Capacity configuration method and device of hydrogen production system, computer equipment, readable storage medium and program product

Abstract

The invention relates to a capacity configuration method and device of a hydrogen production system, computer equipment, a computer readable storage medium and a computer program product, relates to the technical field of energy system optimization, and can improve the operation efficiency of the hydrogen production system. The method comprises the following steps: establishing a system operation model for representing the operation state of the hydrogen production system; obtaining an optimization target of capacity configuration according to operation resources consumed in the operation process of the hydrogen production system; according to the system operation model and the optimization target, determining candidate capacity configuration of each unit; according to the target quantized values of the plurality of candidate capacity configurations relative to the optimization target of the capacity configuration, determining the quality degrees corresponding to the plurality of candidate capacity configurations, and according to the quality degrees, determining the adjustment directions corresponding to the plurality of candidate capacity configurations; and performing configuration iteration adjustment of different adjustment degrees on the plurality of candidate capacity configurations according to each adjustment direction until an iteration ending condition is met, and determining respective target capacity configurations of the units.

Description

Technical Field

[0001] The present application relates to the technical field of energy system optimization, and in particular to a capacity configuration method, apparatus, computer equipment, computer-readable storage medium, and computer program product for a hydrogen production system. Background Art

[0002] Hydrogen has attracted considerable attention as a low-carbon, clean energy carrier. Due to its flexibility, photovoltaic (PV) hydrogen production has become a key technology for absorbing renewable energy and promoting decarbonization in multiple sectors. Related research has largely focused on electrolyzer optimization, system collaborative management, or capacity allocation using a single optimization algorithm. However, traditional approaches struggle to optimally configure system capacity when modeling integrated hydrogen production and refueling systems, encompassing the entire process, including hydrogen purification. This results in inefficient hydrogen production. Summary of the Invention

[0003] Based on this, it is necessary to provide a capacity configuration method, device, computer equipment, computer-readable storage medium and computer program product for a hydrogen production system to address the above technical problems.

[0004] In a first aspect, the present application provides a capacity configuration method for a hydrogen production system, comprising:

[0005] Establish a system operation model for characterizing the operating state of the hydrogen production system; the system operation model includes an electrolyzer hydrogen production unit, a hydrogen purification unit, and a hydrogen storage unit; the hydrogen purification unit is used to receive and purify hydrogen produced by the electrolyzer hydrogen production unit, and the hydrogen storage unit is used to store the purified hydrogen; the hydrogen purification unit operates under unit constraints determined by the temperature in the hydrogen purification unit and the hydrogen flow rate of the electrolyzer hydrogen production unit;

[0006] Obtaining an optimization target for capacity configuration based on the operating resources consumed during the operation of the hydrogen production system;

[0007] Determining candidate capacity configurations for the electrolyzer hydrogen production unit, the hydrogen purification unit, and the hydrogen storage unit, respectively, based on the system operation model and the optimization objective; the candidate capacity configurations include power capacity configurations or hydrogen capacity configurations;

[0008] Determining, based on the target quantified values ​​of the plurality of candidate capacity configurations relative to the optimization target of the capacity configuration, corresponding degrees of superiority or inferiority of the plurality of candidate capacity configurations, and determining, based on the degrees of superiority or inferiority, corresponding adjustment directions of the plurality of candidate capacity configurations;

[0009] According to each of the adjustment directions, the multiple candidate capacity configurations are iteratively adjusted with different adjustment degrees until the iteration end condition is met, and the target capacity configurations of the electrolyzer hydrogen production unit, the hydrogen purification unit and the hydrogen storage unit are determined.

[0010] In one embodiment, the unit constraint of the hydrogen purification unit is determined by the following steps:

[0011] The hydrogen flow rate of the electrolyzer hydrogen production unit is greater than or equal to a preset hydrogen flow rate threshold as a first unit operation constraint condition of the hydrogen purification unit; and

[0012] Obtaining a shutdown critical temperature of the hydrogen purification unit;

[0013] A second operating constraint condition of the hydrogen purification unit is determined based on the temperature, the shutdown critical temperature, and a preset temperature tolerance value.

