CN117996789A - Frequency modulation method of fused salt coupling thermal power generating unit based on bidirectional predictive feedback adjustment - Google Patents

Frequency modulation method of fused salt coupling thermal power generating unit based on bidirectional predictive feedback adjustment Download PDF

Info

Publication number
CN117996789A
CN117996789A CN202410406707.6A CN202410406707A CN117996789A CN 117996789 A CN117996789 A CN 117996789A CN 202410406707 A CN202410406707 A CN 202410406707A CN 117996789 A CN117996789 A CN 117996789A
Authority
CN
China
Prior art keywords
energy storage
requirement
target
error
decomposition layer
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202410406707.6A
Other languages
Chinese (zh)
Other versions
CN117996789B (en
Inventor
李志鹏
兀鹏越
王小辉
高峰
寇水潮
燕云飞
郝博瑜
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Xian Thermal Power Research Institute Co Ltd
Original Assignee
Xian Thermal Power Research Institute Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Xian Thermal Power Research Institute Co Ltd filed Critical Xian Thermal Power Research Institute Co Ltd
Priority to CN202410406707.6A priority Critical patent/CN117996789B/en
Publication of CN117996789A publication Critical patent/CN117996789A/en
Application granted granted Critical
Publication of CN117996789B publication Critical patent/CN117996789B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H02J3/24—Arrangements for preventing or reducing oscillations of power in networks
    • H02J3/241—The oscillation concerning frequency
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H02J3/004—Generation forecast, e.g. methods or systems for forecasting future energy generation
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H02J3/12—Circuit arrangements for ac mains or ac distribution networks for adjusting voltage in ac networks by changing a characteristic of the network load
    • H02J3/14—Circuit arrangements for ac mains or ac distribution networks for adjusting voltage in ac networks by changing a characteristic of the network load by switching loads on to, or off from, network, e.g. progressively balanced loading
    • H02J3/144—Demand-response operation of the power transmission or distribution network
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H02J3/28—Arrangements for balancing of the load in a network by storage of energy
    • H02J3/32—Arrangements for balancing of the load in a network by storage of energy using batteries with converting means
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
    • H02J3/46—Controlling of the sharing of output between the generators, converters, or transformers
    • H02J3/466—Scheduling the operation of the generators, e.g. connecting or disconnecting generators to meet a given demand
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
    • H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
    • H02J2300/40—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation wherein a plurality of decentralised, dispersed or local energy generation technologies are operated simultaneously
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J2310/00—The network for supplying or distributing electric power characterised by its spatial reach or by the load
    • H02J2310/50—The network for supplying or distributing electric power characterised by its spatial reach or by the load for selectively controlling the operation of the loads
    • H02J2310/56—The network for supplying or distributing electric power characterised by its spatial reach or by the load for selectively controlling the operation of the loads characterised by the condition upon which the selective controlling is based
    • H02J2310/58—The condition being electrical
    • H02J2310/60—Limiting power consumption in the network or in one section of the network, e.g. load shedding or peak shaving

Landscapes

  • Engineering & Computer Science (AREA)
  • Power Engineering (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Biomedical Technology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Feedback Control In General (AREA)

Abstract

The application provides a frequency modulation method of a fused salt coupled thermal power generating unit based on bidirectional predictive feedback regulation, which comprises the steps of determining a hybrid energy storage response requirement based on a frequency modulation instruction; inputting the mixed energy storage response requirement and the decomposition layer number of the VMD algorithm into a trained prediction module to predict the aliasing degree; setting an upper limit of iteration times, obtaining a decomposition layer number predicted value and a mixed response predicted value and obtaining an error mean value based on the aliasing degree, the decomposition layer number, the mixed energy storage response requirement and the trained two reverse prediction modules, adjusting the decomposition layer number and the mixed energy storage response requirement to obtain a new error mean value when the current iteration times or the error mean value meet the requirement, and obtaining a target aliasing degree when the current iteration times and the error mean value do not meet the requirement; updating the number of decomposition layers to obtain different target aliasing degrees; and determining the target decomposition layer number based on the minimum target aliasing degree, and further obtaining a high-frequency component and a low-frequency component to control the molten salt energy storage equipment and the lithium battery to respond.

