Frequency modulation control method and system for thermal power generating unit

Abstract

The invention discloses a thermal power generating unit frequency modulation control method and system. The method comprises the following steps: acquiring real-time electric quantity data of a plurality of thermal power generating units; the real-time electric quantity data comprises real-time output power and real-time system frequency of the thermal power generating unit; acquiring historical load data of a power grid, and further constructing an electrical load prediction model for each thermal power generating unit; obtaining a target load demand of the thermal power generating unit according to the electrical load prediction model, judging whether frequency modulation is needed by combining real-time electric quantity data of the thermal power generating unit, and if not, not performing frequency modulation control on the thermal power generating unit; if yes, frequency modulation control parameters are obtained through calculation, and dynamic frequency modulation control is conducted on the thermal power generating unit. According to the method, the electrical load prediction model of each thermal power generating unit is constructed, and the real-time electric quantity data of the thermal power generating units are combined to judge whether frequency modulation is carried out, so that an automatic frequency modulation process is realized without depending on artificial experience and judgment, and the labor cost is greatly reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of frequency modulation control, and particularly to a frequency modulation control method and system for thermal power units. Background Art

[0002] With the increasing proportion of new energy in the energy structure, the stability of the power system has been continuously challenged, and the situation faced by the power grid security has become particularly severe, which poses higher requirements for the frequency modulation and peak shaving capabilities of conventional thermal power units. A thermal power unit is a device that generates electric energy by burning fossil fuels, such as coal, natural gas, or oil, and other materials that can burn and ignite, and then converting the thermal energy into mechanical energy through a steam or gas turbine, and finally driving a generator to generate electricity. According to the different combustion materials, the thermal power unit can be a coal-fired unit or a fuel-oil unit, etc. The frequency modulation of a thermal power unit refers to the process in which the thermal power unit participates in the grid frequency regulation to maintain the stability of the grid frequency. The frequency modulation of a thermal power unit includes natural frequency modulation, primary frequency modulation, and secondary frequency modulation. Natural frequency modulation is the dynamic frequency modulation characteristic of the power grid, which uses the energy storage of the rotational inertia in the power grid to first bear the change of the grid load. Primary frequency modulation is the static frequency modulation characteristic of the power grid. Through the static characteristics of the speed control systems of each unit in the power grid, the energy storage of the unit is used to bear the change of the grid load, and finally a steady-state frequency deviation is formed in the grid frequency. Primary frequency modulation is automatically completed by the prime mover speed control system without the intervention of the power grid dispatching department. Secondary frequency modulation is the process of the power grid dispatching intervening in the grid frequency manually or automatically, transferring the change of the grid load to be borne by the pre-designated frequency modulation units, eliminating the frequency deviation left in the primary frequency modulation process, and making the grid frequency return to the rated value.

[0003] Since the energy characteristics of thermal power units, such as coal-fired units, fuel-oil units, and gas turbine units, are quite different, and frequency modulation needs to ensure energy balance. The traditional unit frequency modulation is to regularly monitor the system frequency, load demand, and unit status by the staff, and judge whether frequency modulation is required based on these data. This process often relies on manual experience and judgment. This manual adjustment is not only time-consuming, but also may cause problems of untimely response and inaccurate frequency modulation due to human factors. Summary of the Invention

[0004] Aiming at the defects in the prior art, the present invention provides a frequency modulation control method and system for thermal power units, constructs an electricity consumption load prediction model for each thermal power unit, and judges whether to perform frequency modulation in combination with the real-time electricity data of the thermal power unit, realizing an automated frequency modulation process, not relying on manual experience and judgment, and greatly reducing the labor cost.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] A frequency modulation control method for a thermal power unit, comprising:

[0007] Obtain the real-time power data of several thermal power units; the real-time power data includes the real-time output power and real-time system frequency of the thermal power units;

[0008] Obtain the historical load data of the power grid, and then construct an electricity load prediction model for each thermal power unit;

[0009] According to the electricity load prediction model, obtain the target load demand of the thermal power unit, and combine the real-time power data of the thermal power unit to judge whether frequency modulation is required. If not, no frequency modulation control is performed on the thermal power unit; if so, calculate the frequency modulation control parameters and perform dynamic frequency modulation control on the thermal power unit.