[0014] In one embodiment, determining adjustment directions corresponding to the plurality of candidate capacity configurations according to the degree of superiority or inferiority includes:

[0015] Determining priorities corresponding to the plurality of candidate capacity configurations based on the pros and cons, wherein the priorities include a first priority and a second priority lower than the first priority;

[0016] If the priority is the second priority, adjusting the candidate capacity configuration corresponding to the second priority level toward the capacity configuration corresponding to the first priority level;

[0017] The iterative adjustment of the plurality of candidate capacity configurations with different adjustment degrees in the adjustment direction until an iteration end condition is satisfied and the target capacity configuration is determined further includes:

[0018] An adjustment degree of the candidate capacity configuration in the adjustment direction is determined according to the priority corresponding to the candidate capacity configuration.

[0019] In one embodiment, the iterative adjustment of the plurality of candidate capacity configurations with different adjustment degrees according to the respective adjustment directions until an iterative end condition is satisfied, thereby determining the target capacity configurations of the electrolyzer hydrogen production unit, the hydrogen purification unit, and the hydrogen storage unit, respectively, includes:

[0020] Performing iterative configuration adjustments with different adjustment degrees in the adjustment direction to obtain multiple adjusted candidate capacity configurations;

[0021] For each of the adjusted candidate capacity configurations, comparing the respective corresponding superiority or inferiority of the adjusted candidate capacity configuration with the candidate capacity configuration before the adjustment;

[0022] The candidate capacity configuration corresponding to the highest degree of quality is used as the starting point of the next iteration, and configuration iterative adjustment with different degrees of adjustment is performed in the adjustment direction until the iteration end condition is met to determine the target capacity configuration.

[0023] In one embodiment, obtaining an optimization target for capacity configuration based on the operating resources consumed during the operation of the hydrogen production system includes:

[0024] The initial investment cost, accumulated operation and maintenance costs, and replacement costs of key components of the hydrogen production system after reaching the end of their service life are determined as sub-goals for the life cycle cost;

[0025] The penalty cost corresponding to the amount of abandoned photovoltaic power caused by the photovoltaic power generation exceeding the system's absorption capacity is determined as the abandoned photovoltaic penalty cost sub-target;

[0026] The electricity purchase cost corresponding to the electricity purchased from the external power grid to meet the operation of the hydrogen production system is determined as the electricity purchase cost sub-target;

[0027] The full life cycle cost sub-target, the curtailment penalty cost sub-target and the electricity purchase cost sub-target are normalized, and each normalized sub-target is weighted according to a preset weight to combine them into the optimization target of the capacity configuration.

[0028] In one embodiment, the hydrogen purification unit model is established by the following steps:

[0029] determining a temperature dynamic equation for describing temperature changes of the hydrogen purification unit according to the temperature of the hydrogen purification unit and the heat exchange rate of each operating stage of the hydrogen purification unit;

[0030] Establishing a timer model for tracking the operating stage of the hydrogen purification unit, and converting the segmented operation logic of the timer model into a preset form by introducing an auxiliary binary variable to obtain a timer model in the preset form;

[0031] The hydrogen purification unit model is determined according to the temperature dynamic equation, the preset timer model and the unit operation constraint conditions.

[0032] In a second aspect, the present application further provides a capacity configuration device for a hydrogen production system, comprising:

[0033] A system operation model establishment module is used to establish a system operation model for characterizing the operating state of the hydrogen production system; the system operation model includes an electrolyzer hydrogen production unit, a hydrogen purification unit, and a hydrogen storage unit; the hydrogen purification unit is used to receive and purify the hydrogen produced by the electrolyzer hydrogen production unit, and the hydrogen storage unit is used to store the purified hydrogen; the hydrogen purification unit operates under unit constraints determined by the temperature in the hydrogen purification unit and the hydrogen flow rate of the electrolyzer hydrogen production unit;

[0034] An optimization target acquisition module, configured to acquire an optimization target for capacity configuration according to the operating resources consumed during the operation of the hydrogen production system;

[0035] a candidate capacity configuration determination module, configured to determine, based on the system operation model and the optimization objective, candidate capacity configurations for the electrolyzer hydrogen production unit, the hydrogen purification unit, and the hydrogen storage unit; the candidate capacity configurations include power capacity configurations or hydrogen capacity configurations;

