Smart Grid Integrated Micro Wind Power Generation and Energy Storage Collaborative System

Abstract

The present invention relates to the technical field of power grid energy storage systems, and discloses a coordinated system for integrated micro-wind power generation and energy storage in a smart grid, including a first prediction module, a second prediction module, a data processing module, a strategy module, and a monitoring module; wherein: the first prediction module is used to predict the wind speed in the area where the micro-wind power generation network is located; the second prediction module is used to predict the load of the power grid; the data processing module calculates the predicted power generation value based on the predicted wind speed value; the strategy module formulates the charge and discharge strategy of the energy storage device based on the predicted load value and the predicted power generation value; the monitoring module is used to monitor the power grid parameters in real time, including the real-time power generation and load, and controls the adjustment of the charge and discharge strategy based on the power grid parameters. The present invention realizes the deep integration of micro-wind power generation and the energy storage system, and opens up a new path for building a more intelligent, efficient and sustainable modern power system.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid energy storage systems, and particularly to a coordinated system of micro wind power generation and energy storage integrated with a smart grid. Background Art

[0002] In recent years, significant progress has been made in micro wind power generation technology. Optimizations have been achieved not only in blade design, material selection, etc., but also in the intelligentization of control systems. Meanwhile, through reasonable energy storage configuration and management, the fluctuations in the output power of renewable energy such as wind power can be effectively smoothed, improving the stability and reliability of power grid operation. Although certain achievements have been made in micro wind power generation technology and energy storage technology respectively, many challenges still exist in practical applications.

[0003] Wind speed prediction, especially for ultra-short-term (such as within a few hours), is difficult, which directly affects the scheduling and planning of micro wind power generation networks. The current statistical methods or machine learning models often fail to accurately capture the complex patterns of wind speed changes, resulting in large deviations in prediction results. Although existing energy storage devices can alleviate the problem of unstable output of renewable energy to a certain extent, they have problems such as low charge-discharge efficiency and high costs. In addition, there is a lack of effective strategies to guide the optimal charge-discharge timing of energy storage devices, so that energy storage resources are not fully utilized. The cooperation between micro wind power generation and energy storage systems is not close enough. The two usually operate independently and lack a unified coordination mechanism. This means that when the wind power generation is excessive, the excess energy cannot be stored in time, and when the power generation is insufficient, the reserved energy cannot be released quickly to make up for the gap, affecting the flexibility and economy of the overall system. Facing the ever-changing power grid environment, the existing regulation means mostly rely on preset rules or empirical judgments and lack sufficient adaptability and rapid response capabilities. Especially under extreme weather conditions, how to ensure the safe and stable power supply has become a major problem.

[0004] For example, Chinese Patent with the authorization announcement number CN116014866B discloses a power supply method and system based on a micro wind power generation wall, belonging to the technical field of clean energy power supply systems, which realizes stable and convenient clean energy in cooperation with photovoltaic power generation technology and energy storage technology. The method includes obtaining the operation data of the main battery, where the operation data includes multiple sampling moments and corresponding multiple sampling voltages; determining whether there is at least one sampling voltage lower than the set voltage among the multiple sampling voltages; if there is at least one sampling voltage, determining at least one sampling moment corresponding to the at least one sampling voltage; determining the maximum first time interval between the at least one sampling moment, and determining the minimum second time interval between the currently obtained moment and the at least one sampling moment; generating and outputting a control instruction according to the first time interval and the second time interval; where the control instruction is used to control the standby battery to charge the main battery.

[0005] For example, the patent application with the publication number CN101237162A discloses a micro-wind power energy storage device, including: a fan; and also including a generator connected to the fan and capable of converting into electric energy; the generator is connected to an energy storage device; the energy storage device is connected to the outside through a diode and a switch; a bracket for fixing the fan and the generator; this invention can convert kinetic energy into electric energy and store the electric energy.

[0006] The above patents all have the problems raised in this background technology: the cooperation between micro-wind power generation and the energy storage system is not close enough, and the two usually operate independently, lacking a unified coordination mechanism.

[0007] The information disclosed in this background technology section is only intended to increase the understanding of the overall background of the present invention, and should not be regarded as an admission or an implication in any form that this information constitutes the prior art already known to those of ordinary skill in the art. Summary of the Invention

[0008] The technical problem to be solved by the present invention is to overcome the defects of the prior art, provide a collaborative system for micro-wind power generation and energy storage integrated with a smart grid, realize the deep integration of micro-wind power generation and the energy storage system, and open up a new path for building a more intelligent, efficient and sustainable modern power system.

[0009] To solve the above technical problems, the present invention provides the following technical solutions:

[0010] A collaborative system for micro-wind power generation and energy storage integrated with a smart grid, including a first prediction module, a second prediction module, a data processing module, a strategy module, and a monitoring module; where:

[0011] The first prediction module is used to predict the wind speed in the area where the micro-wind power generation network is located and output a wind speed prediction value;

[0012] The second prediction module is used to predict the load of the power grid and output a load prediction value;

[0013] The data processing module calculates a power generation prediction value based on the wind speed prediction value;

[0014] The strategy module formulates a charging and discharging strategy for the energy storage device based on the load prediction value and the power generation prediction value;

[0015] The monitoring module is used to monitor the power grid parameters in real time, including the real-time power generation and load, and adjust the charging and discharging strategy based on the power grid parameters.

[0016] As a preferred solution of the integrated micro-wind power generation and energy storage collaborative system of the smart grid according to the present invention, wherein: the first prediction module includes a first statistical unit and a first prediction unit; wherein, the first statistical unit is used to collect and count the historical wind speed data of the area where the micro-wind power generation network is located; the first prediction unit is used to predict the wind speed of the area where the micro-wind power generation network is located based on the historical wind speed data;

[0017] The first statistical unit cleans and normalizes the historical wind speed data and then organizes it into a time series; the first prediction unit is configured with a time series prediction model, and the time series prediction model is any one of an RNN model, an LSTM model, and a GRU model, which is used to process the time series of historical wind speed data and output continuous wind speed prediction values.

[0018] As a preferred solution of the integrated micro-wind power generation and energy storage collaborative system of the smart grid according to the present invention, wherein: the second prediction module includes a second statistical unit and a second prediction unit; wherein, the second statistical unit is used to collect and count the historical load data of the power grid; the second prediction unit is used to predict the load of the power grid based on the historical load data and output the load prediction values for the next m time steps, where m is a positive integer;

[0019] The second statistical unit cleans and normalizes the historical load data and then organizes it into a time series; each historical load data in the time series of historical load data corresponds to a time step; the second prediction unit is configured with a time series prediction model, and the time series prediction model calculates the load prediction values for the next m time steps based on the time series of historical load data.

[0020] As a preferred solution of the integrated micro-wind power generation and energy storage collaborative system of the smart grid according to the present invention, wherein: the data processing module includes a data sorting unit and a power generation prediction unit; wherein, the data sorting unit is used to sort the wind speed prediction values, specifically as follows: divide the continuous wind speed prediction values into m segments where the time steps and the load prediction values correspond one by one; the data sorting unit is configured with the rated wind speed of the micro-wind power generation network. For the wind speed prediction value at any time step, count the duration of the time period when the wind speed prediction value is greater than the rated wind speed, denoted as t1; count the duration of the time period when the wind speed prediction value is not greater than the rated wind speed, denoted as t2, and calculate the average wind speed within the time period when the wind speed prediction value is not greater than the rated wind speed, denoted as v s

[0021] As a preferred solution of the integrated micro-wind power generation and energy storage collaborative system of the smart grid according to the present invention, wherein: the power generation prediction unit is used to calculate the power generation prediction values for the next m time steps; the formula is as follows:

[0022]

[0023] Among them, E represents the predicted power generation value at any future time step; C p represents the wind energy utilization rate; ρ represents the air density; A represents the swept area of the wind turbine; P0 represents the rated power of the micro-wind power generation network.

[0024] As a preferred solution of the micro-wind power generation and energy storage collaborative system integrated with the smart grid according to the present invention, wherein: the strategy module includes an optimization algorithm unit and a simulation operation unit; wherein, the optimization algorithm unit is configured with a genetic algorithm for formulating the charge and discharge strategies of the energy storage device within the next m time steps; the simulation operation unit is used to store the data generated in each iteration of the genetic algorithm; the simulation operation unit is also configured with a fitness function for calculating the fitness in each iteration of the genetic algorithm;

[0025] The method for the optimization algorithm unit to formulate the charge and discharge strategies of the energy storage device is as follows:

[0026] S1: Set the population size, crossover probability, mutation probability, and maximum number of iterations, and generate N individuals to form the initial population; N is the population size;

[0027] S2: Calculate the fitness of each individual based on the simulation operation unit;

[0028] S3: Perform selection operation, crossover operation, and mutation operation in sequence, and generate the next generation population;

[0029] S4: Repeat steps S2 - S3 until the maximum number of iterations is reached;

[0030] S5: Obtain the individual with the highest fitness in all generations of the population as the optimal individual, and generate the charge and discharge strategies of the energy storage device within the next m time steps based on the chromosome of the optimal individual.

[0031] As a preferred solution of the micro-wind power generation and energy storage collaborative system integrated with the smart grid according to the present invention, wherein: any one of the individuals includes a chromosome 1 and a chromosome 2; wherein, both chromosome 1 and chromosome 2 include m genes; wherein, the i-th gene of chromosome 1 represents the charge and discharge state of the energy storage device at the i-th future time step, including charging and discharging; the i-th gene of chromosome 2 represents the average power of charging or discharging of the energy storage device at the i-th future time step, and the value range of i is 1, 2,..., m;

[0032] The crossover operation includes single-point crossover and ordered crossover; the objects of the crossover operation are any pair of chromosomes with the same number in the two individuals participating in the crossover operation.

[0033] As a preferred embodiment of the integrated micro-wind power generation and energy storage collaborative system in the intelligent power grid of the present invention, the fitness function configured by the analog operation unit is specifically as follows:

[0034]

[0035] Wherein, H represents the fitness of any individual; E j represents the predicted power generation value at the j-th future time step, and the value range of j is 1, 2, ……, m; L j represents the predicted load value at the j-th future time step; C j represents the charging amount of the energy storage device at the j-th future time step; D j represents the discharge amount of the energy storage device at the j-th future time step; α j is the first adjustment factor, β j is the second adjustment factor, F j is the power change amount of the energy storage device at the j-th future time step, and the value rule is as follows: if the energy storage device is charged at the j-th future time step, then the value of α j is 1, the value of β j is 0, and F j is equal to C j ; if the energy storage device is discharged at the j-th future time step, then the value of α j is 0, the value of β j is 1, and F j is equal to the opposite of D j ; F j-1 is the power change amount of the energy storage device at the (j-1)-th future time step; w1, w2, and w3 are all weight coefficients.

[0036] As a preferred embodiment of the integrated micro-wind power generation and energy storage collaborative system in the intelligent power grid of the present invention, the monitoring module includes a power grid monitoring unit and an adjustment instruction unit; wherein, the power grid monitoring unit is used to monitor the power generation of the micro-wind power generation network at each time step in real time and compare it with the predicted power generation value at the corresponding time step; it is also used to monitor the load of the power grid at each time step in real time and compare it with the predicted load value at the corresponding time step;

[0037] If the absolute value of the difference between the real-time power generation for consecutive n time steps and the predicted power generation value for the corresponding time step is higher than a preset first power generation error threshold, or if the absolute value of the difference between the real-time load for consecutive n time steps and the predicted load value for the corresponding time step is higher than a preset first load error threshold, the adjustment instruction unit generates a first adjustment instruction; n is a positive integer, and its specific value is set by those skilled in the art based on actual requirements; the first prediction module responds to the first adjustment instruction, re-performs wind speed prediction and updates the wind speed prediction value; the data processing module updates the power generation prediction value based on the updated wind speed prediction value; the second prediction module responds to the first adjustment instruction, re-predicts the load of the power grid and updates the load prediction value; the strategy module responds to the first adjustment instruction, and based on the updated load prediction value and the updated power generation prediction value, re-formulates the charge and discharge strategy of the energy storage device.

[0038] As a preferred embodiment of the integrated micro-wind power generation and energy storage collaborative system of the smart grid according to the present invention, when the first adjustment instruction is generated, if the absolute value of the difference between at least one of the real-time power generations for consecutive n time steps and the predicted power generation value for the corresponding time step is higher than a preset second power generation error threshold, or if the absolute value of the difference between at least one of the real-time loads for consecutive n time steps and the predicted load value for the corresponding time step is higher than a preset second load error threshold, the adjustment instruction unit further generates a second adjustment instruction; the strategy module responds to the second adjustment instruction, and when re-formulating the charge and discharge strategy of the energy storage device, formulates the charge and discharge strategy of the energy storage device within the next k time steps, where k is a positive integer and k is less than m.

[0039] Compared with the prior art, the beneficial effects achieved by the present invention are as follows:

[0040] An advanced deep learning model is used to predict the wind speed in the area where the micro-wind power generation network is located, and combined with historical load data, an accurate estimate of future power demand is made. This not only improves the accuracy of power generation prediction but also enhances the load prediction ability, providing a solid data foundation for subsequent power generation and energy storage collaborative planning.

[0041] Based on accurate wind speed and load prediction values, the system can dynamically adjust the charge and discharge strategy of the energy storage device, ensuring that excess energy is stored in a timely manner when power generation is excessive, and the reserved energy is quickly released to supplement the gap when power generation is insufficient, improving energy utilization efficiency and reducing waste. By reasonably controlling the change amplitude and frequency of the charge and discharge power, the service life of energy storage devices such as batteries is effectively extended, and the maintenance cost is reduced.

[0042] By real-time monitoring of power grid parameters and quickly adjusting the charge and discharge strategy according to the actual situation, the system has strong adaptability. When the prediction deviation is large or in case of emergencies, measures can be taken immediately to avoid system instability caused by prediction errors. Brief Description of the Drawings

[0043] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings. Among them:

[0044] Figure 1 It is a schematic structural diagram of a coordinated system for micro-wind power generation and energy storage integrated into a smart grid provided by the present invention;

[0045] Figure 2 It is a flowchart of a method for formulating a charge and discharge strategy for an energy storage device provided by the present invention. Detailed Embodiments

[0046] The following will detail the technical solutions of the present invention through the drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solutions of the present invention, rather than limitations on the technical solutions of the present invention. Without conflict, the technical features in the embodiments of the present invention and the embodiments can be combined with each other.

[0047] This embodiment introduces a coordinated system for micro-wind power generation and energy storage integrated into a smart grid. Referring to Figure 1 , the system includes a first prediction module, a second prediction module, a data processing module, a strategy module, and a monitoring module; among them:

[0048] The first prediction module is used to predict the wind speed in the area where the micro-wind power generation network is located and output a wind speed prediction value;

[0049] The first prediction module includes a first statistics unit and a first prediction unit; wherein, the first statistics unit is used to collect and statistically analyze the historical wind speed data in the area where the micro-wind power generation network is located; the first prediction unit is used to predict the wind speed in the area where the micro-wind power generation network is located based on the historical wind speed data;

[0050] The first statistics unit cleans and normalizes the historical wind speed data and then organizes it into a time series; the first prediction unit is configured with a time series prediction model, and the time series prediction model is any one of an RNN model, an LSTM model, and a GRU model, which is used to process the time series of historical wind speed data and output continuous wind speed prediction values.

[0051] Wind energy is an energy source with strong intermittency and randomness, and it is difficult to predict. However, accurate wind speed prediction is of great significance for improving power generation efficiency and optimizing resource allocation. With the powerful feature extraction and learning ability of deep learning models such as LSTM, high-precision and multi-point wind speed prediction can be achieved, providing a data basis for subsequent coordinated planning of power generation and energy storage.

[0052] The second prediction module is used to predict the load of the power grid and output the load prediction value;

[0053] The second prediction module includes a second statistics unit and a second prediction unit; among them, the second statistics unit is used to collect and count the historical load data of the power grid; the second prediction unit predicts the load of the power grid based on the historical load data and outputs the load prediction values for the next m time steps, where m is a positive integer;

[0054] The second statistics unit cleans and normalizes the historical load data and organizes it into a time series; each historical load data in the time series of historical load data corresponds to a time step; the second prediction unit is configured with a time series prediction model, such as an ARMA model or an ARIMA model, etc., and the time series prediction model calculates the load prediction values for the next m time steps based on the time series of historical load data.

[0055] The data processing module calculates the power generation prediction value based on the wind speed prediction value;

[0056] The data processing module includes a data arrangement unit and a power generation prediction unit; among them, the data arrangement unit is used to arrange the wind speed prediction value as follows: divide the continuous wind speed prediction values into m segments where the time steps and the load prediction values correspond one by one; the data arrangement unit is configured with the rated wind speed of the low-wind power generation network. For the wind speed prediction value at any time step, count the duration of the time period when the wind speed prediction value is greater than the rated wind speed, denoted as t1; count the duration of the time period when the wind speed prediction value is not greater than the rated wind speed, denoted as t2, and calculate the average wind speed within the time period when the wind speed prediction value is not greater than the rated wind speed, denoted as v s ;

[0057] The power generation prediction unit is used to calculate the power generation prediction values for the next m time steps; the formula is as follows:

[0058]

[0059] Among them, E represents the power generation prediction value at any future time step; C p represents the wind energy utilization rate, determined based on experiments; ρ represents the air density; A represents the swept area of the wind turbine; P0 represents the rated power of the low-wind power generation network.

[0060] The strategy module formulates the charge and discharge strategy of the energy storage device based on the predicted load value and the predicted power generation value;

[0061] The strategy module includes an optimization algorithm unit and a simulation operation unit; among them, the optimization algorithm unit is configured with a genetic algorithm for formulating the charge and discharge strategy of the energy storage device within the next m time steps; the simulation operation unit is used to store the data generated in each iteration of the genetic algorithm; the simulation operation unit is also configured with a fitness function for calculating the fitness in each iteration of the genetic algorithm;

[0062] As Figure 2 shown, the method for the optimization algorithm unit to formulate the charge and discharge strategy of the energy storage device is as follows:

[0063] S1: Set the population size, crossover probability, mutation probability, and maximum number of iterations, and generate N individuals to form the initial population; N is the population size;

[0064] Any individual includes a chromosome No. 1 and a chromosome No. 2; among them, both chromosome No. 1 and chromosome No. 2 contain m genes; among them, the i-th gene of chromosome No. 1 represents the charge and discharge state of the energy storage device at the i-th future time step, including charging and discharging; the i-th gene of chromosome No. 2 represents the average power of charging or discharging of the energy storage device at the i-th future time step, and the value range of i is 1, 2,..., m;

[0065] S2: Calculate the fitness of each individual based on the simulation operation unit;

[0066] S3: Perform selection operation, crossover operation, and mutation operation in sequence, and generate the next generation population;

[0067] The crossover operation includes single-point crossover and ordered crossover; the objects of the crossover operation are any pair of chromosomes with the same number in the two individuals participating in the crossover operation;

[0068] S4: Repeat steps S2 - S3 until the maximum number of iterations is reached;

[0069] S5: Obtain the individual with the highest fitness in all generations of the population as the optimal individual, and generate the charge and discharge strategy of the energy storage device within the next m time steps based on the chromosomes of the optimal individual.

[0070] The fitness function configured by the simulation operation unit is specifically as follows:

[0071]

[0072] Among them, H represents the fitness of any individual; E j represents the predicted power generation value at the j-th future time step, and the value range of j is 1, 2,..., m; L jrepresents the predicted value of the load at the j-th future time step; C j represents the charging amount of the energy storage device at the j-th future time step; D j represents the discharging amount of the energy storage device at the j-th future time step; α j is the first adjustment factor, β j is the second adjustment factor, F j is the power change amount of the energy storage device at the j-th future time step, and the value rule is as follows: if the energy storage device is charged at the j-th future time step, then the value of α j is 1, the value of β j is 0, and F j is equal to C j ; if the energy storage device is discharged at the j-th future time step, then the value of α j is 0, the value of β j is 1, and F j is equal to the opposite of D j ; F j-1 is the power change amount of the energy storage device at the (j - 1)-th future time step; w1, w2, and w3 are all weight coefficients, which are set by those skilled in the art based on actual needs.

[0073] The above fitness function includes three parts; the first part is used to calculate the utilization rate of the power generation of the breeze power generation, the second part is used to calculate the satisfaction rate of the load demand, and the third part is used to calculate the amplitude and frequency of the power change of the charging or discharging of the energy storage device; based on the selection of the above fitness function, the formulated charging and discharging strategy is encouraged to have the following characteristics: when it is predicted that the power generation is higher than the grid demand, the energy storage system is preferentially charged; when it is predicted that the power generation is lower than the grid demand, the electric energy of the energy storage system is released to supplement the grid. By dynamically adjusting the charging and discharging rates, the frequent adjustment of the charging and discharging power of the energy storage system is avoided to extend the service life of the energy storage device.

[0074] The monitoring module is used to monitor the grid parameters in real time, including the real-time power generation and load, and adjust the charging and discharging strategy based on the grid parameters.

[0075] The monitoring module includes a grid monitoring unit and an adjustment instruction unit; among them, the grid monitoring unit is used to monitor the power generation of the breeze power generation network at each time step in real time and compare it with the predicted value of the power generation at the corresponding time step; it is also used to monitor the load of the grid at each time step in real time and compare it with the predicted value of the load at the corresponding time step;

[0076] If the absolute value of the difference between the real-time power generation for consecutive n time steps and the predicted power generation values for the corresponding time steps is higher than a preset first power generation error threshold, or if the absolute value of the difference between the real-time load for consecutive n time steps and the predicted load values for the corresponding time steps is higher than a preset first load error threshold, the adjustment instruction unit generates a first adjustment instruction; n is a positive integer, and its specific value is set by those skilled in the art based on actual requirements; the first prediction module responds to the first adjustment instruction, re-performs wind speed prediction and updates the wind speed prediction value; the data processing module updates the power generation prediction value based on the updated wind speed prediction value; the second prediction module responds to the first adjustment instruction, re-predicts the load of the power grid and updates the load prediction value; the strategy module responds to the first adjustment instruction, and based on the updated load prediction value and the updated power generation prediction value, re-formulates the charge and discharge strategy of the energy storage device. When the gap between the consecutive n predicted values and the measured values is large, it indicates that the accuracy of the predicted values is poor, and the charge and discharge strategy formulated based on the predicted values may not be applicable to the actual power grid. Therefore, it is necessary to update the charge and discharge strategy.

[0077] When generating the first adjustment instruction, if at least one of the real-time power generations for consecutive n time steps has an absolute value of the difference from the predicted power generation value for the corresponding time step higher than a preset second power generation error threshold, or if at least one of the real-time loads for consecutive n time steps has an absolute value of the difference from the predicted load value for the corresponding time step higher than a preset second load error threshold, the adjustment instruction unit further generates a second adjustment instruction; the strategy module responds to the second adjustment instruction and formulates the charge and discharge strategy of the energy storage device for the next k time steps when re-formulating the charge and discharge strategy of the energy storage device, where k is a positive integer and k is less than m. The second power generation error threshold is higher than the first power generation error threshold, and the second load error threshold is higher than the first load error threshold. When the prediction deviation is higher than the corresponding second error threshold, it indicates that there may be special factors causing the predicted values to be abnormal. At this time, it is necessary to reduce the time coverage range of the charge and discharge strategy planning to avoid frequently generating the first adjustment instruction and increasing the system burden.

[0078] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can be implemented in the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can be implemented in the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0079] The embodiments of the present invention have been described above in conjunction with the accompanying drawings. However, the present invention is not limited to the above specific embodiments. The above specific embodiments are merely illustrative rather than restrictive. Under the inspiration of the present invention, those of ordinary skill in the art can also make many forms without departing from the purpose and scope of the present invention. All of these are within the protection scope of the present invention.

Claims

1. A coordinated system for integrating micro-wind power generation and energy storage in a smart grid, characterized in that: It includes a first prediction module, a second prediction module, a data processing module, a strategy module, and a monitoring module; where: The first prediction module is used to predict the wind speed in the area where the micro-wind power generation network is located and output the wind speed prediction value; The second prediction module is used to predict the load of the power grid and output the load prediction value; The data processing module calculates the power generation prediction value based on the wind speed prediction value; The strategy module formulates the charge and discharge strategy of the energy storage device based on the load prediction value and the power generation prediction value; The strategy module includes an optimization algorithm unit and a simulation operation unit; where, the optimization algorithm unit is configured with a genetic algorithm to formulate the charge and discharge strategy of the energy storage device within the next m time steps; the simulation operation unit is used to store the data generated in each iteration of the genetic algorithm; the simulation operation unit is also configured with a fitness function to calculate the fitness during each iteration of the genetic algorithm, and the formula is as follows: Among them, H represents the fitness of any individual; E j represents the predicted power generation value at the j-th future time step, where the value range of j is 1, 2, ……, m; L j represents the predicted load value at the j-th future time step; C j represents the charging amount of the energy storage device at the j-th future time step; D j represents the discharging amount of the energy storage device at the j-th future time step; α j is the first adjustment factor, β j is the second adjustment factor, F j is the power change amount of the energy storage device at the j-th future time step, and the value rule is as follows: if the energy storage device is charged at the j-th future time step, then the value of α j is 1, the value of β j is 0, and F j is equal to C j ; if the energy storage device is discharged at the j-th future time step, then the value of α j is 0, the value of β j is 1, and F j is equal to the opposite of D j ; F j-1 is the power change amount of the energy storage device at the (j - 1)-th future time step; w1, w2, and w3 are all weight coefficients; Any individual in the genetic algorithm includes a chromosome No. 1 and a chromosome No. 2; where, both chromosome No. 1 and chromosome No. 2 include m genes; where, the i-th gene of chromosome No. 1 represents the charge and discharge state of the energy storage device in the i-th future time step, including charging and discharging; the i-th gene of chromosome No. 2 represents the average power of charging or discharging of the energy storage device in the i-th future time step, and the value range of i is 1, 2,..., m; The monitoring module is used to monitor the power grid parameters in real time, including the real-time power generation and load, and control the adjustment of the charge and discharge strategy based on the power grid parameters.

2. The integrated micro-wind power generation and energy storage collaborative system for smart grid according to claim 1, wherein: The first prediction module includes a first statistics unit and a first prediction unit; where, the first statistics unit is used to collect and statistically analyze the historical wind speed data in the area where the micro-wind power generation network is located; the first prediction unit predicts the wind speed in the area where the micro-wind power generation network is located based on the historical wind speed data; The first statistics unit cleans and normalizes the historical wind speed data and then organizes it into a time series; the first prediction unit is configured with a time series prediction model, and the time series prediction model is any one of the RNN model, LSTM model, and GRU model, which is used to process the time series of historical wind speed data and output continuous wind speed prediction values.

3. The integrated micro-wind power generation and energy storage collaborative system for a smart grid according to claim 2, characterized in that: The second prediction module includes a second statistics unit and a second prediction unit; where, the second statistics unit is used to collect and statistically analyze the historical load data of the power grid; the second prediction unit predicts the load of the power grid based on the historical load data and outputs the load prediction values for the next m time steps, where m is a positive integer; The second statistics unit cleans and normalizes the historical load data and then organizes it into a time series; each historical load data in the time series of historical load data corresponds to a time step; the second prediction unit is configured with a time series prediction model, and the time series prediction model calculates the load prediction values for the next m time steps based on the time series of historical load data.

4. The integrated micro-wind power generation and energy storage collaborative system for smart grid as claimed in claim 3, wherein: The data processing module includes a data sorting unit and a power generation prediction unit. Among them, the data sorting unit is used to sort the wind speed prediction values as follows: divide the continuous wind speed prediction values into m segments where the time steps and the load amount prediction values correspond one by one; the data sorting unit is configured with the rated wind speed of the micro wind power network. For the wind speed prediction value within any time step, count the duration of the time period when the wind speed prediction value is greater than the rated wind speed, denoted as t1; count the duration of the time period when the wind speed prediction value is not greater than the rated wind speed, denoted as t2, and calculate the average wind speed within the time period when the wind speed prediction value is not greater than the rated wind speed, denoted as v s .

5. The integrated micro-wind power generation and energy storage collaborative system for smart grid as claimed in claim 4, wherein: The power generation prediction unit is used to calculate the power generation prediction values for the next m time steps; the formula is as follows: Among them, E represents the predicted power generation value at any future time step; C p represents the wind energy utilization rate; ρ represents the air density; A represents the swept area of the wind turbine rotor; P0 represents the rated power of the micro-wind power generation network.

6. The integrated micro-wind power generation and energy storage collaborative system for smart grid according to claim 5, wherein: The method for the optimization algorithm unit to formulate the charge and discharge strategy of the energy storage device is as follows: S1: Set the population size, crossover probability, mutation probability, maximum number of iterations, and generate N individuals to form the initial population; N is the population size. S2: Calculate the fitness of each individual based on the simulation operation unit. S3: Perform selection operation, crossover operation, and mutation operation in sequence, and generate the next generation population. S4: Repeat steps S2 - S3 until the maximum number of iterations is reached. S5: Obtain the individual with the highest fitness in all generations of the population as the optimal individual, and generate the charge and discharge strategy of the energy storage device for the next m time steps based on the chromosome of the optimal individual.

7. The integrated micro-wind power generation and energy storage collaborative system for smart grid as claimed in claim 6, wherein: The crossover operation includes single - point crossover and ordered crossover; the objects of the crossover operation are any pair of chromosomes with the same number in the two individuals participating in the crossover operation.

8. The integrated micro-wind power generation and energy storage collaborative system for a smart grid according to claim 7, characterized in that: The monitoring module includes a power grid monitoring unit and an adjustment instruction unit; among them, the power grid monitoring unit is used to monitor the power generation of the micro - wind power network in real time for each time step and compare it with the predicted power generation value for the corresponding time step; it is also used to monitor the load of the power grid in real time for each time step and compare it with the predicted load value for the corresponding time step. If the absolute value of the difference between the real - time power generation for n consecutive time steps and the predicted power generation value for the corresponding time step is higher than the preset first power generation error threshold, or if the absolute value of the difference between the real - time load for n consecutive time steps and the predicted load value for the corresponding time step is higher than the preset first load error threshold, the adjustment instruction unit generates a first adjustment instruction; n is a positive integer; the first prediction module responds to the first adjustment instruction, re - performs wind speed prediction and updates the wind speed prediction value; the data processing module updates the predicted power generation value based on the updated wind speed prediction value; the second prediction module responds to the first adjustment instruction, re - predicts the load of the power grid and updates the load prediction value; the strategy module responds to the first adjustment instruction, and re - formulates the charge and discharge strategy of the energy storage device based on the updated load prediction value and the updated power generation prediction value.

9. The integrated micro-wind power generation and energy storage collaborative system for smart grid as claimed in claim 8, wherein: When the first adjustment instruction is generated, if at least one of the real - time power generations for n consecutive time steps has an absolute value of the difference from the predicted power generation value for the corresponding time step higher than the preset second power generation error threshold, or if at least one of the real - time loads for n consecutive time steps has an absolute value of the difference from the predicted load value for the corresponding time step higher than the preset second load error threshold, the adjustment instruction unit also generates a second adjustment instruction; the strategy module responds to the second adjustment instruction and formulates the charge and discharge strategy of the energy storage device for the next k time steps when re - formulating the charge and discharge strategy of the energy storage device, where k is a positive integer and k is less than m.

Images