Coordination control method and system for speed regulator and AGC system

Abstract

The invention provides a speed regulator and AGC system coordination control method and system, and the method comprises the steps: determining the load power of a predicted time point based on the load power of each historical time point of a target power utilization region, and calculating and constructing a load change trend based on the load power of a plurality of time points, calculating a first frequency change value of each time point based on the load change trend; acquiring a second frequency change value of each actual historical time point based on the AGC system, and constructing a difference vector based on the difference between the first frequency change value and the second frequency change value of each historical time point; inputting the difference vector into a pre-trained difference prediction model, wherein the difference prediction model outputs a difference value of a prediction time point; and calculating a third frequency change value of the prediction time point based on the difference value of the prediction time point and the first frequency change value of the prediction time point, wherein the AGC system sends a control instruction to the speed regulator based on the third frequency change value.

Description

Technical Field

[0001] The present invention relates to the field of self-generation control technology, and in particular to a coordinated control method and system of a speed regulator and an AGC system. Background Art

[0002] The AGC system, or automatic generation control system, is one of the key technologies for maintaining frequency stability in the power system. It monitors the difference between the load change and the power generation capacity of the power system in real time, and automatically adjusts the output power of the generator set to ensure the balance of supply and demand in the power system, thereby preventing frequency fluctuations and maintaining stable operation of the power system. The following is a detailed description of how the AGC system maintains frequency stability:

[0003] The core function of the AGC system is frequency control, that is, maintaining the system frequency within the set range. When the load of the power system increases, resulting in a downward trend in frequency, the AGC system will respond quickly by increasing the output power of the generator set to compensate for the increase in load, thereby preventing the system frequency from decreasing. On the contrary, when the load decreases and the system frequency tends to rise, the AGC system will reduce the output power of the generator set to avoid excessive system frequency. This automatic adjustment mechanism can ensure that the system frequency always remains within the allowable deviation range, thereby maintaining the stable operation of the power system. In addition, the AGC system also has the function of monitoring the system status. Through sensors and data acquisition equipment, the AGC system can monitor the frequency, load, generator set status and other parameters of the power system in real time, providing data support for the stable operation of the system.

[0004] In summary, the AGC system maintains the frequency stability of the power system by monitoring the difference between the load change and the power generation capacity of the power system in real time, automatically adjusting the output power of the generator set, and working in coordination with other power system control functions. However, the current AGC system often makes adjustments based on the frequency changes of the power system, which has a certain lag.

[0005] In view of this, the present invention is proposed. Summary of the invention

[0006] The object of the present invention is to provide a coordinated control method and system for a speed regulator and an AGC system. The scheme corrects the predicted first frequency change value by calculating the difference value to obtain a third frequency change value, and the AGC system can respond in advance based on the third frequency change value.

[0007] The present invention provides a coordinated control method of a speed regulator and an AGC system, the method comprising the following steps:

[0008] Calling power consumption data of a target power consumption area, the power consumption data including load power at each time point in the target power consumption area, each of the target power consumption areas including a plurality of sub-areas;

[0009] Determine the load power at the predicted time point based on the load power at each historical time point in the target power consumption area, construct a load change trend based on the load power calculations at multiple time points, and calculate the first frequency change value at each time point based on the load change trend;

[0010] Acquiring an actual second frequency change value at each historical time point based on the AGC system, and constructing a difference vector based on a difference between the first frequency change value and the second frequency change value at each historical time point;

[0011] Inputting the difference vector into a pre-trained difference prediction model, the difference prediction model outputs a difference value at a predicted time point;

[0012] A third frequency change value at the predicted time point is calculated based on the difference value at the predicted time point and the first frequency change value at the predicted time point, and the AGC system issues a control instruction to the speed regulator based on the third frequency change value.

