Method for frequency modulation, storage medium and electronic device

Abstract

The present disclosure relates to a method for primary frequency regulation, a storage medium and an electronic device to solve the problem of low accuracy of frequency measurement by frequency conversion device in the related art. The method is applied to a control system, comprising: obtaining a first rotating speed of a generator set, and determining a first grid frequency according to the first rotating speed of the generator set; inputting the first grid frequency into a preset frequency prediction model to obtain a predicted second grid frequency, the frequency prediction model being used to predict the actual frequency of the grid according to the first grid frequency; and sending the second grid frequency to a generator set regulation system, so that the generator set regulation system determines to perform primary frequency regulation when the preset primary frequency regulation condition is met according to the second grid frequency.

Description

Technical Field

[0001] This disclosure relates to primary frequency regulation technology for power grids, specifically to a primary frequency regulation method, a storage medium, and an electronic device. Background Technology

[0002] Primary frequency regulation refers to the automatic control process in which the control system of the generating units in the power grid automatically controls the increase or decrease of the active power of the generating units when the frequency of the power grid deviates from the rated value, thereby limiting the change of the power grid frequency and maintaining the stability of the power grid frequency.

[0003] Currently, the frequency of the power grid cannot be obtained by phasor measurement units (PMUs) due to power grid security requirements. Therefore, frequency transmitters are usually used to measure the power grid frequency. However, even the most accurate frequency transmitters will have errors with the frequency being tested by the power grid, which can lead to a frequency regulation test when the frequency difference is small. Summary of the Invention

[0004] The purpose of this disclosure is to provide a primary frequency modulation method, storage medium, and electronic device to solve the problem of low accuracy in measuring power grid frequency using frequency transmitters in related technologies.

[0005] To achieve the above objectives, a first aspect of this disclosure provides a primary frequency modulation method applied to a control system, the method comprising:

[0006] Obtain the first rotational speed of the generator set, and determine the first grid frequency based on the first rotational speed of the generator set;

[0007] The first power grid frequency is input into a preset frequency prediction model to obtain the predicted second power grid frequency. The frequency prediction model is used to predict the actual frequency of the power grid based on the first power grid frequency.

[0008] The second grid frequency is sent to the generator set regulation system so that the generator set regulation system can perform primary frequency regulation when the preset primary frequency regulation conditions are met based on the second grid frequency.

[0009] Optionally, the method further includes:

[0010] The second rotational speed is determined based on the third grid frequency, which is obtained by inputting the fourth grid frequency, determined by the third rotational speed of the generator set, into the frequency prediction model during a frequency regulation period of the generator set regulation system.

[0011] The theoretical power contribution value of the generator set is determined based on the relationship between the second speed and the preset speed threshold, the maximum speed difference between the second speed and the speed threshold, and the preset relationship between the speed difference and the theoretical power contribution value.

[0012] The actual contribution rate of the generator set is obtained by dividing the actual power contribution value of the generator set by the theoretical power contribution value. The actual power contribution value is the difference between the actual power and the initial power of the generator set.

[0013] Optionally, the method further includes:

[0014] If the actual contribution rate is less than the target contribution rate after the target preset time, then the contribution rate difference between the preset total contribution rate and the actual contribution rate is determined.

[0015] The target load is determined based on the maximum speed difference and the preset speed inequality function;

[0016] The target supplementary value is obtained by multiplying the contribution rate difference and the target load, and the third grid frequency, the actual contribution rate and the target supplementary value are sent to the generator set regulation system so that the generator set regulation system can perform a frequency regulation closed loop regulation based on the third grid frequency, the actual contribution rate and the target supplementary value.

[0017] Optionally, the actual contribution rate includes the first actual contribution rate of the generator set within a first preset time period and the second actual contribution rate within a second preset time period, wherein the first preset time period is less than the second preset time period, the target contribution rate includes the first target contribution rate corresponding to the first preset time period and the second target contribution rate corresponding to the second preset time period, and the maximum speed difference includes the first maximum speed difference within the first preset time period and the second maximum speed difference within the second preset time period;

[0018] If the actual contribution rate is less than the target contribution rate after a preset time period, then determining the contribution rate difference between the preset total contribution rate and the actual contribution rate includes:

[0019] If the first actual contribution rate is less than the first target contribution rate after the first target preset time, then a first contribution rate difference is determined between the total contribution rate and the first actual contribution rate, and the first target preset time is less than the first preset time; and / or,

[0020] If the second actual contribution rate is less than the second target contribution rate after the second target preset time, then the second contribution rate difference between the total contribution rate and the second actual contribution rate is determined, and the second target preset time is less than the second preset time.

[0021] The step of determining the target load based on the maximum speed difference and a preset speed inequality function includes:

[0022] The first target load is determined based on the first maximum speed difference and the speed inequality function; and / or,

[0023] The second target load is determined based on the second maximum speed difference and the speed inequality function.

[0024] Optionally, the step of multiplying the contribution rate difference and the target load to obtain the target supplementary value, and sending the third grid frequency, the actual contribution rate, and the target supplementary value to the generator set regulation system, so that the generator set regulation system performs a first-stage frequency regulation closed-loop regulation based on the third grid frequency, the actual contribution rate, and the target supplementary value, includes:

[0025] The first contribution rate difference is multiplied by the first target load to obtain a first target supplementary value. The third grid frequency, the first actual contribution rate, and the first target supplementary value are then sent to the generator set regulation system, so that the generator set regulation system performs a first-stage frequency regulation closed-loop adjustment based on the third grid frequency, the first actual contribution rate, and the first target supplementary value; and / or,

[0026] The second contribution rate difference is multiplied by the second target load to obtain the second target supplementary value. The third grid frequency, the second actual contribution rate, and the second target supplementary value are then sent to the generator set regulation system so that the generator set regulation system can perform a frequency regulation closed-loop regulation based on the third grid frequency, the second actual contribution rate, and the second target supplementary value.

[0027] Optionally, the preset speed threshold includes an upper speed threshold and a lower speed threshold. The step of determining the theoretical power contribution value of the generator set based on the relationship between the second speed and the preset speed threshold, the maximum speed difference between the second speed and the speed threshold, and a preset relationship between the speed difference and the theoretical power contribution value includes:

[0028] If the second rotational speed is less than the lower speed threshold, then the low-frequency power theoretical contribution value of the generator set is determined according to the maximum speed difference and the preset relationship between the speed difference and the theoretical power contribution value; or,

[0029] If the second rotational speed is greater than the upper limit threshold of rotational speed, the high-frequency power theoretical contribution value of the generator set is determined according to the maximum rotational speed difference and the preset relationship between the rotational speed difference and the theoretical power contribution value.

[0030] The step of dividing the actual power contribution value of the generator set by the theoretical power contribution value to obtain the actual contribution rate of the generator set includes:

[0031] The actual low-frequency contribution rate of the generator set is obtained by dividing the actual power contribution value by the theoretical low-frequency power contribution value; or,

[0032] The actual high-frequency contribution rate of the generator set is obtained by dividing the actual power contribution value by the theoretical high-frequency power contribution value.