[0010] A further improvement of the present invention is that the electricity load prediction model includes several load prediction windows in a preset time period. The time length of each load prediction window is a time period length intercepted from the preset time period, and each load prediction window includes the predicted electricity load curve within the corresponding time length.

[0011] A further improvement of the present invention is that the process of obtaining the electricity load curve of the load prediction window includes:

[0012] Determine the time interval according to the time to which the load prediction window belongs, where the length of the time interval is greater than the time length of the load prediction window;

[0013] Extract the historical load data of each thermal power unit from the historical load data of the power grid, and extract several groups of load data corresponding to the time interval from the historical load data of the thermal power unit; draw the load curve under the time interval for each group of load data;

[0014] Fit all the load curves based on the least squares method to obtain the fitted load curve;

[0015] Cut the fitted load curve based on the time length of the load prediction window to obtain the electricity load curve of the load prediction window.

[0016] A further improvement of the present invention is that the dynamic frequency modulation control of the thermal power unit includes the following steps:

[0017] Fit the electricity load curves of each load prediction window in the electricity load prediction model to obtain the total load demand of the thermal power unit;

[0018] Judge whether the thermal power unit needs frequency modulation, that is, whether the real-time power data of the thermal power unit is equal to the total load demand of the thermal power unit. If so, the thermal power unit does not need frequency modulation and no frequency modulation control is performed on the thermal power unit;

[0019] If not, according to the time interval of the load prediction window corresponding to the time when the thermal power unit belongs, calculate the target system frequency in the corresponding load prediction window, and calculate the frequency deviation based on the target system frequency and the real-time system frequency;

[0020] Calculate the frequency modulation control parameter based on the frequency deviation to achieve dynamic frequency modulation control of the thermal power unit.

[0021] A further improvement of the present invention lies in that the calculation formula for the total load demand of the thermal power unit is:

[0022]

[0023] where Load(T) is the total load demand of the thermal power unit, T is the preset time period length of the electricity load prediction model, a and b i are regression coefficients, I is the number of load prediction windows in the electricity load prediction model, and t i is the time interval to which the i-th load prediction window belongs; load(t i ) is the load demand of the thermal power unit within the time t i .

[0024] A further improvement of the present invention lies in that the calculation formula for the frequency deviation is:

[0025] Δf = f current - f target

[0026] f target = g(load(t i ))

[0027] where Δf is the frequency deviation, f current is the real-time system frequency, f target is the target system frequency, and g(·) is a non-linear function.

[0028] A further improvement of the present invention lies in that the calculation formula for the frequency modulation control parameter is:

[0029] ΔFM = KΔf

[0030] where ΔFM is the frequency modulation control parameter and K is the frequency modulation response parameter.

[0031] A thermal power unit frequency modulation control system includes:

[0032] A real-time power data acquisition module that acquires real-time power data of a number of thermal power units; the real-time power data includes the real-time output power and the real-time system frequency of the thermal power units;

[0033] A prediction model construction module obtains the historical load data of the power grid, and then constructs an electricity load prediction model for each thermal power unit.

[0034] A judgment and frequency modulation control module obtains the target load demand of the thermal power unit according to the electricity load prediction model, and determines whether frequency modulation is required by combining the real-time electricity quantity data of the thermal power unit. If not, no frequency modulation control is performed on the thermal power unit; if so, the frequency modulation control parameters are calculated to perform dynamic frequency modulation control on the thermal power unit.

[0035] A further improvement of the present invention lies in that in the prediction model construction module, the electricity load prediction model includes a plurality of load prediction windows in a preset time period. The time length of each load prediction window is a time period length intercepted from the preset time period, and each load prediction window includes the predicted electricity load curve within the corresponding time length.

