample AGC command signal refers to the AGC command signal received in the same time period as the target thermal power unit; the sample power feedback signal refers to the power feedback signal generated in the same time period as the target thermal power unit.

[0043] Deviation analysis is performed on the real-time operating state of the thermal power unit and the sample operating state, and the difference between the two is calculated to obtain the first distance coefficient, which is used to evaluate the similarity between the current unit state and the sample unit state. Deviation analysis is performed on the predicted load in the future time zone and the sample recorded load, and the difference between the two is calculated to obtain the second distance coefficient, which is used to evaluate the matching degree between the predicted load and the sample load. The first distance coefficient threshold is pre-set to determine whether the deviation between the real-time operating state and the sample operating state is within an acceptable range; the second distance coefficient threshold is pre-set to determine whether the deviation between the predicted load and the sample recorded load is within an acceptable range. The thresholds of the first distance coefficient and the second distance coefficient are reasonably set to ensure that the screened sample data have sufficient similarity. When the first distance coefficient is less than or equal to the first distance coefficient threshold, and the second distance coefficient is less than or equal to the second distance coefficient threshold, it means that the deviation between the real-time operating state and the predicted load and the sample data is small, and it is considered that the sample data has a good reference value for the current control strategy, and the sample data is sufficiently similar to the target unit.

[0044] The corresponding qualified sample AGC command signal and sample power feedback signal are added to the primary control signal set. At the same time, the sample thermal power unit operating status is added to the primary control signal source thermal power unit operating status set, and the sample recorded load is added to the primary control signal source recorded load set to ensure the reliability and accuracy of the control signal. When the number of samples that meet the requirements is greater than or equal to 5, it is considered that the collected sample data is sufficient, the control strategy has a high reliability, and the primary control signal can be output, including the primary AGC command signal and the primary power feedback signal. The samples that meet the requirements refer to the samples whose operating status and recorded load have a deviation from the real-time operating status and predicted load of the target thermal power unit that is less than or equal to the preset threshold. Through deviation analysis and data screening, it is ensured that only sample data that is close enough to the real-time data and predicted data is included in the primary control signal to improve the accuracy and reliability of the data.

[0045] Furthermore, the present application also includes the following steps:

[0046] According to the first-level AGC command signal, the second-level AGC command signal is grouped to obtain multiple groups of second-level AGC command signals, wherein the multiple groups of second-level AGC command signals have multiple first-level AGC command signals corresponding to each other in a one-to-one manner; the multiple groups of second-level AGC command signals are traversed to perform a central tendency analysis to obtain multiple second-level AGC fitting command signals; mean analysis is performed on the multiple second-level AGC fitting command signals and the multiple first-level AGC command signals corresponding to each other in a one-to-one manner to obtain multiple first-level AGC fitting command signals; and a central tendency analysis is performed on the multiple first-level AGC fitting command signals to obtain the reference AGC command signal.

[0047] Specifically, the secondary AGC command signals are grouped according to the characteristics or requirements of the primary AGC command signals. Each group of secondary AGC command signals corresponds to a primary AGC command signal one by one, ensuring that these signals have similarity or correlation to some extent. Ensure that the secondary AGC command signals and the corresponding primary AGC command signals are consistent in time series when grouping. Check and analyze each group of secondary AGC command signals one by one, and use central tendency analysis to find the central tendency or typical value of each group of instructions. Central tendency analysis is a statistical method used to determine the central position or typical value of a set of data, such as the mean value, median, etc. Through central tendency analysis, multiple secondary AGC fitting command signals are obtained, representing the average or typical value of the corresponding secondary command signals. Each secondary AGC fitting command signal and its corresponding primary AGC command signal are subjected to mean analysis separately, that is, the average value of each secondary AGC fitting command signal and its corresponding primary AGC command signal is calculated to obtain multiple primary AGC fitting command signals. Mean analysis is a statistical method used to calculate the average value of a set of data to reflect the central tendency of the data. Perform central trend analysis on all first-level AGC fitting command signals, calculate the average, median or mode of all first-level fitting command signals, and determine the final benchmark AGC command signal. By grouping and analyzing AGC command signals at different levels, a more accurate benchmark AGC command signal is finally generated to reflect the needs of the system, thereby improving the regulation performance and response speed of the thermal power unit.

