CN117277357B - Novel thermal power energy storage frequency modulation method and system adopting flow battery and electronic equipment - Google Patents

Novel thermal power energy storage frequency modulation method and system adopting flow battery and electronic equipment Download PDF

Info

Publication number
CN117277357B
CN117277357B CN202311562868.6A CN202311562868A CN117277357B CN 117277357 B CN117277357 B CN 117277357B CN 202311562868 A CN202311562868 A CN 202311562868A CN 117277357 B CN117277357 B CN 117277357B
Authority
CN
China
Prior art keywords
predicted
charge
state
sampling points
energy storage
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.)
Active
Application number
CN202311562868.6A
Other languages
Chinese (zh)
Other versions
CN117277357A (en
Inventor
李志鹏
寇水潮
杨沛豪
郭昊
燕云飞
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 CN202311562868.6A priority Critical patent/CN117277357B/en
Publication of CN117277357A publication Critical patent/CN117277357A/en
Application granted granted Critical
Publication of CN117277357B publication Critical patent/CN117277357B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • HELECTRICITY
    • H02GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02JCIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00Circuit arrangements for ac mains or ac distribution networks
    • H02J3/24Arrangements for preventing or reducing oscillations of power in networks
    • H02J3/241The oscillation concerning frequency
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10Complex mathematical operations
    • G06F17/15Correlation function computation including computation of convolution operations
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/22Matching criteria, e.g. proximity measures
    • HELECTRICITY
    • H01ELECTRIC ELEMENTS
    • H01MPROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
    • H01M8/00Fuel cells; Manufacture thereof
    • H01M8/04Auxiliary arrangements, e.g. for control of pressure or for circulation of fluids
    • H01M8/04298Processes for controlling fuel cells or fuel cell systems
    • H01M8/04694Processes for controlling fuel cells or fuel cell systems characterised by variables to be controlled
    • H01M8/04955Shut-off or shut-down of fuel cells
    • HELECTRICITY
    • H02GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02JCIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00Circuit arrangements for ac mains or ac distribution networks
    • H02J3/28Arrangements for balancing of the load in a network by storage of energy
    • H02J3/32Arrangements for balancing of the load in a network by storage of energy using batteries with converting means
    • HELECTRICITY
    • H02GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02JCIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J7/00Circuit arrangements for charging or depolarising batteries or for supplying loads from batteries
    • H02J7/0047Circuit arrangements for charging or depolarising batteries or for supplying loads from batteries with monitoring or indicating devices or circuits
    • H02J7/0048Detection of remaining charge capacity or state of charge [SOC]
    • HELECTRICITY
    • H02GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02JCIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J7/00Circuit arrangements for charging or depolarising batteries or for supplying loads from batteries
    • H02J7/34Parallel operation in networks using both storage and other dc sources, e.g. providing buffering
    • H02J7/345Parallel operation in networks using both storage and other dc sources, e.g. providing buffering using capacitors as storage or buffering devices
    • HELECTRICITY
    • H02GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02JCIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J2203/00Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
    • H02J2203/20Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Power Engineering (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Chemical Kinetics & Catalysis (AREA)
  • Sustainable Development (AREA)
  • General Chemical & Material Sciences (AREA)
  • Electrochemistry (AREA)
  • Algebra (AREA)
  • Chemical & Material Sciences (AREA)
  • Sustainable Energy (AREA)
  • Databases & Information Systems (AREA)
  • Software Systems (AREA)
  • Computing Systems (AREA)
  • Manufacturing & Machinery (AREA)
  • Artificial Intelligence (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Charge And Discharge Circuits For Batteries Or The Like (AREA)

Abstract

The application relates to the technical field of power grid frequency modulation, and particularly provides a novel thermal power energy storage frequency modulation method, a system and electronic equipment using a flow battery, wherein the method comprises the steps of determining hybrid energy storage response power after receiving a frequency modulation instruction; dividing the hybrid energy storage response power into a high-frequency component and a low-frequency component through an EEMD algorithm; determining target weights of various battery parameters of sampling points to be predicted and state of charge predicted values of the sampling points to be predicted so as to obtain a state of charge predicted value set of a set time length after the current moment; and judging the predicted state of charge value and the set state of charge range, and combining the high-frequency component and the low-frequency component to control the super capacitor and the flow battery to respond so that the state of charge of the flow battery does not exceed the set state of charge range, thereby reducing the influence on the service life of the battery.