[0036] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it implements the steps of the method for controlling the frequency modulation of a thermal power unit.

[0037] Compared with the prior art, the present invention has at least the following beneficial technical effects:

[0038] The method and system for controlling the frequency modulation of a thermal power unit provided by the present invention constructs an electricity load prediction model for each thermal power unit, determines whether to perform frequency modulation by combining the real-time electricity quantity data of the thermal power unit, realizes an automated frequency modulation process, does not rely on manual experience and judgment, and greatly reduces labor costs. In the present invention, when the real-time electricity quantity data of the thermal power unit is equal to the total load demand of the thermal power unit, no frequency modulation is performed, avoiding frequent frequency modulation and improving the service life of the thermal power unit. In the present invention, the electricity load prediction model is divided into multiple load prediction windows, and the frequency deviation is calculated according to the electricity load curve of each load prediction window, and then the frequency modulation control parameters are obtained to realize the dynamic frequency modulation control of the thermal power unit. Description of the Drawings

[0039] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for use in the description of the specific embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0040] Figure 1 It is the flowchart of the method of the embodiment of the present invention.

[0041] Figure 2 It is the system structure block diagram of the embodiment of the present invention. Detailed Embodiments

[0042] In the following text, only some exemplary embodiments are briefly described. As those skilled in the art can recognize, the described embodiments can be modified in various different ways without departing from the spirit or scope of the present invention. Therefore, the accompanying drawings and description are considered to be exemplary in nature rather than restrictive.

[0043] It should be understood that when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0044] It should also be understood that the terms used in the specification of the present invention are merely for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an", and "the" are intended to include the plural forms.

[0045] It should be further understood that the term " / and" used in the specification of the present invention and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0046] Various structural schematic diagrams according to the disclosed embodiments of the present invention are shown in the drawings. These figures are not drawn to scale, where for the purpose of clear expression, some details are enlarged and some details may be omitted. The shapes of various regions and layers shown in the figures and their relative sizes and positional relationships are merely exemplary, and in practice, there may be deviations due to manufacturing tolerances or technical limitations, and those skilled in the art can design regions / layers with different shapes, sizes, and relative positions according to actual needs.

[0047] The embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0048] Embodiment 1

[0049] As Figure 1 shown, a frequency modulation control method for a thermal power unit in this embodiment includes the following steps:

[0050] S1. Obtain the real-time power data of several thermal power units; the real-time power data includes the real-time output power and the real-time system frequency of the thermal power unit;

[0051] In this embodiment, the real-time output power is obtained by installing a power meter on the thermal power unit, and the real-time system frequency is obtained by a multifunctional electric meter, or can also be obtained from the power grid dispatching center;

[0052] S2. Obtain the historical load data of the power grid, and then construct an electricity load prediction model for each thermal power unit;

[0053] The operating states and electricity load conditions of the power grid are different at different times and under different conditions. However, the electricity load will not fluctuate greatly in the short term. Moreover, the electricity load trend in the future target time can be predicted based on the change of the electricity load in the past period. For example, according to the electricity consumption tendency of the power grid in a certain time period in the historical load data, the future load demand can be predicted according to the electricity load prediction model, which is convenient for formulating a more reasonable frequency modulation control strategy.

[0054] In this embodiment, the electricity load prediction model includes a number of load prediction windows under a preset time period. The time length of each load prediction window is a time period length intercepted from the preset time period. Each load prediction window includes the predicted electricity load curve within the time length it belongs to. For example, 24 hours of a day can be set as the preset time period length of the electricity load prediction model. The electricity load prediction model includes 24 load prediction windows, and the time period of each load prediction window is set to 1 hour, that is, each load prediction window includes the predicted electricity load curve within 1 hour.