[0048] Furthermore, the present application also includes the following steps:

[0049] Construct a frequency modulation-AGC performance index mapping model; configure R-mode primary frequency modulation qualification conditions; when receiving a frequency modulation command signal, obtain an R-mode primary frequency modulation control parameter matrix that meets the R-mode primary frequency modulation qualification conditions, and fit it through the frequency modulation-AGC performance index mapping model to obtain the predicted fluctuation extreme value of the AGC performance index; when the predicted fluctuation extreme value of the AGC performance index is less than or equal to the fluctuation threshold, perform primary frequency modulation control according to the R-mode primary frequency modulation control parameter matrix.

[0050] Specifically, the primary frequency regulation control parameter matrix data set, the regulation accuracy fluctuation extreme value record data set, the regulation rate fluctuation extreme value record data set, and the response time fluctuation extreme value record data set are collected to construct three sub-models, which are used to predict or evaluate the regulation accuracy fluctuation, regulation rate fluctuation, and response time fluctuation, respectively. The three sub-models are integrated to complete the construction of the frequency regulation-AGC performance index mapping model. The primary frequency regulation qualification conditions under the R mode are set, including the requirements of the regulation rate, regulation accuracy, response time and other indicators to ensure that the adopted frequency regulation parameters meet the performance standards. The R mode is a specific primary frequency regulation control mode. Each thermal power unit participating in the primary frequency regulation will be assigned the regulation task according to the same adjustable ratio according to its base power, and will unconditionally bear the regulation amount assigned to them. The base power refers to the initial output power of the thermal power unit before participating in the primary frequency regulation; the same adjustable ratio allocation means that all thermal power units participating in the primary frequency regulation will share the task according to the same ratio according to their base power; unconditionally bearing the regulation amount means that each thermal power unit will unconditionally accept and execute the regulation amount assigned to it, regardless of its current operating status. According to the performance standards, specific qualification conditions are set, such as the fluctuation range of the adjustment accuracy, the minimum value of the adjustment rate, the maximum value of the response time, etc., and these conditions are configured into the control system of the R mode.

[0051] When the system receives the frequency modulation command signal, it starts to prepare to perform a frequency modulation control. The frequency modulation command signal refers to the signal sent by the power grid dispatching center to the thermal power unit, indicating that the unit needs to perform a frequency modulation operation. Obtain the R-mode primary frequency modulation control parameter matrix that meets the R-mode primary frequency modulation qualification conditions. The R-mode primary frequency modulation control parameter matrix is ​​a set of parameters for performing primary frequency modulation control, including various parameters for controlling the thermal power unit during the primary frequency modulation process. The R-mode primary frequency modulation control parameter matrix is ​​fitted using the frequency modulation-AGC performance index mapping model, and the R-mode primary frequency modulation control parameter matrix is ​​fitted using this mapping model to predict the fluctuation extreme value of the AGC performance index. The model parameters are adjusted using historical data so that the model can accurately reflect the frequency modulation performance of the unit under different conditions. For example, the model parameters are optimized by methods such as the least squares method to minimize the error between the predicted results and the actual observed values. Use the fitted model to predict future frequency modulation control and determine the predicted fluctuation extreme values ​​of the AGC performance index of the unit under specific conditions, including the fluctuation extreme value of the regulation accuracy, the fluctuation extreme value of the regulation rate, and the fluctuation extreme value of the response time.

[0052] A fluctuation threshold is set in advance to determine whether the fluctuation of the AGC performance index is within an acceptable range. When the predicted fluctuation extreme value of the AGC performance index is less than or equal to the fluctuation threshold, it means that the predicted fluctuation is within an acceptable range, and a frequency modulation control can be performed to implement the frequency modulation strategy under the premise of ensuring the performance index. According to the R-mode primary frequency modulation control parameter matrix, the thermal power unit is controlled to realize the primary frequency modulation operation. By real-time monitoring of the changes in the regional control error (ACE), the dispatching instructions are dynamically adjusted to achieve fast AGC response, ensuring that the unit can respond to the AGC instruction quickly and accurately in the R mode, meet the requirements of regulation rate and accuracy, and increase the regulation depth of the unit by optimizing the control parameters, thereby improving the AGC service compensation and reducing the primary frequency modulation power assessment, and improving the comprehensive performance indicators. By configuring the R-mode primary frequency modulation qualification conditions and fitting the frequency modulation-AGC performance index mapping model when receiving the frequency modulation instruction signal, the prediction of the predicted fluctuation extreme value of the AGC performance index is realized.