[0033] Optionally, the frequency prediction model is a BP neural network, which is trained in the following manner:

[0034] Construct a BP neural network;

[0035] Acquire the first historical grid frequency data from the PMU device, and the historical speed data of the generator set for the time period corresponding to the historical grid frequency data;

[0036] The second historical power grid frequency data is determined based on the historical rotational speed data;

[0037] The first historical power grid frequency data is used as the output sample, and the second power grid frequency data is used as the input sample to train the BP neural network, thereby obtaining a trained frequency prediction model.

[0038] A second aspect of this disclosure provides a primary frequency regulation method applied to a generator set regulation system, the method comprising:

[0039] The system receives a second grid frequency sent by the control system. The second grid frequency is obtained by the control system inputting the first grid frequency determined according to the first speed of the generator set into a preset frequency prediction model. The frequency prediction model includes the mapping relationship between the first grid frequency and the second grid frequency. The second grid frequency is used to characterize the actual frequency of the grid.

[0040] If the second grid frequency meets the preset primary frequency regulation conditions, a primary frequency regulation is performed.

[0041] Optionally, the method further includes:

[0042] During the first frequency regulation period, the system receives the third grid frequency, the actual contribution rate of the generator set, and the target supplement value sent by the control system. The third grid frequency is obtained by the control system inputting the fourth grid frequency determined according to the third rotational speed of the generator set into the frequency prediction model during the first frequency regulation period.

[0043] The set contribution rate and the actual contribution rate are input into the PID controller to obtain the PID output value, and the PID output value and the target supplement value are added to obtain the first adjustment value;

[0044] A frequency regulation closed-loop adjustment is performed based on the set power and actual power of the generator set, the first adjustment value and the third grid frequency, so that the actual contribution rate reaches the set contribution rate within a preset time period.

[0045] A third aspect of this disclosure provides a non-transitory computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the steps of the method described in any one of the first or second aspects above.

[0046] A fourth aspect of this disclosure provides an electronic device comprising:

[0047] A memory on which computer programs are stored;

[0048] A processor for executing the computer program in the memory to implement the steps of the method described in any one of the first or second aspects above.

[0049] The above technical solution can achieve at least the following technical effects:

[0050] The generator set's first rotational speed is obtained, and a first grid frequency is determined based on this speed. This first grid frequency is then input into a preset frequency prediction model to obtain a predicted second grid frequency. Finally, the second grid frequency is sent to the generator set regulation system, enabling the system to perform primary frequency regulation when preset primary frequency regulation conditions are met. The frequency prediction model is used to predict the actual grid frequency based on the first grid frequency. Using this method, the generator set's rotational speed can be directly obtained, thus avoiding errors caused by the accuracy of measuring devices. Furthermore, predicting the actual grid frequency through the frequency prediction model improves the accuracy of the primary frequency regulation data source compared to measuring the grid frequency with a measuring device.

[0051] Other features and advantages of this disclosure will be described in detail in the following detailed description section. Attached Figure Description

[0052] The accompanying drawings are provided to further illustrate the present disclosure and form part of the specification. They are used together with the following detailed description to explain the present disclosure, but do not constitute a limitation thereof. In the drawings:

[0053] Figure 1 This is a logic diagram of a primary frequency modulation method based on relevant technologies;

[0054] Figure 2 This is a flowchart illustrating a primary frequency modulation method according to an exemplary embodiment;

[0055] Figure 3 This is a comparison diagram of sample output f0 and neural network output f' shown according to an exemplary embodiment;

[0056] Figure 4This is a schematic diagram illustrating the control logic of a primary frequency modulation low-frequency operation in a DCS system according to an exemplary embodiment;

[0057] Figure 5 This is a schematic diagram illustrating the control logic of a DCS system for a single-frequency high-frequency operation, according to an exemplary embodiment.

[0058] Figure 6 This is a schematic diagram illustrating a control logic for calculating the contribution rate of a single-frequency low-frequency action over 15 seconds, according to an exemplary embodiment.

[0059] Figure 7 This is a schematic diagram illustrating a control logic for calculating the contribution rate of a single frequency modulation high-frequency action over 15 seconds, according to an exemplary embodiment.

[0060] Figure 8 This is a schematic diagram illustrating, according to an exemplary embodiment, a control logic for constructing a target supplementary value for calculating a single frequency modulation low-frequency action of 15 seconds;

[0061] Figure 9 This is a schematic diagram illustrating, according to an exemplary embodiment, a control logic for constructing a target supplementary value for calculating a single frequency modulation low-frequency action of 30 seconds;

[0062] Figure 10 This is a flowchart illustrating a primary frequency modulation method according to an exemplary embodiment;

[0063] Figure 11 This is a schematic diagram illustrating the primary frequency regulation control logic of a generator set regulation system according to an exemplary embodiment;

[0064] Figure 12 This is a block diagram illustrating an electronic device according to an exemplary embodiment. Detailed Implementation

[0065] The specific embodiments of this disclosure will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit this disclosure.

[0066] It should be noted that all actions involving the acquisition of signals, information, or data in this disclosure are carried out in compliance with the relevant data protection laws and policies of the country where the location is situated, and with authorization from the owner of the relevant device.

[0067] It should be understood that the various steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect. The term "comprising" and its variations as used herein are open-ended, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Relevant definitions for other terms will be given in the description below.

[0068] Reference Figure 1 Taking thermal power units as an example, the primary frequency regulation method mainly adopts the "DEH+CCS" approach. The DEH side refers to the turbine digital electro-hydraulic control system, and the CCS side refers to the coordinated control system. The DEH side uses a power correction function with a speed unequal rate of 5 as feedforward, while the CCS side uses a power correction function with a speed unequal rate of 5 to generate corrected power, which is superimposed on the original power command to form a new power command (turbine valve position command).

[0069] Currently, optimizations for primary frequency regulation mainly include: improving the accuracy of frequency difference measurement using high-precision frequency transmitters or frequency-coordinated devices, such as synchronous phasor measurement units (PMUs); reducing the dead zone of the frequency difference action to ensure the timeliness of primary frequency regulation action in order to guarantee the actual performance indicators of primary frequency regulation; and setting the speed unequal rate below 5 to increase the amplitude of frequency regulation action. However, the frequency measured by the PMU cannot be obtained due to grid security requirements, and even the most accurate frequency transmitter will have errors with the frequency tested by the grid, which can lead to problems with primary frequency regulation testing when the frequency difference is small. In addition, reducing the dead zone of the frequency difference action can cause the primary frequency regulation to act prematurely, resulting in a higher reference value, which is not conducive to the assessment of primary frequency regulation performance indicators, while reducing the speed unequal rate can cause excessive primary frequency regulation action, increasing disturbances on the unit side and reducing the stability and safety of unit operation.