[0055] The process of obtaining the electricity load curve of each load prediction window includes:

[0056] Determine the time interval according to the time to which the load prediction window belongs, where the length of the time interval is greater than the time length to which the load prediction window belongs;

[0057] Extract the historical load data of each thermal power unit from the historical load data of the power grid, and extract several groups of load data corresponding to the time interval from the historical load data of the thermal power unit; draw the load curve under the time interval for each group of load data. It should be noted that the historical load data of each thermal power unit can be obtained from the power grid dispatching center.

[0058] Fit all the load curves based on the least squares method to obtain the fitted load curve;

[0059] Cut the fitted load curve based on the time length of the load prediction window to obtain the electricity load curve of the load prediction window.

[0060] The present invention constructs an electricity load prediction model for each thermal power unit, combines the real-time power data of the thermal power unit to judge whether to perform frequency modulation, and realizes an automated frequency modulation process, which does not rely on manual experience and judgment, and greatly reduces the labor cost.

[0061] S3. Obtain the target load demand of the thermal power unit according to the electricity load prediction model, and determine whether frequency modulation is required by combining the real-time power data of the thermal power unit. If not, no frequency modulation control is performed on the thermal power unit; if so, calculate the frequency modulation control parameters according to the electricity load curve of the load prediction window, and perform dynamic frequency modulation control on the thermal power unit, including the following steps:

[0062] S31. Fit the electricity load curves of each load prediction window in the electricity load prediction model to obtain the total load demand of the thermal power unit. The calculation formula for the total load demand of the thermal power unit is:

[0063]

[0064] where Load(T) is the total load demand of the thermal power unit, T is the preset time period length of the electricity load prediction model, a and b i are regression coefficients obtained by fitting the electricity load curve, I is the number of load prediction windows in the electricity load prediction model, and t i is the time interval to which the i-th load prediction window belongs; load(t i ) is the load demand of the thermal power unit at time t i .

[0065] S32. Determine whether the thermal power unit needs frequency modulation, that is, whether the real-time power data of the thermal power unit is equal to the total load demand of the thermal power unit. If so, the thermal power unit does not need frequency modulation, and no frequency modulation control is performed on the thermal power unit; if not, go to S33;

[0066] S33. If the real-time power data of the thermal power unit is greater than the total load demand of the thermal power unit, it indicates that the output needs to be reduced to decrease the system frequency; if the real-time power data of the thermal power unit is less than the total load demand of the thermal power unit, it indicates that the output needs to be increased to increase the system frequency; according to the t i corresponding to the time to which the thermal power unit belongs, calculate the target system frequency in the corresponding load prediction window, and calculate the frequency deviation according to the target system frequency and the real-time system frequency. The calculation formula for the frequency deviation is:

[0067] Δf = f current - f target

[0068] f target = g(load(t i ))

[0069] where Δf is the frequency deviation, f current is the real-time system frequency, and f targetis the target system frequency, and g(·) is a non-linear function used to calculate the relationship between the electricity load and the system frequency. This is prior art and will not be elaborated here. The target system frequency can also be obtained through experience or from the database of the power dispatching center.

[0070] S34. Calculate the frequency modulation control parameter based on the frequency deviation to achieve dynamic frequency modulation control of the thermal power unit. The calculation formula for the frequency modulation control parameter is:

[0071] ΔFM = K·Δf

[0072] Where, ΔFM is the frequency modulation control parameter, and K is the frequency modulation response parameter; the frequency modulation response parameter can be obtained through experience or from the database of the power dispatching center. The frequency modulation control parameter is the decisive parameter that determines the real-time output power change of the thermal power unit. By calculating the frequency modulation control parameter, the thermal power unit can work according to the electricity load curve output in the load prediction window of the electricity load prediction model, reduce losses, and improve the overall economic efficiency.

[0073] In the present invention, when the real-time electricity quantity data of the thermal power unit is equal to the total load demand of the thermal power unit, no frequency modulation is performed to avoid frequent frequency modulation and improve the service life of the thermal power unit.

[0074] In addition, in the present invention, the electricity load prediction model is divided into multiple load prediction windows, and the frequency deviation is calculated according to the electricity load curve of each load prediction window, and then the frequency modulation control parameter is obtained to achieve dynamic frequency modulation control of the thermal power unit.