Description

Frequency modulation method of fused salt coupling thermal power generating unit based on bidirectional predictive feedback adjustment
Technical Field
The application relates to the technical field of power grid frequency modulation, in particular to a frequency modulation method of a fused salt coupling thermal power generating unit based on bidirectional predictive feedback regulation.
Background
The fire-storage combined frequency modulation can obviously improve the frequency modulation performance of the thermal power generating unit, and can quickly and effectively reduce the shortage of the frequency modulation capacity of the system. At present, the fire-storage combined frequency modulation technology comprises battery energy storage, super-capacitor energy storage, flywheel energy storage, fused salt energy storage, hybrid energy storage formed by various forms and the like, the cycle life of thermal power pond energy storage is low, certain potential safety hazards exist, super-capacitor energy storage and flywheel energy storage are used as the representation of power type energy storage devices, fire has the defects of high cost, low energy density and the like, the fused salt energy storage uses raw materials such as nitrate as a heat storage medium, energy is stored and released through the conversion of heat energy of a heat transfer working medium and the internal energy of fused salt, and the fire-storage combined frequency modulation technology has the advantages of low cost, high safety, large capacity, long service life and the like.
In the prior art, a fused salt energy storage and variation modal decomposition (variational mode decomposition, VMD) technology is utilized to assist in frequency modulation, however, a plurality of modal components (INTRINSIC MODE FUNCTION, IMF) obtained by simply decomposing signals through VMD have the problem of serious modal aliasing, and the accuracy of subsequent frequency modulation response is affected.
Disclosure of Invention
The present application aims to solve at least one of the technical problems in the related art to some extent.
Therefore, a first object of the present application is to provide a frequency modulation method for a fused salt coupled thermal power generating unit based on bidirectional predictive feedback adjustment, so as to improve accuracy of frequency modulation response.
The second aim of the application is to provide a frequency modulation system of a fused salt coupled thermal power generating unit based on bidirectional predictive feedback regulation.
A third object of the present application is to propose an electronic device.
A fourth object of the present application is to propose a computer readable storage medium.
To achieve the above objective, an embodiment of a first aspect of the present application provides a frequency modulation method for a fused salt coupled thermal power generating unit based on bidirectional predictive feedback adjustment, wherein a hybrid energy storage device configured in a thermal power plant includes fused salt energy storage equipment and a lithium battery, and the frequency modulation method includes the following steps:
determining a hybrid energy storage response requirement based on the frequency modulation instruction received in real time;
Inputting the mixed energy storage response requirement and the decomposition layer number of the VMD algorithm into a trained prediction module to predict the aliasing degree;
Setting an upper limit of iteration times, and obtaining a predicted value of the number of decomposition layers and a predicted value of the mixed response based on the aliasing degree, the number of decomposition layers, the mixed energy storage response requirement and the trained two reverse prediction modules, so as to obtain a corresponding error coefficient;
Determining an error mean value based on the error coefficient, updating the current iteration number when the current iteration number or the error mean value meets the requirement, and adjusting the number of decomposition layers and the hybrid energy storage response requirement to obtain a new error mean value until the current iteration number and the error mean value do not meet the requirement, thereby obtaining a target aliasing degree;
updating the decomposition layer number based on the set decomposition layer number range to obtain target aliasing degrees corresponding to different decomposition layer numbers;
Selecting the decomposition layer number corresponding to the minimum value in all the target aliasing degrees as a target decomposition layer number, and decomposing the hybrid energy storage response requirement by utilizing a VMD algorithm based on the target decomposition layer number to obtain a target modal component and a residual component;
Dividing the target modal component and the residual component to obtain a high-frequency component and a low-frequency component, controlling the molten salt energy storage device to respond according to the high-frequency component and controlling the lithium battery to respond according to the low-frequency component.
In the method of the first aspect of the present application, the obtaining, by the two trained reverse prediction modules, the predicted value of the number of decomposition layers and the predicted value of the hybrid response based on the aliasing degree, the number of decomposition layers, the hybrid energy storage response requirement, and further obtaining the corresponding error coefficient includes: inputting the aliasing degree and the decomposition layer number into a trained first reverse prediction module to obtain a hybrid energy storage response predicted value; obtaining a first error coefficient based on the hybrid energy storage response predicted value and the hybrid energy storage response requirement; inputting the aliasing degree and the hybrid energy storage response requirement into a trained second reverse prediction module to obtain a decomposition layer number prediction value; a second error coefficient is obtained based on the decomposition level prediction value and the decomposition level.
In the method of the first aspect of the present application, the current iteration number meeting the requirement means that the current iteration number does not reach the upper limit of the iteration number, and the error mean value meeting the requirement means that the error mean value is greater than the error threshold.
In the method of the first aspect of the present application, the adjusting the decomposition level and the hybrid energy storage response requirement to obtain a new error mean value includes: determining a reverse modulation coefficient based on an error mean value, and updating the number of decomposition layers and the hybrid energy storage response requirement based on the reverse modulation coefficient; and obtaining a new decomposition layer number predicted value and a new mixed response predicted value based on the updated decomposition layer number and the updated mixed energy storage response requirement, so as to obtain a new error mean value.
In the method of the first aspect of the present application, the inverse adjustment coefficient satisfies:
where β is the inverse coefficient, z is the mean value of the error, and rand () represents the random number.
In the method of the first aspect of the present application, the obtaining the target aliasing degree includes: calculating the ratio of the larger value to the smaller value in the first error coefficient and the second error coefficient; if the ratio is larger than a ratio threshold, taking the corresponding aliasing degree when the current iteration times and the error mean value do not meet the requirement as a target aliasing degree; and if the ratio is not greater than the ratio threshold, obtaining a correction coefficient based on the first error coefficient and the second error coefficient, and obtaining a target aliasing degree based on the correction coefficient and the corresponding aliasing degree when the current iteration number and the error mean value do not meet the requirement.
In the method of the first aspect of the present application, the correction coefficient satisfies:
Where α is a correction coefficient, MAPE a is a first error coefficient, and MAPE b is a second error coefficient.
To achieve the above objective, an embodiment of a second aspect of the present application provides a frequency modulation system of a fused salt coupled thermal power generating unit based on bidirectional predictive feedback adjustment, a hybrid energy storage device configured in a thermal power plant includes fused salt energy storage equipment and a lithium battery, the frequency modulation system includes:
the acquisition module is used for determining the hybrid energy storage response requirement based on the frequency modulation instruction received in real time;
The first prediction module is used for inputting the hybrid energy storage response requirement and the decomposition layer number of the VMD algorithm into the trained prediction module to predict the aliasing degree;
The second prediction module is used for setting an upper limit of iteration times, and obtaining a decomposition layer number predicted value and a mixed response predicted value based on the aliasing degree, the decomposition layer number, the mixed energy storage response requirement and the trained two reverse prediction modules so as to obtain a corresponding error coefficient;
the target aliasing degree determining module is used for determining an error mean value based on the error coefficient, updating the current iteration number when the current iteration number or the error mean value meets the requirement, and adjusting the decomposition layer number and the hybrid energy storage response requirement to obtain a new error mean value until the current iteration number and the error mean value do not meet the requirement, so as to obtain the target aliasing degree;
