Method and device for calculating throttling primary frequency modulation capability of condensed water

Abstract

The embodiment of the invention provides a condensation water throttling primary frequency modulation capability calculation method and device, and the method comprises the steps: inputting a current condensation water change amount into a pre-trained condensation water flow primary frequency modulation basic model, and obtaining a corresponding basic model output result, the state parameters of the current condensation water and the unit load are input into a pre-trained condensation water flow primary frequency modulation compensation model, a corresponding compensation model output result is obtained, and the compensation model is used for correcting a corresponding load parameter prediction value determined by the basic model. According to the basic model output result and the compensation model output result, determining the primary frequency modulation capability of the condensation water throttling mode of the current unit; the method can accurately calculate the primary frequency modulation capability of the condensation water throttling mode at each load point under each working condition, provides a reliable model guarantee for primary frequency modulation control, improves the auxiliary service market income of a unit, and assists in keeping the power grid frequency stable.

Description

Technical Field

[0001] The present application relates to the field of power grid control, and in particular to a method and device for calculating the primary frequency regulation capacity of condensate throttling. Background Art

[0002] In the power system, frequency is one of the key indicators to measure the quality of power. The frequency of the power system must be maintained within an allowable range to ensure the safety and economic benefits of the entire system. If the frequency exceeds this range, it will not only affect the power system itself, but may also have adverse consequences for the generator set and end users. In particular, when the frequency fluctuates for a long time and by a large margin, it may have a serious impact on the power grid, and even lead to the decoupling of the power grid in extreme cases. In order to meet these challenges, improving the primary frequency regulation performance of the unit becomes the key.

[0003] At present, condensate throttling to assist primary frequency regulation has become a hot topic in the research and application of many power plants. The auxiliary regulation method of condensate participating in primary frequency regulation is to adjust the condensate flow rate to change the low-pressure steam extraction volume, so that the unit can instantly increase the output when the fuel response lags behind, and then quickly respond to the peak load and frequency regulation requirements of the power grid.

[0004] However, the existing method for calculating the primary frequency regulation capacity of condensate throttling still has obvious deficiencies. At present, most power plants still use experimental methods to estimate this capacity, that is, under a certain fixed load condition, by changing the condensate flow rate, observing and recording the change in unit load. The above method has two main problems:

[0005] First, due to limited test conditions, power plants can usually only be tested at a few specific load points, making it difficult to cover all possible operating conditions.

[0006] In addition, there are often differences between the unit operating conditions in actual production and the operating conditions during testing. For example, factors such as load, temperature, and pressure change dynamically in actual operation, while test conditions are relatively fixed. Therefore, the test results are difficult to accurately reflect the frequency regulation capabilities in actual production. Summary of the invention

[0007] In response to the problems in the prior art, the present application provides a method and device for calculating the primary frequency regulation capacity of condensate throttling, which can accurately calculate the primary frequency regulation capacity of the condensate throttling method at each load point and under each operating condition, provide a reliable model guarantee for primary frequency regulation control, increase the auxiliary service market revenue of the unit, and help maintain the stability of the power grid frequency.

[0008] In order to solve at least one of the above problems, the present application provides the following technical solutions:

[0009] According to a first aspect of an embodiment of the present application, the present application provides a method for calculating the primary frequency regulation capacity of condensate throttling, including:

[0010] Input the current condensate change into the pre-trained basic model of condensate flow primary frequency modulation to obtain the corresponding basic model output result, wherein the basic model represents the linear relationship between the condensate flow rate and the load change of the unit at full load;

[0011] Inputting the current state parameters of condensate and unit load into the pre-trained compensation model of primary frequency modulation of condensate flow to obtain the corresponding compensation model output result, wherein the compensation model is used to correct the corresponding load parameter prediction value determined by the basic model;

[0012] The primary frequency regulation capability of the current unit in the condensate throttling mode is determined according to the output result of the basic model and the output result of the compensation model.

[0013] According to any implementation of the present application, the training process of the basic model includes:

[0014] Obtain multiple groups of condensate and load changes and current state parameters of the unit at multiple load points;

[0015] Based on the least square fitting method, the linear relationship between the condensate flow rate and the unit load change in the full load section of the unit is determined according to the changes in the condensate and the unit load and used as the basic model.

[0016] According to any embodiment of the present application, the training process of the compensation model includes:

[0017] Determine the corresponding load parameter prediction value according to the condensate change and the basic model, and obtain the load error data according to the unit load change and the unit load state parameter;

[0018] Based on the load error data, the state parameters of condensate and unit load are trained by an extreme learning machine to obtain the compensation model.

[0019] According to any embodiment of the present application, based on the load error data, the state parameters of condensate and unit load are trained by an extreme learning machine to obtain the compensation model, including:

[0020] Classifying the state parameters of the unit load according to the load intensity, and respectively training the state parameters of the unit load at different levels to obtain the corresponding compensation models at different levels;

[0021] The state parameters of the current condensate and the unit load are input into the pre-trained compensation model of the primary frequency modulation of the condensate flow to obtain the corresponding compensation model output result, including:

[0022] The state parameters of the current condensate and unit load are input into the compensation model of the corresponding load intensity to obtain the corresponding compensation model output result.