[0053] Furthermore, the present application also includes the following steps:

[0054] Collect a frequency modulation control parameter matrix data set, an adjustment precision fluctuation extreme value record data set, an adjustment rate fluctuation extreme value record data set, and a response time fluctuation extreme value record data set; supervise the primary frequency modulation control parameter matrix data set according to the adjustment precision fluctuation extreme value record data set, and construct a regulation precision fluctuation extreme value mapping sub-model; supervise the primary frequency modulation control parameter matrix data set according to the adjustment rate fluctuation extreme value record data set, and construct a regulation rate fluctuation extreme value mapping sub-model; supervise the primary frequency modulation control parameter matrix data set according to the response time fluctuation extreme value record data set, and construct a response time fluctuation extreme value mapping sub-model.

[0055] Specifically, the parameter matrix related to primary frequency regulation control is collected, including gain, dead zone, integration time, etc. Primary frequency regulation control parameters refer to the parameters used to control the frequency response of thermal power units. At the same time, the fluctuation extreme value record data set related to regulation accuracy, regulation rate and response time is collected, and the maximum and minimum values ​​of regulation accuracy fluctuation, regulation rate fluctuation and response time fluctuation are recorded respectively. Regulation accuracy refers to the accuracy of the thermal power unit in reaching the target value during the regulation process; regulation rate refers to the speed at which the thermal power unit changes the output power during the regulation process; response time refers to the time from when the thermal power unit receives the regulation command to when it starts to respond.

[0056] Data preprocessing is performed on the primary frequency modulation control parameter matrix data set, the adjustment precision fluctuation extreme value record data set, the adjustment rate fluctuation extreme value record data set, and the response time fluctuation extreme value record data set, including data cleaning, feature extraction, and standardization. The processed adjustment precision fluctuation extreme value record data set and the primary frequency modulation control parameter matrix data set are used to train the model through machine learning algorithms (such as regression analysis, neural networks, etc.), and the input data (primary frequency modulation control parameters) are mapped to the output data (adjustment precision fluctuation extreme values). The primary frequency modulation control parameter matrix data set is associated with the adjustment precision fluctuation extreme value record data set to construct an adjustment precision fluctuation extreme value mapping sub-model. Similarly, the adjustment rate fluctuation extreme value record data set is used to supervise the learning process, and the model is trained in combination with the primary frequency modulation control parameter matrix data set to find the relationship between the control parameters and the adjustment rate fluctuation extreme values, and the adjustment rate fluctuation extreme value mapping sub-model is constructed to predict or evaluate the adjustment rate fluctuation. The response time fluctuation extreme value record data set is used to supervise the learning process, and the model is trained in combination with the primary frequency modulation control parameter matrix data set to find the relationship between the control parameters and the response time fluctuation extreme values, and the response time fluctuation extreme value mapping sub-model is constructed to predict or evaluate the response time fluctuation. Use the training data set to train the model, evaluate the performance and generalization ability of the model through methods such as cross-validation, and adjust the model parameters and structure to optimize performance.

[0057] Through weighted averaging, stacking or other advanced integration techniques, the above three mapping sub-models are integrated into a unified frequency modulation-AGC performance index mapping model, the trained model is deployed to the actual system, and the model is used to predict the frequency modulation-AGC performance index under different control parameters, thereby guiding the optimization of control parameters. In the process of model construction, extra attention should be paid to avoid overfitting, ensure that the model is concise and interpretable, and update the model regularly to reflect the latest system status and control parameters. By constructing three mapping sub-models, a comprehensive frequency modulation-AGC performance index mapping model is constructed to help thermal power units understand how different control parameters affect regulation accuracy, regulation rate and response time.