[0070] In view of this, the present disclosure provides a primary frequency modulation method, a storage medium, and an electronic device to solve the above problems.

[0071] The following provides a detailed description of the embodiments of the technical solution disclosed herein.

[0072] Reference Figure 2 This disclosure provides a primary frequency modulation method applied to a control system, the method comprising:

[0073] S201. Obtain the first rotational speed of the generator set and determine the first grid frequency based on the first rotational speed of the generator set.

[0074] For example, the conversion between rotational speed and frequency can be obtained by dividing rotational speed by 60 to get the frequency.

[0075] S202. Input the first power grid frequency into the preset frequency prediction model to obtain the predicted second power grid frequency.

[0076] Among them, the frequency prediction model is used to predict the actual frequency of the power grid based on the first power grid frequency.

[0077] S203. Send the second grid frequency to the generator set regulation system so that the generator set regulation system can perform primary frequency regulation when the preset primary frequency regulation conditions are met based on the second grid frequency.

[0078] Using the above method, the generator speed can be directly obtained, thus avoiding errors caused by the accuracy of the measuring device. Furthermore, the actual frequency of the power grid can be predicted through a frequency prediction model, which improves the accuracy of the primary frequency regulation data source compared to measuring the power grid frequency through a measuring device.

[0079] To enable those skilled in the art to better understand the primary frequency modulation method provided in this disclosure, the above steps are illustrated in detail below.

[0080] In one possible approach, the frequency prediction model can be a BP neural network, which is trained as follows: a BP neural network is constructed, first historical grid frequency data from the PMU device and historical speed data of the generator set for the time period corresponding to the historical grid frequency data are obtained, second historical grid frequency data are determined based on the historical speed data, and finally the first historical grid frequency data is used as the output sample and the second grid frequency data is used as the input sample to train the BP neural network to obtain the trained frequency prediction model.

[0081] For example, a frequency measurement data sequence f0 (in seconds) for multiple frequency regulation operation periods is exported from the PMU device, and a frequency measurement value sequence f for the same time period as f0 is exported from the control system (e.g., a distributed control system). The frequency measurement value of the control system is obtained by dividing the generator speed by 60.

[0082] Then, a frequency prediction model is constructed. The BP neural network can adopt a three-layer neural network structure, using the ReLU function as the activation function and MSE as the loss function. The number of hidden layer neurons is selected as 10. f is used as the input sample and f0 as the output sample. The input and output are normalized and denormalized within the range of 49.8-50.2 (set according to the power grid frequency). The BP neural network is trained using the [f, f0] data sequence as samples to obtain a neural network that fits f0 to f. For details, refer to the training process of BP neural networks in related technologies. The parameters of the above neural network model can be determined according to the requirements, and this disclosure does not limit them.

[0083] It should be noted that, through its own training, the BP neural network can fit the mapping relationship between the input and the output, and obtain the result that is closest to the expected output value given the input value. Figure 3 This is a comparison diagram of the output sample f0 and the neural network output f', as shown below. Figure 3 As shown, the fitting accuracy is high. Therefore, predicting the actual frequency of the power grid through the frequency prediction model can improve the accuracy of the primary frequency regulation frequency data source.

[0084] It is worth noting that the above frequency prediction model is only an example. The specific model can be determined according to the requirements. As long as it can fit the frequency determined by the generator set speed to predict the actual frequency of the power grid and the fitting accuracy meets the requirements, this disclosure does not impose any limitations on it.

[0085] Secondly, the power grid assessment requires evaluating the 15-second and 30-second output response indices of primary frequency regulation, i.e., performance assessment of primary frequency regulation. Taking the control system as a DCS (Distributed Control System) system as an example, the 15-second and 30-second output response indices can be calculated by constructing control logic.

[0086] In one possible manner, the method further includes: determining a second rotational speed based on a third grid frequency, wherein the third grid frequency is obtained by inputting a fourth grid frequency determined by the third rotational speed of the generator set into a frequency prediction model during a primary frequency regulation period of the generator set regulation system; determining the theoretical power contribution value of the generator set based on the relationship between the second rotational speed and a preset rotational speed threshold, the maximum rotational speed difference between the second rotational speed and the rotational speed threshold, and a preset relationship between the rotational speed difference and the theoretical power contribution value; and dividing the actual power contribution value of the generator set by the theoretical power contribution value to obtain the actual contribution rate of the generator set, wherein the actual power contribution value is the difference between the actual power and the initial power of the generator set.

[0087] For example, during the frequency regulation period of the generator set regulation system, the frequency at which the generator set speed is determined is input into the frequency prediction model to obtain the predicted frequency. Then, the predicted frequency is multiplied by 60 to obtain the second speed. The theoretical power contribution value of the generator set is determined by the relationship between the second speed and the preset speed threshold, the maximum speed difference between the second speed and the speed threshold, and the preset relationship between the speed difference and the theoretical power contribution value. Finally, the actual power contribution value of the generator set is divided by the theoretical power contribution value to obtain the actual contribution rate (output response index) of the generator set.

[0088] In possible methods, the preset speed thresholds include an upper speed threshold and a lower speed threshold. The theoretical power contribution value of the generator set is determined based on the relationship between the second speed and the preset speed threshold, the maximum speed difference between the second speed and the speed threshold, and a preset relationship between the speed difference and the theoretical power contribution value. This can be achieved by: if the second speed is less than the lower speed threshold, then the low-frequency theoretical power contribution value of the generator set is determined based on the maximum speed difference and the preset relationship between the speed difference and the theoretical power contribution value; or, if the second speed is greater than the upper speed threshold, then the high-frequency theoretical power contribution value of the generator set is determined based on the maximum speed difference and the preset relationship between the speed difference and the theoretical power contribution value. The actual contribution rate of the generator set is obtained by dividing the actual power contribution value by the theoretical power contribution value. This can be achieved by dividing the actual power contribution value by the low-frequency theoretical power contribution value to obtain the low-frequency actual contribution rate of the generator set, or by dividing the actual power contribution value by the high-frequency theoretical power contribution value to obtain the high-frequency actual contribution rate of the generator set.

[0089] For example, the control logic for a single-frequency modulation low-frequency action constructed by a DCS system is as follows: Figure 4As shown, the frequency output by the frequency prediction model is multiplied by 60 and converted into a speed signal. L01 is set as the lower speed threshold, and ONDELAY is a delay module. Currently, the standard speed is 3000 rpm, so the lower speed threshold can be set to 2998 rpm, which can be determined according to requirements; this disclosure does not limit this setting. After the speed signal passes through L01, if the speed is less than the lower speed threshold, the generator set regulation system performs a low-frequency frequency regulation action, outputting a value of 1; otherwise, the output is 0. Specifically, the ONDELAY1 parameter is set to 15 seconds. The NOT1 output is 1 if the duration of the frequency regulation action is within 15 seconds, and 0 if it exceeds 15 seconds. Therefore, the AND1 output represents a 15-second low-frequency frequency regulation action. The ONDELAY2 parameter is set to 30 seconds. The NOT2 output is 1 if the duration of the frequency regulation action is within 30 seconds, and 0 if it exceeds 30 seconds. Therefore, the AND2 output represents a 30-second low-frequency frequency regulation action. The ONDELAY3 parameter is 60s. The NOT3 output is 1 when the duration of the first frequency modulation is within 60s, and 0 when it exceeds 60s. Therefore, the output of AND3 represents the low-frequency action of the first frequency modulation for 60s.