[0013] The above scheme is adopted. This scheme first predicts the power load at the prediction time point based on the actual power load, and for each time point, calculates the first frequency change value corresponding to the time point based on the load power at multiple time points. Since there are often differences in the directly predicted first frequency change value, this scheme further predicts the difference through the difference between the second frequency change value at the actual historical time point and the first frequency change value at the historical time point, and corrects the predicted first frequency change value through the difference value to obtain the third frequency change value. The AGC system can respond in advance based on the third frequency change value and issue a control instruction to the speed regulator.

[0014] In some embodiments of the present invention, in the step of determining the load power at the predicted time point based on the load power at each historical time point in the target power consumption area, and constructing the load change trend based on the load power calculation at multiple time points:

[0015] Constructing a load power vector from the load powers at multiple time points, inputting the load power vector into a pre-trained load prediction model, and the load prediction model outputs the load power at the predicted time point;

[0016] The load power at the historical time point and the load power at the predicted time point are both taken as a coordinate point in the coordinate system, and the coordinate points of each time point are sequentially connected to obtain a load change trend graph.

[0017] Using the above scheme, since the frequency change of the power system is related to the change of the load, in the process of calculating the first frequency change value, this scheme constructs a load power vector through the load power at multiple historical time points, outputs the predicted load power through the load prediction model, and constructs the load power at the historical time point and the load power at the predicted time point into a load change trend graph.

[0018] In some embodiments of the present invention, in the step of determining the load power at a predicted time point based on the load power at each historical time point in the target power consumption area, and constructing a load change trend based on the load power calculation at multiple time points, the slope of the line between the corresponding coordinate points of each two time points in the load change trend graph is taken as a trend value.

[0019] In some embodiments of the present invention, in the step of calculating the first frequency change value at each time point based on the load change trend, for each time point, the trend values ​​between a preset number of time points before the time point are obtained from the load change trend graph, constructed as a change trend vector, and the change trend vector is input into a pre-trained frequency change calculation model, and the first frequency change value corresponding to the time point is output through the frequency change calculation model.

[0020] Using the above scheme, since the frequency change of the power system is related to the change of the load, this scheme uses the slope of the coordinate points corresponding to adjacent time points in the load change trend diagram as the load change trend, and then calculates the frequency change of the power system based on the load change trend to ensure the calculation accuracy of the first frequency change value.

[0021] In some embodiments of the present invention, in the step of constructing a difference vector based on the difference between the first frequency change value and the second frequency change value at each historical time point, the difference between the first frequency change value and the second frequency change value at each historical time point is calculated and used as the value of each dimension in the difference vector to construct a difference vector.

[0022] In some embodiments of the present invention, in the step of calculating the third frequency change value of the predicted time point based on the difference value of the predicted time point and the first frequency change value of the predicted time point, addition or subtraction calculation is performed based on the first frequency change value of the predicted time point and the corresponding difference value to obtain the third frequency change value of the corresponding predicted time point.

[0023] Using the above scheme, since the first frequency change value directly predicted is often different from the actual second frequency change value, this scheme constructs a difference vector based on the difference between the first frequency change value and the second frequency change value at the historical time point, and predicts the difference value at the predicted time point, and then corrects the first frequency change value at the predicted time point by the difference value at the predicted time point, thereby improving the accuracy of the third frequency change value finally applied.

[0024] In some embodiments of the present invention, in the step of determining the load power at a predicted time point based on the load power at each historical time point in the target power consumption area, a load distribution graph at a time point is constructed based on the load power of each sub-area at each time point, a load distribution graph at a predicted time point is determined based on the load distribution graphs of multiple time points, and the load power at the predicted time point is determined based on the load distribution graph at the predicted time point.