[0058] In summary, the AGC control strategy optimization method for a thermal power unit provided in this application has the following technical effects:

[0059] By receiving the real-time operating status of the thermal power unit and the predicted load in the future time zone; sending the real-time operating status of the thermal power unit and the predicted load in the future time zone to the RTU mirror module, and processing through the AGC control analysis component of the RTU mirror module to obtain the reference AGC command signal and the reference power feedback signal; when the predicted load in the future time zone is triggered in the future time zone, the communication DCS module receives the first AGC command signal and the first power feedback signal; when the first AGC command signal is inconsistent with the reference AGC command signal, the first AGC command signal is corrected according to the reference AGC command signal, and when the first power feedback signal is inconsistent with the reference power feedback signal, the first power feedback signal is corrected according to the reference power feedback signal. In other words, the remote control terminal continuously adjusts the field control terminal, uses the RTU mirror module to analyze the AGC command and power feedback, and corrects the inconsistent command and feedback signals, thereby improving the adjustment accuracy of the AGC.

[0060] Embodiment 2: Based on the same inventive concept as the method for optimizing the AGC control strategy of a thermal power plant in the above embodiment, the present application also provides an AGC control strategy optimization device for a thermal power plant. Figure 2 , the AGC control strategy optimization device for a thermal power unit comprises:

[0061] The data receiving module 11 is used to receive the real-time operating status of the thermal power unit and the predicted load in the future time zone.

[0062] The component processing module 12 is used to send the real-time operating status of the thermal power unit and the predicted load in the future time zone to the RTU mirror module, and obtain the reference AGC command signal and the reference power feedback signal through the AGC control analysis component processing of the RTU mirror module.

[0063] The signal receiving module 13 is used to communicate with the DCS module and receive the first AGC command signal and the first power feedback signal when the future time zone predicted load is triggered in the future time zone.

[0064] The signal correction module 14 is used to correct the first AGC command signal according to the reference AGC command signal when the first AGC command signal is inconsistent with the reference AGC command signal, and to correct the first power feedback signal according to the reference power feedback signal when the first power feedback signal is inconsistent with the reference power feedback signal.

[0065] Furthermore, the data receiving module 11 in the thermal power unit AGC control strategy optimization device is also used for:

[0066] According to the location number of the thermal power unit, the power supply target area is matched; with a 7-day period, the power load cross-section data of the future time zone is collected; the concentrated value analysis of the power load cross-section data of the same period is performed to obtain the predicted load of the future time zone; the thermal power unit is communicated to receive the real-time operating status of the thermal power unit.

[0067] Furthermore, the component processing module 12 in the thermal power unit AGC control strategy optimization device is also used for:

[0068] Taking the real-time operation status of the thermal power unit and the predicted load in the future time zone as the first-level screening benchmark, the first-level control signals of the thermal power units with the same model and the same service time are collected, wherein the first-level control signals include a first-level AGC command signal and a first-level power feedback signal; taking the operation status of the thermal power unit of the first-level control signal source and the recorded load of the first-level control signal source as the second-level screening benchmark, the second-level control signals of the thermal power units with the same model and the same service time are collected, wherein the second-level control signals include a second-level AGC command signal and a second-level power feedback signal; the first-level AGC command signal and the second-level AGC command signal are integrated to obtain the reference AGC command signal; the first-level power feedback signal and the second-level power feedback signal are integrated to obtain the reference power feedback signal.

[0069] Furthermore, the component processing module 12 in the thermal power unit AGC control strategy optimization device is also used for:

[0070] Collect the operating status, sample recorded load, sample AGC command signal and sample power feedback signal of the same model and the same service time of the thermal power unit; perform deviation analysis based on the real-time operating status of the thermal power unit and the operating status of the sample thermal power unit to obtain a first distance coefficient; perform deviation analysis based on the future time zone predicted load and the sample recorded load to obtain a second distance coefficient; when the first distance coefficient is less than or equal to the first distance coefficient threshold, and the second distance coefficient is less than or equal to the second distance coefficient threshold, add the sample AGC command signal and the sample power feedback signal into the primary control signal, and at the same time add the operating status of the sample thermal power unit into the operating status of the primary control signal source thermal power unit, and add the sample recorded load into the recorded load of the primary control signal source; when the number of sample retrievals that meet the requirements is greater than or equal to 5, output the primary control signal.