[0090] In addition, the control logic for high-frequency operation of the DCS system is as follows: Figure 5 Hl1 is set as the upper limit threshold of the rotational speed, for example, 3002, which can be determined according to requirements, and this disclosure does not limit it. The logic judgment is similar to the control logic of the low-frequency action of the primary frequency modulation, and outputs the primary frequency modulation high-frequency action for 15s, 30s, and 60s respectively.

[0091] Furthermore, taking the low-frequency signal output by the above control logic as an example, which involves a 15-second low-frequency modulation operation, refer to... Figure 6 , Figure 6 This is the control logic for calculating the contribution rate (15-second output response index) of a single-frequency low-frequency action over 15 seconds. Here, A is a constant block, A1 is the lower speed threshold (2998), A2-A5 are 0, SUB represents the subtraction module, and DIVIDE represents the division module. HzLow15 represents the single-frequency low-frequency action over 15 seconds (low-frequency signal). TRANSFER is a switching module; when its switching signal (low-frequency signal) is 1, the output equals the Y-terminal input (TRANSFER1 is the output of HISELECT1, TRANSFER2 is the output of HISELECT3, and RANSFER3 is the output of DIVIDE); when its switching signal is 0, the output equals the N-terminal input (the value of the constant block). HISELECT is a selection module; its output equals the maximum value of all N inputs. FX1 is the speed variability function.

[0092] For example, when HzLow15 primary frequency regulation low-frequency action 15s is 0, it indicates that the generator set regulation system has not experienced a low-frequency action 15s. At this time, each TRANSFER output is its N-terminal input, and the output is 0, ensuring that the output of this loop is 0. When HzLow15 primary frequency regulation low-frequency action 15s is 1, it indicates that the generator set regulation system has experienced a low-frequency action 15s. TRANSFER1 output = Y-terminal input (HISELECT1 output). HISELECT1 input 1 is the system frequency difference 2998-f'×60, and input 2 is the HISELECT1 output (at this time, TRANSFER1 output = HISELECT1 output). Therefore, the selection module can ensure that its output is the maximum speed difference during the HzLow15 primary frequency regulation low-frequency action 15s. After its output is converted by the FX1 speed inequality function, the theoretical power contribution value is obtained, and its value is >0. Therefore, the HISELECT3 output is the theoretical power contribution value during the primary frequency regulation low-frequency action 15s. Similarly, TRANSFER2 can guarantee that its output is the actual power contribution value during the 15s low-frequency operation of a single frequency modulation. TRANSFER2 (actual power contribution value) ÷ HISELECT3 (theoretical power contribution value) can be used to obtain the contribution rate (15-second output response index) of the 15s low-frequency operation of a single frequency modulation.

[0093] Similarly, refer to Figure 7 Construct control logic to calculate the contribution rate (15-second output response index) of a single frequency modulation high-frequency action over 15 seconds, such as... Figure 7 As shown, A is a constant block, where A1 has a value of 3002 and A2-A5 have values ​​of 0. The logic judgment is similar to the control logic for calculating the contribution rate of a single frequency modulation low-frequency action over 15 seconds. Correspondingly, the control logic for calculating the contribution rate of a single frequency modulation low-frequency action over 30 seconds (30-second output response index) can refer to the control logic for calculating the contribution rate of a single frequency modulation low-frequency action over 15 seconds, and the control logic for calculating the contribution rate of a single frequency modulation high-frequency action over 30 seconds (30-second output response index) can refer to the control logic for calculating the contribution rate of a single frequency modulation high-frequency action over 15 seconds. These details will not be elaborated upon here.

[0094] It should be noted that the calculation of the 15-second and 30-second output response indices mentioned above is determined according to relevant requirements, and this disclosure does not impose any limitations on them. In this way, the performance indicators of the generator set regulation system for primary frequency regulation can be calculated in real time, providing technical personnel with reference data for primary frequency regulation assessment.

[0095] In a possible manner, the method further includes: if the actual contribution rate is less than the target contribution rate after a target preset time, then determining the contribution rate difference between the preset total contribution rate and the actual contribution rate, determining the target load based on the maximum speed difference and the preset speed inequality function, multiplying the contribution rate difference and the target load to obtain the target supplementary value, and sending the third grid frequency, the actual contribution rate, and the target supplementary value to the generator set regulation system, so that the generator set regulation system can perform a frequency regulation closed-loop regulation based on the third grid frequency, the actual contribution rate, and the target supplementary value.

[0096] For example, during a primary frequency regulation period, the actual contribution rate of the primary frequency regulation (15-second output response index and 30-second output response index) can be calculated, and then closed-loop regulation can be carried out based on the actual contribution rate so that the actual contribution rate of the generator set regulation system meets the requirements of the primary frequency regulation performance index.

[0097] In possible ways, the actual contribution rate includes the first actual contribution rate of the generator set within a first preset time period and the second actual contribution rate within a second preset time period, wherein the first preset time period is shorter than the second preset time period. The target contribution rate includes the first target contribution rate corresponding to the first preset time period and the second target contribution rate corresponding to the second preset time period. The maximum speed difference includes the first maximum speed difference within the first preset time period and the second maximum speed difference within the second preset time period.

[0098] If the actual contribution rate is less than the target contribution rate after a preset target duration, the contribution rate difference between the preset total contribution rate and the actual contribution rate can be determined as follows: if the first actual contribution rate is less than the first target contribution rate after a preset target duration, then a first contribution rate difference between the total contribution rate and the first actual contribution rate is determined, where the preset target duration is less than the first preset duration; and / or, if the second actual contribution rate is less than the second target contribution rate after a preset second target duration, then a second contribution rate difference between the total contribution rate and the second actual contribution rate is determined, where the preset second target duration is less than the second preset duration. Furthermore, determining the target load based on the maximum speed difference and a preset speed unequal rate function can be as follows: determining the first target load based on the first maximum speed difference and the speed unequal rate function, and / or determining the second target load based on the second maximum speed difference and the speed unequal rate function.

[0099] In one possible manner, multiplying the contribution rate difference by the target load to obtain a target supplementary value, and then sending the third grid frequency, actual contribution rate, and target supplementary value to the generator set regulation system so that the generator set regulation system can perform a primary frequency regulation based on the third grid frequency, actual contribution rate, and target supplementary value, can be: multiplying the first contribution rate difference by the first target load to obtain a first target supplementary value, and then sending the third grid frequency, first actual contribution rate, and first target supplementary value to the generator set regulation system so that the generator set regulation system can perform a primary frequency regulation based on the third grid frequency, first actual contribution rate, and first target supplementary value. And / or, multiplying the second contribution rate difference by the second target load to obtain a second target supplementary value, and then sending the third grid frequency, second actual contribution rate, and second target supplementary value to the generator set regulation system so that the generator set regulation system can perform a primary frequency regulation closed-loop regulation based on the third grid frequency, second actual contribution rate, and second target supplementary value.

