An over-capacity energy storage grid-connected method and system

Abstract

The application discloses an ultra-capacity energy storage grid-connected method and system, and belongs to the technical field of ultra-capacity energy storage. The method first acquires a current frequency modulation instruction sequence and calculates a fluctuation coefficient. Then, the fluctuation coefficient is input into a pre-trained error adjustment model to predict and obtain a final internal resistance increment. If the internal resistance increment exceeds a first preset value, the system will automatically mobilize lithium batteries for compensation. The training process of the error adjustment model involves using the fluctuation coefficient and the internal resistance increment sequence of the historical frequency modulation instruction sequence as a training set, constructing and optimizing the internal resistance fluctuation function until the average error rate is lower than a second preset value, thereby ensuring the accuracy of the model. The method aims to improve the performance and stability of the ultra-capacity energy storage system in grid frequency modulation.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of super-capacitive energy storage, and relates to a super-capacitive energy storage grid-connected method and system. BACKGROUND

[0002] In the power system, thermal power units serve as the main source of electricity generation, and their frequency modulation capability is crucial for maintaining the stability and reliability of the power grid. Traditional frequency modulation methods often rely on the adjustment capability of thermal power units themselves. However, due to the relatively slow response speed of thermal power units, it is difficult to quickly respond to rapid changes in grid frequency. In order to make up for this deficiency, hybrid energy storage systems (usually composed of super-capacitors and lithium batteries) are widely used to assist thermal power units in frequency modulation.

[0003] In the hybrid energy storage system, super-capacitors (super-capacitors) and lithium batteries each undertake different frequency modulation tasks. Specifically, super-capacitors, due to their high power density and fast charging and discharging capability, are mainly responsible for high-frequency part of the frequency modulation instruction, while lithium batteries, due to their high energy density, are more suitable for undertaking low-frequency part of the frequency modulation task. This division of labor and cooperation effectively improves the frequency modulation performance of thermal power units.

[0004] However, in actual application, the traditional hybrid energy storage assisted thermal power unit frequency modulation method has significant deficiencies. This method simply transmits the difference between the frequency modulation instruction and the thermal power unit to the hybrid energy storage system, with the super-capacitor undertaking the high-frequency part and the lithium battery undertaking the low-frequency part, but it ignores the impact of high-frequency volatility on the internal resistance of the super-capacitor.

[0005] The increase in internal resistance of the super-capacitor caused by high-frequency volatility can cause a series of negative effects. First, as the internal resistance increases, the energy loss of the super-capacitor during charging and discharging will also increase accordingly. This means that under the same conditions, the energy that the super-capacitor can store will decrease, i.e. its energy density will decrease. This not only reduces the overall efficiency of the energy storage system, but also may affect the stable operation of the power grid.

[0006] Secondly, the increase in internal resistance also has an adverse effect on the power performance of the super-capacitor. In the discharging process, a capacitor with a larger internal resistance needs to consume more energy to overcome the voltage drop caused by the internal resistance, resulting in a decrease in actual output power. This is undoubtedly a great challenge for high-frequency frequency modulation tasks that require fast response.

[0007] In addition, long-term increase in internal resistance may also accelerate the aging process of the internal materials of the super-capacitor, leading to a decrease in its service life. This not only increases the operation and maintenance cost, but also may pose a threat to the safe and stable operation of the power grid. At the same time, the increase in internal resistance may also increase the risk of damage to the capacitor under extreme conditions such as overcharging and overdischarging, further exacerbating the instability of its application.

[0008] It is worth noting that the specific relationship between the super-capacitor internal resistance and the frequency fluctuation is not fully considered in the existing control technology. This makes it difficult to accurately predict and evaluate the impact of high-frequency fluctuation on the performance of the super-capacitor in practical applications, and thus it is difficult to develop effective control measures to optimize the frequency modulation performance of the hybrid energy storage system. SUMMARY

[0009] The present application aims to solve the technical problem that the performance of the super-capacitor is reduced due to the fact that the specific relationship between the super-capacitor internal resistance and the frequency fluctuation is not considered in the prior art, and the frequency modulation instruction fluctuates greatly, and to provide a super-capacitor energy storage grid-connected method and system.

[0010] To achieve the above-mentioned purpose, the following technical solutions are adopted in the present application:

[0011] The present application provides a super-capacitor energy storage grid-connected method in the first aspect, comprising the following steps:

[0012] Obtaining a current frequency modulation instruction sequence;

[0013] Based on the current frequency modulation instruction sequence, the fluctuation coefficient of the current frequency modulation instruction sequence is calculated;

[0014] The fluctuation coefficient is input into the pre-trained error adjustment model to obtain the final internal resistance increment;

[0015] If the final internal resistance increment is greater than a first preset value, the lithium battery is mobilized for compensation;

[0016] The pre-trained error adjustment model has the following specific training method:

[0017] The fluctuation coefficient sequence of the historical frequency modulation instruction sequence and the internal resistance increment sequence corresponding to the historical frequency modulation instruction are used as a training set;

[0018] An internal resistance fluctuation function representing the relationship between the internal resistance fluctuation and the fluctuation coefficient is constructed, and the internal resistance fluctuation function is initialized;

[0019] The training set is used to train the error adjustment model. In the training, the fluctuation coefficient sequence is input into the internal resistance fluctuation function, and the average error rate is calculated in combination with the internal resistance increment sequence. If the average error rate is greater than a second preset value, the internal resistance fluctuation function is corrected until the average error rate is less than the second preset value, and the trained error adjustment model is obtained.

[0020] Further, the calculation of the fluctuation coefficient of the current frequency modulation instruction sequence is specific to:

[0021] An approximation function of the current frequency modulation instruction sequence is constructed, and the approximation function is initialized;

[0022] Based on the current frequency modulation command sequence and the approximation function, calculate the approximation error sequence. When the mean of the approximation error sequence is greater than the preset mean, update the approximation function. Iterate this step until the mean of the approximation error is less than the preset mean, and obtain the final approximation function and the number of iterations.

[0023] Find the first derivative of the final approximation function to obtain the first approximation derivative; calculate the number of solutions when the first approximation derivative is zero;

[0024] The fluctuation coefficient is obtained based on the number of solutions and the number of iterations when the first-order approximation derivative is zero.

[0025] Furthermore, the approximation function after initialization for:

[0026] Among them, the highest digit coefficient Second highest coefficient and last coefficient All are random values; This represents the value at each position in the current frequency modulation command sequence.

[0027] Furthermore, the approximation error sequence is as follows:

[0028]

[0029] in, For the first The approximation error sequence of each iteration; The current frequency modulation command sequence is the i The value of the position; For the first During the next iteration The approximate function value; ; The length of the current frequency modulation command sequence.

[0030] Furthermore, the mean of the approximation error sequence is described as follows:

[0031]

[0032] in, For the first The mean of the approximation error sequence in each iteration.

[0033] Furthermore, the updated approximation function is specifically as follows:

[0034]

[0035] in, For the first The approximation function for the next iteration;

[0036] ;

[0037] ;

[0038] ;

[0039] wherein, is a random number function; represents the coefficient of the th iteration of the approximation function at the th bit; represents the coefficient of the th iteration of the approximation function at the th bit; represents the coefficient of the th iteration of the approximation function at the th bit; represents th power of ; is the Euler number; represents the coefficient of the th iteration of the approximation function at the th bit; represents the coefficient of the th iteration of the approximation function at the th bit; represents the coefficient of the th iteration of the approximation function at the th bit; represents the coefficient of the th iteration of the approximation function at the th bit.

[0040] Further, the internal resistance fluctuation function is described as:

[0041]

[0042] wherein, is the internal resistance fluctuation function of the th cycle, represents the cycle number;

[0043] ;

[0044] ;

[0045] ;

[0046] ;

[0047] ;

[0048] ;

[0049] wherein, represents the average error, , is the internal resistance increment during the first frequency modulation of the first cycle; M is the length of the fluctuation coefficient sequence of the historical frequency modulation instruction sequence; is an activation function; is a random function; max() is a maximum value function; is the supplementary coefficient of the first cycle; is the supplementary coefficient of the first cycle; is the correction coefficient of the first cycle; is the compensation coefficient of the first cycle; is the correction term of the first cycle; is the compensation term of the first cycle; is the make-up value of the first cycle; is the average error rate of the first cycle; is the correction term of the first cycle; is the compensation term of the first cycle.

[0050] Further, the average error rate, in particular:

[0051]

[0052] wherein, is the internal resistance increment during the first frequency modulation of the first cycle; is the length of the fluctuation coefficient sequence of the historical frequency modulation instruction sequence.

[0053] The second aspect of the present application provides a computer storage medium, which stores instructions, when the instructions are executed, the super-capacitive energy storage grid-connected method is realized.

[0054] The third aspect of the present application provides a super-capacitive energy storage grid-connected system, comprising:

[0055] The data acquisition module is used for acquiring the current frequency modulation instruction sequence;

[0056] A fluctuation coefficient calculation module is configured to calculate a fluctuation coefficient of the current frequency modulation instruction sequence based on the current frequency modulation instruction sequence.

[0057] An internal resistance measurement module is configured to input the fluctuation coefficient into a pre-trained error adjustment model to obtain a final internal resistance increment.

[0058] A grid-connected module is configured to mobilize the lithium battery to compensate if the final internal resistance increment is greater than a first preset value.

[0059] The pre-trained error adjustment model is specifically trained in the following manner:

[0060] The fluctuation coefficient sequence of the historical frequency modulation instruction sequence and the internal resistance increment sequence corresponding to the historical frequency modulation instruction are taken as a training set.

[0061] An internal resistance fluctuation function representing the relationship between the internal resistance fluctuation and the fluctuation coefficient is constructed, and the internal resistance fluctuation function is initialized.

[0062] The error adjustment model is trained using the training set, and in the training process, the fluctuation coefficient sequence is input into the internal resistance fluctuation function, and the average error rate is calculated in combination with the internal resistance increment sequence; if the average error rate is greater than a second preset value, the internal resistance fluctuation function is corrected until the average error rate is less than the second preset value, and the trained error adjustment model is obtained.

[0063] Compared with the prior art, the present application has the following beneficial effects:

[0064] The present application discloses a kind of super-capacitor energy storage grid-connected methods, by pre-trained error adjustment model, can accurately predict and adjust the fluctuation value generated by frequency modulation instruction, ensure that final fluctuation value is in preset range, to effectively improve the stability of super-capacitor energy storage grid-connected system.When final fluctuation value exceeds preset value, the present application can intelligently call lithium battery to compensate, avoid the energy waste and equipment loss caused by fluctuation too large, optimize energy utilization efficiency.In the training process of error adjustment model, by calculating fluctuation coefficient, detecting internal resistance increment, and iterative calculation until average error rate meets preset condition, so that model can more accurately reflect actual power grid state, improve the prediction accuracy and robustness of model.The present application can more comprehensively consider the influence of frequency modulation instruction on power grid by introducing the calculation of approximation error and fluctuation coefficient, enhances the adaptability of system to different frequency modulation instructions, improves the flexibility and reliability of system.

[0065] Further, the application provides an ultra-capacity energy storage grid-connected system. The fluctuation calculation module uses a pre-trained error adjustment model to accurately predict the grid fluctuation caused by the frequency modulation instruction and calculate the final fluctuation value. This mechanism effectively reduces the risk of grid instability caused by acquisition errors, improves grid connection accuracy and system stability. When the final fluctuation value exceeds the preset threshold, the grid connection module can quickly mobilize the lithium battery for compensation to ensure that the grid fluctuation is controlled within a safe range. This intelligent compensation strategy not only avoids the negative impact of grid fluctuation on system stability, but also optimizes energy distribution and improves energy utilization efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0066] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0067] Figure 1 The block diagram of the ultra-capacity energy storage grid connection method of the present application;

[0068] Figure 2 The block diagram of the ultra-capacity energy storage grid connection system of the present application.

[0069] Among them, 201-data acquisition module; 202-fluctuation coefficient calculation module; 203-internal resistance measurement module; 204-grid connection module. DETAILED DESCRIPTION

[0070] In order to make the purpose, technical scheme and advantages of the embodiments of the present application more clear, the following will combine the drawings in the embodiments of the present application to clearly and completely describe the technical scheme in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all. The components of the embodiments of the present application described and indicated in the drawings here can be arranged and designed in various different configurations.

[0071] Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed application, but only represents selected embodiments of the present application. All other embodiments obtained by those skilled in the art without creative labor on the basis of the embodiments in the present application belong to the scope of protection of the present application.

[0072] It should be noted that: similar labels and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.

[0073] The application will be described in further detail below with reference to the drawings:

[0074] Referring to Figure 1 One embodiment of the application discloses an over-capacity energy storage grid-connected method, comprising the following steps:

[0075] S1, obtaining a current frequency modulation instruction sequence; obtaining the current frequency modulation instruction sequence from a power grid dispatching center.

[0076] S2, calculating a fluctuation coefficient of the current frequency modulation instruction sequence based on the current frequency modulation instruction sequence;

[0077] S3, inputting the fluctuation coefficient into a pre-trained error adjustment model to obtain a final internal resistance increment;

[0078] The specific training method of the pre-trained error adjustment model is as follows:

[0079] The fluctuation coefficient sequence of the historical frequency modulation instruction sequence and the internal resistance increment sequence corresponding to the historical frequency modulation instruction are taken as a training set;

[0080] An internal resistance fluctuation function of internal resistance fluctuation and fluctuation coefficient is constructed; and the internal resistance fluctuation function is initialized;

[0081] The fluctuation coefficient sequence is input into the internal resistance fluctuation function, and the average error rate is calculated in combination with the internal resistance increment sequence; if the average error rate is greater than a second preset value, the internal resistance fluctuation function is corrected until the average error rate is less than the second preset value, and the trained error adjustment model is obtained.

[0082] S4, if the final internal resistance increment is greater than a first preset value, lithium batteries are mobilized for compensation.

[0083] The embodiment can accurately capture the dynamic change characteristics of the power grid frequency by obtaining the frequency modulation instruction sequence of the power grid dispatching center in real time and calculating the fluctuation coefficient. In combination with the pre-trained error adjustment model, the internal resistance increment caused by the collection error can be accurately predicted, so that the fine regulation and control of the charging and discharging process of the over-capacity energy storage system can be realized. This not only improves the response speed of the power grid frequency modulation, but also significantly improves the frequency modulation accuracy, which is helpful to maintain the stability of the power grid frequency. In combination with the lithium battery compensation mechanism, the lithium batteries can be automatically mobilized for compensation when the final internal resistance increment exceeds the preset value, so that the energy storage system can always be kept in the best working state. This not only realizes the intelligent scheduling of the energy storage system, but also reduces unnecessary energy loss, and achieves the purpose of energy saving and consumption reduction.

[0084] One embodiment of the application provides an over-capacity energy storage grid-connected method, specifically:

[0085] S1, obtaining a current frequency modulation instruction sequence;

[0086] S2, Calculate the fluctuation coefficient of the current frequency modulation command sequence based on the current frequency modulation command sequence;

[0087] S201, Construct an approximation function for the current frequency modulation command sequence; initialize the approximation function; the initialized approximation function is:

[0088] Among them, the highest digit coefficient Second highest coefficient and last coefficient All values ​​are random.

[0089] S202, based on the current frequency modulation command sequence and the approximation function, calculate the approximation error sequence. When the mean of the approximation error sequence is greater than the preset mean, update the approximation function. Iterate this step until the mean of the approximation error is less than the preset mean, and obtain the final approximation function and the number of iterations.

[0090] The approximation error sequence is as follows:

[0091]

[0092] in, For the first The approximation error sequence of each iteration; The current frequency modulation command sequence is the i The value of the position; For the first During the next iteration The approximate function value; ; The length of the current frequency modulation command sequence.

[0093] The mean of the approximation error sequence is described as follows:

[0094]

[0095] in, For the first The mean of the approximation error sequence in each iteration. The updated approximation function is specifically:

[0096]

[0097] in, For the first The approximation function of the next iteration; the highest-order coefficient It is a random value;

[0098] ;

[0099] ;

[0100] ;

[0101] wherein, is a random number function; represents the coefficient of the th iteration of the approximation function at the th bit; represents the coefficient of the th iteration of the approximation function at the th bit; represents the coefficient of the th iteration of the approximation function at the th bit; represents th power of , wherein is Euler number; represents the coefficient of the th iteration of the approximation function at the th bit; represents the coefficient of the th iteration of the approximation function at the th bit; represents the coefficient of the th iteration of the approximation function at the th bit; represents the coefficient of the th iteration of the approximation function at the th bit.

[0102] S203, the first order derivative of the final approximation function is obtained, and the number of intersection points of the first order approximation derivative and the X axis (that is, the number of solutions when the first order approximation derivative is zero) is calculated;

[0103] S204, based on the number of intersection points and the number of iterations, the fluctuation coefficient is obtained.

[0104] S3, the fluctuation coefficient is input into the pre-trained error adjustment model to obtain the final internal resistance increment;

[0105] S301, the fluctuation coefficient sequence of the historical frequency modulation instruction sequence and the internal resistance increment sequence corresponding to the historical frequency modulation instruction are taken as a training set;

[0106] S302, an internal resistance fluctuation function of internal resistance fluctuation and fluctuation coefficient is constructed; and the internal resistance fluctuation function is initialized;

[0107] The internal resistance fluctuation function is described as:

[0108]

[0109] wherein, the internal resistance fluctuation function, represent the number of cycles;

[0110] ;

[0111] ;

[0112] ;

[0113] ;

[0114] ;

[0115] ;

[0116] wherein, represents the average error, , is the internal resistance increment during the first frequency adjustment of the first cycle; M is the length of the fluctuation coefficient sequence of the historical frequency adjustment instruction sequence; is an activation function; is a random function; max() is a maximum value function; is the supplementary coefficient of the first cycle; is the supplementary coefficient of the first cycle; is the correction coefficient of the first cycle; is the compensation coefficient of the first cycle; is the correction term of the first cycle; is the compensation term of the first cycle; is the make-up value of the first cycle; is the average error rate of the first cycle; is the correction term of the first cycle; is the compensation term of the first cycle.

[0117] S303, the error adjustment model is trained using the training set, and in the training, the fluctuation coefficient sequence is brought into the internal resistance fluctuation function and the average error rate is calculated in combination with the internal resistance increment sequence; if the average error rate is greater than a second preset value, the internal resistance fluctuation function is corrected until the average error rate is less than the second preset value, and a trained error adjustment model is obtained. The calculation of the average error rate is specifically:

[0118]

[0119] in, For the first The corresponding iteration of the 1st cycle The internal resistance increment during the second frequency modulation period, here is the first The frequency modulation period refers to each frequency modulation corresponding to the historical frequency modulation command sequence of the training set. The length of the fluctuation coefficient sequence of the historical frequency modulation command sequence.

[0120] S4. If the final internal resistance increment is greater than the first preset value, then the lithium battery compensation is activated.

[0121] One embodiment of the present invention provides a method for grid connection of supercapacity energy storage, specifically:

[0122] S1, let pci=[ , , ,..., [This refers to the instructions handled by the supercapacitor during a certain frequency modulation process; initialization iteration count] =1.

[0123] Let the initial approximation function be: ; , and All The coefficients at time, where, These are the highest-order coefficients of the approximation function in the first iteration; These are the second-highest coefficients of the approximation function in the first iteration; These are the last coefficients of the approximation function in the first iteration; , and All are given randomly. Substitute get ,Bundle Substitute get ,Bundle Substitute get , ,Bundle Substitute get ; The length of the current frequency modulation command sequence; This is the value of the first bit in the current frequency modulation command sequence; This is the value of the second bit in the current frequency modulation command sequence; This is the value of the 3rd bit in the current frequency modulation command sequence; The current frequency modulation command sequence is the the value of the first bit of the current frequency modulation instruction sequence; the approximation function value of the value of the first bit of the current frequency modulation instruction sequence in the first iteration; the approximation function value of the value of the second bit of the current frequency modulation instruction sequence in the first iteration; the approximation function value of the value of the third bit of the current frequency modulation instruction sequence in the first iteration; the approximation function value of the value of the fourth bit of the current frequency modulation instruction sequence in the first iteration; the approximation function value of the value of the fifth bit of the current frequency modulation instruction sequence in the first iteration.

[0124] the approximation error sequence of the first iteration is :

[0125]

[0126] Based on this, the mean value of the approximation error sequence of the first iteration is :

[0127] .

[0128] If the mean value of the approximation error sequence of the first iteration is greater than the preset mean value 0.2, the approximation function is updated, and the approximation function in the second iteration is:

[0129]

[0130] wherein, is a random value, ;

[0131] ;

[0132] ; is the highest bit coefficient of the approximation function in the second iteration; is the second highest bit coefficient of the approximation function in the second iteration; is the third highest bit coefficient of the approximation function in the second iteration; is the last bit coefficient of the approximation function in the second iteration; denotes the approximation function in the second iteration; is a random function; is Euler's number.

[0133] Next, the is brought into to obtain , the is brought into to obtain , the is brought into to obtain ,......, put into get ; is the approximation function value of the first bit of the current frequency modulation instruction sequence in the second iteration; is the approximation function value of the second bit of the current frequency modulation instruction sequence in the second iteration; is the approximation function value of the third bit of the current frequency modulation instruction sequence in the second iteration; is the approximation function value of the fourth bit of the current frequency modulation instruction sequence in the second iteration.

[0134] Then, the approximation error sequence of the second iteration is:

[0135]

[0136] Find the mean of the approximation error sequence:

[0137]

[0138] If the mean of the approximation error sequence of the second iteration is greater than the preset mean 0.2, update the approximation function, and when the third iteration is performed, the approximation function in the third iteration is:

[0139]

[0140] wherein, is a random value, ;

[0141]

[0142] ;

[0143] ;

[0144] In the formula, indicates the approximation function in the third iteration; is the highest bit coefficient of the approximation function in the third iteration; is the second highest bit coefficient of the approximation function in the third iteration; is the third highest bit coefficient of the approximation function in the third iteration; is the fourth highest bit coefficient of the approximation function in the third iteration; is the last bit coefficient of the approximation function in the third iteration.

[0145] Then, put into get ,​ brings in obtained put brings in obtained , put brings in obtained ; wherein, is the approximation function value of the value of the first bit of the current frequency modulation instruction sequence at the third iteration; is the approximation function value of the value of the second bit of the current frequency modulation instruction sequence at the third iteration; is the approximation function value of the value of the third bit of the current frequency modulation instruction sequence at the third iteration; is the approximation function value of the value of the fourth bit of the current frequency modulation instruction sequence at the third iteration.

[0146] Then the approximation error sequence of the third iteration is:

[0147]

[0148] Based on this, the mean value of the approximation error sequence of the third iteration is:

[0149] .

[0150] According to the above method, the cycle is repeated in turn until the approximation function of the nth iteration corresponds to the mean value of the approximation error sequence of the nth iteration is less than 0.2, and the iteration number is obtained, which is taken as one of the influencing factors of the fluctuation coefficient. .

[0151] For the approximation function of the final nth iteration , the first derivative is obtained by taking the derivative, and the number of intersection points of the first derivative with the X axis (i.e. the number of solutions of when the first derivative is 0) is , then the fluctuation coefficient M .

[0152] S2, collect continuous 50 times of super-capacity frequency modulation instructions pc1, pc2,..., pci,.., pc50, and calculate the corresponding 50 fluctuation coefficients , , ,..., ​​​​and detecting 50 increments of the internal resistance value in the corresponding single frequency modulation period 、 、 、...、 Then, the internal resistance fluctuation function is constructed based on the fluctuation coefficient and the internal resistance increment, specifically:

[0153] First, the initial form of the description function (i.e., the internal resistance fluctuation function of the first cycle) is set as:

[0154]

[0155] wherein, 、 、 and The initial values of , represents the compensation value of the th cycle, and the initial value is 0; and , , ,..., are respectively brought into , and the average error of the first cycle and the average error rate of the first cycle are further calculated; is the internal resistance increment of the th cycle corresponding to the th frequency modulation period; is the fluctuation coefficient corresponding to the th frequency modulation, that is, the fluctuation coefficient corresponding to the th super-capacity frequency modulation instruction; is the compensation coefficient of the th cycle; is the correction coefficient of the th cycle; is the compensation coefficient of the th cycle; is the correction term of the th cycle; is the compensation term of the th cycle; is the compensation value of the th cycle.

[0156] If is greater than 5%, the internal resistance fluctuation function is corrected to obtain the internal resistance fluctuation function of the second cycle:

[0157]

[0158] wherein, ;

[0159] ;

[0160] ;

[0161] ;

[0162] ;

[0163] ;

[0164] wherein, represents the compensation value of the n-th cycle; the , the , , ,..., are respectively brought into , further to obtain the average error of the n-th cycle and the average error rate of the n-th cycle; is the internal resistance increment of the n-th cycle corresponding to the n-th frequency modulation period; is the fluctuation coefficient corresponding to the n-th frequency modulation, that is, the fluctuation coefficient corresponding to the n-th super-capacity frequency modulation instruction; is the compensation coefficient of the n-th cycle; is the correction coefficient of the n-th cycle; is the compensation coefficient of the n-th cycle; is the correction term of the n-th cycle; is the compensation term of the n-th cycle; is the compensation value of the n-th cycle. If is greater than 5%, the internal resistance fluctuation function is corrected to obtain the internal resistance fluctuation function of the third cycle: wherein, ; ;

[0165] If is greater than 5%, the internal resistance fluctuation function is corrected to obtain the internal resistance fluctuation function of the third cycle:

[0166]

[0167] wherein, ; ;

[0168]

[0169] ​​​​​​​

[0170]

[0171] ;

[0172] wherein, is an activation function; is the supplementary coefficient of the th loop; is the correction coefficient of the th loop; is the compensation coefficient of the th loop; is the correction term of the th loop; is the compensation term of the th loop; is the make-up value of the th loop; represents the internal resistance fluctuation function of the 3rd loop.

[0173] The above-mentioned loop is repeated until the average error rate of a certain loop is less than 5%, and the final internal resistance fluctuation function is formed:

[0174] wherein, the internal resistance fluctuation function, represents the number of loops;

[0175] ;

[0176] ;

[0177] ;

[0178] ;

[0179] ;

[0180] ;

[0181] wherein, represents the average error, ; is the internal resistance increment of the th frequency modulation period corresponding to the th loop; M is the length of the fluctuation coefficient sequence of the historical frequency modulation instruction sequence; is an activation function; is a random function; max() is a maximum value function; is the correction term of the a supplementary coefficient of the nth cycle; a correction coefficient of the nth cycle; a supplementary coefficient of the nth cycle; a correction coefficient of the nth cycle; a compensation coefficient of the nth cycle; a correction coefficient of the nth cycle; a compensation coefficient of the nth cycle; a correction coefficient of the nth cycle; a compensation coefficient of the nth cycle; a correction coefficient of the nth cycle; a compensation coefficient of the nth cycle; a correction coefficient of the nth cycle; a compensation coefficient of the nth cycle; a correction coefficient of the nth cycle; a compensation coefficient of the nth cycle; a correction coefficient of the nth cycle; a compensation coefficient of the nth cycle. a correction coefficient of the nth cycle; a compensation coefficient of the nth cycle.

[0182] S3, after forming the final internal resistance fluctuation function, each time the current frequency modulation instruction comes, the fluctuation coefficient of the current frequency modulation instruction is calculated first, and then the final internal resistance increment is calculated according to , the final internal resistance increment = internal resistance fluctuation function value / internal resistance value at the last frequency modulation instruction; if the final internal resistance increment is greater than the first preset value 2%, a part of the instruction is compensated by the battery.

[0183] It should be noted that, in actual implementation, all parameters are processed through Min-Max Scaling before operation.

[0184] An embodiment of the present application provides a computer storage medium, which stores instructions that, when executed on a computer or similar device, can implement the super-capacitive energy storage grid-connected method as described above. The computer storage medium in this embodiment can be any physical device or virtual space that can store data for a computer to read. For example, it can be a hard drive, a solid state drive, a memory stick, a read-only memory, an erasable programmable read-only memory, an electrically erasable programmable read-only memory, a flash memory card, an optical disc, or any other form of computer-readable storage medium. In this embodiment, the instructions of the super-capacitive energy storage grid-connected method are stored in the above-mentioned computer storage medium. These instructions can be in the form of machine code, assembly code, high-level programming language (such as C, C++, Java, Python, etc.) source code or object code, etc. When a computer or similar device reads and executes these instructions, they will trigger a series of operations to implement the super-capacitive energy storage grid-connected method. These operations include but are not limited to:

[0185] read the frequency modulation instruction and input into the pre-trained error adjustment model; calculate and output the final fluctuation value; judge whether the final fluctuation value is greater than the preset fluctuation value, and decide whether to mobilize the lithium battery for compensation according to the final fluctuation value; if compensation is needed, calculate and output the compensation instruction to the lithium battery control system; and realize all the steps in the error adjustment model training process, including calculating the fluctuation coefficient, detecting the internal resistance increment, iteratively calculating the fluctuation value, etc.

[0186] Referring to Figure 2 An embodiment of the present application provides a super-capacity energy storage grid-connected system, comprising:

[0187] The data acquisition module 201 is configured to acquire a current frequency modulation instruction sequence.

[0188] The fluctuation coefficient calculation module 202 is configured to calculate a fluctuation coefficient of the current frequency modulation instruction sequence based on the current frequency modulation instruction sequence.

[0189] The internal resistance measurement module 203 is configured to input the fluctuation coefficient into a pre-trained error adjustment model to obtain a final internal resistance increment.

[0190] The grid-connected module 204 is configured to mobilize the lithium battery for compensation if the final internal resistance increment is greater than a first preset value.

[0191] The pre-trained error adjustment model has the following specific training method:

[0192] The fluctuation coefficient sequence of the historical frequency modulation instruction sequence and the internal resistance increment sequence corresponding to the historical frequency modulation instruction are taken as a training set.

[0193] An internal resistance fluctuation function of internal resistance fluctuation and fluctuation coefficient is constructed, and the internal resistance fluctuation function is initialized.

[0194] The fluctuation coefficient sequence is input into the internal resistance fluctuation function and combined with the internal resistance increment sequence to calculate an average error rate; if the average error rate is greater than a second preset value, the internal resistance fluctuation function is corrected until the average error rate is less than the second preset value, and a trained error adjustment model is obtained.

[0195] The above is only a preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for super-capacitive energy storage grid integration, characterized in that, The method comprises the following steps: obtaining a current frequency modulation instruction sequence; calculating a fluctuation coefficient of the current frequency modulation instruction sequence based on the current frequency modulation instruction sequence; inputting the fluctuation coefficient into a pre-trained error adjustment model to obtain a final internal resistance increment; if the final internal resistance increment is greater than a first preset value, mobilizing a lithium battery compensation; the specific training method of the pre-trained error adjustment model is: taking a fluctuation coefficient sequence of a historical frequency modulation instruction sequence and an internal resistance increment sequence corresponding to the historical frequency modulation instruction as a training set; constructing an internal resistance fluctuation function representing the relationship between internal resistance fluctuation and the fluctuation coefficient, and initializing the internal resistance fluctuation function; training the error adjustment model using the training set, in the training, inputting the fluctuation coefficient sequence into the internal resistance fluctuation function, and calculating an average error rate in combination with the internal resistance increment sequence; if the average error rate is greater than a second preset value, correcting the internal resistance fluctuation function until the average error rate is less than the second preset value, and obtaining the trained error adjustment model; the specific calculation of the fluctuation coefficient of the current frequency modulation instruction sequence is: constructing an approximation function of the current frequency modulation instruction sequence, and initializing the approximation function; calculating an approximation error sequence based on the current frequency modulation instruction sequence and the approximation function, and updating the approximation function when the average of the approximation error sequence is greater than a preset average; iterating the step until the average of the approximation error is less than the preset average, and obtaining a final approximation function and an iteration number; deriving a first-order approximation derivative of the final approximation function to obtain the number of solutions when the first-order approximation derivative is zero; obtaining the fluctuation coefficient based on the number of solutions when the first-order approximation derivative is zero and the iteration number.

2. The super-capacitive energy storage grid-connected method of claim 1, wherein, initialized approximation function is: wherein the most significant coefficient the second most significant coefficient and the least significant coefficient are random values; denotes the value of the respective position in the current sequence of frequency modulation commands.

3. The super-capacitive energy storage grid-connected method of claim 1, wherein, the approximation error sequence is: wherein, is the approximation error sequence for the value of the current frequency modulation command sequence at the i approximation function value at the approximation error sequence for the approximation function value at the approximation function value at the ; is the length of the current frequency modulation command sequence.

4. The super-capacitive energy storage grid-connected method of claim 3, wherein, the average of the approximation error sequence is described as: wherein is the mean of the approximation error sequence for the th iteration.

5. The super-capacitive energy storage grid-connected method of claim 4, wherein, the updating of the approximation function is specifically: wherein is the approximation function for the th iteration; ； ； ； wherein is a random number function; represents the coefficient of the th iteration of the approximation function at the th bit; represents the coefficient of the th iteration of the approximation function at the th bit; represents the coefficient of the th iteration of the approximation function at the th bit; represents th power of , where is Euler's number; represents the coefficient of the th iteration of the approximation function at the th bit; represents the coefficient of the th iteration of the approximation function at the th bit; represents the coefficient of the th iteration of the approximation function at the th bit; represents the coefficient of the th iteration of the approximation function at the th bit.

6. The super-capacitive energy storage grid-tie method of claim 1, wherein, the internal resistance fluctuation function is described as: wherein, is the number of the first cycle, is the function of the internal resistance fluctuation of the nth cycle, represents the number of cycles; ； ； ； ； ； ； In the formula, Indicates the average error. , For the first The corresponding iteration of the 1st cycle The internal resistance increment during the secondary frequency modulation period; M The length of the fluctuation coefficient sequence of the historical frequency modulation command sequence; For activation functions; `max()` is a random function; `max()` is a maximum value function. For the first The supplementary coefficient for the next cycle; For the first The supplementary coefficient for the next cycle; For the first Correction coefficient for the next cycle; For the first The compensation coefficient for the next cycle; For the first The correction term for the next iteration; For the first The compensation term for the next cycle; For the first The compensation value for the next cycle; For the first Average error rate of each cycle; For the first The correction term for the next iteration; For the first The compensation term for the next cycle; middle This represents the volatility coefficient.

7. The super-capacitive energy storage grid-connected method of claim 6, wherein, the average error rate is specifically: wherein, is the number of the first frequency modulation during the first cycle corresponding to the first frequency modulation instruction sequence; is the number of the first frequency modulation during the first cycle corresponding to the first frequency modulation instruction sequence; is the increment of internal resistance during the first frequency modulation corresponding to the first cycle; is the length of the fluctuation coefficient sequence of the historical frequency modulation instruction sequence.

8. A computer storage medium storing instructions, the instructions comprising: when the instruction is executed, the super-capacity energy storage grid-connected method of any one of claims 1-7 is implemented.

9. A super-capacitive energy storage grid-connected system based on the super-capacitive energy storage grid-connected method of any one of claims 1 to 7, characterized in that, comprise: a data acquisition module for obtaining a current frequency modulation instruction sequence; a fluctuation coefficient calculation module for calculating a fluctuation coefficient of the current frequency modulation instruction sequence based on the current frequency modulation instruction sequence; an internal resistance measurement module for inputting the fluctuation coefficient into a pre-trained error adjustment model to obtain a final internal resistance increment; a grid-connected module, if the final internal resistance increment is greater than a first preset value, mobilizing a lithium battery compensation; the specific training method of the pre-trained error adjustment model is: taking a fluctuation coefficient sequence of a historical frequency modulation instruction sequence and an internal resistance increment sequence corresponding to the historical frequency modulation instruction as a training set; constructing an internal resistance fluctuation function representing the relationship between internal resistance fluctuation and the fluctuation coefficient, and initializing the internal resistance fluctuation function; training the error adjustment model using the training set, in the training, inputting the fluctuation coefficient sequence into the internal resistance fluctuation function, and calculating an average error rate in combination with the internal resistance increment sequence; if the average error rate is greater than a second preset value, correcting the internal resistance fluctuation function until the average error rate is less than the second preset value, and obtaining the trained error adjustment model.

Images