[0036] a configuration adjustment direction determining module, configured to determine, based on target quantified values ​​of the plurality of candidate capacity configurations relative to the optimization target of the capacity configuration, the corresponding degrees of excellence of the plurality of candidate capacity configurations, and determine, based on the degrees of excellence, the corresponding adjustment directions of the plurality of candidate capacity configurations;

[0037] The target capacity configuration determination module is used to iteratively adjust the configurations of the multiple candidate capacity configurations with different adjustment degrees according to each of the adjustment directions until the iteration end conditions are met, thereby determining the target capacity configurations of the electrolyzer hydrogen production unit, the hydrogen purification unit and the hydrogen storage unit.

[0038] In a third aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the capacity configuration method of the hydrogen production system as described in any one of the above items are implemented.

[0039] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the capacity configuration method for a hydrogen production system as described in any one of the above items.

[0040] In a fifth aspect, the present application also provides a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the capacity configuration method for a hydrogen production system as described in any one of the above items.

[0041] The capacity configuration method, device, computer equipment, computer-readable storage medium and computer program product of the above-mentioned hydrogen production system are constructed by establishing a system operation model for characterizing the operating state of the hydrogen production system; the system operation model includes an electrolyzer hydrogen production unit, a hydrogen purification unit and a hydrogen storage unit; the hydrogen purification unit is used to receive and purify the hydrogen produced by the electrolyzer hydrogen production unit, and the hydrogen storage unit is used to store the purified hydrogen; the hydrogen purification unit operates under the unit constraint conditions determined by the temperature in the hydrogen purification unit and the hydrogen flow rate of the electrolyzer hydrogen production unit; according to the operating resources consumed during the operation of the hydrogen production system, the optimization target of the capacity configuration is obtained; according to the system operation ... Based on the operation model and optimization objectives, candidate capacity configurations for the electrolyzer hydrogen production unit, hydrogen purification unit, and hydrogen storage unit are determined. Candidate capacity configurations include power capacity configurations or hydrogen capacity configurations. Based on the target quantitative values ​​of the multiple candidate capacity configurations relative to the optimization objectives of the capacity configurations, the corresponding advantages and disadvantages of the multiple candidate capacity configurations are determined, and based on the advantages and disadvantages, the corresponding adjustment directions of the multiple candidate capacity configurations are determined. According to each adjustment direction, the multiple candidate capacity configurations are iteratively adjusted with different adjustment degrees until the iterative end conditions are met, and the target capacity configurations for the electrolyzer hydrogen production unit, hydrogen purification unit, and hydrogen storage unit are determined. By establishing a system operation model for the hydrogen production system that includes the electrolyzer hydrogen production unit, hydrogen storage unit, and a purification unit that considers operating constraints related to temperature and hydrogen flow, and combining it with an optimization objective based on operating resource consumption, an optimization strategy that can determine the adjustment direction based on the advantages and disadvantages of the candidate configurations and perform multi-degree iterative adjustments is adopted. This allows for a more comprehensive and accurate search for capacity configuration solutions for each unit of the hydrogen production system. This not only improves the adaptability of the configuration results to actual complex operating conditions and enhances the responsiveness to the dynamic characteristics of the purification unit, but also increases the possibility of obtaining a global or near-global optimal configuration through a systematic iterative optimization process, thereby improving the overall operating efficiency of the hydrogen production system. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments of the present application or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying any creative work.

[0043] Figure 1 Schematic diagram of a flow chart of a method for configuring the capacity of a hydrogen production system in one embodiment;

[0044] Figure 2 Schematic diagram of a hydrogen production system according to an embodiment;

[0045] Figure 3Schematic diagram of the purification process of a hydrogen purification unit in one embodiment;

[0046] Figure 4 A flowchart of a method for determining target capacity configuration in one embodiment is shown;

[0047] Figure 5 is a flow chart of a method for configuring the capacity of a hydrogen production system in another embodiment;

[0048] Figure 6 is a structural block diagram of a capacity configuration device for a hydrogen production system in one embodiment;

[0049] Figure 7 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0051] It should be noted that the terms "first," "second," etc., used in this application may be used to describe various objects, but these objects are not limited by these terms. These terms are only used to distinguish the first object from the second object. The terms "including," "having," and any variations thereof, used in this application are intended to cover non-exclusive inclusions. The term "plurality" used in this application refers to two or more.