[0025] In some embodiments of the present invention, each sub-area of ​​the target power consumption area corresponds to an image area in the load distribution map, and in the steps of constructing a load distribution map at a time point based on the load power of each sub-area at each time point, determining a predicted load distribution map at a predicted time point based on the load distribution maps of multiple time points, and determining the load power at the predicted time point based on the load distribution map at the predicted time point:

[0026] Determine the pixel value corresponding to the load power of each sub-area based on a preset pixel mapping table, render the pixel value to the corresponding image area, and obtain a load distribution diagram at a time point;

[0027] The pixel values ​​of the same image region in the load distribution graphs at multiple time points are constructed as a pixel prediction vector of a sub-region;

[0028] Inputting the pixel prediction vector into a pre-trained pixel prediction model to obtain a pixel value of a corresponding sub-region in a load distribution diagram at a prediction time point;

[0029] The corresponding load power is determined based on the pixel value of each sub-region in the load distribution diagram at the predicted time point, and the total load power at the predicted time point is obtained based on the load power of each sub-region.

[0030] In some embodiments of the present invention, in the step of constructing the pixel values ​​of the same image area in the load distribution map at multiple time points into a pixel prediction vector of a sub-area, the pixel values ​​of the same image area in the load distribution map at each time point are used as the value of a dimension in the load prediction vector, and the dimension where the corresponding pixel value is located is determined based on the order of the time points.

[0031] By adopting the above scheme, in the process of load forecasting, this scheme refines the target power consumption area and forecasts the load power of each sub-area separately to ensure the final load forecasting accuracy.

[0032] Another aspect of the present invention also relates to a coordinated control system of a speed regulator and an AGC system, the system comprising a computer device, the computer device comprising a processor and a memory, the memory storing computer instructions, the processor being used to execute the computer instructions stored in the memory, and when the computer instructions are executed by the processor, the system implements the steps implemented by the method.

[0033] In summary, the present invention has the following beneficial effects:

[0034] 1. This scheme first predicts the power load at the prediction time point according to the actual power load, and calculates the first frequency change value corresponding to each time point based on the load power at multiple time points. Since there are often differences in the directly predicted first frequency change value, this scheme further predicts the difference by the difference between the second frequency change value at the actual historical time point and the first frequency change value at the historical time point, and corrects the predicted first frequency change value by the difference value to obtain the third frequency change value. The AGC system can respond in advance based on the third frequency change value and issue a control instruction to the speed regulator;

[0035] 2. Since the frequency change of the power system is related to the change of the load, this solution uses the slope of the coordinate points corresponding to adjacent time points in the load change trend diagram as the load change trend, and then calculates the frequency change of the power system based on the load change trend to ensure the calculation accuracy of the first frequency change value;

[0036] 3. Since the first frequency change value obtained by direct prediction often differs from the actual second frequency change value, this solution constructs a difference vector based on the difference between the first frequency change value and the second frequency change value at the historical time point, and predicts the difference value at the prediction time point, and then corrects the first frequency change value at the prediction time point by the difference value at the prediction time point, thereby improving the accuracy of the third frequency change value finally applied;

[0037] 4. In the process of load forecasting, this scheme refines the target power consumption area and predicts the load power of each sub-area separately to ensure the final load forecast accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the embodiments of the present invention 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 only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0039] Figure 1A schematic diagram of a first embodiment of a coordinated control method of a speed regulator and an AGC system according to the present invention;

[0040] Figure 2 It is a schematic diagram of a second implementation of the coordinated control method of the speed regulator and the AGC system of the present invention. DETAILED DESCRIPTION

[0041] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0042] The terms used in the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The singular forms "a", "the" and "the" used in the present invention and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0043] like Figure 1 As shown, the present invention provides a coordinated control method of a speed regulator and an AGC system, the method comprising the steps of:

[0044] Step S100, calling the power consumption data of the target power consumption area, the power consumption data including the load power at each time point in the target power consumption area, each of the target power consumption areas including a plurality of sub-areas;

[0045] In a specific implementation process, the load power of the sub-area can be obtained from a power device in a sub-area.