The updating module is used for updating the decomposition layer number based on the set decomposition layer number range so as to obtain target aliasing degrees corresponding to different decomposition layer numbers;
The decomposition module is used for selecting the decomposition layer number corresponding to the minimum value in all the target aliasing degrees as a target decomposition layer number, and decomposing the hybrid energy storage response requirement by utilizing a VMD algorithm based on the target decomposition layer number to obtain a target modal component and a residual component;
The control module is used for dividing the target modal component and the residual component to obtain a high-frequency component and a low-frequency component, controlling the molten salt energy storage device to respond according to the high-frequency component and controlling the lithium battery to respond according to the low-frequency component.
To achieve the above object, an embodiment of a third aspect of the present application provides an electronic device, including: a processor, and a memory communicatively coupled to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the method according to the first aspect of the present application.
To achieve the above object, an embodiment of a fourth aspect of the present application provides a computer-readable storage medium having stored therein computer-executable instructions for implementing the method set forth in the first aspect of the present application when executed by a processor.
According to the frequency modulation method, the frequency modulation system, the electronic equipment and the storage medium of the fused salt coupled thermal power generating unit based on the bidirectional predictive feedback regulation, which are provided by the application, the hybrid energy storage response requirement is determined through the frequency modulation instruction based on real-time reception; inputting the mixed energy storage response requirement and the decomposition layer number of the VMD algorithm into a trained prediction module to predict the aliasing degree; setting an upper limit of iteration times, and obtaining a predicted value of the number of decomposition layers and a predicted value of the mixed response based on the aliasing degree, the number of decomposition layers, the mixed energy storage response requirement and the trained two reverse prediction modules, so as to obtain a corresponding error coefficient; determining an error mean value based on the error coefficient, updating the current iteration number when the current iteration number or the error mean value meets the requirement, and adjusting the number of decomposition layers and the hybrid energy storage response requirement to obtain a new error mean value until the current iteration number and the error mean value do not meet the requirement, thereby obtaining a target aliasing degree; updating the decomposition layer number based on the set decomposition layer number range to obtain target aliasing degrees corresponding to different decomposition layer numbers; selecting the decomposition layer number corresponding to the minimum value in all the target aliasing degrees as a target decomposition layer number, and decomposing the hybrid energy storage response requirement by utilizing a VMD algorithm based on the target decomposition layer number to obtain a target modal component and a residual component; dividing the target modal component and the residual component to obtain a high-frequency component and a low-frequency component, controlling the molten salt energy storage device to respond according to the high-frequency component and controlling the lithium battery to respond according to the low-frequency component. Under the condition, the aliasing degree is obtained by utilizing the mixed energy storage response requirement, the decomposition layer number and the trained prediction module, and then the decomposition layer number prediction value and the mixed response prediction value are obtained by utilizing the trained two reverse prediction modules, so that the corresponding error coefficient is obtained; and then determining an error mean value based on the error coefficient, and iteratively adjusting the number of decomposition layers and the mixed energy storage response requirement when the current iteration number or the error mean value meets the requirement, so as to continuously optimize the aliasing degree output by the trained prediction module until the current iteration number and the error mean value do not meet the requirement, thereby obtaining a target aliasing degree, improving the accuracy of the target aliasing degree, and then selecting the minimum value in all the target aliasing degrees, wherein the target aliasing degree is the minimum at the moment, so that the aliasing condition among target modal components can be better avoided when the mixed energy storage response requirement is decomposed by utilizing a VMD algorithm based on the target decomposition layer number, and further improving the accuracy of the frequency modulation response.
Additional aspects and advantages of the application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the application.
Drawings
The foregoing and/or additional aspects and advantages of the application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which:
FIG. 1 is a schematic flow chart of a frequency modulation method of a fused salt coupled thermal power generating unit based on bidirectional predictive feedback regulation provided by an embodiment of the application;
fig. 2 is a flow chart of a method for obtaining a corresponding target aliasing degree by using the number of decomposition layers according to the embodiment of the present application;
Fig. 3 is a block diagram of a frequency modulation system of a fused salt coupled thermal power generating unit based on bidirectional predictive feedback regulation provided by an embodiment of the application.
Detailed Description
Embodiments of the present application are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative and intended to explain the present application and should not be construed as limiting the application.
The frequency modulation method and system of the fused salt coupled thermal power generating unit based on bidirectional predictive feedback regulation in the embodiment of the application are described below with reference to the accompanying drawings.
The embodiment of the application provides a frequency modulation method of a fused salt coupling thermal power generating unit based on bidirectional predictive feedback regulation, so as to improve the accuracy of frequency modulation response.
In the application, a hybrid energy storage device configured in a thermal power plant comprises molten salt energy storage equipment and a lithium battery. The hybrid energy storage device assists the thermal power generating unit to participate in frequency modulation. The molten salt energy storage equipment is connected to a power grid through a thermal power unit, and the lithium battery is connected to the power grid through a converter. Before receiving the frequency modulation instruction, a connecting wire between the molten salt energy storage equipment and the thermal power generating unit is disconnected, if the frequency modulation instruction is received, the connecting wire between the molten salt energy storage equipment and the thermal power generating unit is conducted, and the thermal power generating unit supplies power to the molten salt energy storage equipment to convert electric energy into heat energy or release heat energy through the molten salt energy storage equipment to convert the electric energy into electric energy at a generator and send the electric energy to a power grid to perform frequency modulation response. The fused salt energy storage output P C of the fused salt energy storage device for frequency modulation response is determined based on a frequency modulation instruction and a thermal power unit load P G of a thermal power unit when a connecting line is disconnected, specifically, when the power grid issues the frequency modulation instruction, the frequency modulation instruction carries a load response demand P T, at the moment, the thermal power unit responds with the thermal power unit load P G, and the rest is responded by the hybrid energy storage device, so that the hybrid energy storage device is calculated to respond with the energy storage output of P J(PT-PG=PJ), wherein the lithium battery responds with the battery power P L, and the fused salt energy storage device participates in responding with the fused salt energy storage output P C. After the battery power P L and the molten salt energy storage output P C are obtained through calculation, a connecting wire between the molten salt energy storage device and the thermal power generating unit is controlled to be conducted, the molten salt energy storage device is controlled to respond with the calculated value of the molten salt energy storage output P C, and the lithium battery is controlled to respond with the calculated value of the battery power P L, so that frequency modulation is completed. The frequency modulation method can be used for more accurately determining the values of the battery power P L and the molten salt energy storage output P C in the hybrid energy storage device.
Fig. 1 is a schematic flow chart of a frequency modulation method of a fused salt coupled thermal power generating unit based on bidirectional predictive feedback regulation according to an embodiment of the application. Fig. 2 is a flow chart of a method for obtaining a corresponding target aliasing degree by using the number of decomposition layers according to the embodiment of the present application.