[0052] In one embodiment, Figure 1 As shown, a method for capacity configuration of a hydrogen production system is provided. This embodiment uses the method applied to a server as an example for illustration. It is understandable that the method can also be applied to a terminal, or to a system including a terminal and a server, and implemented through interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0053] Step S102: establishing a system operation model for characterizing the operating state of the hydrogen production system.

[0054] The system operation model is a comprehensive mathematical toolkit for digitally representing the entire process of the hydrogen production system. It can accurately and quantitatively describe the complex processes of energy conversion, material flow, and state changes of each physical unit in the system through a series of interrelated algebraic equations, differential equations, and logical rules. The system operation model includes but is not limited to the electrolyzer hydrogen production unit, the hydrogen purification unit, and the hydrogen storage unit. The hydrogen purification unit is used to receive and purify the hydrogen produced by the electrolyzer hydrogen production unit, and the hydrogen storage unit is used to store the purified hydrogen. The hydrogen purification unit operates under the unit constraints determined by the temperature in the hydrogen purification unit and the hydrogen flow rate of the electrolyzer hydrogen production unit.

[0055] For example, the hydrogen production system in this application is as follows Figure 2 As shown, it includes an electrolyzer hydrogen production unit (photovoltaic power generation, water electrolysis hydrogen production), an auxiliary system (hydrogen purification unit), a hydrogen storage unit (buffering, hydrogenation), etc. In one embodiment, the water electrolysis hydrogen production system can be composed of multiple electrolyzers and their auxiliary systems (such as gas-liquid separation, thermal management, purification, etc.). For example, the electrolyzer can be a proton exchange membrane (PEM) electrolyzer, and the demand for hydrogenation comes from commercial vehicles such as buses and heavy trucks.

[0056] In one embodiment, the electrolyzer hydrogen production unit of the hydrogen production system is modeled. By combining the start and stop of the electrolyzer and the load distribution, it is possible to better follow the fluctuation of photovoltaic power generation and improve photovoltaic consumption. For example, the load of the hydrogen production cluster satisfies the power balance constraint shown in formula (1):

[0057]

[0058] Among them, P n,t 、 where is the interaction power of the PEM electrolyzer, auxiliary system, photovoltaic power generation, and grid, respectively; n is the number of the electrolyzer; and t is the time step. For example, the electrolyzer load operating range and hydrogen production capacity satisfy the constraints of formulas (2) and (3), respectively.

[0059]

[0060] Y n,t =η P2H P n,t , formula (3).

[0061] Among them, P max 、P min are the maximum and minimum power of the electrolytic cell load respectively; η P2H is the hydrogen production efficiency; Y n,t The amount of hydrogen produced.

[0062] The power injected into the grid by photovoltaic power generation is limited by the actual photovoltaic output and needs to satisfy formula (4):

[0063]

[0064] Among them, P PV_max is the maximum output power of photovoltaic power generation.

[0065] Due to the PEM electrolyzer's flexible load regulation characteristics, its ramping characteristics need to be ignored on a 15-minute scheduling timescale. The interaction between the hydrogen refueling station and the grid is subject to power constraints. For example, some projects require only power purchased from the grid, not accessing the grid. For example, the grid power is always greater than or equal to 0 to ensure normal operation of the electrolyzer. For example, as shown in Equation (5).

[0066]

[0067] Exemplarily, the operating states of the electrolytic cell include operation, standby, and shutdown, and the start-stop combination and switching of multiple machines meet the constraints of the following formula (6).

[0068]

[0069] in, are the operating, standby and shutdown state variables of the electrolyzer respectively; are the electrolytic cell startup and shutdown actions, respectively. If the electrolytic cells share a water circulation and thermal management system, the electrolytic cells must be started and stopped at the same time. For example, this is guaranteed by the constraints of formula (7).