[0100] For example, refer to Figure 8 This document describes a control logic for calculating the target supplementary value (supplementary action value) for a 15-second (first preset duration) low-frequency action during primary frequency modulation. Specifically, A is a constant block, A1 is 1, A2 is 0, FX1 is the speed variability function, ONDELAY is the ON delay module with a time constant of 10 seconds (first preset duration), ONESHOT is the pulse function with a time constant of 5 seconds, and LO1 is the low-limit alarm module with a value of 75% (first target contribution rate). The specific value of LO1 can be set according to requirements, for example, based on the performance specifications of primary frequency modulation.

[0101] For example, when the low-frequency action 15s of the primary frequency regulation of HzLow15 is 0, it indicates that the generator set regulation system has not experienced a low-frequency action 15s. At this time, the output of TRANSFER1 is its N-terminal input (constant block A2), and the output is 0, ensuring that the output of this loop is 0. When the low-frequency action 15s of the primary frequency regulation of HzLow15 is 1 for more than 10s and the contribution rate of GXL15L during low-frequency action is less than 75% during 15s, it indicates that the power contribution of the generator set regulation system during low-frequency action cannot meet the dispatch requirements. TRANSFER1 output = Y-end input (MULTIPLY output). MULTIPLY module input 1 is 100% (total contribution rate) - GXL15L (contribution rate during low-frequency operation for 15 seconds, i.e., the first target contribution rate), resulting in a contribution rate that is less than a percentage. MULTIPLY module input 2 is DehR15 (maximum speed difference for 15 seconds) obtained through the FX1 speed unequal rate function, which represents the load value. Finally, TRANSFER1 outputs HzLow, the first frequency modulation low-frequency operation 15-second supplementary action value (target supplementary value).

[0102] For example, when a generator set regulation system experiences a low-frequency operation during primary frequency regulation, it needs to assess the 15-second output response index. Taking the system requirement that the generator set's contribution rate reach 75% within 15 seconds as an example, if the generator set's contribution rate does not reach 75% within 15 seconds, the 15-second output response index for primary frequency regulation fails to meet the standard, meaning the primary frequency regulation performance indicator fails to meet the standard. Therefore, a time period less than 15 seconds can be set, such as 10 seconds, to determine whether the generator set's contribution rate reaches 75% within 10 seconds. If it does not, the grid frequency for generator set speed conversion, the first actual contribution rate, and the first target supplementary value are sent to the generator set regulation system. This allows the generator set regulation system to perform closed-loop regulation, thereby ensuring that the generator set's contribution rate reaches 75% within 15 seconds, thus meeting the primary frequency regulation performance indicator.

[0103] In addition, refer to Figure 9 This document describes the control logic for calculating the target supplementary value (supplementary action value) for a 30-second (second preset duration) low-frequency action during a single frequency modulation. Specifically, A is a constant block, A1 is 1, A2 is 0, FX1 is the speed variability function, ONDELAY is the ON delay module with a time constant of 20 seconds (second preset duration), ONESHOT is the pulse function with a time constant of 10 seconds, and LO1 is the low-limit alarm module with a value of 90% (second target contribution rate), which can be set according to requirements. The logic judgment is similar to the control logic for calculating the target supplementary value for a 15-second low-frequency action during a single frequency modulation.

[0104] For example, when a generator set regulation system experiences a low-frequency operation during primary frequency regulation, a 30-second output response index needs to be assessed. Taking the system requirement that the generator set's contribution rate reach 90% within 30 seconds as an example, if the generator set's contribution rate does not reach 90% within 30 seconds, the 30-second output response index for primary frequency regulation fails to meet the standard, meaning the primary frequency regulation performance indicator fails to meet the standard. Therefore, a time period less than 30 seconds can be set, such as 20 seconds, to determine whether the generator set's contribution rate reaches 90% within 20 seconds. If it does not, the grid frequency for generator set speed conversion, the second actual contribution rate, and the second target supplementary value are sent to the generator set regulation system. This allows the generator set regulation system to perform closed-loop regulation, thereby ensuring that the generator set's contribution rate reaches 90% within 30 seconds, thus meeting the primary frequency regulation performance indicator.

[0105] Accordingly, the control logic for calculating the target supplement value of a 15s high-frequency FM action can refer to the control logic for calculating the target supplement value of a 15s low-frequency FM action described above. Only the value of LO1 needs to be changed to the second target contribution rate (e.g., 90%). The control logic for calculating the target supplement value of a 30s high-frequency FM action can refer to the control logic for calculating the target supplement value of a 30s low-frequency FM action described above. Only the value of LO1 needs to be changed to the second target contribution rate (e.g., 90%). This disclosure will not elaborate further here.

[0106] Through the above logic control, a basis can be provided for the closed-loop regulation of the performance indicators of the generator set regulation system during the primary frequency regulation period, so as to improve the compliance rate of the primary frequency regulation performance indicators of the generator set regulation system.

[0107] Based on the same inventive concept, this disclosure provides a primary frequency regulation method applied to a generator set regulation system, referring to... Figure 10 The method includes:

[0108] S1001, Receive the second power grid frequency sent by the control system.

[0109] The second grid frequency is obtained by inputting the first grid frequency, which is determined by the first speed of the generator set, into a preset frequency prediction model. The frequency prediction model is used to predict the actual frequency of the grid based on the first grid frequency.

[0110] S1002. If the second power grid frequency meets the preset primary frequency regulation conditions, a primary frequency regulation shall be performed.

[0111] For example, the primary frequency regulation condition may be that the second grid frequency is less than or greater than a set frequency threshold range, or that the rotational speed of the second grid frequency conversion is less than or greater than a preset rotational speed threshold range. For details, please refer to relevant technologies, which will not be elaborated here.

[0112] Using the above method, the generator speed can be directly obtained, thus avoiding errors caused by the accuracy of the measuring device. Furthermore, the actual frequency of the power grid can be predicted through a frequency prediction model, which improves the accuracy of the primary frequency regulation data source compared to measuring the power grid frequency through a measuring device.

[0113] In one possible manner, the method further includes: during a primary frequency regulation period, receiving a third grid frequency, the actual contribution rate of the generator set, and a target supplementary value sent by the control system; the third grid frequency is obtained by the control system inputting a fourth grid frequency determined based on the third rotational speed of the generator set into a frequency prediction model during the primary frequency regulation period; inputting the set contribution rate and the actual contribution rate into a PID controller to obtain a PID output value; adding the PID output value and the target supplementary value to obtain a first adjustment value; and performing a primary frequency regulation closed-loop adjustment based on the set power and actual power of the generator set, the first adjustment value, and the third grid frequency to ensure that the actual contribution rate reaches the set contribution rate within a preset time period.