As shown in FIG. 1, the frequency modulation method of the fused salt coupled thermal power generating unit based on bidirectional predictive feedback adjustment comprises the following steps:
step S101, determining a hybrid energy storage response requirement based on the frequency modulation command received in real time.
In step S101, since the frequency modulation command carries the load response requirement P T, the load response requirement P T can be obtained based on the frequency modulation command received in real time, the thermal power unit load P G is obtained, and the difference between the load response requirement P T and the thermal power unit load P G is calculated to obtain the hybrid energy storage response requirement P J (also referred to as energy storage output), i.e. P T-PG=PJ.
And step S102, inputting the mixed energy storage response requirement and the decomposition layer number of the VMD algorithm into a trained prediction module to predict the aliasing degree.
In step S102, the prediction module is trained using the first historical data set to obtain a trained prediction module. The prediction module generally adopts a neural network which is mature in engineering, such as GRU (Gate Recurrent Unit, gate control circulation unit) and the like. The first historical data set includes a historical hybrid energy storage response demand, a number of decomposition levels, and a degree of aliasing of the historical hybrid energy storage response demand. The input of the prediction module is the historical hybrid energy storage response requirement and the number of decomposition layers, the output is the aliasing degree, the samples of the first historical data set are for example > 20000, and the prediction module is trained after training is completed. In addition, the aliasing degree of the historical hybrid energy storage response requirement is obtained by decomposing the historical hybrid energy storage response requirement into K modal components IMFs by using a VMD algorithm and then mapping the K IMFs to a frequency domain. The degree of aliasing satisfies: wherein, K is the number of decomposition layers, Representing the frequency overlap interval of two adjacent modal components,/>Representing the frequency interval in which two adjacent modal components are located,/>Is the frequency maximum of the latter one (i.e. the i+1th modality component) of the two adjacent modality components,/>Is the frequency minimum of the previous (i.e., i-th) of the two adjacent modal components.
In step S102, the hybrid energy storage response requirement and the decomposition layer number of the VMD algorithm are input to a trained prediction module for prediction to output the aliasing degree.
Step S103, setting an upper limit of iteration times, and obtaining a predicted value of the number of decomposition layers and a predicted value of the mixed response based on the aliasing degree, the number of decomposition layers, the mixed energy storage response requirement and the trained two reverse prediction modules, so as to obtain a corresponding error coefficient.
In step S103, based on the aliasing degree, the number of decomposition layers, the hybrid energy storage response requirement, and the trained two reverse prediction modules, a prediction value of the number of decomposition layers and a prediction value of the hybrid response are obtained, so as to obtain a corresponding error coefficient, which includes: inputting the aliasing degree and the decomposition layer number into a trained first reverse prediction module to obtain a hybrid energy storage response predicted value; obtaining a first error coefficient based on the hybrid energy storage response predicted value and the hybrid energy storage response requirement; inputting the aliasing degree and the hybrid energy storage response requirement into a trained second reverse prediction module to obtain a decomposition layer number prediction value; a second error coefficient is obtained based on the decomposition level prediction value and the decomposition level.
In step S103, the prediction module is trained using the second historical data set to obtain a trained first reverse prediction module. The first backward prediction module may also employ a GRU model. The second historical data set includes a historical hybrid energy storage response demand, a number of decomposition levels, and a degree of aliasing of the historical hybrid energy storage response demand. The input of the first backward prediction module is the aliasing degree and the decomposition layer number K of the historical hybrid energy storage response requirement, and the output is the historical hybrid energy storage response requirement. Samples of the second historical data set are, for example, > 20000, and after training is completed are referred to as a trained first backward prediction module.
In step S103, the trained input of the first inverse prediction module is the aliasing degree and the number of decomposition layers output by the trained prediction module, the output is a hybrid energy storage response predicted value, a first error coefficient is calculated based on the hybrid energy storage response predicted value and the hybrid energy storage response requirement, MAPE (Mean Absolute Percentage Error, average absolute percentage error) may be used in calculating the first error coefficient, and the first error coefficient may be expressed as MAPE a.
In step S103, the prediction module is trained using the third historical data set to obtain a trained second reverse prediction module. The second backward prediction module may also employ a GRU model. The third historical data set includes a historical hybrid energy storage response demand, a number of decomposition levels, and a degree of aliasing of the historical hybrid energy storage response demand. The inputs of the second backward prediction module are the aliasing degree of the historical hybrid energy storage response requirement and the historical hybrid energy storage response requirement, and the output is the decomposition layer number K. Samples of the third historical data set are, for example, > 20000, and after training is completed are referred to as a trained second backward prediction module.
In step S103, the trained second inverse prediction module inputs the aliasing degree and the hybrid energy storage response requirement output by the trained prediction module, the output is a decomposition layer number prediction value, a second error coefficient is calculated based on the decomposition layer number prediction value and the decomposition layer number, MAPE (Mean Absolute Percentage Error, average absolute percentage error) may also be used to calculate the second error coefficient, and the second error coefficient may be expressed as MAPE b.
Step S104, determining an error mean value based on the error coefficient, updating the current iteration number when the current iteration number or the error mean value meets the requirement, and adjusting the decomposition layer number and the hybrid energy storage response requirement to obtain a new error mean value until the current iteration number and the error mean value do not meet the requirement, thereby obtaining the target aliasing degree.
In step S104, the error average is the average of the first error coefficient and the second error coefficient. For example, the error mean z satisfies:
。
In step S104, the current iteration number meeting the requirement means that the current iteration number does not reach the upper limit of the iteration number, and the error mean meeting the requirement means that the error mean is greater than the error threshold.
In step S104, adjusting the decomposition level and the hybrid energy storage response requirement to obtain a new error mean value includes: determining a reverse modulation coefficient based on the error mean value, and updating the number of decomposition layers and the hybrid energy storage response requirement based on the reverse modulation coefficient; and obtaining a new decomposition layer number predicted value and a new mixed response predicted value based on the updated decomposition layer number and the updated mixed energy storage response requirement, so as to obtain a new error mean value.
Wherein, the inverse adjustment coefficient satisfies:
where β is the inverse coefficient, z is the mean value of the error, and rand () represents the random number.
In step S104, the number of decomposition layers is multiplied by the inverse adjustment coefficient to obtain an updated number of decomposition layers. And multiplying the hybrid energy storage response requirement by the inverse adjustment coefficient to obtain an updated hybrid energy storage response requirement.
In step S104, a target aliasing degree is obtained, including: calculating the ratio of the larger value to the smaller value in the first error coefficient and the second error coefficient; if the ratio is larger than the ratio threshold, the corresponding aliasing degree when the current iteration times and the error mean value do not meet the requirement is taken as the target aliasing degree; if the ratio is not greater than the ratio threshold, a correction coefficient is obtained based on the first error coefficient and the second error coefficient, and a target aliasing degree is obtained based on the correction coefficient and the corresponding aliasing degree when the current iteration number and the error mean value do not meet the requirements.
The ratio of the larger value to the smaller value in the first error coefficient and the second error coefficient is expressed as:
。
The correction coefficient satisfies:
Where α is a correction coefficient, MAPE a is a first error coefficient, and MAPE b is a second error coefficient.