Description

Novel thermal power energy storage frequency modulation method and system adopting flow battery and electronic equipment
Technical Field
The application relates to the technical field of power grid frequency modulation, in particular to a novel thermal power energy storage frequency modulation method, system and electronic equipment adopting a flow battery.
Background
For thermal power generating units, long-term frequency modulation can lead to increased coal consumption, reduced reliability and reduced operating life of the units. On the other hand, the high-quality and high-efficiency frequency modulation power supply is scarce, the coal-fired thermal power unit is still used as a main frequency modulation power supply at present, the large-scale new energy grid connection requirement is added, the environmental protection pressure restricts the unit adjustment capability, and the heat supply unit has the problems of 'electricity fixation by heat', and the like, so that the electric power frequency modulation requirement is further increased. However, the performance of the auxiliary frequency modulation energy storage equipment matched with the thermal power plant at present cannot meet the requirements on the efficiency and reliability of the unit, and the service life of a battery is greatly influenced when the auxiliary frequency modulation energy storage equipment participates in frequency modulation, so that the acquisition of the benefit of the power grid subsidy is influenced, and the economic benefit is lower.
Disclosure of Invention
The present application aims to solve, at least to some extent, one of the technical problems in the related art.
Therefore, a first object of the present application is to provide a novel thermal power energy storage frequency modulation method using a flow battery, so as to reduce the influence on the service life of the battery.
A second object of the present application is to provide a novel thermal power energy storage frequency modulation system using a flow battery.
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 novel thermal power energy storage frequency modulation method using a flow battery, a hybrid energy storage device configured in a thermal power plant includes the flow battery and a supercapacitor, and the frequency modulation method includes the following steps:
after receiving the frequency modulation instruction, determining hybrid energy storage response power;
dividing the hybrid energy storage response power into a high-frequency component and a low-frequency component through an EEMD algorithm;
obtaining target weights of various battery parameters of the sampling points to be predicted based on various battery parameters and charge states of all the sampling points in a set time before the sampling points to be predicted and various battery parameters of the sampling points to be predicted by utilizing the improved pearson correlation coefficient and the improved cosine similarity to obtain target battery parameters of the sampling points to be predicted, inputting the target battery parameters of the sampling points to be predicted into a trained prediction model to obtain charge state predicted values of the sampling points to be predicted, and obtaining a charge state predicted value set of the set time after the current time, wherein the sampling points to be predicted are the sampling points at the current time or any one of all the sampling points in the set time after the current time;
In a set time length after the current time, if the state of charge predicted value of the sampling point to be predicted in the state of charge predicted value set is in a state of charge set range, controlling the super capacitor to respond according to the high-frequency component and controlling the flow battery to respond according to the low-frequency component; otherwise, a super capacitor power compensation value is obtained based on the charge state predicted value, and the super capacitor is controlled to respond according to the super capacitor power compensation value and the high-frequency component, and the flow battery is controlled to stop running.
In the method of the first aspect of the present application, the cosine similarity is optimized by using normalized values of a plurality of battery parameters of the sampling points to be predicted, so as to obtain improved cosine similarity; and optimizing the pearson correlation coefficient by using the normalized values of various battery parameters of the sampling points to be predicted to obtain an improved pearson correlation coefficient.
In the method of the first aspect of the present application, the obtaining the target weights of the various battery parameters of the sampling points to be predicted includes: based on various battery parameters and charge states of all sampling points in a set time period before a sampling point to be predicted of the flow battery and normalized values of various battery parameters of the sampling point to be predicted, obtaining first similarity of various battery parameters by adopting improved cosine similarity, and obtaining second similarity of various battery parameters by sampling improved pearson correlation coefficients; and obtaining the target weights of the various battery parameters of the sampling points to be predicted based on the first similarity and the second similarity of the various battery parameters.
In the method of the first aspect of the present application, the prediction model employs a BP neural network.
In the method of the first aspect of the present application, the predictive model training step includes: based on various battery parameters and charge states in a set time before a sampling point at the current moment, obtaining a training error by using the BP neural network; and taking the initial weight and the initial threshold value of each neuron of the BP neural network and the total number of the neurons as position vectors of whales, taking the training error as an fitness function, adopting an improved whale algorithm to obtain the optimal weight, the optimal threshold value and the total number of the optimal neurons of each neuron, and obtaining a trained prediction model based on the total number of the optimal neurons, the optimal weight and the optimal threshold value.
In the method of the first aspect of the present application, the convergence factor of the whale algorithm is optimised using a maximum number of iterations, a natural logarithmic function, to obtain said improved whale algorithm.
In the method of the first aspect of the present application, the obtaining the supercapacitor power compensation value based on the state of charge predicted value includes: and if the state of charge predicted value is smaller than the lower limit of the state of charge setting range or larger than the upper limit of the state of charge setting range, acquiring the super-capacitor power compensation value based on the state of charge predicted value of the sampling point to be predicted in the state of charge predicted value set, the lower limit of the state of charge setting range and the rated capacity of the battery.
To achieve the above objective, in a second aspect of the present application, an embodiment provides a novel thermal power energy storage frequency modulation system using a flow battery, a hybrid energy storage device configured in a thermal power plant includes the flow battery and a super capacitor, the frequency modulation system includes:
the determining module is used for determining the hybrid energy storage response power after receiving the frequency modulation instruction;
the dividing module is used for dividing the hybrid energy storage response power into a high-frequency component and a low-frequency component through an EEMD algorithm;
the prediction module is used for obtaining target weights of various battery parameters of the sampling points to be predicted based on various battery parameters and charge states of all the sampling points in a set time before the sampling points to be predicted and various battery parameters of the sampling points to be predicted by utilizing the improved pearson correlation coefficient and the improved cosine similarity so as to obtain target battery parameters of the sampling points to be predicted, inputting the target battery parameters of the sampling points to be predicted into a trained prediction model so as to obtain a charge state predicted value of the sampling points to be predicted, and obtaining a charge state predicted value set of the set time after the current time, wherein the sampling points to be predicted are any one of the sampling points at the current time or the set time after the current time;
The control module is used for controlling the super capacitor to respond according to the high-frequency component and controlling the flow battery to respond according to the low-frequency component if the state-of-charge predicted value of the sampling point to be predicted in the state-of-charge predicted value set is within the state-of-charge set range within a set time period after the current moment; otherwise, a super capacitor power compensation value is obtained based on the charge state predicted value, and the super capacitor is controlled to respond according to the super capacitor power compensation value and the high-frequency component, and the flow battery is controlled to stop running.
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 set forth in the first aspect of the present application.
To achieve the above object, an embodiment of a fourth aspect of the present application proposes a computer-readable storage medium having stored therein computer-executable instructions for implementing the method proposed in the first aspect of the present application when being executed by a processor.