[0046] Step S200, determining the load power at the predicted time point based on the load power at each historical time point in the target power consumption area, constructing a load change trend based on the load power calculations at multiple time points, and calculating a first frequency change value at each time point based on the load change trend;

[0047] Step S300, obtaining the actual second frequency change value at each historical time point based on the AGC system, and constructing a difference vector based on the difference between the first frequency change value and the second frequency change value at each historical time point;

[0048] In the specific implementation process, the AGC system, namely the Automatic Generation Control system, is a complete power regulation control system. The AGC system collects information such as the frequency, load and exchange power of the interconnection line in real time through the power grid data acquisition and monitoring control system, and sends control instructions to the speed regulator through the frequency change of the power grid;

[0049] Specifically, when the system load decreases, if the generator output power remains the same or decreases slower than the load reduction rate, the total output power of the system will be greater than the total load power, causing the system frequency to increase;

[0050] If the output power of the generator sets increases while the load remains constant or decreases, the total output power of the system will also increase, resulting in an increase in the system frequency;

[0051] When the system load increases, if the generator output power cannot be increased in time to match the load increase, the total output power of the system will be less than the total load power, causing the system frequency to drop;

[0052] If the output power of the generator sets decreases while the load remains unchanged or increases, the total output power of the system will also decrease, resulting in a decrease in system frequency.

[0053] Step S400, inputting the difference vector into a pre-trained difference prediction model, and the difference prediction model outputs a difference value at a prediction time point;

[0054] In the specific implementation process, the difference prediction model, load prediction model and pixel prediction model are all pre-trained LSTM models. The LSTM network model was proposed by Hochreiter and Schmidhuber in 1997. Compared with the traditional RNN, the LSTM network model introduces three gate control units, namely input gate, forget gate and output gate, so as to realize the selective memory of information;

[0055] Forget gate: The forget gate is responsible for deciding which information to remove from the memory cell. It receives the current input and the hidden state of the previous time step, and generates a vector between 0 and 1 through the sigmoid function, indicating the proportion of forgetting. The result is multiplied by the state of the memory cell to achieve selective forgetting. The forget gate mechanism allows LSTM to flexibly and selectively discard irrelevant historical information, thereby preventing the state of the memory cell from being accumulated by irrelevant information;

[0056] Input gate: The input gate is responsible for controlling the degree of influence of the current input information on the memory cell. It determines the current input value and which information in the hidden state of the previous time step needs to be added to the memory cell. The calculation of the input gate involves a sigmoid activation function and a tanh activation function. The sigmoid function determines which information needs to be updated, while the tanh function generates new candidate memory cells. After the two results are multiplied, they are added to the memory cell state to update the memory cell state;

[0057] Output gate: The output gate determines how the state of the memory cell at the current time step affects the output hidden state. It controls the output of the content of the memory cell at the current time step. The result of the output gate passes through the sigmoid function to limit its value between 0 and 1. This output value determines the content of the current hidden state.

[0058] Step S500, calculating a third frequency change value at the predicted time point based on the difference value at the predicted time point and the first frequency change value at the predicted time point, and the AGC system issues a control instruction to the speed regulator based on the third frequency change value.

[0059] In the specific implementation process, the frequency change of the power system is closely related to the output power of the generator set. When the system frequency drops, it means that the load exceeds the output power of the generator. At this time, the output power of the generator set needs to be increased to restore the frequency. On the contrary, when the system frequency rises, it means that the output power of the generator set exceeds the load. At this time, the output power of the generator set needs to be reduced to maintain frequency stability. This solution issues control instructions in advance through the predicted frequency changes, so that the AGC system controls the speed regulator to make corresponding adjustments.

[0060] The above scheme is adopted. This scheme first predicts the power load at the prediction time point based on the actual power load, and for each time point, calculates the first frequency change value corresponding to the time point based on the load power at multiple time points. Since there are often differences in the directly predicted first frequency change value, this scheme further predicts the difference through the difference between the second frequency change value at the actual historical time point and the first frequency change value at the historical time point, and corrects the predicted first frequency change value through the difference value to obtain the third frequency change value. The AGC system can respond in advance based on the third frequency change value and issue a control instruction to the speed regulator.