In step S104, obtaining the target aliasing degree based on the correction coefficient and the corresponding aliasing degree when the current iteration number and the error mean value do not meet the requirement, including: and multiplying the correction coefficient by the corresponding aliasing degree when the current iteration times and the error mean value do not meet the requirement to obtain the target aliasing degree.
Taking any decomposition layer number within the set decomposition layer number range as an example, if the initial value of the iteration number is 1, the upper limit of the iteration number is 30, the error threshold is 6, and the ratio threshold is 2, as shown in fig. 2, the method for acquiring the corresponding target aliasing degree of a certain decomposition layer number includes:
inputting a signal X (i.e. hybrid energy storage response requirement), and determining the decomposition layer number K of the VMD algorithm; inputting the input signals and the number of decomposition layers into a trained prediction module to predict the aliasing degree Dk under the current K;
Inputting the aliasing degree Dk and the decomposition layer number K into a trained reverse prediction module a (namely a first reverse prediction module) to predict an input signal X' (namely a hybrid energy storage response predicted value), so as to obtain an error coefficient MAPE a;
Inputting the aliasing degree Dk and the input signal X into a trained reverse prediction module b (namely a second reverse prediction module) to predict the decomposition layer number K' (namely a decomposition layer number predicted value), so as to obtain an error coefficient MAPE b;
Judging whether the error mean value z is larger than an error threshold value 6 or whether the current iteration time t is smaller than the upper limit 30 of the iteration time or not, if yes, updating the iteration time (t=t+1), and calculating a reverse-tuning-coefficient reverse-tuning input signal X and a decomposition layer number K to obtain a new error coefficient MAPE a and an error coefficient MAPE b; until the error mean value z is smaller than or equal to the error threshold value 6 and the current iteration number t reaches the upper limit of the iteration number 30;
Calculating the ratio of the larger value to the smaller value in the first error coefficient and the second error coefficient; if the ratio is larger than the ratio threshold 2, taking the corresponding aliasing degree Dk when the current iteration times and the error mean value do not meet the requirement as a target aliasing degree; if the ratio is not greater than the ratio threshold 2, multiplying the correction coefficient alpha by the corresponding aliasing degree Dk when the current iteration times and the error mean value do not meet the requirements to obtain the target aliasing degree.
Step S105, updating the decomposition layer number based on the set decomposition layer number range to obtain the target aliasing degree corresponding to the different decomposition layer numbers.
In step S105, taking the case where the set decomposition layer number range is [4,12], the target aliasing degree corresponding to each decomposition layer number is obtained by processing in step S102 and step S104 for each decomposition layer number in the set decomposition layer number range [4,12 ].
And S106, selecting the decomposition layer number corresponding to the minimum value in all the target aliasing degrees as a target decomposition layer number, and decomposing the hybrid energy storage response requirement by utilizing a VMD algorithm based on the target decomposition layer number to obtain a target modal component and a residual component.
In step S106, a minimum target aliasing degree is selected from the target aliasing degrees corresponding to all the decomposition layers, and the decomposition layer corresponding to the minimum value of the target aliasing degree is the target decomposition layer.
As will be readily appreciated, the VMD algorithm is a completely non-recursive modal variation method that decomposes the original signal into a plurality of modal components with certain sparsity. The number of modal components obtained by decomposition is equal to the number of decomposition layers.
In step S106, the VMD algorithm is used to decompose the hybrid energy storage response requirement to obtain a plurality of target modal components, where the number of target modal components is equal to the number of target decomposition layers. And (3) carrying out difference on the sum of the hybrid energy storage response requirement and all the target modal components to obtain a residual component.
And step S107, dividing the target modal component and the residual component to obtain a high-frequency component and a low-frequency component, controlling the molten salt energy storage device to respond according to the high-frequency component and controlling the lithium battery to respond according to the low-frequency component.
In step S107, high and low frequency reconstruction is performed on the target modal component and the residual component according to the characteristics of the molten salt and the stabilized power fluctuation of the lithium battery. Specifically, in step S107, the target modal component and the residual component are divided to obtain a high-frequency component and a low-frequency component, including: rounding based on half of the target decomposition layer number to obtain a filtering order; and carrying out high-low frequency reconstruction on the target modal component and the residual component based on the filtering order, wherein the sum of the target modal components smaller than or equal to the filtering order is a high-frequency component, and the sum of all the target modal components larger than the filtering order and the residual component is a low-frequency component.
Considering that the high frequency component is stabilized by the molten salt and the low frequency component is stabilized by the lithium battery, specifically, in step S107, the molten salt energy storage device is controlled to respond according to the high frequency component and the lithium battery is controlled to respond according to the low frequency component. That is, the molten salt energy storage output P C of the molten salt energy storage device is equal to the high frequency component and the battery power P L is equal to the low frequency component.
To further verify the advantages of the algorithm of the present application, the algorithm of the present application and the conventional prediction method were used to decompose the fm instruction, respectively, and the results of the conventional model prediction D MAPE and the VMD prediction D MAPE of the present application are shown in table 1.
Table 1 error table
As can be seen from Table 1, the average prediction error of the algorithm provided by the application is 8.7, and the average prediction error of the traditional model is 15.5, so that the algorithm provided by the application greatly improves the prediction precision.
In order to achieve the embodiment, the application further provides a frequency modulation system of the fused salt coupling thermal power unit based on bidirectional predictive feedback regulation, and the hybrid energy storage device of the thermal power plant comprises fused salt energy storage equipment and a lithium battery.
Fig. 3 is a block diagram of a frequency modulation system of a fused salt coupled thermal power generating unit based on bidirectional predictive feedback regulation provided by an embodiment of the application.
As shown in fig. 3, the frequency modulation system of the fused salt coupled thermal power generating unit based on bidirectional predictive feedback adjustment comprises an acquisition module 11, a first prediction module 12, a second prediction module 13, a target aliasing degree determination module 14, an updating module 15, a selective decomposition module 16 and a control module 17, wherein:
an acquisition module 11, configured to determine a hybrid energy storage response requirement based on the frequency modulation instruction received in real time;
a first prediction module 12, configured to input the hybrid energy storage response requirement and the decomposition layer number of the VMD algorithm into a trained prediction module to predict the aliasing degree;
the second prediction module 13 is configured to set an upper limit of the iteration number, obtain a decomposition layer number predicted value and a hybrid response predicted value based on the aliasing degree, the decomposition layer number, the hybrid energy storage response requirement, and the trained two reverse prediction modules, and further obtain a corresponding error coefficient;
The target aliasing degree determining module 14 is configured to determine an error mean value based on the error coefficient, update the current iteration number when the current iteration number or the error mean value meets the requirement, and adjust the number of decomposition layers and the hybrid energy storage response requirement to obtain a new error mean value until the current iteration number and the error mean value do not meet the requirement, thereby obtaining a target aliasing degree;
an updating module 15, configured to update the decomposition layer number based on the set decomposition layer number range to obtain a target aliasing degree corresponding to different decomposition layer numbers;
the decomposition module 16 is configured to select a decomposition layer number corresponding to a minimum value in all target aliasing degrees as a target decomposition layer number, and decompose the hybrid energy storage response requirement by using a VMD algorithm based on the target decomposition layer number to obtain a target modal component and a residual component;