According to the novel thermal power energy storage frequency modulation method, the system, the electronic equipment and the storage medium adopting the flow battery, the super capacitor belongs to a power type energy storage device and is more suitable for high-frequency response, the flow battery belongs to an energy type energy storage device and is more suitable for low-frequency response, the hybrid energy storage response power is divided into the high-frequency component and the low-frequency component through an EEMD algorithm, the super capacitor is controlled to respond according to the high-frequency component and is controlled to respond according to the low-frequency component when the state of charge predicted value is in a state of charge setting range, so that the influence on the service life of the flow battery is reduced, in addition, the improved Pearson correlation coefficient and the improved cosine similarity are utilized, the target weights of various battery parameters of all sampling points in a set time period before the sampling point to be predicted and the various battery parameters of the sampling point to be predicted are obtained, so that the state of charge predicted is predicted, the degree of influence of different battery parameters on the state of charge is quantized, the state of charge is further accurately predicted, the state of charge is more accurately, the super state of charge is controlled when the state of charge predicted value is not in the state of charge setting range, the state of charge is controlled, the super capacitor is controlled to compensate the state of charge of the state of charge in the state of charge, the state of charge is not set, the super state of charge is controlled, and the flow battery is controlled according to the state of charge, and the flow battery is controlled to the state of the super capacitor is set.
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 present 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 diagram of connection between a thermal power plant and a power grid according to an embodiment of the present application;
fig. 2 is a schematic flow chart of a novel thermal power energy storage frequency modulation method using a flow battery according to an embodiment of the present application;
fig. 3 is a schematic flowchart of a novel thermal power energy storage frequency modulation method using a flow battery according to an embodiment of the present application;
fig. 4 is a graph of predicted values of states of charge within a set period of time after a current time provided in an embodiment of the present application;
fig. 5 is a graph of a change in state of charge of a flow battery according to an embodiment of the present disclosure during power absorption or compensation;
fig. 6 is a block diagram of a novel thermal power energy storage frequency modulation system employing a flow battery according to an embodiment of the present application.
Detailed Description
Embodiments of the present application are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the drawings are exemplary and intended for the purpose of explaining the present application and are not to be construed as limiting the present application.
The novel thermal power energy storage frequency modulation method and system adopting a flow battery in the embodiment of the application are described below with reference to the accompanying drawings.
At present, for a thermal power generating unit, long-term frequency modulation can lead to increased coal consumption, reduced reliability and reduced operation life of the unit. On the other hand, the high-quality and high-efficiency frequency modulation power supply is scarce, the coal-fired thermal power unit is still used as a main frequency modulation power supply at present, the large-scale new energy grid connection requirement is added, the environmental protection pressure restricts the unit adjustment capability, and the heat supply unit has the problems of 'electricity fixation by heat', and the like, so that the electric power frequency modulation requirement is further increased. However, the performance of the auxiliary frequency modulation energy storage equipment matched with the thermal power plant at present cannot meet the requirements on the efficiency and reliability of the unit, and the service life of a battery is greatly influenced when the auxiliary frequency modulation energy storage equipment participates in frequency modulation, so that the acquisition of the benefit of the power grid subsidy is influenced, and the economic benefit is lower. Based on the method, the embodiment of the application provides a novel thermal power energy storage frequency modulation method adopting a flow battery so as to reduce the influence on the service life of the battery.
In this application, a hybrid energy storage device configured for a thermal power plant includes a flow battery and a supercapacitor. The hybrid energy storage device assists the thermal power generating unit to participate in frequency modulation.
Fig. 1 is a schematic diagram of connection between a thermal power plant and a power grid according to an embodiment of the present application. As shown in fig. 1, a thermal power generating unit G is connected with a power grid through a bus, and a flow battery and a supercapacitor are connected with the power grid through a first converter and a second converter respectively and then connected with the bus. When the power grid issues a frequency modulation instruction, the frequency modulation instruction carries a load response requirement P T After receiving the frequency modulation instruction, the thermal power plant G uses the thermal power unit load P G In response, the flow battery responds with battery power P L In response, the super capacitor is powered with super capacity P C And responding.
Fig. 2 is a schematic flow chart of a novel thermal power energy storage frequency modulation method using a flow battery according to an embodiment of the present application. Fig. 3 is a schematic diagram of a specific flow chart of a novel thermal power energy storage frequency modulation method using a flow battery according to an embodiment of the present application.
As shown in fig. 2, the novel thermal power energy storage frequency modulation method adopting the flow battery comprises the following steps:
step S101, after receiving the frequency modulation instruction, determining the hybrid energy storage response power.
Specifically, in step S101, the thermal power plant load P is continuously acquired G (also called unit output), after receiving the frequency modulation command, obtaining the load response requirement P from the frequency modulation command T As shown in fig. 3, the load response requirement P is calculated T And the load P of the thermal power unit G Obtain the hybrid energy storage response power P by the difference value of (2) J (also known as stored energy output), i.e. P T -P G =P J
Step S102, the hybrid energy storage response power is divided into a high-frequency component and a low-frequency component through an EEMD algorithm.
Specifically, in step S102, considering that in the hybrid energy storage device, the super capacitor belongs to the power type energy storage device, the energy density is low but the power density is high, and the cycle number is large, it is suitable to compensate the load response requirement P T And the load P of the thermal power unit G A high frequency component of the difference of (2); the battery belongs to an energy type energy storage device, has low power density but large energy density, and is suitable for compensating the load response requirement P T And the load P of the thermal power unit G Is a low frequency component of the difference of (c). Therefore, the hybrid energy storage response power is transmitted into an energy storage control system, and the energy storage control system divides the hybrid energy storage response power into a high-frequency component and a low-frequency component through an integrated empirical mode decomposition (Ensemble Empirical Mode Decomposition, EEMD) algorithm so as to be convenient for follow-up based on an energy storage control instructionAnd regulating the charge and discharge of the flow battery and the super capacitor by using the high-frequency component and the low-frequency component.
Wherein, the hybrid energy storage response power P J Can be obtained after decomposition by EEMD algorithmIn which, in the process,is the component of the decomposed gamma-th eigenmode function (Intrinsic Mode Function, IMF)>Is the residual component after decomposition. And carrying out high-frequency and low-frequency reconstruction on the IMF component according to the characteristic of stabilizing power fluctuation of the flow battery and the super capacitor. Selecting proper filtering order, determining the sum of IMF components less than or equal to j as high-frequency component, stabilizing by super capacitor to obtain super capacitance power P C The sum of the IMF component and the residual allowance which are larger than j is a low-frequency component, and the IMF component and the residual allowance are stabilized by the flow battery, namely the battery power P L This can be expressed as:
where n is the number of IMF components, j represents a division factor, the division factor is generally rounded up after [ n/2] is half the number of IMF components, and k is time.
Step S103, determining target weights of various battery parameters of the sampling point to be predicted and the state of charge predicted value of the sampling point to be predicted so as to obtain a state of charge predicted value set of a set time length after the current time.
In step S103, considering that in the SOC (state of charge) prediction, the influence degree of different battery parameters (for example, battery current I, battery voltage U, and battery temperature T) on the SOC is different, the present application uses the modified pearson correlation coefficient and the modified cosine similarity to perform weight distribution on the different battery parameters, so as to quantify the influence degree of the different battery parameters.
Specifically, the improved pearson correlation coefficient and the improved cosine similarity are utilized, the target weights of various battery parameters of the sampling points to be predicted are obtained based on various battery parameters and charge states of all the sampling points in a set time period before the sampling points to be predicted and various battery parameters of the sampling points to be predicted, so as to obtain the target battery parameters of the sampling points to be predicted, the target battery parameters of the sampling points to be predicted are input into a trained prediction model to obtain the charge state predicted value of the sampling points to be predicted, so as to obtain a charge state predicted value set of the set time period after the current time, wherein the sampling points to be predicted are any one of the sampling points at the current time or the set time period after the current time.