[0071] Furthermore, the component processing module 12 in the thermal power unit AGC control strategy optimization device is also used for:

[0072] According to the first-level AGC command signal, the second-level AGC command signal is grouped to obtain multiple groups of second-level AGC command signals, wherein the multiple groups of second-level AGC command signals have multiple first-level AGC command signals corresponding to each other in a one-to-one manner; the multiple groups of second-level AGC command signals are traversed to perform a central tendency analysis to obtain multiple second-level AGC fitting command signals; mean analysis is performed on the multiple second-level AGC fitting command signals and the multiple first-level AGC command signals corresponding to each other in a one-to-one manner to obtain multiple first-level AGC fitting command signals; and a central tendency analysis is performed on the multiple first-level AGC fitting command signals to obtain the reference AGC command signal.

[0073] Furthermore, the AGC control strategy optimization device for a thermal power unit further includes a frequency modulation control module, which is used to:

[0074] Construct a frequency modulation-AGC performance index mapping model; configure R-mode primary frequency modulation qualification conditions; when receiving a frequency modulation command signal, obtain an R-mode primary frequency modulation control parameter matrix that meets the R-mode primary frequency modulation qualification conditions, and fit it through the frequency modulation-AGC performance index mapping model to obtain the predicted fluctuation extreme value of the AGC performance index; when the predicted fluctuation extreme value of the AGC performance index is less than or equal to the fluctuation threshold, perform primary frequency modulation control according to the R-mode primary frequency modulation control parameter matrix.

[0075] Furthermore, the AGC control strategy optimization device for a thermal power unit further includes a model building module for:

[0076] Collect a frequency modulation control parameter matrix data set, an adjustment precision fluctuation extreme value record data set, an adjustment rate fluctuation extreme value record data set, and a response time fluctuation extreme value record data set; supervise the primary frequency modulation control parameter matrix data set according to the adjustment precision fluctuation extreme value record data set, and construct a regulation precision fluctuation extreme value mapping sub-model; supervise the primary frequency modulation control parameter matrix data set according to the adjustment rate fluctuation extreme value record data set, and construct a regulation rate fluctuation extreme value mapping sub-model; supervise the primary frequency modulation control parameter matrix data set according to the response time fluctuation extreme value record data set, and construct a response time fluctuation extreme value mapping sub-model.

[0077] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. Figure 1The method and specific examples for optimizing the AGC control strategy of a thermal power unit in the first embodiment are also applicable to the device for optimizing the AGC control strategy of a thermal power unit in the present embodiment. Through the detailed description of the method for optimizing the AGC control strategy of a thermal power unit, those skilled in the art can clearly know the device for optimizing the AGC control strategy of a thermal power unit in the present embodiment, so for the sake of brevity of the specification, it will not be described in detail here. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method part.

[0078] Embodiment three, based on the inventive concept of a method for optimizing an AGC control strategy for a thermal power unit in the aforementioned embodiment one, the present application also provides an electronic device, comprising: at least one processor; a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the steps of a method for optimizing an AGC control strategy for a thermal power unit described in any one of the aforementioned embodiments one.

[0079] Attached Figure 3 This is a schematic diagram of the structure of an exemplary electronic device of this application. Figure 3 In the embodiment, the bus architecture is represented by bus 300, which may include any number of interconnected buses and bridges, and bus 300 connects various circuits including one or more processors represented by processor 302 and memory represented by memory 304. Bus 300 may also connect various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. Bus interface 305 provides an interface between bus 300 and receiver 301 and transmitter 303. Receiver 301 and transmitter 303 may be the same element, namely a transceiver, providing a unit for communicating with various other devices over a transmission medium. Processor 302 is responsible for managing bus 300 and general processing, while memory 304 may be used to store data used by processor 302 when performing operations.

[0080] Embodiment 4, based on the same inventive concept as the method for optimizing the AGC control strategy of a thermal power unit in the aforementioned embodiment 1, the present application also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed, the steps of the method for optimizing the AGC control strategy of a thermal power unit described in any one of the aforementioned embodiments 1 are implemented.

[0081] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0082] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is also intended to include these modifications and variations.