[0023] According to a second aspect of an embodiment of the present application, the present application provides a condensate throttling primary frequency modulation capacity calculation device, comprising:

[0024] A basic determination module is used to: input the current condensate change into a pre-trained basic model of condensate flow primary frequency modulation to obtain a corresponding basic model output result, wherein the basic model represents the linear relationship between the condensate flow rate and the unit load change in the full load section of the unit;

[0025] A model correction module is used to: input the current condensate and unit load state parameters into a pre-trained condensate flow primary frequency modulation compensation model to obtain a corresponding compensation model output result, wherein the compensation model is used to correct the corresponding load parameter prediction value determined by the basic model;

[0026] The capacity determination module is used to determine the primary frequency regulation capacity of the current unit in the condensate throttling mode according to the output results of the basic model and the output results of the compensation model.

[0027] According to any implementation of the present application, the training process of the basic model includes:

[0028] The parameter acquisition module is used to obtain multiple groups of condensate water and load changes and current state parameters of the unit at multiple load points;

[0029] The model fitting module is used to: determine the linear relationship between the condensate flow rate and the unit load change in the full load section of the unit based on the least squares fitting method and the change in the condensate and the unit load as the basic model.

[0030] According to any embodiment of the present application, the training process of the compensation model includes:

[0031] An error determination module is used to: determine the corresponding load parameter prediction value according to the condensate change and the basic model, and obtain load error data according to the unit load change and the unit load state parameter;

[0032] The model training module is used to: based on the load error data, train the state parameters of condensate and unit load through an extreme learning machine to obtain the compensation model.

[0033] According to any implementation of the present application, the model training module is specifically used for:

[0034] Classifying the state parameters of the unit load according to the load intensity, and respectively training the state parameters of the unit load at different levels to obtain the corresponding compensation models at different levels;

[0035] The model correction module is specifically used for:

[0036] The state parameters of the current condensate and unit load are input into the compensation model of the corresponding load intensity to obtain the corresponding compensation model output result.

[0037] According to the third aspect of the embodiment of the present application, the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the method for calculating the primary frequency regulation capacity of condensate throttling are implemented.

[0038] According to a fourth aspect of the embodiments of the present application, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method for calculating the primary frequency modulation capacity of condensate throttling.

[0039] According to a fifth aspect of the embodiments of the present application, the present application provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the steps of the method for calculating the primary frequency regulation capacity of condensate throttling.

[0040] It can be seen from the above technical scheme that the present application provides a method and device for calculating the primary frequency regulation capacity of condensate throttling, by inputting the current condensate change into the pre-trained basic model of condensate flow primary frequency regulation to obtain the corresponding basic model output result, the basic model characterizes the linear relationship between the condensate flow rate and the unit load change in the full load section of the unit, and the state parameters of the current condensate and unit load are input into the pre-trained compensation model of condensate flow primary frequency regulation to obtain the corresponding compensation model output result, the compensation model is used to correct the corresponding load parameter prediction value determined by the basic model, and the primary frequency regulation capacity of the current unit condensate throttling method is determined according to the output result of the basic model and the output result of the compensation model, which can accurately calculate the primary frequency regulation capacity of the condensate throttling method at each load point and each operating condition, provide a reliable model guarantee for primary frequency regulation control, improve the auxiliary service market revenue of the unit, and help maintain the stability of the power grid frequency. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present application or the technical solutions in 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 described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0042] Figure 1 This is a schematic diagram of condensate throttling assisted primary frequency modulation in an embodiment of the present application.

[0043] Figure 2 It is one of the flow charts of the method for calculating the primary frequency modulation capacity of condensate throttling in the embodiment of the present application;

[0044] Figure 3 The second flow chart of the method for calculating the primary frequency modulation capacity of condensate throttling in the embodiment of the present application;

[0045] Figure 4 The third flow chart of the method for calculating the primary frequency modulation capacity of condensate throttling in the embodiment of the present application;

[0046] Figure 5 This is a schematic diagram of an extreme learning machine application in an embodiment of the present application;

[0047] Figure 6 Schematic diagram of the structure of the extreme learning machine in the embodiment of the present application;

[0048] Figure 7 The fourth flowchart of the method for calculating the primary frequency modulation capacity of condensate throttling in the embodiment of the present application;

[0049] Figure 8 One of the structural diagrams of the condensate throttling primary frequency modulation capacity calculation device in the embodiment of the present application;

[0050] Fig. 9 This is the second structural diagram of the condensate throttling primary frequency modulation capacity calculation device in the embodiment of the present application;

[0051] Fig.10 The third structural diagram of the condensate throttling primary frequency modulation capacity calculation device in the embodiment of the present application;

[0052] Fig.11 It is a schematic diagram of the structure of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0054] The acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of national laws and regulations.

[0055] like Figure 1 As shown, the existing auxiliary regulation method for condensate water to participate in primary frequency regulation is to adjust the condensate flow rate to change the low-pressure steam extraction volume, so that the unit can instantly increase the output when the fuel response lags behind, and then quickly respond to the peak regulation and frequency regulation requirements of the power grid.