In this embodiment, in step S103, the cosine similarity is improved in consideration of the complex relationship that has an influence on each other between different pearson correlation coefficients (e.g., the battery current I, the battery voltage U, and the battery temperature T) when the cosine similarity or pearson correlation coefficient is calculated. Specifically, the cosine similarity is optimized by using the normalized values of various battery parameters of the sampling points to be predicted, so that the cosine similarity is improved. And optimizing the pearson correlation coefficient by using the normalized values of various battery parameters of the sampling points to be predicted to obtain an improved pearson correlation coefficient.
Considering that the battery voltage, the battery current and the battery temperature are selected as inputs to predict the SOC value in general research, however, the influence degree of the battery voltage, the battery current and the current temperature on the SOC is different, so that the method adopts a quantization method to determine the correlation degree of three battery parameters and the SOC so as to improve the prediction precision of the SOC. Taking the number of all sampling points in a set period before the sampling point to be predicted as 300 as an example, various battery parameters including three types of parameters including battery current, battery voltage and battery temperature are taken as the example.
The modified cosine similarity satisfies:
in the method, in the process of the invention, l i Setting the first time length before the sampling point to be predictedOne battery parameter at i sampling points,l i u for respectively taking corresponding sampling points i 、I i Or T i In the time-course of which the first and second contact surfaces,is the voltage cosine similarity (also called voltage first similarity) q 1 Current cosine similarity (also called current first similarity) q 2 Temperature cosine similarity (also called temperature first similarity) q 3 。SOC i And setting the charge state at the ith sampling point in the duration before the sampling point to be predicted, wherein i=1, 2, … and 300.Um’、Im’、Tm' Battery Voltage at sampling points to be predicted respectivelyUmBattery currentImTemperature of currentTmIs included in the above formula (c).Xm' fetchl i Correspondence of uniform typeUm’、Im’、Tm'. The improved cosine similarity considers the mutual influence among the battery parameters, and improves the subsequent SOC prediction precision.
The improved pearson correlation coefficient satisfies:
in the method, in the process of the invention,L i setting a battery parameter at the ith sampling point in a time period before the sampling point to be predicted,L i u for respectively taking corresponding sampling points i 、I i Or T i In the time-course of which the first and second contact surfaces,is the Pirson correlation coefficient of voltage (also called voltage second similarity) q 1 ' current pearson correlation coefficient (also called current second similarity) q 2 ' temperature pearson correlation coefficient (also called temperature second similarity) q 3 ’。
In this embodiment, obtaining target weights of various battery parameters of a sampling point to be predicted includes: based on various battery parameters and charge states of all sampling points in a set time period before a sampling point to be predicted of the flow battery and normalized values of various battery parameters of the sampling point to be predicted, obtaining first similarity of various battery parameters by adopting improved cosine similarity, and obtaining second similarity of various battery parameters by sampling improved pearson correlation coefficients; the target weights of the various battery parameters of the sampling points to be predicted are obtained based on the first similarity and the second similarity of the various battery parameters.
The target weight satisfies:
in the method, in the process of the invention,time->Representing the target weights of the battery voltage, the battery current, and the current temperature, respectively. else is other ranges.
In step S103, after obtaining the target weights of the various battery parameters of the sampling point to be predicted, multiplying the various battery parameters of the sampling point to be predicted by the corresponding target weights to obtain the target battery parameters of the sampling point to be predicted. I.e. the target battery voltage at the sampling point to be predictedUm * Is thatUm * = *UmTarget battery currentIm * Is thatIm * =/>*ImTarget current temperatureTm * Is thatTm * =/>*Tm
Inputting the target battery parameters of the sampling point to be predicted into a trained prediction model to obtain a state of charge predicted value of the sampling point to be predicted, namely, the target battery voltage of the sampling point to be predictedUm * Target battery powerFlow ofIm * Target current temperatureTm * The SOC value of the sampling point to be predicted is obtained after the input data serving as the trained prediction model is input into the model m
In step S103, the sampling point to be predicted is any one of the sampling points (e.g., 300 sampling points) within the current time or the set time period (e.g., the future time period H after the current time).
When the sampling point to be predicted is the sampling point at the current time, the data for obtaining the target weights of the various battery parameters of the sampling point at the current time are various battery parameters and states of charge of 300 sampling points in a set time before the sampling point at the current time, and various battery parameters of the sampling point at the current time. The battery parameters and the states of charge of all sampling points in a set time period before the sampling point at the current moment are historical data, and the battery parameters of the sampling point at the current moment can be acquired in real time. At this time, the state of charge of the sampling point at the current moment is a predicted value of the state of charge obtained by using a prediction model.
Taking the next sampling point of the sampling point at the current moment as an example when the predicted sampling point is any one of all the sampling points in the set time period after the current moment, the data for obtaining the target weights of various battery parameters of the sampling point are various battery parameters and charge states of 300 sampling points in the set time period before the sampling point and various battery parameters of the sampling point. The battery parameters of 300 sampling points in the set duration before the sampling point include battery parameters of the sampling point at the current time and battery parameters of 299 before the sampling point at the current time, and the states of charge of 300 sampling points in the set duration before the sampling point include states of charge of the sampling point at the current time (which is a predicted value obtained by using a prediction model) and states of charge of 299 before the sampling point at the current time (which is historical data). The various battery parameters of the sampling point are battery voltage, battery current and battery temperature obtained by using the existing prediction method. When the rest 299 sampling points in the set duration after the current time are respectively used as sampling points to be predicted, the data required for calculating the target weight can be described by referring to the data in the next sampling point of the sampling point at the current time.
In step S103, after the corresponding state of charge predicted values are obtained by taking the sampling point at the current time and all the sampling points in the set time period after the current time as the sampling points to be predicted, a set of state of charge predicted values for the set time period after the current time can be obtained.
In this embodiment, in step S103, the state of charge predicted value is obtained using a prediction model. The predictive model uses a BP (Back Propagation) neural network.
In this embodiment, the prediction model training step includes: based on various battery parameters and charge states in a set time before a sampling point at the current moment, obtaining a training error by using a BP neural network; the initial weight and the initial threshold of each neuron of the BP neural network and the total number of the neurons are used as position vectors of the whales, training errors are used as fitness functions, an improved whale algorithm is adopted to obtain the optimal weight, the optimal threshold and the total number of the optimal neurons of each neuron, and a trained prediction model is obtained based on the total number of the optimal neurons, the optimal weight and the optimal threshold.
The BP neural network is a multi-layer feedforward network trained by an error back propagation algorithm, and comprises an input layer, an hidden layer and an output layer, wherein the BP neural network is divided into two stages of forward transmission and back propagation, a signal in the forward transmission is transmitted from the input layer to the output layer through the hidden layer through a series of calculation to calculate a predicted value, and if the error of the predicted value and an actual value does not reach a threshold value, the weight and the bias of the network are updated through the error back propagation, so that the error is reduced. The present application uses battery voltage, battery current, and battery temperature as input data, and SOC as output data. And transmitting various battery parameter input models in a set time period before the sampling point at the current moment to an output layer through an input layer and an implicit layer to calculate an output data predicted value during training, and obtaining a training error by combining the obtained state of charge in the corresponding time period. Training errors were used as a fitness function of the improved whale algorithm.