[0114] For example, refer to Figure 11 The generator set regulation system includes a CCS side and a DEH side. A performance index closed-loop correction is added to the control logic on the CCS side, and the correction value is superimposed on the power command. A 15-second output response index closed-loop regulation PID controller is added, incorporating the calculated value and setpoint (the standard requirement is 75%, but it can generally be set to 85%) of ΔP15% (the 15-second output response index, i.e., the first actual contribution rate) into the PID controller. When the 15-second output response index does not meet the ΔP15% setpoint (set contribution rate), the closed loop will continue to correct the power action until it meets the requirement. A 30-second output response index closed-loop regulation PID controller is added, incorporating the calculated value and setpoint (the standard requirement is 90%, but it can generally be set to 100%) of ΔP30% (the 30-second output response index, i.e., the second actual contribution rate) into the PID controller. When the 30-second response index does not meet the ΔP30% setpoint, the closed loop will continue to correct the power action until it meets the requirement. Furthermore, the first regulation value is obtained by adding the PID controller output value and the target supplementary value, where BC15L represents the target supplementary value for a 15s low-frequency operation, BC30L represents the target supplementary value for a 30s low-frequency operation, BC15H represents the target supplementary value for a 15s high-frequency operation, and BC30H represents the target supplementary value for a 30s high-frequency operation. The parameters of the PID controller within the closed-loop circuit can be determined through demand and experimentation, as long as the contribution rate of the generator set gets closer and closer to the set value; this disclosure does not impose any limitations on this.

[0115] For example, taking the closed-loop regulation of a 15-second low-frequency action in primary frequency regulation as an example, if the control system determines that the generator set regulation system has not reached a contribution rate of 75% within 10 seconds during the primary frequency regulation period, it sends the grid frequency for generator speed conversion, the first actual contribution rate, and the first target supplementary value to the generator set regulation system. Upon receiving these values, the generator set regulation system outputs the first regulation value of the closed-loop control based on the logic control of the performance index closed-loop control. Then, combining the grid frequency fitted by the frequency prediction model (neural network) on the CCS side, the set power of the generator set, and the actual power, it determines the regulation command and sends it to the DEH side. The DEH side also uses the grid frequency fitted by the frequency prediction model to output the final turbine valve position command, ensuring that the actual contribution rate reaches 75% within 15 seconds and gets closer and closer to the set value (85%), thus meeting the performance index requirements of primary frequency regulation and improving the compliance rate of primary frequency regulation performance index.

[0116] For example, the closed-loop adjustment of a single FM low-frequency action for 30 seconds, the closed-loop adjustment of a single FM high-frequency action for 15 seconds, and the closed-loop adjustment of a single FM high-frequency action for 30 seconds can refer to the process of the closed-loop adjustment of a single FM low-frequency action for 15 seconds described above, and will not be repeated here.

[0117] It should be noted that the primary frequency regulation method provided in this disclosure can be applied to power grid systems with primary frequency regulation capabilities, such as thermal power units, hydropower units, wind power, photovoltaic power, and energy storage. Taking a thermal power unit as an example, the control system can be a distributed control system (DCS), and the generator unit regulation system includes a CCS side and a DEH side, performing primary frequency regulation by outputting turbine valve position commands. In practical applications, adjustments can be made according to the specific generator units, control systems, and regulation systems of the power grid system. For example, hydropower units can be controlled by turbine valve position commands, etc., and this disclosure does not limit this.

[0118] Based on the same inventive concept, this disclosure provides a primary frequency modulation device for use in a control system, the device comprising:

[0119] An acquisition module is used to acquire the first rotational speed of the generator set and determine the first grid frequency based on the first rotational speed of the generator set;

[0120] The prediction module is used to input the first power grid frequency into a preset frequency prediction model to obtain a predicted second power grid frequency. The frequency prediction model is used to predict the actual frequency of the power grid based on the first power grid frequency.

[0121] The transmitting module is used to transmit the second grid frequency to the generator set regulation system, so that the generator set regulation system can perform primary frequency regulation when it determines that the preset primary frequency regulation conditions are met based on the second grid frequency.

[0122] Optionally, the device further includes an actual contribution rate calculation module, which is used for:

[0123] The second rotational speed is determined based on the third grid frequency, which is obtained by inputting the fourth grid frequency, determined by the third rotational speed of the generator set, into the frequency prediction model during a frequency regulation period of the generator set regulation system.

[0124] The theoretical power contribution value of the generator set is determined based on the relationship between the second speed and the preset speed threshold, the maximum speed difference between the second speed and the speed threshold, and the preset relationship between the speed difference and the theoretical power contribution value.

[0125] The actual contribution rate of the generator set is obtained by dividing the actual power contribution value of the generator set by the theoretical power contribution value. The actual power contribution value is the difference between the actual power and the initial power of the generator set.

[0126] Optionally, the device further includes a supplementary value calculation module, the supplementary value calculation module being used for:

[0127] If the actual contribution rate is less than the target contribution rate after the target preset time, then the contribution rate difference between the preset total contribution rate and the actual contribution rate is determined.

[0128] The target load is determined based on the maximum speed difference and the preset speed inequality function;

[0129] The target supplementary value is obtained by multiplying the contribution rate difference and the target load, and the third grid frequency, the actual contribution rate and the target supplementary value are sent to the generator set regulation system so that the generator set regulation system can perform a frequency regulation closed loop regulation based on the third grid frequency, the actual contribution rate and the target supplementary value.

[0130] Optionally, the actual contribution rate includes the first actual contribution rate of the generator set within a first preset time period and the second actual contribution rate within a second preset time period, wherein the first preset time period is less than the second preset time period, the target contribution rate includes the first target contribution rate corresponding to the first preset time period and the second target contribution rate corresponding to the second preset time period, and the maximum speed difference includes the first maximum speed difference within the first preset time period and the second maximum speed difference within the second preset time period;

[0131] The supplementary value calculation module is also used for:

[0132] If the first actual contribution rate is less than the first target contribution rate after the first target preset time, then a first contribution rate difference is determined between the total contribution rate and the first actual contribution rate, and the first target preset time is less than the first preset time; and / or,

[0133] If the second actual contribution rate is less than the second target contribution rate after the second target preset time, then the second contribution rate difference between the total contribution rate and the second actual contribution rate is determined, and the second target preset time is less than the second preset time.

[0134] The supplementary value calculation module is also used for:

[0135] The first target load is determined based on the first maximum speed difference and the speed inequality function; and / or,

[0136] The second target load is determined based on the second maximum speed difference and the speed inequality function.

[0137] Optionally, the supplementary value calculation module is further configured to:

[0138] The first contribution rate difference is multiplied by the first target load to obtain a first target supplementary value. The third grid frequency, the first actual contribution rate, and the first target supplementary value are then sent to the generator set regulation system, so that the generator set regulation system performs a first-stage frequency regulation closed-loop adjustment based on the third grid frequency, the first actual contribution rate, and the first target supplementary value; and / or,

[0139] The second contribution rate difference is multiplied by the second target load to obtain the second target supplementary value. The third grid frequency, the second actual contribution rate, and the second target supplementary value are then sent to the generator set regulation system so that the generator set regulation system can perform a frequency regulation closed-loop regulation based on the third grid frequency, the second actual contribution rate, and the second target supplementary value.

[0140] Optionally, the preset speed threshold includes an upper speed threshold and a lower speed threshold, and the actual contribution rate calculation module is further used for:

[0141] If the second rotational speed is less than the lower speed threshold, then the low-frequency power theoretical contribution value of the generator set is determined according to the maximum speed difference and the preset relationship between the speed difference and the theoretical power contribution value; or,

[0142] If the second rotational speed is greater than the upper limit threshold of rotational speed, the high-frequency power theoretical contribution value of the generator set is determined according to the maximum rotational speed difference and the preset relationship between the rotational speed difference and the theoretical power contribution value.

[0143] The actual contribution rate calculation module is also used for:

[0144] The actual low-frequency contribution rate of the generator set is obtained by dividing the actual power contribution value by the theoretical low-frequency power contribution value; or,

[0145] The actual high-frequency contribution rate of the generator set is obtained by dividing the actual power contribution value by the theoretical high-frequency power contribution value.

[0146] Optionally, the frequency prediction model is a BP neural network, and the device further includes a model training module, which is used for:

[0147] Construct a BP neural network;

[0148] Acquire the first historical grid frequency data from the PMU device, and the historical speed data of the generator set for the time period corresponding to the historical grid frequency data;

[0149] The second historical power grid frequency data is determined based on the historical rotational speed data;

[0150] The first historical power grid frequency data is used as the output sample, and the second power grid frequency data is used as the input sample to train the BP neural network, thereby obtaining a trained frequency prediction model.

[0151] Based on the same inventive concept, this disclosure provides a primary frequency regulation device applied to a generator set regulation system, the device comprising:

[0152] The receiving module is used to receive a second grid frequency sent by the control system. The second grid frequency is obtained by the control system inputting a first grid frequency determined according to the first speed of the generator set into a preset frequency prediction model. The frequency prediction model is used to predict the actual frequency of the grid based on the first grid frequency.

[0153] The first frequency regulation module is used to perform primary frequency regulation if the second power grid frequency meets the preset primary frequency regulation conditions.

[0154] Optionally, the device further includes a second frequency modulation module, the second frequency modulation module being used for:

[0155] During the first frequency regulation period, the system receives the third grid frequency, the actual contribution rate of the generator set, and the target supplement value sent by the control system. The third grid frequency is obtained by the control system inputting the fourth grid frequency determined according to the third rotational speed of the generator set into the frequency prediction model during the first frequency regulation period.

[0156] The set contribution rate and the actual contribution rate are input into the PID controller to obtain the PID output value, and the PID output value and the target supplement value are added to obtain the first adjustment value;

[0157] A frequency regulation closed-loop adjustment is performed based on the set power and actual power of the generator set, the first adjustment value and the third grid frequency, so that the actual contribution rate reaches the set contribution rate within a preset time period.

[0158] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0159] Based on the same inventive concept, this disclosure also provides a non-transitory computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the primary frequency regulation method applied to a control system, or the steps of the primary frequency regulation method applied to a generator set regulation system.

[0160] Based on the same inventive concept, this disclosure also provides an electronic device, including:

[0161] A memory on which computer programs are stored;

[0162] A processor is configured to execute the computer program in the memory to implement the steps of the primary frequency regulation method applied to a control system, or the steps of the primary frequency regulation method applied to a generator set regulation system.

[0163] Figure 12 This is a block diagram illustrating an electronic device 120 according to an exemplary embodiment. (Refer to...) Figure 12 The electronic device 120 includes a processor 121, which may be one or more, and a memory 122 for storing computer programs executable by the processor 121. The computer program stored in the memory 122 may include one or more modules, each corresponding to a set of instructions. Furthermore, the processor 121 may be configured to execute the computer program to perform the aforementioned frequency modulation method.

[0164] Additionally, the electronic device 120 may also include a power supply component 125 and a communication component 123. The power supply component 125 can be configured to perform power management of the electronic device 120, and the communication component 123 can be configured to enable communication of the electronic device 120, such as wired or wireless communication. Furthermore, the electronic device 120 may also include an input / output (I / O) interface 124. The electronic device 120 can operate on an operating system, such as Windows Server, stored in memory 122. TM Mac OSXTM Unix TM Linux TM etc.

[0165] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, which, when executed by a processor, implement the steps of the primary frequency modulation method described above. For example, the non-transitory computer-readable storage medium may be the memory 122 including the program instructions described above, which may be executed by the processor 121 of the electronic device 120 to complete the primary frequency modulation method described above.

[0166] In another exemplary embodiment, a computer program product is also provided, the computer program product comprising a computer program executable by a programmable device, the computer program having a code portion for performing the above-described primary frequency modulation method when executed by the programmable device.

[0167] The preferred embodiments of this disclosure have been described in detail above with reference to the accompanying drawings. However, this disclosure is not limited to the specific details of the above embodiments. Within the scope of the technical concept of this disclosure, various simple modifications can be made to the technical solutions of this disclosure, and these simple modifications all fall within the protection scope of this disclosure.

[0168] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, this disclosure will not describe the various possible combinations separately.

[0169] Furthermore, various different embodiments of this disclosure can be combined in any way, as long as they do not violate the spirit of this disclosure, they should also be regarded as the content disclosed in this disclosure.

Claims

1. A primary frequency modulation method, characterized in that, Applied to a control system, the method includes: Obtain the first rotational speed of the generator set, and determine the first grid frequency based on the first rotational speed of the generator set; The first power grid frequency is input into a preset frequency prediction model to obtain the predicted second power grid frequency. The frequency prediction model is used to predict the actual frequency of the power grid based on the first power grid frequency. The second grid frequency is sent to the generator set regulation system so that the generator set regulation system can perform primary frequency regulation when the preset primary frequency regulation conditions are met based on the second grid frequency. The frequency prediction model is a BP neural network, which is trained in the following way: Construct a BP neural network; Acquire the first historical grid frequency data from the PMU device, and the historical speed data of the generator set for the time period corresponding to the first historical grid frequency data; The second historical power grid frequency data is determined based on the historical rotational speed data; The first historical power grid frequency data is used as the output sample, and the second historical power grid frequency data is used as the input sample to train the BP neural network, thereby obtaining a trained frequency prediction model.

2. The method according to claim 1, characterized in that, The method further includes: The second rotational speed is determined based on the third grid frequency, which is obtained by inputting the fourth grid frequency, determined by the third rotational speed of the generator set, into the frequency prediction model during a frequency regulation period of the generator set regulation system. The theoretical power contribution value of the generator set is determined based on the relationship between the second speed and the preset speed threshold, the maximum speed difference between the second speed and the speed threshold, and the preset relationship between the speed difference and the theoretical power contribution value. The actual contribution rate of the generator set is obtained by dividing the actual power contribution value of the generator set by the theoretical power contribution value. The actual power contribution value is the difference between the actual power and the initial power of the generator set.

3. The method according to claim 2, characterized in that, The method further includes: If the actual contribution rate is less than the target contribution rate after the target preset time, then the contribution rate difference between the preset total contribution rate and the actual contribution rate is determined. The target load is determined based on the maximum speed difference and the preset speed inequality function; The target supplementary value is obtained by multiplying the contribution rate difference and the target load, and the third grid frequency, the actual contribution rate and the target supplementary value are sent to the generator set regulation system so that the generator set regulation system can perform a frequency regulation closed loop regulation based on the third grid frequency, the actual contribution rate and the target supplementary value.

4. The method according to claim 3, characterized in that, The actual contribution rate includes the first actual contribution rate of the generator set within a first preset time period and the second actual contribution rate within a second preset time period, wherein the first preset time period is less than the second preset time period. The target contribution rate includes the first target contribution rate corresponding to the first preset time period and the second target contribution rate corresponding to the second preset time period. The maximum speed difference includes the first maximum speed difference within the first preset time period and the second maximum speed difference within the second preset time period. If the actual contribution rate is less than the target contribution rate after a preset time period, then determining the contribution rate difference between the preset total contribution rate and the actual contribution rate includes: If the first actual contribution rate is less than the first target contribution rate after the first target preset time, then a first contribution rate difference is determined between the total contribution rate and the first actual contribution rate, and the first target preset time is less than the first preset time; and / or, If the second actual contribution rate is less than the second target contribution rate after the second target preset time, then the second contribution rate difference between the total contribution rate and the second actual contribution rate is determined, and the second target preset time is less than the second preset time. The step of determining the target load based on the maximum speed difference and a preset speed inequality function includes: The first target load is determined based on the first maximum speed difference and the speed inequality function; and / or, The second target load is determined based on the second maximum speed difference and the speed inequality function.

5. The method according to claim 4, characterized in that, The step of multiplying the contribution rate difference and the target load to obtain the target supplementary value, and sending the third grid frequency, the actual contribution rate, and the target supplementary value to the generator set regulation system, so that the generator set regulation system can perform a first-stage frequency regulation closed-loop regulation based on the third grid frequency, the actual contribution rate, and the target supplementary value, includes: The first contribution rate difference is multiplied by the first target load to obtain a first target supplementary value. The third grid frequency, the first actual contribution rate, and the first target supplementary value are then sent to the generator set regulation system, so that the generator set regulation system performs a first-stage frequency regulation closed-loop adjustment based on the third grid frequency, the first actual contribution rate, and the first target supplementary value; and / or, The second contribution rate difference is multiplied by the second target load to obtain the second target supplementary value. The third grid frequency, the second actual contribution rate, and the second target supplementary value are then sent to the generator set regulation system so that the generator set regulation system can perform a frequency regulation closed-loop regulation based on the third grid frequency, the second actual contribution rate, and the second target supplementary value.

6. The method according to claim 2, characterized in that, The preset speed threshold includes an upper speed threshold and a lower speed threshold. Determining the theoretical power contribution value of the generator set based on the relationship between the second speed and the preset speed threshold, the maximum speed difference between the second speed and the preset speed threshold, and the preset relationship between the speed difference and the theoretical power contribution value includes: If the second rotational speed is less than the lower speed threshold, then the low-frequency power theoretical contribution value of the generator set is determined according to the maximum speed difference and the preset relationship between the speed difference and the theoretical power contribution value; or, If the second rotational speed is greater than the upper limit threshold of rotational speed, then the high-frequency power theoretical contribution value of the generator set is determined according to the maximum rotational speed difference and the preset relationship between the rotational speed difference and the theoretical power contribution value. The step of dividing the actual power contribution value of the generator set by the theoretical power contribution value to obtain the actual contribution rate of the generator set includes: The actual low-frequency contribution rate of the generator set is obtained by dividing the actual power contribution value by the theoretical low-frequency power contribution value; or, The actual high-frequency contribution rate of the generator set is obtained by dividing the actual power contribution value by the theoretical high-frequency power contribution value.

7. A primary frequency modulation method, characterized in that, The method, applied to a generator set regulating system, includes: The system receives a second grid frequency sent by the control system. The second grid frequency is obtained by the control system inputting a first grid frequency determined according to the first speed of the generator set into a preset frequency prediction model. The frequency prediction model is used to predict the actual frequency of the grid based on the first grid frequency. If the second power grid frequency meets the preset primary frequency regulation conditions, a primary frequency regulation is performed; The frequency prediction model is a BP neural network, which is trained in the following way: Construct a BP neural network; Acquire the first historical grid frequency data from the PMU device, and the historical speed data of the generator set for the time period corresponding to the first historical grid frequency data; The second historical power grid frequency data is determined based on the historical rotational speed data; The first historical power grid frequency data is used as the output sample, and the second historical power grid frequency data is used as the input sample to train the BP neural network, thereby obtaining a trained frequency prediction model.

8. The method according to claim 7, characterized in that, The method further includes: During the first frequency regulation period, the system receives the third grid frequency, the actual contribution rate of the generator set, and the target supplementary value sent by the control system. The third grid frequency is obtained by the control system inputting the fourth grid frequency, determined based on the third rotational speed of the generator set, into the frequency prediction model during the first frequency regulation period. The actual contribution rate is obtained by the control system dividing the actual power contribution value and the theoretical power contribution value of the generator set. The actual power contribution value is the difference between the actual power and the initial power of the generator set. The theoretical power contribution value is determined based on the relationship between the second rotational speed and a preset rotational speed threshold, the maximum rotational speed difference between the second rotational speed and the rotational speed threshold, and a preset relationship between the rotational speed difference and the theoretical power contribution value. The second rotational speed is determined based on the third grid frequency. The target supplementary value is obtained by the control system multiplying the contribution rate difference and the target load. The contribution rate difference is determined based on the preset total contribution rate and the actual contribution rate if the actual contribution rate is less than the target contribution rate after a preset target duration. The target load is determined based on the maximum rotational speed difference and a preset rotational speed inequality function. The set contribution rate and the actual contribution rate are input into the PID controller to obtain the PID output value, and the PID output value and the target supplement value are added to obtain the first adjustment value; A frequency regulation closed-loop adjustment is performed based on the set power and actual power of the generator set, the first adjustment value and the third grid frequency, so that the actual contribution rate reaches the set contribution rate within a preset time period.

9. An electronic device, characterized in that, include: A memory on which computer programs are stored; A processor for executing the computer program in the memory to implement the steps of the method according to any one of claims 1-8.

Images