[0061] like Figure 2 As shown, in some embodiments of the present invention, in the step of determining the load power at the predicted time point based on the load power at each historical time point in the target power consumption area, and constructing the load change trend based on the load power calculation at multiple time points:

[0062] Step S210, constructing a load power vector from the load powers at multiple time points, inputting the load power vector into a pre-trained load prediction model, and the load prediction model outputs the load power at the predicted time point;

[0063] Step S220 , taking the load power at the historical time point and the load power at the predicted time point as a coordinate point in the coordinate system, and sequentially connecting the coordinate points at each time point to obtain a load change trend graph.

[0064] Using the above scheme, since the frequency change of the power system is related to the change of the load, in the process of calculating the first frequency change value, this scheme constructs a load power vector through the load power at multiple historical time points, outputs the predicted load power through the load prediction model, and constructs the load power at the historical time point and the load power at the predicted time point into a load change trend graph.

[0065] In some embodiments of the present invention, in the step of determining the load power at a predicted time point based on the load power at each historical time point in the target power consumption area, and constructing a load change trend based on the load power calculation at multiple time points, the slope of the line between the corresponding coordinate points of each two time points in the load change trend graph is taken as a trend value.

[0066] like Figure 2 As shown, in some embodiments of the present invention, the step of calculating the first frequency change value at each time point based on the load change trend includes: step S230, for each time point, obtaining the trend values ​​between a preset number of time points before the time point from the load change trend chart, constructing them into a change trend vector, inputting the change trend vector into a pre-trained frequency change calculation model, and outputting the first frequency change value corresponding to the time point through the frequency change calculation model.

[0067] In the specific implementation process, the frequency change calculation model is a pre-trained convolutional neural network model.

[0068] Using the above scheme, since the frequency change of the power system is related to the change of the load, this scheme uses the slope of the coordinate points corresponding to adjacent time points in the load change trend diagram as the load change trend, and then calculates the frequency change of the power system based on the load change trend to ensure the calculation accuracy of the first frequency change value.

[0069] In some embodiments of the present invention, in the step of constructing a difference vector based on the difference between the first frequency change value and the second frequency change value at each historical time point, the difference between the first frequency change value and the second frequency change value at each historical time point is calculated and used as the value of each dimension in the difference vector to construct a difference vector.

[0070] In some embodiments of the present invention, in the step of calculating the third frequency change value of the predicted time point based on the difference value of the predicted time point and the first frequency change value of the predicted time point, addition or subtraction calculation is performed based on the first frequency change value of the predicted time point and the corresponding difference value to obtain the third frequency change value of the corresponding predicted time point.

[0071] In the specific implementation process, the first frequency change value at the predicted time point is added to the difference value at the predicted time point. If the difference value is a positive value, it is adjusted in an increasing direction; if the difference value is a negative value, it is adjusted in a decreasing direction.

[0072] Using the above scheme, since the first frequency change value directly predicted is often different from the actual second frequency change value, this scheme constructs a difference vector based on the difference between the first frequency change value and the second frequency change value at the historical time point, and predicts the difference value at the predicted time point, and then corrects the first frequency change value at the predicted time point by the difference value at the predicted time point, thereby improving the accuracy of the third frequency change value finally applied.

[0073] In some embodiments of the present invention, in the step of determining the load power at a predicted time point based on the load power at each historical time point in the target power consumption area, a load distribution graph at a time point is constructed based on the load power of each sub-area at each time point, a load distribution graph at a predicted time point is determined based on the load distribution graphs of multiple time points, and the load power at the predicted time point is determined based on the load distribution graph at the predicted time point.