Conventional whale algorithms (Whale Optimization Algorithm, WOA) generally include surrounding a target prey, spiral location updating, and searching for prey. Taking the position of the whale of the seat nearest to the position of the target object as an optimal solution when surrounding the target object, and gradually updating the position of the whale of the seat aiming at approaching the position of the optimal solution, wherein the calculation formula of a mathematical model surrounding the target object is as follows:
in the method, in the process of the invention,Dfor the distance of the whale individual from the current optimal solution,is the globally optimal solution corresponding to the t-th iteration,>for the position of whale corresponding to the t-th iteration,Aas a result of the first coefficient of the coefficient,Cis a second coefficient>For the position of whale corresponding to iteration t+1, wherein +.>、/>,/>For the first random vector, +.>For the second random vector,>,/>all belong to [0,1 ]],/>For astringing factor, ++>,/>Is the maximum number of iterations.
In the spiral position update, the spiral path is expressed mathematically as follows, in the form of a spiral rise to the prey:
in the method, in the process of the invention,=|X*(t)-X(t)|,/>indicating the distance between whale and prey,bis a constant value, which is set to be a constant value,lis located at [ -1,1]Random numbers in between. The whale hunting time assumes that there is a 50% probability of whale to randomly choose between shrink wrap and spiral rise, optimizing whale position. The expression is as follows:
In searching for a prey, the mathematical model of the search for a prey stage is calculated as follows:
in the method, in the process of the invention,the positions of whale individuals randomly selected for the current iteration t.
In this embodiment, the convergence factor is determined by considering that the WOA algorithm is nonlinear during the evolutionary searchThe linear decrementing strategy can not fully embody the actual optimization searching process of the algorithm, so the application optimizes the convergence factor of the whale algorithm by using the maximum iteration times and natural logarithmic function, and proposes the early increase ++>Value increases the searching ability of WOA in the global solution space, later decrease +.>The values enable finer local development of WOA to obtain an improved whale algorithm (Improved Whale Optimization Algorithm, IWOA).
Optimized convergence factor employing such non-linear strategiesThe specific formula of (2) is:
where t is the current iteration,for maximum number of iterations, e is a natural constant, +.>Taking 1 to->. The global and local search capabilities of WOA can be better balanced based on an improved whale algorithm.
In this embodiment, the trained predictive model obtained in step S103 using the modified whale algorithm may be represented by IWA-BP. The specific process comprises the following steps:
1) Initializing: determining an initial structure of the BP neural network, the total number of neurons, and an initial weight and an initial threshold value of connected neurons, wherein the total number of neurons is in+hn+hn+on+on, and wherein in is the BP neural The number of neurons of the input layer of the network, hn is the number of neurons of the hidden layer of the BP neural network, and on is the number of neurons of the output layer of the BP neural network; converting the initial weight and initial threshold into position vector of head whale, setting population scale (20 head whale, for example), maximum iteration number (20 head whale, for example)T max =150), initial minimum and maximum weights, and convergence factor
2) Selecting a training error as an adaptation function of an improved whale algorithm, and recording a current optimal adaptation value and position information thereof;
3) Updating position information of whale bodies of the seat head, judging whether the iteration number reaches the maximum iteration number, if so, ending the algorithm; if not, adding 1 to the current iteration number t, and returning to the step 2);
4) Outputting an optimal solution, wherein the optimal solution comprises the optimal weight value, the optimal threshold value and the total number of the optimal neurons of each neuron, and taking the optimal weight value, the optimal threshold value and the total number of the optimal neurons obtained at the moment as the optimal parameters of the BP neural network to obtain a trained prediction model (IWOA-BP model).
In step S103, the obtained state of charge predicted value set of the set time period (e.g., the future H time period) after the current time is obtained, and the state of charge set range is obtained, wherein the lower limit of the state of charge set range is SOC min . The upper limit of the charge state setting range is SOC max
In step S103, the specific process of obtaining the state of charge predicted value set may also refer to fig. 3, in which, as illustrated in fig. 3, 300 sampling points in a set period of time are taken as an example, based on the voltage/current/temperature sampling data 300 times before the predicted time and the SOC data 300 times before the predicted time, a target weight is obtained by using the improved cosine similarity and the improved pearson correlation coefficient, and the target weight and the voltage/current/temperature sampling data at the predicted time are sent to the SOC predicted value outputted by the IWOA-BP model and sent to the control system.
And step S104, judging the predicted value of the state of charge and the set range of the state of charge, and combining the high-frequency component and the low-frequency component to control the super capacitor and the flow battery to respond so that the state of charge of the flow battery does not exceed the set range of the state of charge.
In step S104, it is considered that the number of cycle life times is continuously reduced as the battery charge/discharge depth is increased. Therefore, it is necessary to control the charge/discharge depth of the battery so as to be always within a suitable range (i.e., state of charge setting range) from the viewpoint of cost and battery life.
Specifically, in step S104, if the state of charge predicted value of the sampling point to be predicted in the set state of charge predicted value set is within the set state of charge range within a set period of time after the current time, the supercapacitor is controlled to respond according to the high-frequency component, and the flow battery is controlled to respond according to the low-frequency component; and otherwise, obtaining a super-capacitor power compensation value based on the charge state predicted value, and controlling the super-capacitor to respond according to the super-capacitor power compensation value and the high-frequency component and controlling the flow battery to stop running.
In this embodiment, obtaining the supercapacitor power compensation value based on the state of charge predicted value includes: and if the state of charge predicted value is smaller than the lower limit of the state of charge setting range or larger than the upper limit of the state of charge setting range, acquiring the super capacitor power compensation value based on the state of charge predicted value of the sampling point to be predicted in the state of charge predicted value set, the lower limit of the state of charge setting range and the rated capacity of the battery.
Fig. 4 is a graph of predicted state of charge values within a set period of time after a current time provided in an embodiment of the present application. The 0 moment is the current moment, the abscissa is time, and the ordinate is the state of charge predicted value.
As shown in FIG. 4, the predicted state of charge of the flow battery is within [ tau a-tau b ] for a future H-length after the current time]Lower limit SOC with period lower than state of charge setting range min . At [ τc- τd ]]Upper limit SOC for a period of time higher than a state of charge setting range max
Starting from the current time, if the time reaches [ tau a-tau b ]]During the period, the flow battery stops charging and discharging, namely P L =0, the missing power is compensated by the supercapacitor, and the specific compensation formula is:
wherein m is 0 For adjusting the coefficient, SOC (τ) is the state of charge predicted value of the sampling point corresponding to time τ in the set of state of charge predicted values m For the time when the state of charge predicted value is minimum, Q L Is the rated capacity of the flow battery. At [ tau a-tau b ]]Calculating the power compensation value P of the super capacitor in a period of time c1 compensation And the sum of the high-frequency components obtains first power, and the super capacitor is controlled to respond according to the first power and the flow battery is controlled to stop running.
Starting from the current time, if the time reaches [ τc- τd ]]During the period, the flow battery stops charging and discharging, namely P L =0, the missing power is compensated by the supercapacitor, and the specific compensation formula is:
τ in n The time when the predicted value of the charge state is maximum is [ τc- τd ]]Calculating the power compensation value P of the super capacitor in a period of time c2 compensation And obtaining second power by the sum of the high-frequency components, and controlling the super capacitor to respond according to the second power and controlling the flow battery to stop running.
And starting from the current moment, if the time is in other time periods except [ tau a-tau b ] and [ tau c-tau d ], the predicted value of the state of charge is in the set range of the state of charge, and at the moment, the super capacitor is controlled to respond according to the high-frequency component, and the flow battery is controlled to respond according to the low-frequency component.