The control module 17 is configured to divide the target modal component and the residual component to obtain a high-frequency component and a low-frequency component, control the molten salt energy storage device to respond according to the high-frequency component, and control the lithium battery to respond according to the low-frequency component.
Further, in one possible implementation manner of the embodiment of the present application, the target aliasing degree determining module 14 is specifically configured to: inputting the aliasing degree and the decomposition layer number into a trained first reverse prediction module to obtain a hybrid energy storage response predicted value; obtaining a first error coefficient based on the hybrid energy storage response predicted value and the hybrid energy storage response requirement; inputting the aliasing degree and the hybrid energy storage response requirement into a trained second reverse prediction module to obtain a decomposition layer number prediction value; a second error coefficient is obtained based on the decomposition level prediction value and the decomposition level.
Further, in a possible implementation manner of the embodiment of the present application, in the target aliasing degree determining module 14, the current iteration number meets the requirement that the current iteration number does not reach the upper iteration number limit, and the error mean meets the requirement that the error mean is greater than the error threshold.
Further, in one possible implementation manner of the embodiment of the present application, in the target aliasing determining module 14, the adjusting the decomposition layer number and the hybrid energy storage response requirement to obtain the new error average value includes: determining a reverse modulation coefficient based on the error mean value, and updating the number of decomposition layers and the hybrid energy storage response requirement based on the reverse modulation coefficient; and obtaining a new decomposition layer number predicted value and a new mixed response predicted value based on the updated decomposition layer number and the updated mixed energy storage response requirement, so as to obtain a new error mean value.
Further, in a possible implementation manner of the embodiment of the present application, the target aliasing degree determining module 14 obtains a target aliasing degree, including: calculating the ratio of the larger value to the smaller value in the first error coefficient and the second error coefficient; if the ratio is larger than the ratio threshold, the corresponding aliasing degree when the current iteration times and the error mean value do not meet the requirement is taken as the target aliasing degree; if the ratio is not greater than the ratio threshold, a correction coefficient is obtained based on the first error coefficient and the second error coefficient, and a target aliasing degree is obtained based on the correction coefficient and the corresponding aliasing degree when the current iteration number and the error mean value do not meet the requirements.
It should be noted that, the foregoing explanation of the embodiment of the frequency modulation method of the fused salt coupled thermal power generating unit based on the bidirectional predictive feedback adjustment is also applicable to the frequency modulation system of the fused salt coupled thermal power generating unit based on the bidirectional predictive feedback adjustment of the embodiment, which is not described herein again.
In the embodiment of the application, the hybrid energy storage response requirement is determined based on the frequency modulation instruction received in real time; inputting the mixed energy storage response requirement and the decomposition layer number of the VMD algorithm into a trained prediction module to predict the aliasing degree; setting an upper limit of iteration times, and obtaining a predicted value of the number of decomposition layers and a predicted value of the mixed response based on the aliasing degree, the number of decomposition layers, the mixed energy storage response requirement and the trained two reverse prediction modules, so as to obtain a corresponding error coefficient; determining an error mean value based on the error coefficient, updating the current iteration number when the current iteration number or the error mean value meets the requirement, and adjusting the number of decomposition layers and the hybrid energy storage response requirement to obtain a new error mean value until the current iteration number and the error mean value do not meet the requirement, thereby obtaining a target aliasing degree; updating the decomposition layer number based on the set decomposition layer number range to obtain target aliasing degrees corresponding to different decomposition layer numbers; selecting the decomposition layer number corresponding to the minimum value in all the target aliasing degrees as a target decomposition layer number, and decomposing the hybrid energy storage response requirement by utilizing a VMD algorithm based on the target decomposition layer number to obtain a target modal component and a residual component; dividing the target modal component and the residual component to obtain a high-frequency component and a low-frequency component, controlling the molten salt energy storage device to respond according to the high-frequency component and controlling the lithium battery to respond according to the low-frequency component. Under the condition, the aliasing degree is obtained by utilizing the mixed energy storage response requirement, the decomposition layer number and the trained prediction module, and then the decomposition layer number prediction value and the mixed response prediction value are obtained by utilizing the trained two reverse prediction modules, so that the corresponding error coefficient is obtained; and then determining an error mean value based on the error coefficient, and iteratively adjusting the number of decomposition layers and the mixed energy storage response requirement when the current iteration number or the error mean value meets the requirement, so as to continuously optimize the aliasing degree output by the trained prediction module until the current iteration number and the error mean value do not meet the requirement, thereby obtaining a target aliasing degree, improving the accuracy of the target aliasing degree, and then selecting the minimum value in all the target aliasing degrees, wherein the target aliasing degree is the minimum at the moment, so that the aliasing condition among target modal components can be better avoided when the mixed energy storage response requirement is decomposed by utilizing a VMD algorithm based on the target decomposition layer number, and further improving the accuracy of the frequency modulation response. The mode of the application which utilizes the bidirectional predictive feedback regulation better solves the problem of larger prediction errors compared with the traditional single prediction.
In order to achieve the above embodiment, the present application further provides an electronic device, including: a processor, a memory communicatively coupled to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the methods provided by the previous embodiments.
In order to implement the above embodiment, the present application also proposes a computer-readable storage medium having stored therein computer-executable instructions, which when executed by a processor are configured to implement the method provided in the foregoing embodiment.
In order to implement the above embodiments, the present application also proposes a computer program product comprising a computer program which, when executed by a processor, implements the method provided by the above embodiments.
In the foregoing description of embodiments, reference has been made to the terms "one embodiment," "some embodiments," "example," "a particular example," or "some examples," etc., meaning that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present application, the meaning of "plurality" means at least two, for example, two, three, etc., unless specifically defined otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and additional implementations are included within the scope of the preferred embodiment of the present application in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order from that shown or discussed, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the embodiments of the present application.
Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.
It is to be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. As with the other embodiments, if implemented in hardware, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
Those of ordinary skill in the art will appreciate that all or a portion of the steps carried out in the method of the above-described embodiments may be implemented by a program to instruct related hardware, where the program may be stored in a computer readable storage medium, and where the program, when executed, includes one or a combination of the steps of the method embodiments.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing module, or each unit may exist alone physically, or two or more units may be integrated in one module. The integrated modules may be implemented in hardware or in software functional modules. The integrated modules may also be stored in a computer readable storage medium if implemented in the form of software functional modules and sold or used as a stand-alone product.
The above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, or the like. While embodiments of the present application have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the application, and that variations, modifications, alternatives and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the application.