[0075] From the description of the above embodiments, those skilled in the art can clearly understand that all or part of the steps in the above embodiment methods can be implemented by means of software plus a general hardware platform. Based on such an understanding, the technical solution of the present application can be embodied in the form of a software product. This computer software product can be stored in a storage medium. The memory can be various types of memories, such as random access memory, read-only memory, flash memory, etc., such as read-only memory (English: read-only memory, ROM) / RAM, magnetic disk, optical disk, etc., including several instructions to enable a computer device (which can be a personal computer, a server, or a network communication device such as a router) to execute the methods described in each embodiment or some parts of the embodiments of the present application.

[0076] Embodiment 2

[0077] As Figure 2 shown, a frequency modulation control system for a thermal power unit in this embodiment includes:

[0078] A real-time power data acquisition module is used to acquire real-time power data of several thermal power units; the real-time power data includes the real-time output power and real-time system frequency of the thermal power units;

[0079] The prediction model building module obtains the historical load data of the power grid and then builds a power load prediction model for each thermal power unit;

[0080] The frequency control module determines whether frequency regulation is needed based on the target load demand of the thermal power unit according to the power load forecasting model, and determines whether frequency regulation is needed based on the real-time power data of the thermal power unit. If not, frequency regulation control is not performed on the thermal power unit; if so, frequency regulation control parameters are calculated and dynamic frequency regulation control is performed on the thermal power unit.

[0081] In an embodiment, in the prediction model construction module, the power load prediction model includes a number of load prediction windows under a preset time period, the time length of each load prediction window is a time period length intercepted from the preset time period, and each load prediction window includes a predicted power load curve within the corresponding time length.

[0082] Example 3

[0083] A computer-readable storage medium of this embodiment stores a computer program, and when the computer program is executed by a processor, the steps of the frequency regulation control method of a thermal power unit are implemented.

[0084] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0085] The present application is described with reference to the flowcharts and / or block diagrams of the methods, systems and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A system that specifies the functions of a box or boxes.

[0086] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to work in a particular manner, such that the instructions stored in the computer-readable memory produce a manufacture including an instruction device that implements the functions specified in one or more processes and / or blocks Figure 1 in the process Figure 1 or processes and / or boxes

[0087] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, so that a series of operation steps are executed on the computer or other programmable apparatus to produce a computer-implemented process, and thus the instructions executed on the computer or other programmable apparatus provide steps for implementing the functions specified in one or more processes and / or blocks Figure 1 in the process Figure 1 or processes and / or boxes

[0088] The foregoing has shown and described the basic principles, main features and advantages of the present invention. For a person skilled in the art, it is obvious that the present invention is not limited to the details of the above-described exemplary embodiments, and without departing from the spirit or essential characteristics of the present invention, the present invention can be implemented in other specific forms. Therefore, in any regard, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, it is intended to embrace all changes falling within the meaning and scope of the equivalent elements of the claims in the present invention. Any reference signs in the claims should not be construed as limiting the claimed invention.

[0089] In addition, it should be understood that although this specification is described in terms of embodiments, not every embodiment only contains an independent technical solution. This narrative manner of the specification is only for clarity. Those skilled in the art should regard the specification as a whole, and the technical solutions in each embodiment can also be appropriately combined to form other embodiments that can be understood by those skilled in the art. The above content is only to illustrate the technical idea of the present invention and cannot limit the protection scope of the present invention. Any modification made on the basis of the technical solution according to the technical idea proposed by the present invention falls within the protection scope of the claims of the present invention.

Claims

1. A frequency modulation control method for a thermal power unit, characterized in that: include: Obtain real-time power data of several thermal power units; Real-time power data includes real-time output power of thermal power units and real-time system frequency; Obtain historical load data of the power grid and then build a power load forecasting model for each thermal power unit; The target load demand of the thermal power unit is obtained according to the power load forecasting model, and the real-time power data of the thermal power unit is combined to determine whether frequency regulation is required. If not, the thermal power unit will not be subject to frequency regulation control; If so, the frequency control parameters are calculated and dynamic frequency control is performed on the thermal power unit.

2. A frequency modulation control method for a thermal power unit according to claim 1, characterized in that: The power load forecasting model includes several load forecasting windows under a preset time period. The time length of each load forecasting window is a time period length intercepted from the preset time period. Each load forecasting window includes a predicted power load curve within the corresponding time length.

3. A frequency modulation control method for a thermal power unit according to claim 2, characterized in that: The process of obtaining the power load curve in the load forecast window includes: Determine a time interval according to the time to which the load forecast window belongs, wherein the length of the time interval is greater than the length of the time to which the load forecast window belongs; Extract the historical load data of each thermal power unit from the historical load data of the power grid, and extract several groups of load data corresponding to the time interval from the historical load data of the thermal power unit; draw a load curve under the time interval for each group of load data; All load curves are fitted based on the least square method to obtain the fitted load curve; The fitted load curve is cut based on the time length of the load forecast window to obtain the power load curve of the load forecast window.

4. A frequency modulation control method for a thermal power unit according to claim 1, characterized in that: Dynamic frequency control of thermal power units includes the following steps: The total load demand of thermal power units is obtained by fitting the power load curve of each load forecast window in the power load forecast model; Determine whether the thermal power unit needs frequency modulation, that is, whether the real-time power data of the thermal power unit is equal to the total load demand of the thermal power unit. If so, the thermal power unit does not need frequency modulation, and the thermal power unit will not be controlled by frequency modulation; If not, the target system frequency is calculated in the corresponding load forecast window according to the time interval of the load forecast window corresponding to the time of the thermal power unit, and the frequency deviation is calculated according to the target system frequency and the real-time system frequency; The frequency control parameters are obtained according to the frequency deviation calculation to realize the dynamic frequency control of the thermal power unit.

5. A frequency modulation control method for a thermal power unit according to claim 4, characterized in that: The calculation formula for the total load demand of thermal power units is: Among them, Load(T) is the total load demand of thermal power units, T is the preset time period length of the power load forecasting model, a, b i is the regression coefficient, I is the number of load forecast windows in the power load forecasting model, t i is the time interval to which the ith load forecast window belongs; load(t i ) is the thermal power unit at t i Load demand over time.

6. A frequency modulation control method for a thermal power unit according to claim 4, characterized in that: The frequency deviation is calculated as: Δf=f current -f target f target =g(load(t i )) Where Δf is the frequency deviation, f current is the real-time system frequency, f target is the target system frequency, and g(·) is a nonlinear function.

7. A frequency modulation control method for a thermal power unit according to claim 4, characterized in that: The calculation formula of frequency modulation control parameters is: ΔFM=K·Δf Among them, ΔFM is the frequency modulation control parameter, and K is the frequency modulation response parameter.

8. A frequency modulation control system for a thermal power unit, characterized in that: include: A real-time power data acquisition module is used to acquire real-time power data of several thermal power units; the real-time power data includes the real-time output power and real-time system frequency of the thermal power units; The prediction model building module obtains the historical load data of the power grid and then builds a power load prediction model for each thermal power unit; The frequency control module determines whether frequency regulation is needed based on the target load demand of the thermal power unit according to the power load forecasting model, and determines whether frequency regulation is needed based on the real-time power data of the thermal power unit. If not, frequency regulation control is not performed on the thermal power unit; if so, frequency regulation control parameters are calculated and dynamic frequency regulation control is performed on the thermal power unit.

9. A frequency modulation control system for a thermal power unit according to claim 8, characterized in that: In the prediction model construction module, the power load prediction model includes several load prediction windows under a preset time period. The time length of each load prediction window is the length of a time period intercepted in the preset time period, and each load prediction window includes the predicted power load curve within the corresponding time length.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of a frequency regulation control method for a thermal power unit according to any one of claims 1 to 7 are implemented.

Images