Referring to fig. 3, the SOC predicted value outputted from the iwoa-BP model is sent to the control system, which controls the flow battery to stop charging/discharging at a time according to the predicted value part based on the processing of step S104 described above, and controls the supercapacitor to increase/decrease the output at a time according to the predicted value part.
In order to verify the effect of the method, SOC prediction model prediction capability verification is performed. The experimental data set is data of a lithium ion battery pack acquired in a certain power plant site. Among the collected data, the battery current, battery voltage, and battery temperature collection time interval is 1S, and the predicted period H is 100S, so that 100 pieces of data are collected for prediction. To verify the performance of the proposed model, three reference models, namely BP, WOA-BP, IWA-BP, were compared with the model of the present application (weight assignment-IWA-BP), respectively, at the time of the experiment. Four evaluation indexes are adopted to evaluate the quality of the predicted result. The four evaluation indexes are average absolute error (Mean absolute error, MAE), residual error square sum (Sum of Squares for Error, SSE), average absolute percent error (Mean absolute percentage error, MAPE) and root mean square error (Root mean square error, RMSE) which are taken as model evaluation standards.
The prediction index pairs of the reference model and the model proposed in the present application are shown in table 1.
Table 1 model predictive index comparison table
As shown in table 1, the model proposed in this application has the smallest error coefficient when compared to all other reference models. For example, the above conclusion can be drawn from the table, wherein the predicted average MAPE values are reduced by 82%,85.65%,85.56% respectively, over all baseline models. In all cases MAE, SSE, RMSE follows the same law. When comparing the model proposed in this application with IWAA-BP, the former had better predictive performance, and the average MAE value in the table was reduced by 94.34%. The reason for the reduction is that giving the input variable a target weight can better mine the nonlinear relation between the input variable and the predicted value and evaluate the influence degree of different variables on the predicted value. When the IWA-BP model is compared with the WOA-BP model, the IWA-BP model also improves the prediction precision of the WOA-BP model, and the reduction is caused by the fact that the improved convergence factor provided by the application can improve the global convergence capacity of the WOA algorithm. WOA-BP has satisfactory predictive performance compared with the BP model, which proves that the WOA algorithm well optimizes the weight and threshold of BP.
In addition, liquid flow is also carried outThe battery state of charge feedback control test comprises setting up a hybrid energy storage system model in Matlab/Simulink, wherein the energy storage system has the main parameters that BESS adopts a flow battery pack, rated capacity is 320Ah, and SOC max Set to 80%, SOC min Set to 20%. The SC capacitance value (supercapacitor) was 11F. Fig. 5 is a graph of a change in state of charge of a flow battery according to an embodiment of the present disclosure during power absorption or compensation. The SOC variation curve of the flow battery during power absorption or compensation is shown in fig. 5 below. It can be seen from fig. 5 (a) that if charge feedback control is not employed, SOC is continuously lower than 20% at around 295s in the circle, and after feedback control is employed, the flow battery stops discharging, and SOC is maintained around 20%. It is seen from fig. 5 (b) that if the charge feedback control is not employed, the SOC is continuously higher than 80% at around 290s in the circle, whereas after the feedback control is employed, the flow battery stops charging, and the SOC is maintained around 80%.
In order to achieve the above embodiment, the application further provides a novel thermal power energy storage frequency modulation system adopting a flow battery, and the hybrid energy storage device configured in the thermal power plant comprises the flow battery and a supercapacitor.
Fig. 6 is a block diagram of a novel thermal power energy storage frequency modulation system employing a flow battery according to an embodiment of the present application.
As shown in fig. 6, the novel thermal power energy storage frequency modulation system adopting the flow battery comprises a determining module 11, a dividing module 12, a predicting module 13 and a control module 14, wherein:
the determining module 11 is used for determining the hybrid energy storage response power after receiving the frequency modulation instruction;
a dividing module 12 for dividing the hybrid energy storage response power into a high frequency component and a low frequency component by an EEMD algorithm;
the prediction module 13 is configured to obtain target weights of various battery parameters of the sampling point to be predicted based on various battery parameters and states of charge of all the sampling points in a set period before the sampling point to be predicted and various battery parameters of the sampling point to be predicted by using the improved pearson correlation coefficient and the improved cosine similarity, so as to obtain target battery parameters of the sampling point to be predicted, and input the target battery parameters of the sampling point to be predicted into a trained prediction model to obtain a state of charge predicted value of the sampling point to be predicted, so as to obtain a set of state of charge predicted values of the set period after the current time, where the sampling point to be predicted is the sampling point at the current time or any one of all the sampling points in the set period after the current time;
The control module 14 is configured to control the supercapacitor to respond according to the high-frequency component and control the flow battery to respond according to the low-frequency component if the state-of-charge predicted value of the sampling point to be predicted in the set state-of-charge predicted value set is within a set state-of-charge range within a set period of time after the current moment; and otherwise, obtaining a super-capacitor power compensation value based on the charge state predicted value, and controlling the super-capacitor to respond according to the super-capacitor power compensation value and the high-frequency component and controlling the flow battery to stop running.
Further, in one possible implementation manner of the embodiment of the present application, in the prediction module 13, the cosine similarity is optimized by using the normalized values of the various battery parameters of the sampling points to be predicted, so as to obtain the improved cosine similarity; and optimizing the pearson correlation coefficient by using the normalized values of various battery parameters of the sampling points to be predicted to obtain an improved pearson correlation coefficient.
Further, in one possible implementation manner of the embodiment of the present application, in the prediction module 13, based on the multiple battery parameters and states of charge of all sampling points in a set period before the sampling point to be predicted of the flow battery and the normalized values of the multiple battery parameters of the sampling point to be predicted, the modified cosine similarity is adopted to obtain a first similarity of the various battery parameters, and the modified pearson correlation coefficient is sampled to obtain a second similarity of the various battery parameters; the target weights of the various battery parameters of the sampling points to be predicted are obtained based on the first similarity and the second similarity of the various battery parameters.
Further, in a possible implementation manner of the embodiment of the present application, in the prediction module 13, a BP neural network is used as a prediction model.
Further, in a possible implementation manner of the embodiment of the present application, in the prediction module 13, the prediction model training step includes: based on various battery parameters and charge states in a set time before a sampling point at the current moment, obtaining a training error by using a BP neural network; the initial weight and the initial threshold of each neuron of the BP neural network and the total number of the neurons are used as position vectors of the whales, training errors are used as fitness functions, an improved whale algorithm is adopted to obtain the optimal weight, the optimal threshold and the total number of the optimal neurons of each neuron, and a trained prediction model is obtained based on the total number of the optimal neurons, the optimal weight and the optimal threshold.
Further, in a possible implementation of the embodiment of the present application, in the prediction module 13, the convergence factor of the whale algorithm is optimized by using the maximum iteration number, natural logarithm function, so as to obtain an improved whale algorithm.
Further, in one possible implementation manner of the embodiment of the present application, if the state of charge predicted value is smaller than the lower limit of the state of charge setting range or greater than the upper limit of the state of charge setting range, the control module 14 obtains the supercapacitor power compensation value based on the state of charge predicted value of the sampling point to be predicted in the state of charge predicted value set, the lower limit of the state of charge setting range, and the rated capacity of the battery.
It should be noted that the foregoing explanation of the novel thermal power energy storage frequency modulation embodiment using the flow battery is also applicable to the novel thermal power energy storage frequency modulation system using the flow battery of this embodiment, and will not be repeated herein.
In the embodiment of the application, considering that the super capacitor belongs to the power type energy storage device and is more suitable for high-frequency response, the flow battery belongs to the energy type energy storage device and is more suitable for low-frequency response, the hybrid energy storage response power is divided into a high-frequency component and a low-frequency component through an EEMD algorithm, when the predicted state of charge value is in a state of charge setting range, the super capacitor is controlled to respond according to the high-frequency component and the flow battery is controlled to respond according to the low-frequency component, so that the influence on the service life of the flow battery is reduced.
In the embodiment of the application, the supercapacitor is coupled with the hybrid energy storage device formed by the flow battery to respectively compensate low-frequency components and high-frequency components. A charge state feedback control method is provided for the hybrid energy storage device, so that the flow battery can compensate power fluctuation and ensure that the charge state of the flow battery does not exceed a preset range. The service life of the flow battery is prolonged. In addition, the problem that the existing cosine similarity and the pearson correlation coefficient cannot reflect the mutual coupling influence between input variables is solved.
In order to achieve the above embodiments, the present application further proposes 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 further proposes a computer-readable storage medium, in which computer-executable instructions are stored, 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 descriptions of embodiments, descriptions of the terms "one embodiment," "some embodiments," "example," "particular example," or "some examples," etc., mean 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 present 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" is at least two, such as two, three, etc., unless explicitly 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, 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 each embodiment 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. Although 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 thermal power energy storage frequency modulation method adopting the flow battery is characterized in that a hybrid energy storage device configured in a thermal power plant comprises the flow battery and a super capacitor, and the frequency modulation method comprises the following steps:
after receiving the frequency modulation instruction, determining hybrid energy storage response power;
dividing the hybrid energy storage response power into a high-frequency component and a low-frequency component through an EEMD algorithm;
obtaining target weights of various battery parameters of the sampling points to be predicted based on various battery parameters and charge states of all the sampling points in a set time before the sampling points to be predicted and various battery parameters of the sampling points to be predicted by utilizing the improved pearson correlation coefficient and the improved cosine similarity to obtain target battery parameters of the sampling points to be predicted, inputting the target battery parameters of the sampling points to be predicted into a trained prediction model to obtain charge state predicted values of the sampling points to be predicted, and obtaining a charge state predicted value set of the set time after the current time, wherein the sampling points to be predicted are the sampling points at the current time or any one of all the sampling points in the set time after the current time;
In a set time length after the current time, if the state of charge predicted value of the sampling point to be predicted in the state of charge predicted value set is in a state of charge set range, controlling the super capacitor to respond according to the high-frequency component and controlling the flow battery to respond according to the low-frequency component; otherwise, a super capacitor power compensation value is obtained based on the charge state predicted value, and the super capacitor is controlled to respond according to the super capacitor power compensation value and the high-frequency component, and the flow battery is controlled to stop running.
2. The novel thermal power energy storage frequency modulation method adopting the flow battery according to claim 1, wherein the cosine similarity is optimized by using normalized values of various battery parameters of sampling points to be predicted to obtain improved cosine similarity; and optimizing the pearson correlation coefficient by using the normalized values of various battery parameters of the sampling points to be predicted to obtain an improved pearson correlation coefficient.
3. The method for modulating the energy storage frequency of the thermal power generation by using the flow battery according to claim 2, wherein the obtaining the target weights of the various battery parameters of the sampling point to be predicted comprises:
based on various battery parameters and charge states of all sampling points in a set time period before a sampling point to be predicted of the flow battery and normalized values of various battery parameters of the sampling point to be predicted, obtaining first similarity of various battery parameters by adopting improved cosine similarity, and obtaining second similarity of various battery parameters by sampling improved pearson correlation coefficients; and obtaining the target weights of the various battery parameters of the sampling points to be predicted based on the first similarity and the second similarity of the various battery parameters.
4. The novel thermal power energy storage frequency modulation method adopting a flow battery according to claim 3, wherein the prediction model adopts a BP neural network.
5. The method for modulating energy in thermal power storage using a flow battery according to claim 4, wherein the step of training the predictive model comprises:
based on various battery parameters and charge states in a set time before a sampling point at the current moment, obtaining a training error by using the BP neural network;
and taking the initial weight and the initial threshold value of each neuron of the BP neural network and the total number of the neurons as position vectors of whales, taking the training error as an fitness function, adopting an improved whale algorithm to obtain the optimal weight, the optimal threshold value and the total number of the optimal neurons of each neuron, and obtaining a trained prediction model based on the total number of the optimal neurons, the optimal weight and the optimal threshold value.
6. The method according to claim 5, wherein the convergence factor of the whale algorithm is optimized by using a natural logarithmic function with a maximum number of iterations to obtain the improved whale algorithm.
7. The method for modulating energy storage and frequency modulation of a thermal power plant according to claim 1, wherein obtaining the power compensation value of the super capacitor based on the state of charge predicted value comprises:
And if the state of charge predicted value is smaller than the lower limit of the state of charge setting range or larger than the upper limit of the state of charge setting range, acquiring the super-capacitor power compensation value based on the state of charge predicted value of the sampling point to be predicted in the state of charge predicted value set, the lower limit of the state of charge setting range and the rated capacity of the battery.
8. Novel thermal power energy storage frequency modulation system adopting flow battery, characterized in that, the hybrid energy storage device of thermal power plant configuration includes flow battery and supercapacitor, and frequency modulation system includes:
the determining module is used for determining the hybrid energy storage response power after receiving the frequency modulation instruction;
the dividing module is used for dividing the hybrid energy storage response power into a high-frequency component and a low-frequency component through an EEMD algorithm;
the prediction module is used for obtaining target weights of various battery parameters of the sampling points to be predicted based on various battery parameters and charge states of all the sampling points in a set time before the sampling points to be predicted and various battery parameters of the sampling points to be predicted by utilizing the improved pearson correlation coefficient and the improved cosine similarity so as to obtain target battery parameters of the sampling points to be predicted, inputting the target battery parameters of the sampling points to be predicted into a trained prediction model so as to obtain a charge state predicted value of the sampling points to be predicted, and obtaining a charge state predicted value set of the set time after the current time, wherein the sampling points to be predicted are any one of the sampling points at the current time or the set time after the current time;
The control module is used for controlling the super capacitor to respond according to the high-frequency component and controlling the flow battery to respond according to the low-frequency component if the state-of-charge predicted value of the sampling point to be predicted in the state-of-charge predicted value set is within the state-of-charge set range within a set time period after the current moment; otherwise, a super capacitor power compensation value is obtained based on the charge state predicted value, and the super capacitor is controlled to respond according to the super capacitor power compensation value and the high-frequency component, and the flow battery is controlled to stop running.
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.
CN202311562868.6A 2023-11-22 2023-11-22 Novel thermal power energy storage frequency modulation method and system adopting flow battery and electronic equipment Active CN117277357B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311562868.6A CN117277357B (en) 2023-11-22 2023-11-22 Novel thermal power energy storage frequency modulation method and system adopting flow battery and electronic equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311562868.6A CN117277357B (en) 2023-11-22 2023-11-22 Novel thermal power energy storage frequency modulation method and system adopting flow battery and electronic equipment