[0070]

[0071] In one embodiment, a hydrogen purification unit of a hydrogen production system is modeled. The hydrogen produced by the electrolyzer contains some impurities, mainly O2, H2O, and a small amount of N2. Purification is required to obtain hydrogen with a purity that meets the standard. The purification process includes catalytic deoxygenation, adsorption drying, and other process structures. Figure 3 As shown in the figure, the crude hydrogen is dried using a temperature swing adsorption (TSA) system in the hydrogen purification unit. TSA involves three stages: adsorption, heating regeneration, and cooling, which are performed in alternating cycles.

[0072] Specifically, during the adsorption process, hydrogen undergoes gas-liquid separation to remove free water, but still contains saturated water. The feed gas and regenerated gas merge and flow from top to bottom into the adsorption tower for adsorption drying. During the adsorption process, impurities in the hydrogen are adsorbed by the porous desiccant (e.g., molecular sieve, silica gel, etc.) within the tower. After passing dew point monitoring, the purified hydrogen is sent to subsequent processing stages for further use.

[0073] Specifically, during the heating regeneration process, as the number of molecules adsorbed on the solid surface increases, the adsorbent in the drying tower gradually becomes saturated, reaching adsorption equilibrium and losing adsorption capacity. To ensure continuous operation of the drying tower, TSA achieves regeneration by varying the adsorption bed temperature. A portion of the feed gas, heated by a heater through a gas flow control valve, is then fed into the adsorption tower in the opposite direction of adsorption. As the adsorption bed temperature gradually rises, water in the adsorbent begins to desorb and be discharged with the airflow.

[0074] Specifically, during the cooling process, after the heating and regeneration phase, adsorbed water is largely desorbed. At this point, the adsorbent bed temperature is high, necessitating cooling. A gas flow control valve regulates the flow of feed gas into the adsorption tower in the adsorption direction to cool the adsorbent, restoring it to the adsorption temperature and preparing for the next stage of adsorption. The regenerated gas then passes through the drying tower, reuniting with the feed gas and entering the drying tower for adsorption.

[0075] Through the temperature-swing adsorption process, the drying tower can be recycled to effectively extend its service life and ensure the long-term stable operation of the system. In actual engineering, multiple adsorption towers can be designed to work alternately, ensuring that one tower is always in the adsorption state and the other is in the regeneration state, thereby achieving seamless continuous operation. The specific operation logic can be simplified into a cycle. Assume that the cycle is heating for 10 hours → cooling for 8 hours → heating for 3 hours → cooling for 3 hours → heating for 10 hours (second cycle). After clarifying the operation logic of the purification unit, its temperature change process, heating regeneration / cooling logic, and start-stop constraints are modeled in detail and incorporated into the scheduling framework.

[0076] In one embodiment, the hydrogen produced by photovoltaic power generation is volatile and intermittent, which cannot match the vehicle's hydrogen refueling needs. Therefore, a hydrogen storage tank of appropriate capacity is configured to balance hydrogen supply and demand. For example, the charging, discharging, pressure, and initial and final state constraints of the hydrogen storage tank are as follows, as shown in formulas (8)-(11):

[0077]

[0078] in, is the pressure of the hydrogen storage tank; R H2 is the gas constant; T H2 is the hydrogen temperature; V H2 is the volume of the hydrogen storage tank; mol H2 is the molar mass of hydrogen; p HB,rated is the maximum pressure of the hydrogen storage tank; c HB is the maximum pressure hydrogen storage capacity under standard conditions, is the vehicle hydrogen refueling demand at time t; t is the time step, and T is the total duration of the entire optimization cycle.

[0079] Step S104: obtaining an optimization target for capacity configuration according to the operating resources consumed during the operation of the hydrogen production system.

[0080] Among them, the optimization goal of capacity configuration is the evaluation criterion used to evaluate the pros and cons of any group of candidate capacity configuration schemes. It can be a mathematical function that quantifies engineering goals (such as the pursuit of economy, reliability, environmental protection, etc.) and integrates them into a single calibration value.