Claims (10)

1. The frequency modulation method of the fused salt coupling thermal power unit based on bidirectional predictive feedback regulation is characterized in that a hybrid energy storage device configured in a thermal power plant comprises fused salt energy storage equipment and a lithium battery, and the frequency modulation method comprises the following steps:
determining a hybrid energy storage response requirement based on the frequency modulation instruction received in real time;
Inputting the mixed energy storage response requirement and the decomposition layer number of the VMD algorithm into a trained prediction module to predict the aliasing degree;
Setting an upper limit of iteration times, and obtaining a predicted value of the number of decomposition layers and a predicted value of the mixed response based on the aliasing degree, the number of decomposition layers, the mixed energy storage response requirement and the trained two reverse prediction modules, so as to obtain a corresponding error coefficient;
Determining an error mean value based on the error coefficient, updating the current iteration number when the current iteration number or the error mean value meets the requirement, and adjusting the number of decomposition layers and the hybrid energy storage response requirement to obtain a new error mean value until the current iteration number and the error mean value do not meet the requirement, thereby obtaining a target aliasing degree;
updating the decomposition layer number based on the set decomposition layer number range to obtain target aliasing degrees corresponding to different decomposition layer numbers;
Selecting the decomposition layer number corresponding to the minimum value in all the target aliasing degrees as a target decomposition layer number, and decomposing the hybrid energy storage response requirement by utilizing a VMD algorithm based on the target decomposition layer number to obtain a target modal component and a residual component;
Dividing the target modal component and the residual component to obtain a high-frequency component and a low-frequency component, controlling the molten salt energy storage device to respond according to the high-frequency component and controlling the lithium battery to respond according to the low-frequency component.
2. The frequency modulation method of the fused salt coupled thermal power generating unit based on bidirectional predictive feedback adjustment according to claim 1, wherein the two trained reverse prediction modules obtain a predicted value of the number of decomposition layers and a predicted value of the mixed response based on the aliasing degree, the number of decomposition layers and the mixed energy storage response requirement, and further obtain corresponding error coefficients, and the method comprises the following steps:
Inputting the aliasing degree and the decomposition layer number into a trained first reverse prediction module to obtain a hybrid energy storage response predicted value; obtaining a first error coefficient based on the hybrid energy storage response predicted value and the hybrid energy storage response requirement;
Inputting the aliasing degree and the hybrid energy storage response requirement into a trained second reverse prediction module to obtain a decomposition layer number prediction value; a second error coefficient is obtained based on the decomposition level prediction value and the decomposition level.
3. The frequency modulation method of the fused salt coupled thermal power generating unit based on bidirectional predictive feedback adjustment according to claim 1, wherein the fact that the current iteration number meets the requirement means that the current iteration number does not reach the upper limit of the iteration number, and the fact that the error mean meets the requirement means that the error mean is larger than the error threshold.
4. The method for frequency modulation of a fused salt coupled thermal power generating unit based on bidirectional predictive feedback regulation according to claim 1, wherein the steps of regulating the number of decomposition layers and the hybrid energy storage response requirement to obtain a new error mean value comprise:
Determining a reverse modulation coefficient based on an error mean value, and updating the number of decomposition layers and the hybrid energy storage response requirement based on the reverse modulation coefficient;
And obtaining a new decomposition layer number predicted value and a new mixed response predicted value based on the updated decomposition layer number and the updated mixed energy storage response requirement, so as to obtain a new error mean value.
5. The frequency modulation method of the fused salt coupled thermal power generating unit based on bidirectional predictive feedback regulation according to claim 4, wherein the inverse modulation coefficient satisfies:
where β is the inverse coefficient, z is the mean value of the error, and rand () represents the random number.
6. The frequency modulation method of a fused salt coupled thermal power generating unit based on bidirectional predictive feedback adjustment according to claim 2, wherein the obtaining the target aliasing degree comprises:
calculating the ratio of the larger value to the smaller value in the first error coefficient and the second error coefficient;
If the ratio is larger than a ratio threshold, taking the corresponding aliasing degree when the current iteration times and the error mean value do not meet the requirement as a target aliasing degree;
and if the ratio is not greater than the ratio threshold, obtaining a correction coefficient based on the first error coefficient and the second error coefficient, and obtaining a target aliasing degree based on the correction coefficient and the corresponding aliasing degree when the current iteration number and the error mean value do not meet the requirement.
7. The frequency modulation method of the fused salt coupled thermal power generating unit based on bidirectional predictive feedback regulation according to claim 6, wherein the correction coefficient satisfies:
Where α is a correction coefficient, MAPE a is a first error coefficient, and MAPE b is a second error coefficient.
8. Frequency modulation system of fused salt coupling thermal power generating unit based on two-way prediction feedback is adjusted, its characterized in that, the mixed energy storage device of thermal power plant configuration includes fused salt energy storage equipment and lithium cell, and frequency modulation system includes:
the acquisition module is used for determining the hybrid energy storage response requirement based on the frequency modulation instruction received in real time;
The first prediction module is used for inputting the hybrid energy storage response requirement and the decomposition layer number of the VMD algorithm into the trained prediction module to predict the aliasing degree;
The second prediction module is used for setting an upper limit of iteration times, and obtaining a decomposition layer number predicted value and a mixed response predicted value based on the aliasing degree, the decomposition layer number, the mixed energy storage response requirement and the trained two reverse prediction modules so as to obtain a corresponding error coefficient;
the target aliasing degree determining module is used for determining an error mean value based on the error coefficient, updating the current iteration number when the current iteration number or the error mean value meets the requirement, and adjusting the decomposition layer number and the hybrid energy storage response requirement to obtain a new error mean value until the current iteration number and the error mean value do not meet the requirement, so as to obtain the target aliasing degree;
The updating module is used for updating the decomposition layer number based on the set decomposition layer number range so as to obtain target aliasing degrees corresponding to different decomposition layer numbers;
The decomposition module is used for selecting the decomposition layer number corresponding to the minimum value in all the target aliasing degrees as a target decomposition layer number, and decomposing the hybrid energy storage response requirement by utilizing a VMD algorithm based on the target decomposition layer number to obtain a target modal component and a residual component;
The control module is used for dividing the target modal component and the residual component to obtain a high-frequency component and a low-frequency component, controlling the molten salt energy storage device to respond according to the high-frequency component and controlling the lithium battery to respond according to the low-frequency component.
9. An electronic device, comprising: a processor, and a memory communicatively coupled to the processor;
The memory stores computer-executable instructions;
The processor executes computer-executable instructions stored in the memory to implement the method of any one of claims 1-7.
10. A computer readable storage medium having stored therein computer executable instructions which when executed by a processor are adapted to carry out the method of any one of claims 1-7.
CN202410406707.6A 2024-04-07 2024-04-07 Frequency modulation method of fused salt coupling thermal power generating unit based on bidirectional predictive feedback adjustment Active CN117996789B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202410406707.6A CN117996789B (en) 2024-04-07 2024-04-07 Frequency modulation method of fused salt coupling thermal power generating unit based on bidirectional predictive feedback adjustment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202410406707.6A CN117996789B (en) 2024-04-07 2024-04-07 Frequency modulation method of fused salt coupling thermal power generating unit based on bidirectional predictive feedback adjustment