Publications (2)

Publication Number Publication Date
CN117277357A CN117277357A (en) 2023-12-22
CN117277357B true CN117277357B (en) 2024-01-26

Family

ID=89203082

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311562868.6A Active CN117277357B (en) 2023-11-22 2023-11-22 Novel thermal power energy storage frequency modulation method and system adopting flow battery and electronic equipment

Country Status (1)

Country Link
CN (1) CN117277357B (en)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117674199B (en) * 2024-02-01 2024-04-23 西安热工研究院有限公司 Power system frequency modulation method and system of super-capacitor coupling lithium battery
CN117691630B (en) * 2024-02-04 2024-04-30 西安热工研究院有限公司 VMD-CEEMD-based power system frequency modulation method and system
CN117811023B (en) * 2024-02-28 2024-07-02 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
CN117996788B (en) * 2024-04-03 2024-06-11 西安热工研究院有限公司 Frequency modulation method of fused salt coupling thermal power generating unit based on two-dimensional predictive feedback

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105226689A (en) * 2015-10-16 2016-01-06 中国电力科学研究院 Consider polymorphic type energy-storage system energy management method and the system of operation and maintenance
CN112103980A (en) * 2020-09-27 2020-12-18 中国科学院电工研究所 Energy management method of hybrid energy storage system combining AGC frequency modulation of thermal power generating unit
WO2021114849A1 (en) * 2019-12-12 2021-06-17 国网浙江省电力有限公司台州供电公司 Island power grid energy storage system hierarchical control method for ameliorating new energy power generation fluctuation
CN115036920A (en) * 2022-07-05 2022-09-09 东南大学 Capacity bidding method for mixed energy storage participating in frequency modulation auxiliary service market
WO2023005581A1 (en) * 2021-07-30 2023-02-02 西安热工研究院有限公司 Power distribution method for hybrid energy storage
CN115714435A (en) * 2022-11-14 2023-02-24 天津大学 Photovoltaic hybrid energy storage system power distribution and virtual inertia control method based on virtual synchronous generator

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105226689A (en) * 2015-10-16 2016-01-06 中国电力科学研究院 Consider polymorphic type energy-storage system energy management method and the system of operation and maintenance
WO2021114849A1 (en) * 2019-12-12 2021-06-17 国网浙江省电力有限公司台州供电公司 Island power grid energy storage system hierarchical control method for ameliorating new energy power generation fluctuation
CN112103980A (en) * 2020-09-27 2020-12-18 中国科学院电工研究所 Energy management method of hybrid energy storage system combining AGC frequency modulation of thermal power generating unit
WO2023005581A1 (en) * 2021-07-30 2023-02-02 西安热工研究院有限公司 Power distribution method for hybrid energy storage
CN115036920A (en) * 2022-07-05 2022-09-09 东南大学 Capacity bidding method for mixed energy storage participating in frequency modulation auxiliary service market
CN115714435A (en) * 2022-11-14 2023-02-24 天津大学 Photovoltaic hybrid energy storage system power distribution and virtual inertia control method based on virtual synchronous generator

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
基于荷电状态预测反馈的混合储能系统控制方法设计;宫毓斌;滕欢;潘晨;;科学技术与工程(第01期);全文 *
火电机组与储能系统联合自动发电控制调频技术及应用;牟春华;兀鹏越;孙钢虎;杨沛豪;陈世峰;王峥;常东锋;居文平;于洋;;热力发电(第05期);全文 *

Also Published As

Publication number Publication date
CN117277357A (en) 2023-12-22

Similar Documents

Publication Publication Date Title
CN117277357B (en) Novel thermal power energy storage frequency modulation method and system adopting flow battery and electronic equipment
CN107591844B (en) Active power distribution network robust reconstruction method considering node injection power uncertainty
CN112103980B (en) Energy management method of hybrid energy storage system combining AGC frequency modulation of thermal power generating unit
CN112510701A (en) Multi-energy ship energy management control device and method
CN110518580A (en) Active power distribution network operation optimization method considering micro-grid active optimization
CN105896575B (en) Hundred megawatt energy storage power control method and system based on self-adaptive dynamic programming
CN112507614A (en) Comprehensive optimization method for power grid in distributed power supply high-permeability area
CN113422375A (en) Double-layer coordination control method for stabilizing wind power fluctuation of hybrid energy storage system
Guo et al. Two‐stage optimal MPC for hybrid energy storage operation to enable smooth wind power integration
CN115236526A (en) Method and device for predicting residual charging time, storage medium and vehicle
Ramasamy et al. Energy management in plugin hybrid electric vehicles with hybrid energy storage system using hybrid approach
CN115169957A (en) Power distribution network scheduling method, device and medium based on deep reinforcement learning
Zhang et al. A review of energy management optimization based on the equivalent consumption minimization strategy for fuel cell hybrid power systems
CN117154906B (en) Wireless charging regulation and control method with refrigeration function
CN105119285B (en) Multiobjective optimization control method is coordinated in wind storage based on dynamic weight index
Kim et al. Optimize the operating range for improving the cycle life of battery energy storage systems under uncertainty by managing the depth of discharge
CN111651878B (en) Large power grid static voltage stability optimization decision method and system considering situation assessment
CN111516702B (en) Online real-time layered energy management method and system for hybrid electric vehicle
CN115001002B (en) Optimal scheduling method and system for solving problem of energy storage participation peak clipping and valley filling
Kamoona et al. Load-Sharing Management for Fuel Cell Hybrid Electric Vehicle (FCHEV) Based on Intelligent Controllers and Optimization Algorithms
CN117996789B (en) Frequency modulation method of fused salt coupling thermal power generating unit based on bidirectional predictive feedback adjustment
Lian et al. Real‐time energy management strategy for fuel cell plug‐in hybrid electric bus using short‐term power smoothing prediction and distance adaptive state‐of‐charge consumption
WO2024057581A1 (en) Charge-state calculation device
CN117220318B (en) Power grid digital driving control method and system
CN117878973B (en) Frequency modulation method and system for fused salt coupling thermal power generating unit

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