[0074] In some embodiments of the present invention, each sub-area of ​​the target power consumption area corresponds to an image area in the load distribution map, and in the steps of constructing a load distribution map at a time point based on the load power of each sub-area at each time point, determining a predicted load distribution map at a predicted time point based on the load distribution maps of multiple time points, and determining the load power at the predicted time point based on the load distribution map at the predicted time point:

[0075] Determine the pixel value corresponding to the load power of each sub-area based on a preset pixel mapping table, render the pixel value to the corresponding image area, and obtain a load distribution diagram at a time point;

[0076] In a specific implementation process, each pixel power value in the pixel mapping table corresponds to a pixel value.

[0077] The pixel values ​​of the same image region in the load distribution graphs at multiple time points are constructed as a pixel prediction vector of a sub-region;

[0078] In a specific implementation process, the image area may be a pixel area of ​​a size such as 4*4, 8*8 or 16*16.

[0079] Inputting the pixel prediction vector into a pre-trained pixel prediction model to obtain a pixel value of a corresponding sub-region in a load distribution diagram at a prediction time point;

[0080] The corresponding load power is determined based on the pixel value of each sub-region in the load distribution diagram at the predicted time point, and the total load power at the predicted time point is obtained based on the load power of each sub-region.

[0081] In some embodiments of the present invention, in the step of constructing the pixel values ​​of the same image area in the load distribution map at multiple time points into a pixel prediction vector of a sub-area, the pixel values ​​of the same image area in the load distribution map at each time point are used as the value of a dimension in the load prediction vector, and the dimension where the corresponding pixel value is located is determined based on the order of the time points.

[0082] By adopting the above scheme, in the process of load forecasting, this scheme refines the target power consumption area and forecasts the load power of each sub-area separately to ensure the final load forecasting accuracy.

[0083] Another aspect of the present invention also relates to a coordinated control system of a speed regulator and an AGC system, the system comprising a computer device, the computer device comprising a processor and a memory, the memory storing computer instructions, the processor being used to execute the computer instructions stored in the memory, and when the computer instructions are executed by the processor, the system implements the steps implemented by the method.

[0084] The embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the coordinated control method of the speed regulator and the AGC system is implemented. The computer-readable storage medium can be a tangible storage medium, such as a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a floppy disk, a hard disk, a removable storage disk, a CD-ROM, or any other form of storage medium known in the technical field.

[0085] It should be understood by those skilled in the art that the exemplary components, systems and methods described in conjunction with the embodiments disclosed herein can be implemented in hardware, software or a combination of the two. Whether it is performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present invention are programs or code segments used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link via a data signal carried in a carrier.

[0086] It should be clear that the present invention is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present invention is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present invention.

[0087] In the present invention, features described and / or illustrated for one embodiment may be used in the same or similar manner in one or more other embodiments, and / or combined with features of other embodiments or replace features of other embodiments.

[0088] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the embodiments of the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A coordinated control method of a speed regulator and an AGC system, characterized in that: The steps of the method include: Calling power consumption data of a target power consumption area, the power consumption data including load power at each time point in the target power consumption area, each of the target power consumption areas including a plurality of sub-areas; Determine the load power at the predicted time point based on the load power at each historical time point in the target power consumption area, construct a load change trend based on the load power calculations at multiple time points, and calculate the first frequency change value at each time point based on the load change trend; Acquiring an actual second frequency change value at each historical time point based on the AGC system, and constructing a difference vector based on a difference between the first frequency change value and the second frequency change value at each historical time point; Inputting the difference vector into a pre-trained difference prediction model, the difference prediction model outputs a difference value at a predicted time point; A third frequency change value at the predicted time point is calculated based on the difference value at the predicted time point and the first frequency change value at the predicted time point, and the AGC system issues a control instruction to the speed regulator based on the third frequency change value.

2. The coordinated control method of the speed regulator and the AGC system according to claim 1, characterized in that: In the step of determining the load power at a predicted time point based on the load power at each historical time point in the target power consumption area, and constructing a load change trend based on the load power calculation at multiple time points: Constructing a load power vector from the load powers at multiple time points, inputting the load power vector into a pre-trained load prediction model, and the load prediction model outputs the load power at the predicted time point; The load power at the historical time point and the load power at the predicted time point are both taken as a coordinate point in the coordinate system, and the coordinate points of each time point are sequentially connected to obtain a load change trend graph.

3. The coordinated control method of the speed regulator and the AGC system according to claim 2, characterized in that: In the step of determining the load power at a predicted time point based on the load power at each historical time point in the target power consumption area, and constructing a load change trend based on the load power calculation at multiple time points, the slope of the line between the corresponding coordinate points of each two time points in the load change trend graph is taken as a trend value.

4. The coordinated control method of the speed regulator and the AGC system according to claim 3, characterized in that: In the step of calculating the first frequency change value at each time point based on the load change trend, for each time point, the trend values ​​between a preset number of time points before the time point are obtained from the load change trend graph, constructed as a change trend vector, and the change trend vector is input into a pre-trained frequency change calculation model, and the first frequency change value corresponding to the time point is output through the frequency change calculation model.

5. The coordinated control method of the speed regulator and the AGC system according to any one of claims 1 to 4, characterized in that: In the step of constructing a difference vector based on the difference between the first frequency change value and the second frequency change value at each historical time point, the difference between the first frequency change value and the second frequency change value at each historical time point is calculated and used as the value of each dimension in the difference vector to construct a difference vector.

6. The coordinated control method of the speed regulator and the AGC system according to claim 1, characterized in that: In the step of calculating the third frequency change value of the predicted time point based on the difference value of the predicted time point and the first frequency change value of the predicted time point, addition or subtraction calculation is performed based on the first frequency change value of the predicted time point and the corresponding difference value to obtain the corresponding third frequency change value of the predicted time point.

7. The coordinated control method of the speed regulator and the AGC system according to claim 1, characterized in that: In the step of determining the load power at a predicted time point based on the load power at each historical time point of the target power consumption area, a load distribution graph at a time point is constructed based on the load power of each sub-area at each time point, a load distribution graph at a predicted time point is determined based on the load distribution graphs of multiple time points, and the load power at the predicted time point is determined based on the load distribution graph at the predicted time point.

8. The coordinated control method of the speed regulator and the AGC system according to claim 7, characterized in that: Each sub-area of ​​the target power consumption area corresponds to an image area in the load distribution map, in the steps of constructing a load distribution map at a time point based on the load power of each sub-area at each time point, determining a load distribution map at a predicted time point based on the load distribution maps at multiple time points, and determining the load power at the predicted time point based on the load distribution map at the predicted time point: Determine the pixel value corresponding to the load power of each sub-area based on a preset pixel mapping table, render the pixel value to the corresponding image area, and obtain a load distribution diagram at a time point; The pixel values ​​of the same image region in the load distribution graphs at multiple time points are constructed as a pixel prediction vector of a sub-region; Inputting the pixel prediction vector into a pre-trained pixel prediction model to obtain a pixel value of a corresponding sub-region in a load distribution diagram at a prediction time point; The corresponding load power is determined based on the pixel value of each sub-region in the load distribution diagram at the predicted time point, and the total load power at the predicted time point is obtained based on the load power of each sub-region.

9. The coordinated control method of the speed regulator and the AGC system according to claim 8, characterized in that: In the step of constructing a pixel prediction vector of a sub-area from the pixel values ​​of the same image area in the load distribution map at multiple time points, the pixel values ​​of the same image area in the load distribution map at each time point are used as the value of a dimension in the load prediction vector, and the dimension where the corresponding pixel value is located is determined based on the order of the time points.

10. A coordinated control system of a speed regulator and an AGC system, characterized in that: The system includes a computer device, which includes a processor and a memory, wherein the memory stores computer instructions, and the processor is used to execute the computer instructions stored in the memory. When the computer instructions are executed by the processor, the system implements the steps implemented by the method described in any one of claims 1 to 9.

Images