[0056] The deaerator plays the role of an energy storage device in the condensate throttling primary frequency modulation. During the condensate throttling primary frequency modulation, the amount of condensate entering the deaerator decreases, the temperature of the condensate increases, and the feed water pump continues to supply water to lower the water level of the deaerator, and the amount of water stored in the deaerator decreases. In this process, the outlet water temperature of the deaerator remains basically unchanged, that is, the feed water system maintains normal operation. During the condensate throttling primary frequency modulation process, the hot water stored in the deaerator is released, reducing the steam extraction of the low-pressure heater and increasing the power generation output.

[0057] The change in condensate is directly related to the change in unit load caused by condensate throttling. The calculation method for designing the primary frequency regulation capacity of condensate throttling is the basis of primary frequency regulation control, which is of great significance for the rapid response of primary frequency regulation in power plants and the stability of grid frequency.

[0058] However, considering that there are relatively few methods for calculating the primary frequency regulation capacity of the existing condensate throttling method, most of them adopt an experimental method, that is, changing the condensate flow rate under a certain load and recording the load change at the same time. Due to the limited number of tests and the fact that the unit operating conditions when primary frequency regulation occurs in the actual production process are difficult to be consistent with the unit operating conditions during the test, the traditional condensate throttling primary frequency regulation calculation method has the problem of inaccurate results. The present application provides a condensate throttling primary frequency regulation capacity calculation method and device, which accurately calculates the primary frequency regulation capacity of the condensate throttling method at each load point and each operating condition, provides a reliable model guarantee for primary frequency regulation control, increases the auxiliary service market revenue of the unit, and helps maintain the stability of the power grid frequency.

[0059] In order to accurately calculate the primary frequency regulation capacity of the condensate throttling method at each load point and under each operating condition, provide a reliable model guarantee for the primary frequency regulation control, increase the auxiliary service market revenue of the unit, and help maintain the stability of the power grid frequency, this application provides an embodiment of a method for calculating the primary frequency regulation capacity of condensate throttling, see Figure 2 The method for calculating the primary frequency regulation capacity of condensate throttling specifically includes the following contents:

[0060] Step S101: input the current condensate change into the pre-trained basic model of condensate flow primary frequency modulation to obtain the corresponding basic model output result, wherein the basic model represents the linear relationship between the condensate flow rate and the unit load change in the full load section of the unit.

[0061] First, the current condensate change is input into a pre-trained basic model. After being trained with a large amount of data, the basic model can accurately characterize the linear relationship between the condensate flow rate and the load change of the unit under full load. By inputting the condensate change, the model outputs a basic result, which reflects how the condensate flow change affects the load change of the unit under the current load conditions. The basic model of the above linear relationship provides preliminary data support for the prediction of frequency regulation capability.

[0062] Step S102: inputting the current condensate and unit load state parameters into the pre-trained condensate flow primary frequency modulation compensation model to obtain the corresponding compensation model output result, wherein the compensation model is used to correct the corresponding load parameter prediction value determined by the basic model.

[0063] After obtaining the preliminary prediction results of the basic model, it is necessary to drive the compensation model through data from different load segments to improve the prediction accuracy. To this end, the current condensate state parameters (such as condensate flow, temperature, etc.) and the load state parameters of the unit (such as current load, main steam pressure, etc.) are input into a pre-trained compensation model. The original intention of the design of the compensation model is to correct the output of the basic model, to consider the influence of nonlinear factors under actual operating conditions, and to make appropriate adjustments to the linear prediction of the basic model. Through the correction of the compensation model, the final prediction result can more accurately reflect the actual frequency regulation capability of the unit under the current load, thereby compensating for the errors that may be caused by a single linear model.

[0064] Step S103: determining the primary frequency regulation capability of the current unit in the condensate throttling mode according to the output result of the basic model and the output result of the compensation model.

[0065] The output results of the basic model are combined with the correction results of the compensation model for comprehensive analysis to obtain a more accurate frequency regulation capacity calculation value. It not only takes into account the basic relationship between the change in condensate flow and the change in unit load, but also reflects the actual state under the current working conditions, ensuring the reliability of the prediction results, providing strong support for the power plant to quickly and accurately calculate the primary frequency regulation capacity of the condensate throttling method in actual operation, and helping to improve the efficiency and stability of power grid frequency regulation.

[0066] From the above description, it can be seen that the condensate throttling primary frequency regulation capacity calculation method provided in the embodiment of the present application can accurately calculate the primary frequency regulation capacity of the condensate throttling method at each load point and under each operating condition, provide a reliable model guarantee for primary frequency regulation control, increase the auxiliary service market revenue of the unit, and help maintain the stability of the grid frequency.

[0067] In one embodiment of the condensate throttling primary frequency modulation capacity calculation method of the present application, see Figure 3 , the training process of the basic model includes:

[0068] Step S001: obtaining multiple groups of condensate water and load changes and current state parameters of the unit at multiple load points;

[0069] Step S002: Based on the least squares fitting method, the linear relationship between the condensate flow rate and the unit load change in the full load section of the unit is determined according to the change in the condensate and the unit load and used as the basic model.

[0070] Among them, in order to establish an accurate frequency regulation capacity calculation model, the unit must be tested under different load conditions. It is necessary to gradually adjust the condensate flow rate under various power generation loads (such as different power levels of the unit operation) and obtain key data sets for each load point, including condensate change ΔF, unit actual load change Δp, condensate original flow F, condensate temperature T, unit load value P, main steam pressure Y, main steam temperature YT, comprehensive valve position C and condenser pressure NT.

[0071] By repeating such experiments at multiple load points, the multiple sets of data collected will provide a rich basis for the establishment of subsequent models.

[0072] Afterwards, a basic model is established using the experimental data collected in the first step. For example, the least square method can be used to find the best linear relationship between the variables.

[0073] Specifically, each set of data in the experiment includes the condensate change ΔF and the corresponding unit actual load change Δp. At all experimental points, multiple sets of such data pairs are accumulated (such as ΔF1 corresponding to Δp1, ΔF2 corresponding to Δp2, etc.). By inputting these data into the least squares algorithm, the linear relationship between the condensate change and the unit load change is calculated, which can be expressed as:

[0074] Δp=k×ΔF+b

[0075] Among them, k is the fitted slope, which represents the influence of condensate flow rate change on load change; b is the intercept, which represents the basic influence of other unconsidered factors on the load.

[0076] This basic model lays a theoretical foundation for the subsequent frequency regulation capability calculation and can preliminarily reflect how changes in condensate flow affect the load adjustment of the unit.

[0077] In one embodiment of the condensate throttling primary frequency modulation capacity calculation method of the present application, see Figure 4 , the training process of the compensation model includes:

[0078] Step S003: determining a corresponding load parameter prediction value according to the condensate change and the basic model, and obtaining load error data according to the unit load change and the unit load state parameter;

[0079] Step S004: Based on the load error data, the state parameters of condensate and unit load are trained by an extreme learning machine to obtain the compensation model.

[0080] Since the load changes of the units in actual operation may be affected by a variety of complex factors, the linear prediction results of the basic model obtained through the above steps often have certain errors.

[0081] In order to correct this error, the difference between the actual unit load change and the basic model prediction result is calculated to obtain error data. Next, this error data will be input into the extreme learning machine (ELM) as training data for deep learning.

[0082] like Figure 5 As shown in the figure, the extreme learning machine combines the condensate change, the original condensate flow, the main steam pressure, the main steam temperature, the unit load, the condensate temperature, the condenser pressure and the comprehensive valve position to learn and capture the complex nonlinear relationship that the basic model fails to accurately reflect.

[0083] Through this training process, the generated compensation model can effectively correct the output of the basic model and finally output a more accurate prediction result of the frequency regulation capacity. The above method combines the basic model with the compensation model, which not only improves the prediction accuracy, but also enhances the adaptability of the model under various load conditions, providing more reliable data support for the actual operation of the power plant.

[0084] Furthermore, the extreme learning machine (ELM) is a new type of single feedforward neural hidden layer network, whose input weights and hidden layer thresholds are randomly generated and independent of the training sample data, and the output layer weight matrix is ​​obtained by one-step analytical calculation. The model structure of ELM is as follows Figure 6 shown.

[0085] For the observed sample (x i ,t i ), where the input vector x i =[x i1 ,x i2 ,x i3 ,…x in ] T ∈R n , (i=1,2,3,…,N), N is the number of observed samples, n is the dimension of the sample input vector, the output vector ti=[ti1,ti2,…tim]T∈Rm, m is the output sample dimension, that is, the number of nodes in the output layer of the ELM model. Assuming the number of nodes in the hidden layer of the model is l, and the activation function is g(·), the ELM model is:

[0086]

[0087] In the formula, βi=[βi1,βi2,…,βim]T is the weight from the i-th node of the hidden layer to the output layer of the model, wi=[wi1,wi2,…,win]T is the weight from the input layer to the i-th node of the hidden layer, and bi represents the threshold of the i-th node of the hidden layer. Studies have shown that the output value of the ELM model can fit the sample with zero error, that is:

[0088]

[0089] That is, there exist βi, wi and bi that satisfy:

[0090]

[0091] It can be shortened to:

[0092] Hβ=T

[0093] in:

[0094]

[0095]

[0096] In the formula, H is called the hidden layer output matrix. In the model training stage, the input weights and bias values ​​of the feedforward neural network are randomly set, and the output matrix H is calculated. In this way, the ELM learning and training problem is transformed into the problem of solving the least squares norm of the output weight matrix β, that is:

[0097]

[0098] Where H+ is the generalized inverse matrix of matrix H.

[0099] In one embodiment of the method for calculating the primary frequency regulation capability of condensate throttling of the present application, the state parameters of condensate and unit load are trained by an extreme learning machine based on the load error data to obtain the compensation model, including:

[0100] Classifying the state parameters of the unit load according to the load intensity, and respectively training the state parameters of the unit load at different levels to obtain the corresponding compensation models at different levels;

[0101] The state parameters of the current condensate and the unit load are input into the pre-trained compensation model of the primary frequency modulation of the condensate flow to obtain the corresponding compensation model output result, including:

[0102] The state parameters of the current condensate and unit load are input into the compensation model of the corresponding load intensity to obtain the corresponding compensation model output result.

[0103] Exemplarily, in this application, in order to more accurately calculate the condensate throttling primary frequency regulation capability of the computer unit, a segmented modeling method for different load segments is proposed. Specifically, the units of the power plant will experience different load conditions in actual operation, namely high load, medium load and low load, and the frequency regulation response characteristics under each load condition may be different. In order to solve this problem, the operating load of the unit is first divided into three parts: high load segment, medium load segment and low load segment. Then, a compensation model is established for each load segment, and these models are trained by extreme learning machines (ELM), and the data used comes from the test data collected in the previous experiment.

[0104] The role of these compensation models is to modify the prediction results of the basic model to adapt to the nonlinear characteristics and complex operating conditions of different load segments. For example, in the high load segment, the unit may be more susceptible to certain operating factors, so a special high load segment compensation model (G1) is required to deal with these characteristics. Similarly, the medium load segment and low load segment also have their own specific frequency regulation characteristics, so a medium load segment compensation model (G2) and a low load segment compensation model (G3) are established respectively. Each model is trained based on the test data of the corresponding load segment to ensure that the model can provide accurate frequency regulation capability predictions under these load conditions.

[0105] Finally, the process of calculating the primary frequency regulation capability of the condensate throttling mode of the computer unit will comprehensively use the basic model (G) established by the least squares method and the compensation models of each load segment (G1, G2, G3). In actual operation, no matter what load condition the unit is in, the corresponding compensation model can be selected to correct the prediction results of the basic model, and finally the accurate frequency regulation capability can be calculated. Through segmented modeling and targeted correction, the accuracy and adaptability of the frequency regulation capability calculation can be effectively improved, providing reliable support for the frequency response of the power plant under different load conditions.

[0106] In order to further illustrate the present scheme, the present application also provides a specific application example of using the above-mentioned condensate throttling primary frequency regulation capacity calculation device to implement the condensate throttling primary frequency regulation capacity calculation method. Taking a 660MW (Pe=660MW) load unit as an example, the normal operating range of the unit load is (330MW-660MW, i.e. 50% Pe-100% Pe). The specific process is as follows.

[0107] Step 1: Carry out condensate flow rate change tests at load points near 100%Pe, 95%Pe, 90%Pe, 85%Pe, 80%Pe, 75%Pe, 70%Pe, 65%Pe, 60%Pe, 55%Pe and 50%Pe respectively. Assume that n different condensate flow rate tests are carried out at each test point, then 11n groups of data are obtained for 11 operating points. Each group of data records the following data: condensate change ΔF, actual unit load change Δp, original condensate flow rate F, condensate temperature T, unit load value P, main steam pressure Y, main steam temperature YT, comprehensive valve position C and condenser pressure NT.

[0108] Step 2: Establish the basic model: Use the least squares fitting of the condensate change ΔF=(ΔF1, ΔF2, ... ΔF11n) in each of the 11n data sets and the actual load change Δp=(Δp1, Δp2, ... Δp11n) to obtain the basic model Δp=k×ΔF+b.

[0109] Step 3: Obtain error data: Substitute the condensate change ΔF=(ΔF1, ΔF2,......ΔF11n) in each of the 11n data groups into the basic model Δp=k×ΔF+b to obtain the model calculated value Δp1=(Δp11, Δp12,......Δp111n), and subtract the model calculated value Δp1=(Δp11, Δp12,......Δp111n) from the actual load change of the unit Δp=(Δp1, Δp2,......Δp11n) to obtain the error data: Δpe=(Δpe1, Δpe2,......Δpe11n).

[0110] Step 4: Divide the load segment into a high load segment (85%Pe<actual load), a medium load segment (65%Pe≤actual load≤85%Pe), and a low load segment (actual load<65%Pe). A compensation model is established for each load segment. The model structure is shown in the figure below. The training data is the test data.

[0111] Finally, if Figure 7 As shown, according to the above steps, the basic model of the primary frequency regulation capability of the condensate throttling mode (least square model G), the high load segment compensation model (extreme learning machine model G1), the medium load segment compensation model (extreme learning machine model G2) and the low load segment compensation model (extreme learning machine model G3) are obtained. Under any load condition, the primary frequency regulation capability of the condensate throttling mode can be calculated.

[0112] In order to accurately calculate the primary frequency regulation capacity of the condensate throttling method at each load point and under each operating condition, provide a reliable model guarantee for the primary frequency regulation control, increase the auxiliary service market revenue of the unit, and help maintain the stability of the power grid frequency, the present application provides an embodiment of a condensate throttling primary frequency regulation capacity calculation device for realizing all or part of the contents of the condensate throttling primary frequency regulation capacity calculation method, see Figure 8 The condensate throttling primary frequency modulation capacity calculation device specifically includes the following contents:

[0113] The basic determination module 1101 is used to: input the current condensate change amount into the pre-trained basic model of condensate flow primary frequency modulation to obtain the corresponding basic model output result, wherein the basic model represents the linear relationship between the condensate flow rate and the unit load change amount in the full load section of the unit;

[0114] The model correction module 1102 is used to: input the current condensate and unit load state parameters into the pre-trained condensate flow primary frequency modulation compensation model to obtain the corresponding compensation model output result, and the compensation model is used to correct the corresponding load parameter prediction value determined by the basic model;

[0115] The capacity determination module 1103 is used to determine the primary frequency regulation capacity of the current unit in the condensate throttling mode according to the output result of the basic model and the output result of the compensation model.

[0116] According to any embodiment of the present application, see Fig. 9 , the training process of the basic model includes:

[0117] The parameter acquisition module 1001 is used to: acquire multiple groups of condensate water and unit load changes and current state parameters of the unit at multiple load points;

[0118] The model fitting module 1002 is used to: determine the linear relationship between the condensate flow rate and the unit load change in the full load section of the unit based on the least squares fitting method and the change in the condensate and the unit load, and use it as the basic model.

[0119] According to any embodiment of the present application, see Fig.10 , the training process of the compensation model includes:

[0120] The error determination module 1003 is used to: determine the corresponding load parameter prediction value according to the condensate change and the basic model, and obtain the load error data according to the unit load change and the unit load state parameter;

[0121] The model training module 1004 is used to: based on the load error data, train the state parameters of condensate and unit load through an extreme learning machine to obtain the compensation model.

[0122] According to any implementation of the present application, the model training module is specifically used for:

[0123] Classifying the state parameters of the unit load according to the load intensity, and respectively training the state parameters of the unit load at different levels to obtain the corresponding compensation models at different levels;

[0124] The model correction module is specifically used for:

[0125] The state parameters of the current condensate and unit load are input into the compensation model of the corresponding load intensity to obtain the corresponding compensation model output result.

[0126] From the above description, it can be seen that the condensate throttling primary frequency regulation capacity calculation device provided in the embodiment of the present application can accurately calculate the primary frequency regulation capacity of the condensate throttling method at each load point and under each operating condition, provide a reliable model guarantee for primary frequency regulation control, increase the auxiliary service market revenue of the unit, and help maintain the stability of the power grid frequency.

[0127] From the hardware level, in order to accurately calculate the primary frequency regulation capacity of the condensate throttling method at each load point and under each working condition, provide a reliable model guarantee for the primary frequency regulation control, increase the auxiliary service market revenue of the unit, and help maintain the stability of the power grid frequency, the present application provides an embodiment of an electronic device for implementing all or part of the contents of the condensate throttling primary frequency regulation capacity calculation method, and the electronic device specifically includes the following contents:

[0128] Processor, memory, communication interface and bus; wherein the processor, memory and communication interface communicate with each other through the bus; the communication interface is used to realize information transmission between the condensate throttling primary frequency modulation capacity calculation device and the core business system, user terminal and related database and other related equipment; the logic controller can be a desktop computer, a tablet computer and a mobile terminal, etc., and the present embodiment is not limited thereto. In the present embodiment, the logic controller can be implemented with reference to the embodiment of the condensate throttling primary frequency modulation capacity calculation method and the embodiment of the condensate throttling primary frequency modulation capacity calculation device in the embodiment, and the contents thereof are incorporated herein, and the repeated parts are not repeated.

[0129] It is understandable that the user terminal may include a smart phone, a tablet electronic device, a network set-top box, a portable computer, a desktop computer, a personal digital assistant (PDA), a vehicle-mounted device, a smart wearable device, etc. Among them, the smart wearable device may include smart glasses, a smart watch, a smart bracelet, etc.

[0130] In practical applications, part of the method for calculating the primary frequency modulation capacity of condensate throttling can be executed on the electronic device side as described above, or all operations can be completed in the client device. The selection can be made based on the processing capacity of the client device and the limitations of the user's usage scenario. This application does not limit this. If all operations are completed in the client device, the client device may also include a processor.

[0131] The client device may have a communication module (i.e., a communication unit) that can communicate with a remote server to achieve data transmission with the server. The server may include a server on the task scheduling center side, and other implementation scenarios may also include a server on an intermediate platform, such as a server on a third-party server platform that has a communication link with the task scheduling center server. The server may include a single computer device, or a server cluster consisting of multiple servers, or a server structure of a distributed device.

[0132] Fig.11FIG. 9 is a schematic block diagram of the system structure of the electronic device 9600 according to an embodiment of the present application. Fig.11 As shown, the electronic device 9600 may include a central processor 9100 and a memory 9140; the memory 9140 is coupled to the central processor 9100. It is worth noting that Fig.11 is exemplary; other types of structures may also be used to supplement or replace this structure to implement telecommunication functions or other functions.

[0133] In one embodiment, the condensate throttling primary frequency modulation capacity calculation method function may be integrated into the central processor 9100. The central processor 9100 may be configured to perform the following control:

[0134] Step S101: inputting the current condensate change into a pre-trained basic model of primary frequency modulation of condensate flow to obtain a corresponding basic model output result, wherein the basic model represents the linear relationship between the condensate flow rate and the load change of the unit at full load;

[0135] Step S102: inputting the current condensate and unit load state parameters into the pre-trained condensate flow primary frequency modulation compensation model to obtain a corresponding compensation model output result, wherein the compensation model is used to correct the corresponding load parameter prediction value determined by the basic model;

[0136] Step S103: determining the primary frequency regulation capability of the current unit in the condensate throttling mode according to the output result of the basic model and the output result of the compensation model.

[0137] From the above description, it can be seen that the electronic device provided in the embodiment of the present application accurately calculates the primary frequency regulation capability of the condensate throttling method at each load point and under each operating condition, provides a reliable model guarantee for the primary frequency regulation control, increases the auxiliary service market revenue of the unit, and helps maintain the stability of the grid frequency.

[0138] In another embodiment, the condensate water throttling primary frequency modulation capacity calculation device can be configured separately from the central processing unit 9100. For example, the condensate water throttling primary frequency modulation capacity calculation device can be configured as a chip connected to the central processing unit 9100, and the condensate water throttling primary frequency modulation capacity calculation method function can be implemented through the control of the central processing unit.

[0139] like Fig.11 As shown, the electronic device 9600 may also include: a communication module 9110, an input unit 9120, an audio processor 9130, a display 9160, and a power supply 9170. It is worth noting that the electronic device 9600 does not necessarily have to include Fig.11 In addition, the electronic device 9600 may also include Fig.11 For components not shown, reference may be made to the prior art.

[0140] like Fig.11 As shown, the central processing unit 9100 is sometimes also referred to as a controller or an operation control, and may include a microprocessor or other processor device and / or logic device. The central processing unit 9100 receives input and controls the operation of various components of the electronic device 9600.

[0141] The memory 9140 may be, for example, one or more of a cache, a flash memory, a hard drive, a removable medium, a volatile memory, a non-volatile memory or other suitable devices. The above-mentioned information related to the failure may be stored, and a program for executing the relevant information may also be stored. The CPU 9100 may execute the program stored in the memory 9140 to implement information storage or processing, etc.

[0142] The input unit 9120 provides input to the central processing unit 9100. The input unit 9120 is, for example, a key or a touch input device. The power supply 9170 is used to provide power to the electronic device 9600. The display 9160 is used to display display objects such as images and texts. The display may be, for example, an LCD display, but is not limited thereto.

[0143] The memory 9140 may be a solid-state memory, such as a read-only memory (ROM), a random access memory (RAM), a SIM card, etc. It may also be a memory that saves information even when the power is off, can be selectively erased, and is provided with more data, examples of which are sometimes referred to as EPROMs, etc. The memory 9140 may also be some other type of device. The memory 9140 includes a buffer memory 9141 (sometimes referred to as a buffer). The memory 9140 may include an application / function storage unit 9142, which is used to store application programs and function programs or processes for executing the operation of the electronic device 9600 through the central processor 9100.

[0144] The memory 9140 may also include a data storage unit 9143 for storing data, such as contacts, digital data, pictures, sounds, and / or any other data used by the electronic device. The driver storage unit 9144 of the memory 9140 may include various drivers for communication functions of the electronic device and / or for executing other functions of the electronic device (such as messaging applications, address book applications, etc.).

[0145] The communication module 9110 is a transmitter / receiver 9110 that sends and receives signals via an antenna 9111. The communication module (transmitter / receiver) 9110 is coupled to the central processor 9100 to provide input signals and receive output signals, which may be the same as the case of a conventional mobile communication terminal.

[0146] Based on different communication technologies, multiple communication modules 9110 may be provided in the same electronic device, such as a cellular network module, a Bluetooth module and / or a wireless LAN module, etc. The communication module (transmitter / receiver) 9110 is also coupled to a speaker 9131 and a microphone 9132 via an audio processor 9130 to provide an audio output via the speaker 9131 and receive an audio input from the microphone 9132, thereby realizing a common telecommunication function. The audio processor 9130 may include any suitable buffer, decoder, amplifier, etc. In addition, the audio processor 9130 is also coupled to the central processor 9100, so that recording can be performed on the local machine through the microphone 9132, and the sound stored on the local machine can be played through the speaker 9131.

[0147] The embodiments of the present application also provide a computer-readable storage medium capable of implementing all steps of the method for calculating the primary frequency modulation capacity of condensate throttling in the above embodiment, where the execution subject is a server or a client. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, all steps of the method for calculating the primary frequency modulation capacity of condensate throttling in the above embodiment are implemented. For example, when the processor executes the computer program, the following steps are implemented:

[0148] Step S101: inputting the current condensate change into a pre-trained basic model of primary frequency modulation of condensate flow to obtain a corresponding basic model output result, wherein the basic model represents the linear relationship between the condensate flow rate and the load change of the unit at full load;

[0149] Step S102: inputting the current condensate and unit load state parameters into the pre-trained condensate flow primary frequency modulation compensation model to obtain a corresponding compensation model output result, wherein the compensation model is used to correct the corresponding load parameter prediction value determined by the basic model;

[0150] Step S103: determining the primary frequency regulation capability of the current unit in the condensate throttling mode according to the output result of the basic model and the output result of the compensation model.

[0151] From the above description, it can be seen that the computer-readable storage medium provided in the embodiment of the present application accurately calculates the primary frequency regulation capability of the condensate throttling method at each load point and under each operating condition, provides a reliable model guarantee for the primary frequency regulation control, increases the auxiliary service market revenue of the unit, and helps maintain the stability of the grid frequency.

[0152] The embodiments of the present application also provide a computer program product capable of implementing all steps of the method for calculating the primary frequency modulation capacity of condensate throttling in the above embodiment, where the execution subject is a server or a client. When the computer program / instruction is executed by a processor, the steps of the method for calculating the primary frequency modulation capacity of condensate throttling are implemented. For example, the computer program / instruction implements the following steps:

[0153] Step S101: inputting the current condensate change into a pre-trained basic model of primary frequency modulation of condensate flow to obtain a corresponding basic model output result, wherein the basic model represents the linear relationship between the condensate flow rate and the load change of the unit at full load;

[0154] Step S102: inputting the current condensate and unit load state parameters into the pre-trained condensate flow primary frequency modulation compensation model to obtain a corresponding compensation model output result, wherein the compensation model is used to correct the corresponding load parameter prediction value determined by the basic model;

[0155] Step S103: determining the primary frequency regulation capability of the current unit in the condensate throttling mode according to the output result of the basic model and the output result of the compensation model.

[0156] From the above description, it can be seen that the computer program product provided in the embodiment of the present application accurately calculates the primary frequency regulation capability of the condensate throttling method at each load point and under each operating condition, provides a reliable model guarantee for the primary frequency regulation control, increases the auxiliary service market revenue of the unit, and helps maintain the stability of the grid frequency.

[0157] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, devices, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product 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.

[0158] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (apparatus), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1A device that provides the functions specified in a block or multiple blocks.

[0159] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0160] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0161] The present invention uses specific embodiments to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A method for calculating the primary frequency modulation capacity of condensate throttling, characterized in that: The method comprises: Input the current condensate change into the pre-trained basic model of condensate flow primary frequency modulation to obtain the corresponding basic model output result, wherein the basic model represents the linear relationship between the condensate flow rate and the load change of the unit at full load; Inputting the current condensate and unit load state parameters into the pre-trained condensate flow primary frequency modulation compensation model to obtain the corresponding compensation model output result, wherein the compensation model is used to correct the corresponding load parameter prediction value determined by the basic model; The primary frequency regulation capability of the current unit in the condensate throttling mode is determined according to the output result of the basic model and the output result of the compensation model.

2. The method for calculating the condensate throttling primary frequency modulation capacity according to claim 1 is characterized in that: The training process of the basic model includes: Obtain multiple groups of condensate and load changes and current state parameters of the unit at multiple load points; Based on the least square fitting method, the linear relationship between the condensate flow rate and the unit load change in the full load section of the unit is determined according to the changes in the condensate and the unit load and used as the basic model.

3. The method for calculating the condensate throttling primary frequency modulation capacity according to claim 1 is characterized in that: The training process of the compensation model includes: Determine the corresponding load parameter prediction value according to the condensate change and the basic model, and obtain the load error data according to the unit load change and the unit load state parameter; Based on the load error data, the state parameters of condensate and unit load are trained by an extreme learning machine to obtain the compensation model.

4. The method for calculating the condensate throttling primary frequency modulation capacity according to claim 3 is characterized in that: The method of training the state parameters of condensate and unit load by an extreme learning machine based on the load error data to obtain the compensation model includes: Classifying the state parameters of the unit load according to the load intensity, and respectively training the state parameters of the unit load at different levels to obtain the corresponding compensation models at different levels; The state parameters of the current condensate and the unit load are input into the pre-trained compensation model of the primary frequency modulation of the condensate flow to obtain the corresponding compensation model output result, including: The state parameters of the current condensate and unit load are input into the compensation model of the corresponding load intensity to obtain the corresponding compensation model output result.

5. A condensate throttling primary frequency modulation capacity calculation device, characterized in that: The device comprises: A basic determination module is used to: input the current condensate change into a pre-trained basic model of condensate flow primary frequency modulation to obtain a corresponding basic model output result, wherein the basic model represents the linear relationship between the condensate flow rate and the unit load change in the full load section of the unit; A model correction module is used to: input the current condensate and unit load state parameters into a pre-trained condensate flow primary frequency modulation compensation model to obtain a corresponding compensation model output result, wherein the compensation model is used to correct the corresponding load parameter prediction value determined by the basic model; The capacity determination module is used to determine the primary frequency regulation capacity of the current unit in the condensate throttling mode according to the output results of the basic model and the output results of the compensation model.

6. The condensate throttling primary frequency modulation capacity calculation device according to claim 5, characterized in that: The training process of the basic model includes: The parameter acquisition module is used to: acquire multiple groups of condensate water and unit load changes and current state parameters of the unit at multiple load points; The model fitting module is used to: determine the linear relationship between the condensate flow rate and the unit load change in the full load section of the unit based on the least squares fitting method and the change in the condensate and the unit load as the basic model.

7. The condensate throttling primary frequency modulation capacity calculation device according to claim 5, characterized in that: The training process of the compensation model includes: An error determination module is used to: determine the corresponding load parameter prediction value according to the condensate change and the basic model, and obtain load error data according to the unit load change and the unit load state parameter; The model training module is used to: based on the load error data, train the state parameters of condensate and unit load through an extreme learning machine to obtain the compensation model.

8. The condensate throttling primary frequency modulation capacity calculation device according to claim 7 is characterized in that: The model training module is specifically used for: Classifying the state parameters of the unit load according to the load intensity, and respectively training the state parameters of the unit load at different levels to obtain the corresponding compensation models at different levels; The model correction module is specifically used for: The state parameters of the current condensate and unit load are input into the compensation model of the corresponding load intensity to obtain the corresponding compensation model output result.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the method for calculating the condensate throttling primary frequency regulation capacity described in any one of claims 1 to 4 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for calculating the condensate throttling primary frequency regulation capacity described in any one of claims 1 to 4 are implemented.

11. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instruction is executed by a processor, the steps of the method for calculating the condensate throttling primary frequency regulation capacity described in any one of claims 1 to 4 are implemented.

Images