Publications (2)

Publication Number Publication Date
CN117996789A true CN117996789A (en) 2024-05-07
CN117996789B CN117996789B (en) 2024-06-11

Family

ID=90889262

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202410406707.6A Active CN117996789B (en) 2024-04-07 2024-04-07 Frequency modulation method of fused salt coupling thermal power generating unit based on bidirectional predictive feedback adjustment

Country Status (1)

Country Link
CN (1) CN117996789B (en)

Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170104344A1 (en) * 2015-10-08 2017-04-13 Johnson Controls Technology Company Electrical energy storage system with constant state-of charge frequency response optimization
CN115189370A (en) * 2022-07-18 2022-10-14 广东电网有限责任公司 Capacity allocation method and system for participating in frequency modulation by hybrid energy storage
CN117220302A (en) * 2023-07-25 2023-12-12 国电环境保护研究院有限公司 Fire-storage combined frequency modulation energy storage capacity optimal configuration method and system
CN117674199A (en) * 2024-02-01 2024-03-08 西安热工研究院有限公司 Novel power system frequency modulation method and system for super-capacitor coupled lithium battery
CN117674198A (en) * 2024-02-01 2024-03-08 西安热工研究院有限公司 Novel frequency modulation method and system for super-capacitor coupled lithium battery
CN117691630A (en) * 2024-02-04 2024-03-12 西安热工研究院有限公司 Novel power system frequency modulation method and system based on VMD-CEEMD
CN117691631A (en) * 2024-02-04 2024-03-12 西安热工研究院有限公司 Electric power frequency modulation method and system based on hybrid energy storage device
CN117691629A (en) * 2024-02-04 2024-03-12 西安热工研究院有限公司 Frequency modulation method and system for fused salt coupling thermal power generating unit
CN117713144A (en) * 2024-02-06 2024-03-15 西安热工研究院有限公司 Thermal power generating unit frequency modulation method and system based on molten salt energy storage
CN117811023A (en) * 2024-02-28 2024-04-02 西安热工研究院有限公司 Frequency modulation method and system for fused salt energy storage coupling thermal power generating unit
CN117833282A (en) * 2024-03-04 2024-04-05 西安热工研究院有限公司 Frequency modulation method and system for fused salt coupling thermal power generating unit

Patent Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170104344A1 (en) * 2015-10-08 2017-04-13 Johnson Controls Technology Company Electrical energy storage system with constant state-of charge frequency response optimization
CN115189370A (en) * 2022-07-18 2022-10-14 广东电网有限责任公司 Capacity allocation method and system for participating in frequency modulation by hybrid energy storage
CN117220302A (en) * 2023-07-25 2023-12-12 国电环境保护研究院有限公司 Fire-storage combined frequency modulation energy storage capacity optimal configuration method and system
CN117674199A (en) * 2024-02-01 2024-03-08 西安热工研究院有限公司 Novel power system frequency modulation method and system for super-capacitor coupled lithium battery
CN117674198A (en) * 2024-02-01 2024-03-08 西安热工研究院有限公司 Novel frequency modulation method and system for super-capacitor coupled lithium battery
CN117691630A (en) * 2024-02-04 2024-03-12 西安热工研究院有限公司 Novel power system frequency modulation method and system based on VMD-CEEMD
CN117691631A (en) * 2024-02-04 2024-03-12 西安热工研究院有限公司 Electric power frequency modulation method and system based on hybrid energy storage device
CN117691629A (en) * 2024-02-04 2024-03-12 西安热工研究院有限公司 Frequency modulation method and system for fused salt coupling thermal power generating unit
CN117713144A (en) * 2024-02-06 2024-03-15 西安热工研究院有限公司 Thermal power generating unit frequency modulation method and system based on molten salt energy storage
CN117811023A (en) * 2024-02-28 2024-04-02 西安热工研究院有限公司 Frequency modulation method and system for fused salt energy storage coupling thermal power generating unit
CN117833282A (en) * 2024-03-04 2024-04-05 西安热工研究院有限公司 Frequency modulation method and system for fused salt coupling thermal power generating unit

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
李卫国;焦盘龙;刘新宇;徐备;: "基于变分模态分解的储能辅助传统机组调频的容量优化配置", 电力系统保护与控制, no. 06, 16 March 2020 (2020-03-16) *
贾燕冰;郑晋;陈浩;严正;王金浩;常潇;: "基于集合经验模态分解的火-储联合调度调频储能容量优化配置", 电网技术, no. 09, 25 August 2018 (2018-08-25) *

Also Published As

Publication number Publication date
CN117996789B (en) 2024-06-11

Similar Documents

Publication Publication Date Title
CN117691629B (en) Frequency modulation method and system for fused salt coupling thermal power generating unit
CN117674198B (en) Frequency modulation method and system for super-capacitor coupling lithium battery
CN117691630B (en) VMD-CEEMD-based power system frequency modulation method and system
CN117674199B (en) Power system frequency modulation method and system of super-capacitor coupling lithium battery
CN117691631B (en) Electric power frequency modulation method and system based on hybrid energy storage device
CN117713144B (en) Thermal power generating unit frequency modulation method and system based on molten salt energy storage
CN117277357B (en) Novel thermal power energy storage frequency modulation method and system adopting flow battery and electronic equipment
CN113515884A (en) Distributed electric vehicle real-time optimization scheduling method, system, terminal and medium
CN117811023B (en) Frequency modulation method and system for fused salt energy storage coupling thermal power generating unit
CN117878974B (en) Frequency modulation method and system for fused salt energy storage coupling thermal power generating unit based on error feedback
CN117833282B (en) Frequency modulation method and system for fused salt coupling thermal power generating unit
CN118013235B (en) Energy storage auxiliary black start wind speed prediction method based on cyclic integrated error compensation
CN117996789B (en) Frequency modulation method of fused salt coupling thermal power generating unit based on bidirectional predictive feedback adjustment
CN117996787B (en) Frequency modulation method of fused salt coupling thermal power generating unit based on bidirectional prediction
CN117996788B (en) Frequency modulation method of fused salt coupling thermal power generating unit based on two-dimensional predictive feedback
CN117996786B (en) Frequency modulation method of fused salt coupling thermal power generating unit based on secondary correction
CN117878973B (en) Frequency modulation method and system for fused salt coupling thermal power generating unit
CN115378017A (en) Thermal power generating unit frequency modulation method and device based on flywheel lithium battery hybrid energy storage system
CN117878975B (en) Frequency modulation method and system for fused salt energy storage coupling thermal power generating unit based on predictive clustering
CN117977637B (en) Frequency modulation method and system for fused salt coupling thermal power generating unit
CN117977634B (en) Frequency modulation method and system for fused salt coupling thermal power generating unit based on double decomposition
CN115360768A (en) Power scheduling method and device based on muzero and deep reinforcement learning and storage medium
CN117878971B (en) Frequency modulation method and system for fused salt energy storage coupling thermal power generating unit
CN118157159B (en) Frequency modulation method and system for fused salt energy storage coupling thermal power generating unit
CN118174321A (en) Frequency modulation method and system for fused salt energy storage coupling thermal power generating unit based on VMD algorithm

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant