Electrolyzer configuration processing method and device based on fluctuating wind-solar coupled power generation

Abstract

This specification provides an electrolyzer configuration processing method and device based on fluctuating wind-solar coupled power generation. Based on this method, first obtain and construct a wind-solar output curve with good representativeness based on the historical wind-solar data of the target area; then determine and use the gradient step size based on the wind-solar output curve to process the wind-solar output curve and split the base load component and the fluctuating load component; and based on the preset matching rules and gradient step size, optimize and solve according to the base load component, the fluctuating load component, and the decision-making influence data to determine a target configuration scheme that meets the requirements; wherein the preset matching rules include: the base load component preferentially matches the first standard electrolyzer, and the fluctuating load component preferentially matches the second standard electrolyzer; according to the target configuration scheme, the target electrolyzer group for the target wind-solar coupled power station is arranged. Thereby, the arrangement of the electrolyzer group for the target wind-solar coupled power station can be accurately and reasonably achieved.

Description

Technical Field

[0001] This specification belongs to the field of electrical data processing technology related to wind and solar energy, and in particular to an electrolytic cell configuration processing method and device based on fluctuating wind and solar coupled power generation. Background Art

[0002] With the promotion and development of wind and solar energy technologies, many power stations have begun to use wind-solar coupling technology to generate electricity, and convert the electricity obtained through wind-solar coupling into hydrogen energy and store it in electrolyzers, so that the hydrogen energy can be converted back into electricity and provided to downstream electricity users or fed into the power grid as needed.

[0003] However, wind-solar coupled power generation is easily affected by natural conditions, resulting in great uncertainty in the actual power generation situation. Based on the existing methods, when configuring and laying out electrolyzers for power stations, there are often problems with unreasonable configuration and layout. For example, the scale of electrolyzers laid out in some power stations is insufficient, resulting in the inability to convert all the electricity generated by wind-coupled power generation into hydrogen energy and store it in the electrolyzers, resulting in a large amount of abandoned electricity. For another example, the scale of electrolyzers laid out in some power stations is too large, which, on the one hand, increases the cost of building and maintaining the power station, affecting the overall economic benefits of the power station, and on the other hand, causes a large number of electrolyzers in the power station to be idle for a long time, resulting in a waste of equipment resources.

[0004] To address the above problems, no effective solution has been proposed yet. Summary of the invention

[0005] This specification provides an electrolytic cell configuration processing method and device based on fluctuating wind-solar coupled power generation, which can be well adapted to the wind-solar coupled power generation scenario with fluctuations, effectively take into account multiple factors such as cost, benefit, and utilization rate, and accurately and reasonably realize the layout of the electrolytic cell group of the target wind-solar coupled power station in the target area.

[0006] This specification provides an electrolyzer configuration processing method based on fluctuating wind-solar coupled power generation, including:

[0007] Acquire historical scenery data of the target area; wherein the historical scenery data includes scenery data of multiple historical time points, and the scenery data of the historical time points also carry a timestamp corresponding to the historical time point;

[0008] Determine decision-making impact data for target areas;

[0009] According to the preset construction rules, the wind-solar output curve is constructed using the historical wind-solar data of the target area; wherein the wind-solar output curve is used to characterize the reference power of wind-solar coupled power generation at various time points in a year;

[0010] According to the wind and solar power output curve, a matching gradient step is determined; and the wind and solar power output curve is processed using the gradient step to separate the base load component and the fluctuating load component;

[0011] Based on the preset matching rules and gradient step length, an optimization solution is performed according to the base load component, the fluctuating load component, and the decision-making influence data to determine a target configuration scheme that meets the requirements; wherein the preset matching rules include: the base load component preferentially matches the first standard square electrolytic cell, and the fluctuating load component preferentially matches the second standard square electrolytic cell, and the standard square of the first standard square electrolytic cell is greater than that of the second standard square electrolytic cell;

[0012] According to the target configuration scheme, a target electrolytic cell group is arranged for a target wind-solar coupling power station to store the electric energy generated by the wind-solar coupling power generation.

[0013] In one embodiment, the decision-influencing data includes at least one of the following: electrolytic cell equipment and auxiliary equipment parameters, construction cost, operation period cost, and operation period income;

[0014] Accordingly, determine the decision-making impact data for the target area, including:

[0015] Obtain electricity price data and grid rules for the target area;

[0016] The electricity price data and grid rules of the target area are used in combination to determine the decision-making impact data for the target area.

[0017] In one embodiment, according to a preset construction rule, the historical wind and solar data of the target area is used to construct a wind and solar output curve, including:

[0018] According to the timestamp, the historical wind and solar data of the target area are used to divide multiple power generation data groups; wherein one power generation data group corresponds to one month, and contains wind and solar data of multiple historical time points of the month in different years, and wind and solar data of multiple historical time points of different months adjacent to the month in the same year;

[0019] According to the plurality of power generation data groups, a plurality of corresponding power generation data matrices are constructed; wherein the plurality of power generation data matrices correspond to one month respectively;

[0020] Using a preset typical data generation model to process multiple power generation data matrices, a reference data set of multiple wind and solar power generation powers corresponding to different months is obtained;

[0021] Multiple wind and solar power generation reference data sets are spliced ​​and utilized to obtain the corresponding wind and solar power output curve.

[0022] In one embodiment, according to the wind and solar power output curve, determining the matching gradient step length includes:

[0023] Extracting graphic features from the wind and solar power output curve to obtain corresponding graphic features;

[0024] According to the graphical features, determining the fluctuation characteristics of the wind and solar power output curve;

[0025] According to the fluctuation characteristics, a matching gradient step length is determined.

[0026] In one embodiment, based on the preset matching rules and gradient step length, an optimization solution is performed according to the base load component, the fluctuating load component, and the decision-making influence data to determine a target configuration scheme that meets the requirements, including:

[0027] Construct an objective function group based on decision-making impact data; and construct objective constraints based on preset matching rules, base load components, and fluctuating load components;

[0028] According to the preset processing rules, multiple computing nodes and initial solutions of each computing node are determined;

[0029] Calling multiple computing nodes to perform multiple rounds of iterative solutions on the objective function group based on the objective constraint conditions and the initial solution to obtain corresponding objective processing results;

[0030] According to the target processing results, determine the target configuration plan that meets the requirements.

[0031] In one embodiment, calling multiple computing nodes to perform multiple rounds of iterative solutions on the objective function group based on the objective constraint conditions and the initial solution includes:

[0032] Call multiple computing nodes to perform the current round of iterative solution in the following way:

[0033] Obtain and filter out the retained solutions of the current round that meet the retention conditions based on the solutions of the previous round of each computing node;

[0034] Mark the computing nodes holding the reserved solutions of the current round as first-category nodes, and mark the other computing nodes among the multiple computing nodes except the first-category nodes as second-category nodes;

[0035] Performing preset coding processing on the reserved solution of the current round to obtain corresponding coding data; and performing transformation processing according to the coding data to obtain multiple transformation codes;

[0036] Decoding the transformation code to obtain multiple transformation solutions of the current round; and assigning the multiple transformation solutions of the current round to corresponding second-type nodes;

[0037] The first type of nodes and the second type of nodes are called to iteratively solve the current round of retained solutions and the current round of transformed solutions according to the local iterative solution rules and gradient step size, respectively, to obtain the current round of solutions of each computing node.

[0038] In one embodiment, after calling the first type of nodes and the second type of nodes to perform iterative solutions using the retained solution of the current round and the modified solution of the current round respectively according to the local iterative solution rule and the gradient step size to obtain the solution of the current round of each computing node, the method further includes:

[0039] Check whether the iterative solution termination condition is met;

[0040] When it is determined that the termination condition of the iterative solution is met, the solution with the highest matching degree with the objective function group is selected from the solutions of the current round of multiple computing nodes as the target processing result.

[0041] This specification also provides an electrolyzer configuration processing device based on fluctuating wind-solar coupled power generation, including:

[0042] An acquisition module, used to acquire historical scenery data of a target area; wherein the historical scenery data includes scenery data of multiple historical time points, and the scenery data of the historical time points also carries a timestamp corresponding to the historical time point;

[0043] A determination module, for determining decision-making impact data for a target area;

[0044] A construction module, used to construct a wind-solar output curve according to a preset construction rule and using historical wind-solar data of a target area; wherein the wind-solar output curve is used to characterize the reference power of wind-solar coupled power generation at various time points in a year;

[0045] A splitting module is used to determine a matching gradient step length according to the wind and solar power output curve; and use the gradient step length to process the wind and solar power output curve to split the base load component and the fluctuating load component;

[0046] A solution module is used to optimize and solve according to the base load component, the fluctuating load component, and the decision-making influence data based on a preset matching rule and a gradient step size, and determine a target configuration scheme that meets the requirements; wherein the preset matching rule includes: the base load component preferentially matches the first standard square electrolytic cell, and the fluctuating load component preferentially matches the second standard square electrolytic cell, and the standard square of the first standard square electrolytic cell is greater than that of the second standard square electrolytic cell;

[0047] A deployment module is used to deploy a target electrolytic cell group for a target wind-solar coupling power station according to the target configuration plan, so as to store the electric energy generated by the wind-solar coupling power generation.

[0048] This specification also provides a server, including a processor and a memory for storing processor executable instructions, and when the processor executes the instructions, the relevant steps of the electrolyzer configuration processing method based on fluctuating wind-solar coupled power generation are implemented.

[0049] The present specification also provides a computer-readable storage medium having computer instructions stored thereon, which, when executed by a processor, implement the steps of the electrolyzer configuration processing method based on fluctuating wind-solar coupled power generation.

[0050] Based on the electrolyzer configuration processing method and device based on fluctuating wind-solar coupled power generation provided in this specification, first obtain the historical wind-solar data of the target area; at the same time, determine the decision-making influence data for the target area; according to the preset construction rules, use the historical wind-solar data of the target area to construct a wind-solar output curve with good stability that can fully and representatively reflect the fluctuation changes of wind-solar coupled power generation throughout the year; then determine the matching gradient step according to the wind-solar output curve; and use the gradient step to split the base load component and the fluctuating load component by processing the wind-solar output curve; and based on the preset matching rules and gradient step, optimize and solve according to the base load component, the fluctuating load component, and the decision-making influence data to determine a target configuration scheme that meets the requirements; wherein the preset matching rules include: the base load component preferentially matches the first standard electrolytic cell, and the fluctuating load component preferentially matches the second standard electrolytic cell, and the standard of the first standard electrolytic cell is larger than the second standard electrolytic cell; according to the target configuration scheme, arrange the target electrolytic cell group for the target wind-solar coupled power station. This enables it to better adapt to the fluctuating wind-solar coupled power generation scenarios, fully consider the fluctuating characteristics of wind and solar data in the target area throughout the year, effectively balance multiple factors such as cost, benefit, and utilization rate, accurately and reasonably implement the layout of the electrolytic cell group of the target wind-solar coupled power station in the target area, and improve the overall benefits of the target wind-solar coupled power station. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the embodiments of this specification, the drawings required for use in the embodiments will be briefly introduced below. The drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0052] Figure 1 It is a flow chart of an electrolyzer configuration processing method based on fluctuating wind-solar coupled power generation provided by an embodiment of this specification;

[0053] Figure 2It is a schematic diagram of an embodiment of an electrolyzer configuration processing method based on fluctuating wind-solar coupled power generation provided by an embodiment of this specification, in a scenario example;

[0054] Figure 3 It is a schematic diagram of an embodiment of an electrolyzer configuration processing method based on fluctuating wind-solar coupled power generation provided by an embodiment of this specification, in a scenario example;

[0055] Figure 4 It is a schematic diagram of an embodiment of an electrolyzer configuration processing method based on fluctuating wind-solar coupled power generation provided by an embodiment of this specification, in a scenario example;

[0056] Figure 5 It is a schematic diagram of the structure of a server provided by an embodiment of this specification;

[0057] Figure 6 It is a schematic diagram of the structure of an electrolyzer configuration processing device based on fluctuating wind-solar coupled power generation provided by an embodiment of this specification;

[0058] Figure 7 It is a schematic diagram of an embodiment of an electrolyzer configuration processing method based on fluctuating wind-solar coupled power generation provided by an embodiment of this specification, in a scenario example. DETAILED DESCRIPTION

[0059] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this specification.

[0060] It should be noted that in the embodiments of this specification, certain software, components, models and other existing solutions in the industry may be mentioned, and they should be regarded as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of this application, but it does not mean that the applicant has or will necessarily use the solution.

[0061] See also Figure 1 As shown, the embodiment of this specification provides a method for processing the configuration of an electrolyzer based on fluctuating wind-solar coupled power generation. The method is specifically applied to the server side. When implemented specifically, the method may include the following contents:

[0062] S101: Acquire historical scenery data of a target area; wherein the historical scenery data includes scenery data at multiple historical time points, and the scenery data at the historical time points also carry a timestamp corresponding to the historical time point;

[0063] S102: Determine decision-making impact data for the target area;

[0064] S103: constructing a wind-solar output curve according to a preset construction rule and using historical wind-solar data of the target area; wherein the wind-solar output curve is used to characterize the reference power of wind-solar coupled power generation at various time points in a year;

[0065] S104: determining a matching gradient step length according to the wind and solar power output curve; and using the gradient step length to process the wind and solar power output curve to separate the base load component and the fluctuating load component;

[0066] S105: Based on the preset matching rules and gradient step length, according to the base load component, the fluctuating load component, and the decision-making influence data, an optimization solution is performed to determine a target configuration scheme that meets the requirements; wherein the preset matching rules include: the base load component preferentially matches the first standard square electrolytic cell, and the fluctuating load component preferentially matches the second standard square electrolytic cell, and the standard square of the first standard square electrolytic cell is greater than that of the second standard square electrolytic cell;

[0067] S106: According to the target configuration plan, a target electrolytic cell group is arranged for the target wind-solar coupling power station to store the electric energy generated by the wind-solar coupling power generation.

[0068] Among them, the above-mentioned target area can be specifically understood as an area where a target wind-solar coupled power station is deployed.

[0069] The above-mentioned target wind-solar coupling power station can be specifically understood as a new energy power station that uses wind-solar coupling power generation technology to generate electricity. The above-mentioned wind-solar coupling power generation specifically refers to a power generation method that combines wind energy and solar energy. Based on this power generation method, through the joint action of wind turbines and solar panels, the complementarity of wind energy and solar energy resources can be effectively utilized to provide a relatively stable and reliable power supply.

[0070] The historical wind and solar data of the target area can be specifically understood as the historical wind and solar data of the target area in the past years, for example, the real wind and solar data of 8760 in each of the past five years in the target area. The wind and solar data can include wind data, light data, and the like.

[0071] Specifically, the historical scenery data may include scenery data of multiple consecutive historical time points, wherein the time interval between two adjacent historical time points may be 1 hour.

[0072] Specifically, the historical scenery data may also carry a timestamp corresponding to a historical time point. Further, the historical scenery data may also include relevant information such as year information and month information when the data was collected.

[0073] For example, the wind and solar data at a historical time point can be expressed in the following form (F, G, T, Y, M). Among them, the above F represents the wind data at the historical time point, G represents the light data at the historical time point, T represents the timestamp corresponding to the historical time point, Y represents the year, and M represents the month. Furthermore, the wind and solar data at the above historical time point can also be expressed in the following form (P, T, Y, M). Among them, P represents the power generation at the historical time point determined based on the wind data and light data at the time point, combined with the parameters of the generator set of the target wind-solar coupled power station.

[0074] The above decision-making influencing data can be specifically understood as parameter data that will affect the configuration and layout of the electrolytic cell based on multiple different angles such as cost, benefit, and utilization rate.

[0075] The above-mentioned wind-solar output curve is specifically automatically constructed based on artificial intelligence, and can comprehensively characterize the curve data of the reference power of wind-solar coupling power generation that is representative and relatively stable at each time point in a whole year. Among them, the time interval between two adjacent time points can be 1 hour. Specifically, the above-mentioned wind-solar output curve can be a curve graph drawn with time as the horizontal axis and the power generation power of wind-solar coupling power generation as the vertical axis.

[0076] Accordingly, in specific implementation, the above-mentioned wind and solar power output curve can be utilized, and the gradient wavelength determined based on the fluctuation characteristics of the curve can be used to finely divide the base load component that is relatively stable at different times and the fluctuating load component that changes relatively between different time points.

[0077] The preset matching rules may specifically include: the base load component is preferentially matched with the first standard electrolytic cell, and the fluctuating load component is preferentially matched with the second standard electrolytic cell, and the standard of the first standard electrolytic cell is greater than that of the second standard electrolytic cell.

[0078] The first electrolytic cell may also be referred to as a large electrolytic cell, specifically an electrolytic cell with a capacity of greater than 1000. The second electrolytic cell may also be referred to as a small electrolytic cell, specifically an electrolytic cell with a capacity of less than 1000.

[0079] Specifically, the size of the first standard electrolytic cell is larger than that of the second standard electrolytic cell; correspondingly, the installation cost and maintenance difficulty of the first standard electrolytic cell are higher than those of the second standard electrolytic cell, but the response speed of the first standard electrolytic cell is lower than that of the second standard electrolytic cell.

[0080] Based on the above preset matching rules, in the process of optimization solution, the first standard electrolytic cell with higher cost can be used preferentially to match the relatively stable extremely low load component, and the second standard electrolytic cell with lower cost and more flexibility can be used preferentially to match the relatively changing fluctuating load component.

[0081] Furthermore, the second standard electrolyzer may include electrolyzers of various different standards, for example, an electrolyzer of 500, an electrolyzer of 300, an electrolyzer of 200, an electrolyzer of 50, etc. Accordingly, in specific implementation, a plurality of second standard electrolyzers of various different standards and the first standard electrolyzer may be used in combination to better match the fluctuation characteristics of wind and solar data, thereby enabling relatively more reasonable and accurate configuration and layout.

[0082] Based on the above embodiment, the historical wind and solar data of the target area can be obtained and used to construct a wind and solar output curve with good stability, which can fully and representatively reflect the fluctuation and change of wind-solar coupled power generation power throughout the year; then, the wind and solar output curve is used to finely divide the relatively stable base load component and the relatively changing fluctuating load component using the gradient step; then, based on the preset matching rules and gradient step, according to the base load component, the fluctuating load component, and the decision-making influencing data, through optimization solution, the target configuration scheme of the target wind-solar coupled power station in the target area is efficiently and accurately determined; and then, based on the target configuration scheme, the layout of the electrolytic cell group for the target wind-solar coupled power station can be accurately and reasonably realized.

[0083] In some embodiments, after acquiring the historical scenery data of the target area, the method may be implemented by preprocessing the historical scenery data, wherein the preprocessing includes: default value processing, anomaly detection processing, noise filtering processing, etc.

[0084] The above-mentioned abnormality detection process includes: for the wind and solar data at each historical time point, detecting whether the difference between the data value of the power generation (or wind data and light data) at the historical time point and the average value of the data values ​​of a preset number of (for example, 10) historical time points adjacent to the historical time point is greater than a preset amplitude threshold. If it is greater, it is determined that the wind and solar data at the historical time point is abnormal. At this time, the data values ​​of the preset number of time points adjacent to the historical time point can be obtained and used to perform data fitting to obtain a fitting curve; then based on the fitting curve, the fitting value of the historical time point is determined; and the original data value of the historical time point is replaced by the fitting value.

[0085] In some embodiments, the decision-influencing data may specifically include at least one of the following: electrolyzer equipment and auxiliary machine parameters, construction cost, operation period cost, operation period income, etc.;

[0086] Accordingly, the above-mentioned determination of decision-making impact data for the target area may include:

[0087] S1: Obtain electricity price data and grid rules in the target area;

[0088] S2: Determine decision-making impact data for the target area by combining electricity price data and grid rules for the target area.

[0089] The above-mentioned electrolytic cell equipment and auxiliary machine parameters may specifically include: the current price of each standard electrolytic cell (including the first standard electrolytic cell and the second standard electrolytic cell), and the price and floor space of auxiliary machines of corresponding specifications.

[0090] The above construction costs may specifically include one or more of the following: wind-solar coupling power generation equipment costs, hydrogen production equipment costs, energy storage equipment costs, transmission costs, etc. Furthermore, the above construction costs may also include other costs such as various land acquisition fees and pre-construction fees that need to be paid during the construction period.

[0091] The above-mentioned operating period costs may specifically include one or more of the following: personnel costs, material costs, repair costs, insurance premiums, construction period interest, rent paid regularly during the operating period, energy storage core replacement costs, electrolyzer maintenance costs, depreciation, as well as safety production fees, other manufacturing costs, other management fees, water and electricity costs, catalyst fees, etc. incurred during hydrogen production.

[0092] The above-mentioned operating period income may specifically include: hydrogen price data, hydrogen sales volume, electricity sales volume, electricity price data, etc.

[0093] The above-mentioned grid rules may specifically include: grid-connected rules, or off-grid rules. The above-mentioned grid-connected rules define the time point at which power can be fed into the grid, the amount of power required to be fed into the grid at different time points, relevant reward data and penalty data, etc. The above-mentioned off-grid rules define the time point at which the grid stipulates that power can be rejected, and the triggering conditions for rejecting power feed-in, etc.

[0094] In specific implementation, the electricity price data and grid rules of the target area can be used in combination to precisely determine the decision-making impact data corresponding to each time point for the target area.

[0095] Based on the above embodiments, relatively accurate, effective and fine-grained decision impact data based on time points can be obtained, so that a relatively better objective function group and objective constraint conditions can be constructed based on the above decision impact data.

[0096] In some embodiments, see Figure 2As shown, the above-mentioned wind and solar output curve is constructed according to the preset construction rules and using the historical wind and solar data of the target area. When implemented specifically, the following contents may be included:

[0097] S1: Based on the timestamp, the historical wind and solar data of the target area are used to divide multiple power generation data groups; wherein one power generation data group corresponds to one month, and includes wind and solar data of multiple historical time points of the month in different years, and wind and solar data of multiple historical time points of different months adjacent to the month in the same year;

[0098] S2: constructing a corresponding plurality of power generation data matrices according to the plurality of power generation data groups; wherein the plurality of power generation data matrices respectively correspond to a month;

[0099] S3: using a preset typical data generation model to process multiple power generation data matrices to obtain reference data groups of multiple wind and solar power generation powers corresponding to different months;

[0100] S4: splicing and utilizing multiple wind and solar power generation power reference data sets to obtain corresponding wind and solar power output curves.

[0101] In specific implementation, the wind and solar data (for example, power generation) of multiple historical time points in different years but belonging to the same month can be screened out according to the timestamp, combined with the year information and the month information, and the wind and solar data of multiple historical time points in adjacent months of the same year (for example, the previous month and the next month) can be combined to obtain a power generation data group corresponding to one month. In the above manner, 12 power generation data groups corresponding to 12 months can be obtained.

[0102] For each power generation data group, according to the corresponding matrix construction rules, the wind and solar data of multiple historical time points in the power generation data group are used to construct a power generation data matrix corresponding to the month. In the power generation data matrix, each row element corresponds to a year, and contains the data values ​​of wind and solar data of multiple historical time points of the corresponding month and adjacent months arranged in order; each row element corresponds to a timestamp, and contains the data values ​​of wind and solar data of different years at the same historical time point corresponding to the timestamp.

[0103] The pre-trained preset typical data generation model is used to process each power generation data matrix to obtain multiple wind and solar power generation reference data groups corresponding to different months. Each wind and solar power generation reference data group contains representative, relatively stable, and high reference value power generation reference data values ​​at each time point in the corresponding month.

[0104] Through the above method, using the preset typical data generation model, taking the month as the group unit of the time node, for the wind and solar data at each time point in each month, multi-angle learning and sorting are carried out based on the vertical dimension (adjacent months in the same year) and the horizontal dimension (the same month in different years), so as to effectively reduce the deviation impact caused by the volatility of wind and solar data, and obtain relatively stable, representative reference data groups with good reference value.

[0105] Furthermore, the above-mentioned multiple wind and solar power generation reference data groups can be used to construct curve segments for a single month respectively; then, multiple curve segments can be spliced ​​in order according to the order of the months; and the connection positions of adjacent curve segments can be smoothed to obtain the required wind and solar power output curve that can correspond to the whole year.

[0106] Among them, the above-mentioned preset typical data generation model can be specifically understood as a model that is obtained by deep learning training using big data samples in advance, which can take months as the overall field of view, and extract and integrate the volatility feature vectors of the data from two different dimensions, namely, vertical and horizontal, for a single time point; and then, based on the integrated volatility feature vector of the data at the time point, combined with the influence relationship of the data at other time points adjacent to the time point in the vertical and horizontal directions, determine and output the reference power of the typical wind and solar power generation at the time point.

[0107] Based on the above embodiments, by using a preset typical data generation model to process a power generation data matrix of a corresponding structure, the fluctuation characteristics of wind and solar data can be fully considered, and a wind and solar output curve with good representativeness and high reference value can be efficiently and accurately constructed.

[0108] In some embodiments, according to the wind and solar power output curve, the above determination of the matching gradient step length may include the following contents during specific implementation:

[0109] S1: extracting graphic features from the wind and solar power output curve to obtain corresponding graphic features;

[0110] S2: determining the fluctuation characteristics of the wind and solar power output curve according to the graphic characteristics;

[0111] S3: Determine a matching gradient step length according to the fluctuation characteristics.

[0112] In specific implementation, multiple adjacent graphic features can be divided into a graphic feature group; then, the adjacent graphic feature groups are combined and used to determine multiple fluctuation difference features through feature difference calculation; and then, based on the multiple fluctuation difference features, the fluctuation characteristics for the wind and solar output curve are determined.

[0113] Based on the above embodiments, the fluctuation characteristics of the wind and solar power output curve can be fully explored and utilized to construct a gradient step size with better effect on the wind and solar power output curve.

[0114] In specific implementation, the gradient step can be used to interpolate the wind and solar output curve to obtain a trapezoidal combination diagram that is close to the wind and solar output curve; the graphic area of ​​the time points whose height is less than the threshold value is segmented from the trapezoidal combination diagram as the base load component (which can be recorded as LB); the remaining graphic area except the base load component in the figure surrounded by the wind and solar output curve and the horizontal axis is taken as the fluctuating load component (which can be recorded as LF). In this way, the fluctuation characteristics of wind and solar data are fully considered, and the base load component and fluctuating load component with higher application value are accurately divided.

[0115] In some embodiments, see Figure 3 As shown, the above optimization solution is performed based on the base load component, the fluctuating load component, and the decision-making influence data to determine a target configuration scheme that meets the requirements. When implemented specifically, the following contents may be included:

[0116] S1: Construct an objective function group based on decision-making impact data; and construct objective constraints based on preset matching rules, base load components, and fluctuating load components;

[0117] S2: Determine multiple computing nodes and initial solutions of each computing node according to a preset processing rule;

[0118] S3: calling multiple computing nodes to perform multiple rounds of iterative solutions on the objective function group based on the objective constraint conditions and the initial solution to obtain corresponding objective processing results;

[0119] S4: Determine a target configuration plan that meets the requirements based on the target processing results.

[0120] In specific implementation, the following functions can be constructed based on the decision-making influencing data: economic benefit maximization function, idle electrolyzer standard volume minimization function, and abandoned power minimization function; and then the above functions are used together to construct the objective function group. At the same time, the corresponding target constraint conditions are constructed based on the preset matching rules, grid rules, and the performance upper limit of the generator set parameters of the target wind-solar coupled power station.

[0121] The decision variables to be optimized and determined contained in the above objective function group may at least include: the number of first standard square electrolytic cells configured, and the number of second standard square electrolytic cells configured with different standard square values.

[0122] Furthermore, the decision variables may also include: the connection relationship between the first standard electrolyzer and the second standard electrolyzer with different standard values, and the connection relationship between the second standard electrolyzers with different standard values. Based on the above connection relationship, it can be used to determine the priority order of using the second standard electrolyzer when the hydrogen energy storage capacity of the first standard electrolyzer reaches the full value; and determine the priority order of using the first standard electrolyzer and the second standard electrolyzer when external conversion and provision of electric energy are required.

[0123] The above-mentioned preset processing rules may specifically be obtained by integrating multiple optimization algorithms (for example, genetic algorithm, simulated annealing algorithm, etc.), and are solution rules suitable for wind-solar coupled power generation scenarios with fluctuations.

[0124] In specific implementation, the overall amount of computation can be estimated based on the preset processing rules and the data size of the fluctuating load component; and the appropriate number of computing nodes can be determined based on the estimated amount of computation.

[0125] The computing nodes mentioned above can be relatively independent computing nodes (e.g., computer nodes) in a distributed cluster. Each computing node can be regarded as a population individual, and is deployed with corresponding local iterative solution rules and connected to different computing nodes. The distributed cluster can be understood as a system composed of multiple computer nodes, which communicate and collaborate with each other through the network to jointly complete a task or provide a service, and have the advantages of high availability, high performance, and scalability. In this way, the performance advantages of the distributed system can be utilized to efficiently complete the relevant solutions.

[0126] In specific implementation, multiple initial solutions can be randomly generated and assigned to each computing node; then, according to the preset processing rules, multiple computing nodes are called to perform multiple rounds of iterative solutions to the optimization problem of the objective function group based on the target constraints and the initial solutions, so as to obtain a target configuration solution that meets the requirements.

[0127] Based on the above embodiment, multiple computing nodes can be called according to preset processing rules to solve through multiple rounds of iterations, which can avoid falling into a local optimal solution and efficiently and accurately find a target configuration solution that meets the requirements.

[0128] In some embodiments, the above-mentioned calling of multiple computing nodes performs multiple rounds of iterative solutions on the objective function group based on the objective constraint conditions and the initial solution. When specifically implemented, refer to Figure 4 As shown, multiple computing nodes can be called in the following way to perform the current round of iterative solution:

[0129] S1: Obtain and filter out the reserved solutions of the current round that meet the reservation conditions based on the solutions of the previous round of each computing node;

[0130] S2: Mark the computing nodes holding the reserved solutions of the current round as first-class nodes, and mark the other computing nodes among the multiple computing nodes except the first-class nodes as second-class nodes;

[0131] S3: Performing preset coding processing on the reserved solution of the current round to obtain corresponding coding data; and performing transformation processing according to the coding data to obtain multiple transformation codes;

[0132] S4: Decode the transformation code to obtain multiple transformation solutions of the current round; and assign the multiple transformation solutions of the current round to corresponding second-type nodes;

[0133] S5: Call the first type of nodes and the second type of nodes to perform iterative solutions using the retained solution of the current round and the transformed solution of the current round respectively according to the local iterative solution rules and gradient step size, and obtain the solution of the current round of each computing node.

[0134] In specific implementation, the solutions of the previous round of each computing node can be encoded according to the preset encoding rules to obtain the corresponding encoded data of the solution of the previous round; then, a selection operator constructed by a pre-configured loss function based on the objective function group is used to process the encoded data of the solution of the previous round to determine the selected encoded data; the solution corresponding to the selected encoded data is determined as the retained solution of the current round that meets the retention conditions.

[0135] The above-mentioned preset encoding rule can be a floating-point encoding rule. Based on the floating-point encoding rule, the data value can be represented by a floating-point number within a certain range, which is suitable for integration with other types of optimization algorithms, and helps to improve the complexity of solving the calculation, realize the search of a relatively larger solution space, and avoid falling into the local optimal solution.

[0136] In specific implementation, the pre-configured crossover operator and mutation operator can be used to process the encoded data of the retained solution of the current round to achieve transformation processing and obtain multiple corresponding transformation codes; then, according to the preset encoding rules, the above-mentioned transformation codes are decoded respectively to obtain the corresponding transformation solution of the current round; and the transformation solution of the current round is assigned to the corresponding second-type node to replace the original solution of the second-type node in the previous round.

[0137] It is also possible to encode the solution of the previous round of the second-type node according to the preset encoding rules to obtain the starting code; then use the multiple encoding data obtained based on the retained solution of the current round, combined with the above-mentioned starting code, to calculate the corresponding optimization vector; then use the optimization vector to optimize and transform the starting codes of the second-type nodes respectively, to obtain the transformed codes of each second-type node.

[0138] Then, the first type of nodes are called to perform multiple iterative solutions separately using the retained solution of the current round according to the local iterative solution rules and gradient step size; at the same time, the second type of nodes are called to perform multiple iterative solutions separately using the modified solution of the current round according to the local iterative solution rules and gradient step size to complete the iterative solution of the current round and obtain the solution of the current round of each computing node.

[0139] The above-mentioned local iterative solution rules may specifically be solution rules modified and designed based on an optimization algorithm.

[0140] Specifically, different computing nodes can be deployed with different local iterative solution rules. For example, the local iterative solution rules deployed by computing nodes whose node numbers end with 1, 3, and 5 can be iterative solution rules based on the simulated annealing algorithm; the local iterative solution rules deployed by computing nodes whose node numbers end with 2, 4, and 6 can be iterative solution rules based on the conjugate gradient algorithm; the local iterative solution rules deployed by computing nodes whose node numbers end with 0, 7, 9, and 8 can be iterative solution rules based on the quasi-Newton algorithm.

[0141] In this way, in each round of iterative solution process, the advantages of different optimization algorithms can be fully utilized, the search mechanism can be effectively increased, and the search space can be expanded, so that the optimal solution can be searched more comprehensively and finely.

[0142] Based on the above embodiments, according to the preset processing rules, by integrating and using a variety of different optimization algorithms to complete each round of iterative solution, the efficiency and accuracy of the solution operation can be effectively improved, and the overall processing time can be shortened.

[0143] In some embodiments, after calling the first type of nodes and the second type of nodes to perform iterative solutions using the retained solution of the current round and the modified solution of the current round respectively according to the local iterative solution rule and the gradient step size to obtain the solution of the current round of each computing node, the method may further include the following contents when it is specifically implemented:

[0144] S1: Check whether the iterative solution termination condition is met;

[0145] S2: When it is determined that the termination condition of the iterative solution is met, the solution with the highest matching degree with the objective function group is selected from the solutions of the current round of multiple computing nodes as the target processing result.

[0146] In specific implementation, it is possible to detect whether the number of rounds in the current round has reached a specified round value; when it is determined that the specified round value has been reached, the deviation values ​​between the solutions of the current rounds of multiple computing nodes are calculated, and it is detected whether the deviation value is less than a preset deviation threshold; when it is determined that it is less than the preset deviation threshold, it can be determined that a stable solution has been obtained, and then it can be determined that the termination condition of the iterative solution is met.

[0147] When it is determined that the termination conditions of the iterative solution are met, the solutions of the current round of multiple computing nodes can be substituted into the objective function group respectively to obtain a joint evaluation result based on the objective function value; according to the joint evaluation result, the solution with the best effect based on multiple factors such as cost, benefit, and utilization rate is screened out from the solutions of the current round of multiple computing nodes as the solution with the highest matching degree with the objective function group and as the target processing result.

[0148] Specifically, for example, the solutions of the current round of multiple computing nodes can be respectively substituted into the objective function group, and the IRR economic benefit index can be calculated using the objective function group; and the IRR economic benefit index can be used as the joint evaluation result.

[0149] On the contrary, when it is determined that the iterative solution termination condition is not met, the above process can be repeated to perform the next round of iterative solution until the target processing result is obtained.

[0150] Based on the above embodiments, multiple rounds of iterative solutions can be used to accurately obtain target processing results that meet the requirements.

[0151] In some embodiments, after the target electrolyzer group for the target wind-solar coupled power station is arranged according to the target configuration scheme, the method may further include the following contents when it is specifically implemented:

[0152] S1: receiving electricity price data and grid rule change data about the target area;

[0153] S2: Reconstruct the objective function group and objective constraints based on the changed data;

[0154] S3: Determine multiple computing nodes according to a preset processing rule; and determine an initial solution for each computing node based on the target processing result that has been determined previously;

[0155] S4: Call multiple computing nodes to control the configuration quantity of the first standard electrolytic cell to remain unchanged according to the target processing result; and perform multiple rounds of iterative solutions on the target function group based on the target constraint conditions and the initial solution to obtain a configuration optimization solution;

[0156] S5: According to the configuration optimization plan, the previously deployed first standard electrolyzer is kept unchanged, and the target electrolyzer group is optimized and improved to obtain an optimized target electrolyzer group to adapt to the latest wind-solar coupled power generation scenario.

[0157] Based on the above embodiments, the target electrolytic cell group can be optimized and updated efficiently at a relatively low cost to meet the latest scenario requirements.

[0158] In some embodiments, after the target electrolyzer group for the target wind-solar coupling power station is arranged according to the target configuration scheme, the method may also include: when the energy storage capacity of the first standard electrolyzer is detected to be full, the startup priority of the second standard electrolyzer is determined according to the connection relationship between the first standard electrolyzer and the second standard electrolyzer in the target configuration scheme; and the second standard electrolyzer is started step by step in sequence according to the startup priority. This can effectively store the newly added wind-solar coupling power generation, better balance the overall cost, and obtain better benefits.

[0159] As can be seen from the above, the electrolyzer configuration processing method based on fluctuating wind-solar coupled power generation provided in the embodiment of this specification first obtains the historical wind-solar data of the target area; at the same time, determines the decision-making influence data for the target area; according to the preset construction rules, the historical wind-solar data of the target area is used to construct a wind-solar output curve with good stability, which can fully and representatively reflect the fluctuation changes of wind-solar coupled power generation throughout the year; then, according to the wind-solar output curve, a matching gradient step is determined; and the gradient step is used to process the wind-solar output curve to split the base load component and the fluctuating load component; and based on the preset matching rules and gradient step, according to the base load component, the fluctuating load component, and the decision-making influence data, an optimization solution is performed to determine a target configuration scheme that meets the requirements; wherein the preset matching rules include: the base load component preferentially matches the first standard electrolytic cell, and the fluctuating load component preferentially matches the second standard electrolytic cell, and the standard of the first standard electrolytic cell is larger than the second standard electrolytic cell; according to the target configuration scheme, a target electrolytic cell group for the target wind-solar coupled power station is arranged. This enables it to better adapt to the fluctuating wind-solar coupled power generation scenarios, fully consider the fluctuation characteristics of wind and solar data in the target area throughout the year, effectively take into account multiple factors such as cost, benefit, and utilization rate, and accurately and reasonably realize the layout of the electrolytic cell group of the target wind-solar coupled power station in the target area.

[0160] This specification embodiment provides a server, referring to Figure 5 The server includes a network communication port 501, a processor 502 and a memory 503, and the above structures are connected through internal cables so that each structure can perform specific data interaction.

[0161] Among them, the network communication port 501 can be specifically used to obtain historical scenery data of the target area; wherein the historical scenery data includes scenery data of multiple historical time points, and the scenery data of the historical time points also carry a timestamp corresponding to the historical time point.

[0162] The processor 502 can be specifically used to determine decision-making influencing data for a target area; construct a wind-solar output curve using historical wind-solar data of the target area according to preset construction rules; wherein the wind-solar output curve is used to characterize the reference power of wind-solar coupled power generation at various time points within a year; determine a matching gradient step according to the wind-solar output curve; and use the gradient step to process the wind-solar output curve to split the base load component and the fluctuating load component; based on the preset matching rules and gradient step, perform optimization and solution according to the base load component, the fluctuating load component, and the decision-making influencing data to determine a target configuration scheme that meets the requirements; wherein the preset matching rules include: the base load component preferentially matches the first standard electrolytic cell, and the fluctuating load component preferentially matches the second standard electrolytic cell, and the standard of the first standard electrolytic cell is larger than that of the second standard electrolytic cell; according to the target configuration scheme, a target electrolytic cell group for the target wind-solar coupled power station is arranged to store the electric energy generated by the wind-solar coupled power generation.

[0163] The memory 503 can be specifically used to store corresponding instruction programs, as well as decision-making influencing data, wind and solar power output curves, base load components, fluctuating load components, objective function groups, objective constraint conditions and other related data.

[0164] Based on the above method, the relevant structural performance of the server can be effectively utilized, the data processing speed of the electronic equipment can be improved, and the data processing of the electrolyzer based on the fluctuating wind-solar coupled power generation can be efficiently realized.

[0165] In this embodiment, the network communication port 501 can be a virtual port that is bound to different communication protocols so that different data can be sent or received. For example, the network communication port can be a port responsible for web data communication, a port responsible for FTP data communication, or a port responsible for email data communication. In addition, the network communication port can also be a physical communication interface or communication chip. For example, it can be a wireless mobile network communication chip, such as GSM, CDMA, etc.; it can also be a Wifi chip; it can also be a Bluetooth chip.

[0166] In this embodiment, the processor 502 may be implemented in any appropriate manner. For example, the processor may take the form of a microprocessor or a processor and a computer-readable medium storing a computer-readable program code (such as software or firmware) executable by the (micro)processor, a logic gate, a switch, an application specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller, etc. This specification does not limit this.

[0167] In this embodiment, the memory 503 may include multiple levels. In a digital system, anything that can store binary data can be a memory; in an integrated circuit, a circuit with a storage function but no physical form is also called a memory, such as RAM, FIFO, etc.; in a system, a storage device with a physical form is also called a memory, such as a memory stick, TF card, etc.

[0168] The embodiments of the present specification also provide a computer-readable storage medium based on the above-mentioned electrolyzer configuration processing method based on fluctuating wind-solar coupled power generation, wherein the computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed, the following steps are implemented: obtaining historical wind-solar data of the target area; wherein the historical wind-solar data includes wind-solar data of multiple historical time points, and the wind-solar data of the historical time points also carry timestamps corresponding to the historical time points; determining decision-making influencing data for the target area; constructing a wind-solar output curve using the historical wind-solar data of the target area according to preset construction rules; wherein the wind-solar output curve is used to characterize the reference of wind-solar coupled power generation at various time points within a year. Power; according to the wind-solar output curve, determine the matching gradient step; and use the gradient step to process the wind-solar output curve, and split the base load component and the fluctuating load component; based on the preset matching rules and gradient step, according to the base load component, the fluctuating load component, and the decision-making influence data, optimize and solve, and determine the target configuration scheme that meets the requirements; wherein the preset matching rules include: the base load component preferentially matches the first standard square electrolytic cell, and the fluctuating load component preferentially matches the second standard square electrolytic cell, the standard square of the first standard square electrolytic cell is larger than the second standard square electrolytic cell; according to the target configuration scheme, a target electrolytic cell group for the target wind-solar coupling power station is arranged to store the electric energy generated by the wind-solar coupling power generation.

[0169] In this embodiment, the storage medium includes but is not limited to a random access memory (RAM), a read-only memory (ROM), a cache, a hard disk (HDD) or a memory card. The memory may be used to store computer program instructions. The network communication unit may be an interface for network connection communication set in accordance with the standard specified by the communication protocol.

[0170] In this embodiment, the functions and effects specifically implemented by the program instructions stored in the computer-readable storage medium can be explained in comparison with other implementations and will not be described in detail here.

[0171] The embodiment of the present specification also provides a computer program product, which at least includes a computer program, and when the computer program is executed by a processor, the following method steps are implemented: obtaining historical wind and solar data of a target area; wherein the historical wind and solar data includes wind and solar data of multiple historical time points, and the wind and solar data of the historical time points also carry a timestamp corresponding to the historical time point; determining decision-making impact data for the target area; constructing a wind and solar output curve using the historical wind and solar data of the target area according to a preset construction rule; wherein the wind and solar output curve is used to characterize the reference power of wind-solar coupled power generation at each time point in a year; and determining a matching wind and solar output curve according to the wind and solar output curve. Gradient step length; and use the gradient step length to process the wind-solar output curve, and split the base load component and the fluctuating load component; based on the preset matching rules and gradient step length, according to the base load component, the fluctuating load component, and the decision-making influencing data, optimize and solve, and determine the target configuration scheme that meets the requirements; wherein the preset matching rules include: the base load component preferentially matches the first standard square electrolytic cell, and the fluctuating load component preferentially matches the second standard square electrolytic cell, the standard square of the first standard square electrolytic cell is larger than that of the second standard square electrolytic cell; according to the target configuration scheme, a target electrolytic cell group for the target wind-solar coupling power station is arranged to store the electric energy generated by the wind-solar coupling power generation.

[0172] See also Figure 6 As shown, the embodiment of this specification also provides an electrolyzer configuration processing device based on fluctuating wind-solar coupled power generation, and the device may specifically include the following structural modules:

[0173] The acquisition module 601 may be specifically used to acquire historical scenery data of a target area; wherein the historical scenery data includes scenery data of multiple historical time points, and the scenery data of the historical time points also carries a timestamp corresponding to the historical time point;

[0174] A determination module 602 may be specifically used to determine decision-making impact data for a target area;

[0175] The construction module 603 may be specifically used to construct a wind-solar output curve according to a preset construction rule and using historical wind-solar data of a target area; wherein the wind-solar output curve is used to characterize the reference power of wind-solar coupled power generation at various time points in a year;

[0176] The splitting module 604 can be specifically used to determine a matching gradient step length according to the wind and solar power output curve; and use the gradient step length to process the wind and solar power output curve to split the base load component and the fluctuating load component;

[0177] The solution module 605 can be specifically used to optimize and solve according to the base load component, the fluctuating load component, and the decision-making influence data based on the preset matching rules and gradient step length, and determine a target configuration scheme that meets the requirements; wherein the preset matching rules include: the base load component preferentially matches the first standard square electrolytic cell, and the fluctuating load component preferentially matches the second standard square electrolytic cell, and the standard square of the first standard square electrolytic cell is greater than that of the second standard square electrolytic cell;

[0178] The deployment module 606 can be specifically used to deploy a target electrolytic cell group for a target wind-solar coupled power station according to the target configuration plan, so as to store the electric energy generated by the wind-solar coupled power generation.

[0179] In some embodiments, the decision-influencing data includes at least one of the following: electrolyzer equipment and auxiliary equipment parameters, construction costs, operating period costs, and operating period revenues;

[0180] Accordingly, when the above-mentioned determination module 602 is implemented, the decision-making impact data for the target area can be determined in the following manner: obtaining the electricity price data and grid rules of the target area; and combining the electricity price data and grid rules of the target area to determine the decision-making impact data for the target area.

[0181] In some embodiments, when the above-mentioned construction module 603 is implemented, the wind-solar output curve can be constructed according to the preset construction rules using the historical wind-solar data of the target area in the following manner: according to the timestamp, the historical wind-solar data of the target area are used to divide multiple power generation data groups; wherein, one power generation data group corresponds to one month, including wind-solar data of multiple historical time points of the month in different years, and wind-solar data of multiple historical time points of different months adjacent to the month in the same year; according to the multiple power generation data groups, multiple corresponding power generation data matrices are constructed; wherein, the multiple power generation data matrices correspond to one month respectively; the multiple power generation data matrices are processed using a preset typical data generation model to obtain multiple reference data groups of wind-solar power generation power corresponding to different months; the multiple reference data groups of wind-solar power generation power are spliced ​​and used to obtain the corresponding wind-solar output curve.

[0182] In some embodiments, when the above-mentioned splitting module 604 is implemented, a matching gradient step size can be determined based on the wind and solar power output curve in the following manner: performing graphic feature extraction on the wind and solar power output curve to obtain corresponding graphic features; determining the fluctuation characteristics of the wind and solar power output curve based on the graphic features; and determining a matching gradient step size based on the fluctuation characteristics.

[0183] In some embodiments, when the above-mentioned solution module 605 is implemented, it can be optimized and solved in the following manner based on preset matching rules and gradient steps, according to the base load component, fluctuating load component, and decision-making influence data, to determine a target configuration scheme that meets the requirements: construct an objective function group according to the decision-making influence data; and construct target constraints according to preset matching rules, base load components, and fluctuating load components; determine multiple computing nodes and an initial solution for each computing node according to preset processing rules; call multiple computing nodes to perform multiple rounds of iterative solutions on the objective function group based on the target constraints and initial solutions to obtain corresponding target processing results; and determine a target configuration scheme that meets the requirements according to the target processing results.

[0184] In some embodiments, when the above-mentioned solution module 605 is implemented, multiple computing nodes can be called in the following manner to perform iterative solution for the current round: obtain and filter out the retained solution for the current round that meets the retention condition based on the solution of the previous round of each computing node; mark the computing node holding the retained solution for the current round as a first-class node, and mark the other computing nodes except the first-class nodes among the multiple computing nodes as second-class nodes; perform preset encoding processing on the retained solution for the current round to obtain corresponding encoding data; and perform transformation processing based on the encoding data to obtain multiple transformed codes; decode the transformed codes to obtain multiple transformed solutions for the current round; and assign multiple transformed solutions for the current round to corresponding second-class nodes; call the first-class nodes and the second-class nodes to perform iterative solution according to local iterative solution rules and gradient step sizes, respectively using the retained solution for the current round and the transformed solution for the current round to obtain the solution for the current round of each computing node.

[0185] In some embodiments, after calling the first type of nodes and the second type of nodes to perform iterative solution according to the local iterative solution rules and gradient step size, respectively using the retained solution of the current round and the modified solution of the current round to obtain the solution of the current round of each computing node, the above-mentioned solution module 605 can also be used to detect whether the iterative solution termination condition is met when it is implemented; when it is determined that the iterative solution termination condition is met, the solution with the highest matching degree with the objective function group is selected from the solutions of the current round of multiple computing nodes as the target processing result.

[0186] It should be noted that the units, devices or modules described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. For the convenience of description, the above devices are described separately by functions divided into various modules. Of course, when implementing this specification, the functions of each module can be implemented in the same or more software and / or hardware, or the modules that implement the same function can be implemented by a combination of multiple sub-modules or sub-units. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0187] It can be seen from the above that the electrolytic cell configuration processing device based on fluctuating wind-solar coupled power generation provided in the embodiments of this specification can be better adapted to the wind-solar coupled power generation scenario with fluctuations, fully consider the fluctuation characteristics of wind and solar data in the target area throughout the year, effectively take into account multiple factors such as cost, benefit, and utilization rate, and accurately and reasonably realize the layout of the electrolytic cell group of the target wind-solar coupled power station in the target area.

[0188] In a specific scenario example, the electrolyzer configuration processing method based on fluctuating wind-solar coupled power generation provided in this specification can be applied to realize the gradient matching of electrolyzers of different specifications under fluctuating power sources. The specific implementation process may include the following contents.

[0189] Considering that the existing methods are often designed for stable power supply, most of them use electrolyzers with unified specifications and corresponding supporting equipment. However, in the case of fluctuating power supply, if all electrolyzers with unified specifications are used, two situations often occur: one is that the electrolyzer configuration scale is insufficient, and there will be power abandonment when new energy is developed; the other is that the electrolyzer is over-equipped, resulting in the inability to fully utilize the hydrogen production capacity of the electrolyzer. Both situations will result in the overall economic benefits of the project not being optimal.

[0190] In response to the above problems, the applicant, through creative thinking, proposed a method of mixing and matching electrolytic cells of different sizes under fluctuating power supply, so as to fully combine the resource endowment of the power source point and match the electrolytic cell with the output curve that is more suitable for it, so as to respond to the fluctuation of new energy through the small-sized electrolytic cell (for example, the second-sized electrolytic cell) as much as possible, and ensure that the large-sized electrolytic cell (for example, the first-sized electrolytic cell) maintains stable working conditions as much as possible. In order to achieve the purpose of reducing the overall project investment and increasing the service life of the large-sized electrolytic cell. For details, please refer to Figure 7 As shown, the following steps are included.

[0191] S1: Obtain the target area's real wind 8760 data for many years (e.g., historical wind data of the target area) and preprocess it.

[0192] Preferably, the wind-solar 8760 real data described in step S1 includes a timestamp and the output at the corresponding time (for example, the power generated by wind-solar coupled power generation).

[0193] Preferably, the preprocessing of the real data of wind and solar 8760 includes default value processing and exception processing of the timestamp and the corresponding power field, and the processed power field P and timestamp field T, the corresponding year Y and the corresponding month M are obtained, and finally the processed 8760 real sample data structure is expressed as D1=(P,T,Y,M).

[0194] S2: Obtain local electricity prices and corresponding policies (e.g., electricity price data and grid rules in the target area).

[0195] Preferably, the acquired information in step S2 includes local electricity prices, grid-connection and off-grid policies such as: requirements for grid connection or off-grid connection; grid-connection and off-grid power allowed, etc., as well as mandatory requirements for project supporting energy storage capacity.

[0196] S3: Obtain the current prices and floor space of the electrolytic cells and auxiliary equipment of corresponding specifications of each bidder, as well as other data required for evaluation and calculation (for example, decision-making impact data), and pre-process them.

[0197] Preferably, the data described in step S3 include four categories, namely, electrolyzer equipment and auxiliary machine parameters, construction period investment, operating period income and costs. Among them, the electrolyzer equipment and auxiliary machine parameters include the current prices and floor space of each standard electrolyzer and auxiliary machine of corresponding specifications. Construction period investment includes wind and solar investment, hydrogen production investment, energy storage investment, delivery investment and various land acquisition fees, pre-construction fees and other fees to be paid during the construction period. Operation period income includes hydrogen price, hydrogen volume, electricity (if any) and other possible income items such as oxygen sales. Operation period costs include personnel costs, material costs, repair costs, insurance premiums, construction period interest, rent paid regularly during the operation period, energy storage core replacement costs, electrolyzer overhaul costs, depreciation costs, and safety production costs, other manufacturing costs, other management fees, water and electricity costs, and catalyst fees for hydrogen production.

[0198] Preferably, the data is preprocessed using the same steps as S1 and the processed data is represented as D2.

[0199] S4: Use the pre-processed wind-solar coupling data to compare the monthly output differences of each year, select the typical data of each month from the data of each year and piece them together.

[0200] Preferably, the specific process of step S4 is:

[0201] S41. Construct a data D3 to organize the wind-solar coupling output of the corresponding months of each year.

[0202] S42. In D3, the data of each time stamp is compared and filtered by machine learning to be the typical data calculated for the current month.

[0203] S43. The filtered monthly wind and solar power output data are pieced together to form the annual 8760 wind and solar power output curve D4 (eg, wind and solar power output curve).

[0204] S5: Use the assembled data to subdivide the wind and solar output capacity by gradient.

[0205] Preferably, the data used in step S5 is the D4 data set sorted by S4. When subdividing the wind-solar output ratio by gradient, the step length S (e.g., gradient step length) must be determined first. After S is determined, D4 is subdivided according to the step length of S to form a base load LB (e.g., base load component) and a fluctuating load LF (e.g., fluctuating load component), and D5=(S,LB,LF) is formed, where LB+LF=D4.

[0206] S6: Based on the principle that large-scale electrolytic cells meet the base load and small-scale electrolytic cells respond to wind and solar fluctuations (for example, based on preset matching rules), calculations are performed according to the step size of the previous step in combination with the data required for the evaluation calculation.

[0207] Preferably, the specific process of step S6 is:

[0208] S61. The basic principle is to use large-sized electrolytic cells to meet the base load and small-sized electrolytic cells to respond to wind and solar fluctuations, that is, large-sized electrolytic cells are used for LB and small-sized electrolytic cells are used for LF.

[0209] S62. Using the electrolytic cell data collected in D2 as input parameters, the data in D5 are calculated one by one according to the principle of S61 and the step size S determined in S5 to form multiple configuration schemes.

[0210] S63. The configuration scheme formed in S62 is combined with the parameters in D2 to calculate the economic reference index of the project.

[0211] S7: Based on the principle of economic optimization, calculate the optimal electrolytic cell configuration plan (e.g., the target configuration plan).

[0212] Preferably, step S7 uses the IRR formed in S63 as a reference indicator to select the optimal electrolytic cell configuration scheme with different specifications.

[0213] Through the above scenario examples, the electrolytic cell configuration processing method based on fluctuating wind-solar coupled power generation provided in this specification is verified. The large-scale electrolytic cells are used as the base load, and the small-scale electrolytic cells respond to the fluctuations of new energy as the basic principle. By configuring electrolytic cells of different scales in a step-by-step manner to maximize the use of the electrolytic cell's own equipment characteristics, the configuration of the electrolytic cells can be accurate and reasonable, which can effectively increase the project rate of return of new energy power stations.

[0214] Although the present specification provides method operation steps as described in the embodiments or flow charts, more or fewer operation steps may be included based on conventional or non-creative means. The order of steps listed in the embodiments is only one way of executing the order of many steps and does not represent the only order of execution. When the device or client product in practice is executed, it can be executed in sequence or in parallel according to the method shown in the embodiments or the drawings (for example, a parallel processor or a multi-threaded processing environment, or even a distributed data processing environment). The terms "include", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, product or device including a series of elements includes not only those elements, but also other elements that are not explicitly listed, or also includes elements inherent to such a process, method, product or device. In the absence of more restrictions, it is not excluded that there are other identical or equivalent elements in the process, method, product or device including the elements. The words first, second, etc. are used to represent the name, and do not represent any particular order.

[0215] Those skilled in the art also know that, in addition to implementing the controller in a purely computer-readable program code, the controller can be made to implement the same function in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers by logically programming the method steps. Therefore, such a controller can be considered as a hardware component, and the devices for implementing various functions included therein can also be considered as structures within the hardware component. Or even, the devices for implementing various functions can be considered as both software modules for implementing the method and structures within the hardware component.

[0216] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, classes, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer-readable storage media including storage devices.

[0217] Through the description of the above embodiments, it can be known that those skilled in the art can clearly understand that the present specification can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present specification can essentially be embodied in the form of a software product, which can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a mobile terminal, a server, or a network device, etc.) to execute the methods described in each embodiment of the present specification or some parts of the embodiments.

[0218] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. This specification can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld devices or portable devices, tablet devices, multi-processor systems, microprocessor-based systems, set-top boxes, programmable electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc.

[0219] Although the present specification is described through embodiments, those skilled in the art will appreciate that there are many modifications and changes to the present specification without departing from the spirit of the present specification, and it is intended that the appended claims include these modifications and changes without departing from the spirit of the present specification.

Claims

1. A method for configuring and processing an electrolyzer based on fluctuating wind-solar coupled power generation, characterized in that: include: Acquire historical scenery data of the target area; wherein the historical scenery data includes scenery data of multiple historical time points, and the scenery data of the historical time points also carry a timestamp corresponding to the historical time point; Determine decision-making impact data for target areas; According to the preset construction rules, the wind-solar output curve is constructed using the historical wind-solar data of the target area; wherein the wind-solar output curve is used to characterize the reference power of wind-solar coupled power generation at various time points in a year; According to the wind and solar power output curve, a matching gradient step is determined; and the wind and solar power output curve is processed using the gradient step to separate the base load component and the fluctuating load component; Based on the preset matching rules and gradient step length, an optimization solution is performed according to the base load component, the fluctuating load component, and the decision-making influence data to determine a target configuration scheme that meets the requirements; wherein the preset matching rules include: the base load component preferentially matches the first standard square electrolytic cell, and the fluctuating load component preferentially matches the second standard square electrolytic cell, and the standard square of the first standard square electrolytic cell is greater than that of the second standard square electrolytic cell; According to the target configuration scheme, a target electrolytic cell group is arranged for a target wind-solar coupling power station to store the electric energy generated by the wind-solar coupling power generation.

2. The method according to claim 1, characterized in that The decision-making influencing data includes at least one of the following: electrolytic cell equipment and auxiliary machine parameters, construction cost, operation period cost, and operation period income; Accordingly, determine the decision-making impact data for the target area, including: Obtain electricity price data and grid rules for the target area; The electricity price data and grid rules of the target area are used in combination to determine the decision-making impact data for the target area.

3. The method according to claim 1, characterized in that According to the preset construction rules, the historical wind and solar data of the target area are used to construct the wind and solar output curve, including: According to the timestamp, the historical wind and solar data of the target area are used to divide multiple power generation data groups; wherein one power generation data group corresponds to one month, and contains wind and solar data of multiple historical time points of the month in different years, and wind and solar data of multiple historical time points of different months adjacent to the month in the same year; According to the plurality of power generation data groups, a plurality of corresponding power generation data matrices are constructed; wherein the plurality of power generation data matrices correspond to one month respectively; Using a preset typical data generation model to process multiple power generation data matrices, a reference data set of multiple wind and solar power generation powers corresponding to different months is obtained; Multiple wind and solar power generation reference data sets are spliced ​​and utilized to obtain the corresponding wind and solar power output curve.

4. The method according to claim 1, characterized in that: According to the wind and solar power output curve, determine the matching gradient step length, including: Extracting graphic features from the wind and solar power output curve to obtain corresponding graphic features; According to the graphical features, determining the fluctuation characteristics of the wind and solar power output curve; According to the fluctuation characteristics, a matching gradient step length is determined.

5. The method according to claim 1, characterized in that Based on the preset matching rules and gradient step length, an optimization solution is performed according to the base load component, fluctuating load component, and decision-making impact data to determine a target configuration scheme that meets the requirements, including: Construct an objective function group based on decision-making impact data; and construct objective constraints based on preset matching rules, base load components, and fluctuating load components; According to the preset processing rules, multiple computing nodes and initial solutions of each computing node are determined; Calling multiple computing nodes to perform multiple rounds of iterative solutions on the objective function group based on the objective constraint conditions and the initial solution to obtain corresponding objective processing results; According to the target processing results, determine the target configuration plan that meets the requirements.

6. The method according to claim 5, characterized in that Calling multiple computing nodes to perform multiple rounds of iterative solutions on the objective function group based on the objective constraint conditions and the initial solution, including: Call multiple computing nodes to perform the current round of iterative solution in the following way: Obtain and filter out the retained solutions of the current round that meet the retention conditions based on the solutions of the previous round of each computing node; Mark the computing nodes holding the reserved solutions of the current round as first-category nodes, and mark the other computing nodes among the multiple computing nodes except the first-category nodes as second-category nodes; Performing preset coding processing on the reserved solution of the current round to obtain corresponding coding data; and performing transformation processing according to the coding data to obtain multiple transformation codes; Decoding the transformation code to obtain multiple transformation solutions of the current round; and assigning the multiple transformation solutions of the current round to corresponding second-type nodes; The first type of nodes and the second type of nodes are called to iteratively solve the current round of retained solutions and the current round of transformed solutions according to the local iterative solution rules and gradient step size, respectively, to obtain the current round of solutions of each computing node.

7. The method according to claim 6, characterized in that After the first type of nodes and the second type of nodes are called to perform iterative solutions using the retained solution of the current round and the modified solution of the current round respectively according to the local iterative solution rule and the gradient step size to obtain the solution of the current round of each computing node, the method further includes: Check whether the iterative solution termination condition is met; When it is determined that the termination condition of the iterative solution is met, the solution with the highest matching degree with the objective function group is selected from the solutions of the current round of multiple computing nodes as the target processing result.

8. An electrolytic cell configuration processing device based on fluctuating wind-solar coupled power generation, characterized in that: include: An acquisition module, used to acquire historical scenery data of a target area; wherein the historical scenery data includes scenery data of multiple historical time points, and the scenery data of the historical time points also carries a timestamp corresponding to the historical time point; A determination module, for determining decision-making impact data for a target area; A construction module, used to construct a wind-solar output curve according to a preset construction rule and using historical wind-solar data of a target area; wherein the wind-solar output curve is used to characterize the reference power of wind-solar coupled power generation at various time points in a year; A splitting module is used to determine a matching gradient step length according to the wind and solar power output curve; and use the gradient step length to process the wind and solar power output curve to split the base load component and the fluctuating load component; A solution module is used to optimize and solve according to the base load component, the fluctuating load component, and the decision-making influence data based on a preset matching rule and a gradient step size, and determine a target configuration scheme that meets the requirements; wherein the preset matching rule includes: the base load component preferentially matches the first standard square electrolytic cell, and the fluctuating load component preferentially matches the second standard square electrolytic cell, and the standard square of the first standard square electrolytic cell is greater than that of the second standard square electrolytic cell; A deployment module is used to deploy a target electrolytic cell group for a target wind-solar coupling power station according to the target configuration plan, so as to store the electric energy generated by the wind-solar coupling power generation.

9. A server, characterized in that: The method comprises a processor and a memory for storing processor-executable instructions, wherein the processor implements the steps of the method according to any one of claims 1 to 7 when executing the instructions.

10. A computer-readable storage medium, characterized in that: Computer instructions are stored thereon, and when the instructions are executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images