Claims

1. A method for optimizing the AGC control strategy of a thermal power unit, characterized in that: include: Receive the real-time operating status of thermal power units and the predicted load in future time zones; The real-time operating status of the thermal power unit and the predicted load in the future time zone are sent to the RTU mirror module, and the AGC control analysis component of the RTU mirror module processes the AGC command signal and the reference power feedback signal; When the future time zone predicted load is triggered in the future time zone, the communication DCS module receives the first AGC command signal and the first power feedback signal; When the first AGC command signal is inconsistent with the reference AGC command signal, the first AGC command signal is corrected according to the reference AGC command signal; when the first power feedback signal is inconsistent with the reference power feedback signal, the first power feedback signal is corrected according to the reference power feedback signal; The real-time operation status of the thermal power unit and the predicted load in the future time zone are sent to the RTU mirror module, and the AGC control analysis component of the RTU mirror module processes to obtain a reference AGC command signal and a reference power feedback signal, including: Taking the real-time operation status of the thermal power unit and the predicted load in the future time zone as the primary screening benchmark, collecting the primary control signals of the thermal power units of the same model and the same service time, wherein the primary control signals include the primary AGC command signal and the primary power feedback signal; Taking the operating state of the thermal power unit of the primary control signal source and the recorded load of the primary control signal source as the secondary screening benchmark, the secondary control signals of the thermal power units of the same model and the same service time are collected, wherein the secondary control signals include the secondary AGC command signal and the secondary power feedback signal; fusing the primary AGC command signal and the secondary AGC command signal to obtain the reference AGC command signal; fusing the primary power feedback signal and the secondary power feedback signal to obtain the reference power feedback signal; The first-level AGC command signal and the second-level AGC command signal are integrated to obtain the reference AGC command signal, including: According to the primary AGC command signal, the secondary AGC command signal is grouped to obtain a plurality of groups of secondary AGC command signals, wherein the plurality of groups of secondary AGC command signals have a plurality of primary AGC command signals corresponding one to one; Traversing the plurality of groups of secondary AGC command signals to perform a central trend analysis to obtain a plurality of secondary AGC fitting command signals; Performing mean analysis on the multiple secondary AGC fitting command signals and the multiple primary AGC command signals corresponding to each other to obtain multiple primary AGC fitting command signals; A central tendency analysis is performed on the plurality of first-level AGC fitting command signals to obtain the reference AGC command signal.

2. A thermal power unit AGC control strategy optimization method as claimed in claim 1, characterized in that: Receive the real-time operating status of thermal power units and the predicted load in the future time zone, including: Match the power supply target area according to the location number of the thermal power unit; Collect the electricity load cross-section data of the future time zone in the same period with a 7-day cycle; Performing concentrated value analysis on the cross-sectional data of the electricity load in the same period to obtain the predicted load in the future time zone; Communicate with the thermal power unit and receive the real-time operating status of the thermal power unit.

3. A thermal power unit AGC control strategy optimization method as claimed in claim 1, characterized in that: Taking the real-time operation status of the thermal power unit and the predicted load in the future time zone as the primary screening benchmark, the primary control signals of the thermal power units of the same model and the same service time are collected, including: Collecting the operating status, sample recorded load, sample AGC command signal and sample power feedback signal of sample thermal power units of the same model and the same service time as the thermal power units; Perform deviation analysis based on the real-time operating status of the thermal power unit and the operating status of the sample thermal power unit to obtain a first distance coefficient; Perform deviation analysis based on the predicted load in the future time zone and the sample recorded load to obtain a second distance coefficient; When the first distance coefficient is less than or equal to a first distance coefficient threshold, and the second distance coefficient is less than or equal to a second distance coefficient threshold, the sample AGC command signal and the sample power feedback signal are added to the primary control signal, and at the same time, the sample thermal power unit operation state is added to the primary control signal source thermal power unit operation state, and the sample recorded load is added to the primary control signal source recorded load; When the number of samples that meet the requirements is greater than or equal to 5, the first-level control signal is output.

4. A thermal power unit AGC control strategy optimization method as claimed in claim 1, characterized in that: Also includes: Construct FM-AGC performance index mapping model; Configure the R-mode primary frequency modulation qualification conditions; When receiving the frequency modulation command signal, an R-mode primary frequency modulation control parameter matrix that meets the R-mode primary frequency modulation qualification condition is obtained, and the frequency modulation-AGC performance index mapping model is used for fitting to obtain the AGC performance index predicted fluctuation extreme value; When the predicted fluctuation extreme value of the AGC performance indicator is less than or equal to the fluctuation threshold, primary frequency modulation control is performed according to the R-mode primary frequency modulation control parameter matrix.

5. A method for optimizing the AGC control strategy of a thermal power unit according to claim 4, characterized in that: Construct the FM-AGC performance indicator mapping model, including: Collecting a frequency modulation control parameter matrix data set, a regulation accuracy fluctuation extreme value record data set, a regulation rate fluctuation extreme value record data set, and a response time fluctuation extreme value record data set; According to the regulation precision fluctuation extreme value record data set, the primary frequency modulation control parameter matrix data set is supervised to construct a regulation precision fluctuation extreme value mapping sub-model; According to the regulation rate fluctuation extreme value record data set, the primary frequency modulation control parameter matrix data set is supervised to construct a regulation rate fluctuation extreme value mapping sub-model; The primary frequency modulation control parameter matrix data set is supervised according to the response time fluctuation extreme value record data set, and a response time fluctuation extreme value mapping sub-model is constructed.

6. A thermal power unit AGC control strategy optimization device, characterized in that: The steps for implementing the method for optimizing the AGC control strategy of a thermal power unit according to any one of claims 1 to 5, wherein the device for optimizing the AGC control strategy of a thermal power unit comprises: A data receiving module, the data receiving module is used to receive the real-time operating status of the thermal power unit and the predicted load in the future time zone; A component processing module, wherein the component processing module is used to send the real-time operating status of the thermal power unit and the predicted load in the future time zone to the RTU mirror module, and obtain a reference AGC command signal and a reference power feedback signal through the AGC control analysis component processing of the RTU mirror module; A signal receiving module, the signal receiving module is used to communicate with the DCS module and receive a first AGC command signal and a first power feedback signal when the future time zone predicted load is triggered in the future time zone; a signal correction module, the signal correction module being used to correct the first AGC command signal according to the reference AGC command signal when the first AGC command signal is inconsistent with the reference AGC command signal, and to correct the first power feedback signal according to the reference power feedback signal when the first power feedback signal is inconsistent with the reference power feedback signal; The component processing module is also used for: Taking the real-time operation status of the thermal power unit and the predicted load in the future time zone as the first-level screening benchmark, collecting the first-level control signals of the thermal power unit of the same model and the same service time, wherein the first-level control signal includes a first-level AGC command signal and a first-level power feedback signal; taking the operation status of the thermal power unit of the first-level control signal source and the recorded load of the first-level control signal source as the second-level screening benchmark, collecting the second-level control signals of the thermal power unit of the same model and the same service time, wherein the second-level control signal includes a second-level AGC command signal and a second-level power feedback signal; fusing the first-level AGC command signal and the second-level AGC command signal to obtain the reference AGC command signal; fusing the first-level power feedback signal and the second-level power feedback signal to obtain the reference power feedback signal; The component processing module is also used for: According to the first-level AGC command signal, the second-level AGC command signal is grouped to obtain multiple groups of second-level AGC command signals, wherein the multiple groups of second-level AGC command signals have multiple first-level AGC command signals corresponding to each other in a one-to-one manner; the multiple groups of second-level AGC command signals are traversed to perform a central tendency analysis to obtain multiple second-level AGC fitting command signals; mean analysis is performed on the multiple second-level AGC fitting command signals and the multiple first-level AGC command signals corresponding to each other in a one-to-one manner to obtain multiple first-level AGC fitting command signals; and a central tendency analysis is performed on the multiple first-level AGC fitting command signals to obtain the reference AGC command signal.

7. An electronic device comprising: at least one processor; a memory communicatively coupled to the at least one processor; Wherein, the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the steps of a method for optimizing the AGC control strategy of a thermal power unit as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed, the steps of the method for optimizing the AGC control strategy of a thermal power unit described in any one of claims 1 to 5 are implemented.

Images