[0081] Exemplarily, the terminal determines the various key resources consumed by the hydrogen production system during the planned operation cycle, quantifies the consumption of these resources or their corresponding costs, and finally combines them into one or more objective functions for evaluating the pros and cons of candidate capacity configuration schemes.

[0082] Step S106, determining candidate capacity configurations of the electrolyzer hydrogen production unit, the hydrogen purification unit, and the hydrogen storage unit according to the system operation model and the optimization target; the candidate capacity configurations include power capacity configurations or hydrogen capacity configurations.

[0083] The candidate capacity configurations can be generated or iteratively produced by the terminal during the target optimization process, representing a set of specific unit capacity parameters that numerically define the scale of each unit to be optimized in the hydrogen production system. In one embodiment, the candidate capacity configurations include, but are not limited to, the power configuration capacity of the photovoltaic array, the power configuration capacity of the electrolyzer, the hydrogen configuration capacity of the hydrogen storage tank, and the power configuration capacity of the battery.

[0084] Exemplarily, the terminal uses a preset generation algorithm to create a set of initial candidate capacity configurations that meet the quantitative requirements of the subsequent optimization algorithm based on the pre-set value range for each capacity parameter to be optimized. The generation algorithm can be a sampling method that ensures that the initial population is evenly distributed in the solution space. For example, the terminal can stratify the value range of each parameter into equal probability layers and perform sampling combinations from these layers. This ensures that the generated initial population more comprehensively and evenly covers the entire high-dimensional parameter space, avoiding the problem of premature convergence of the optimization algorithm caused by an overly concentrated initial solution.

[0085] In one embodiment, the population can be initialized based on the Kent map. The Kent map is a type of chaos theory. Chaos theory is widely used in swarm intelligence algorithms due to its characteristics such as randomness, ergodicity, and non-repetitiveness to enhance the diversity of the initialized population, thereby improving the optimization performance of the algorithm. Compared with random search, chaos theory can explore the search space more comprehensively. In an optional embodiment, the Kent map is introduced into the IGWO algorithm for population initialization. For example, its mathematical model can be expressed by formulas (12)-(13):

[0086]

[0087] x i,j =x mini,j +x k,j ×(x maxi,j x mini,j ), formula (13).

[0088] in, is a random number between 0 and 1; x k is the chaotic variable value of the individual in the current iteration round, where k is the number of iteration steps; x k,j is the chaotic variable value of the jth attribute of the individual in the current iteration round; x mini,j and x maxi,j is the minimum and maximum value of the jth attribute of population i. The Kent map is a chaotic map within its parameter range, but when When φ is used, the system presents a short periodic state, so this application does not take 0.5. When using this mapping, the initial value x0 cannot be the same as φ, otherwise the system will evolve into a periodic system. The specific steps of using Kent chaotic mapping to generate the initial population include: randomly initializing the population initial value x i,j , set the population size N, dimension d and maximum chaotic iteration step number K, and randomly generate a number and Iterate, j and k iteratively increase, and generate x k,j Sequence; i increases by 1, generating sequence x i,j ; If the maximum number of iterations is reached, the iteration ends. Otherwise, the execution returns to the next iteration. j and k are incremented iteratively to generate x k,j sequence; terminate the run and save the x sequence as the solution population for optimization.

[0089] Step S108 : determining the pros and cons of the plurality of candidate capacity configurations according to the target quantized values ​​of the plurality of candidate capacity configurations relative to the optimization target of the capacity configuration, and determining adjustment directions of the plurality of candidate capacity configurations according to the pros and cons.

[0090] The "quality" is a quantitative indicator used to measure the quality of each candidate capacity configuration. By substituting the candidate configuration into the system operation model for simulation and calculating the corresponding optimization target, the quantitative value directly reflects the degree of proximity of the candidate capacity configuration to the optimization target. The adjustment direction can be strategic information determined based on the quality of the candidate capacity configurations corresponding to each unit, guiding how to generate the next generation of better solutions from the current solution set. This information can be a specific mathematical modification vector, a set of evolutionary operations, or a heuristic guidance rule pointing to a region of better solutions, rather than a physical direction.

[0091] Exemplarily, the terminal calls the mathematical function corresponding to the optimization target for each candidate capacity configuration generated in the previous step to calculate and obtain its target quantitative value, thereby determining its degree of excellence. Subsequently, the terminal determines an adjustment direction for generating the next generation of new configurations for each or each group of candidate configurations based on the set of the degrees of excellence of all candidate configurations. Specifically, for a certain candidate capacity configuration, its adjustment direction can be a composite vector synthesized by multiple vectors. These vectors may include a global guidance vector pointing to the optimal solution position among all current candidate configurations, an individual memory vector pointing to the optimal solution position that the candidate configuration itself has historically achieved, and an inertia vector that maintains its current motion trend. By performing a weighted combination of these vectors, the adjustment direction and amplitude of the candidate configuration in the next iteration will be obtained.

[0092] In step S110 , the multiple candidate capacity configurations are iteratively adjusted with different adjustment degrees according to various adjustment directions until the iteration end condition is met, thereby determining the target capacity configurations of the electrolyzer hydrogen production unit, the hydrogen purification unit, and the hydrogen storage unit.

[0093] The iteration end condition is a logical criterion used to determine when the loop process terminates. It can be set to a preset maximum number of iterations or triggered when the improvement of the optimal solution falls below a minimum threshold over multiple generations. The target capacity configuration can be the optimal solution selected from all candidate capacity configurations after the iteration end condition is met.

[0094] For example, in a loop, the terminal repeatedly applies the adjustment direction determined in the previous step to the current set of candidate capacity configurations to generate an updated set of candidate capacity configurations. At the end of each loop, the terminal checks whether the iteration end condition is met. If not, the next loop is continued; if so, the loop is terminated and the final target capacity configuration is selected and output from all recorded optimal configurations.

[0095] In this embodiment, by establishing a system operation model for a hydrogen production system comprising an electrolyzer hydrogen production unit, a hydrogen storage unit, and a purification unit that considers operational constraints related to temperature and hydrogen flow, and combining it with an optimization objective based on operational resource consumption, an optimization strategy is employed that determines adjustment directions based on the merits of candidate configurations and performs multi-level iterative adjustments. This allows for a more comprehensive and accurate search for optimal capacity configurations for each unit in the hydrogen production system. This not only improves the adaptability of the configuration results to complex actual operating conditions and enhances their responsiveness to the dynamic characteristics of the purification units, but also increases the likelihood of achieving a global or near-global optimal configuration through a systematic iterative optimization process, thereby improving the overall operational efficiency of the hydrogen production system.

[0096] In an exemplary embodiment, the unit constraints of the hydrogen purification unit are determined by the following steps:

[0097] The hydrogen flow rate of the electrolyzer hydrogen production unit is greater than or equal to a preset hydrogen flow rate threshold as the first unit operation constraint condition of the hydrogen purification unit; and the shutdown critical temperature of the hydrogen purification unit is obtained; based on the temperature, the shutdown critical temperature and the preset temperature tolerance value, the second operation constraint condition of the hydrogen purification unit is determined.

[0098] Among them, the first unit operation constraint condition is the minimum hydrogen inlet flow requirement maintained to ensure that the hydrogen purification unit (for example, a temperature swing adsorption device) can operate normally during specific working stages such as high-temperature regeneration and prevent the performance degradation or damage of materials such as the adsorbent filled inside it. The shutdown critical temperature is a key safety temperature threshold inside the hydrogen purification unit. In some embodiments, when the actual temperature inside the unit is higher than the safety temperature threshold, if the hydrogen flow is suddenly interrupted and the unit is shut down, the equipment may suffer a life decline or safety risk due to local overheating. The second operation constraint condition is a start-stop logic constraint that is strongly related to the temperature state and is set based on the shutdown critical temperature. It is used to stipulate that the system is allowed to perform a shutdown operation only when the actual operating temperature of the purification unit has cooled to a safe range below the critical temperature.

[0099] Specifically, when determining the operating constraint condition of the first unit, the terminal uses a minimum regeneration flow value determined according to the design specifications of the purification device as a preset hydrogen flow threshold (Y min ). In each time step t of the system operation model, the terminal determines whether the purification unit is in operation. If so (that is, its state variable ), then the constraint is imposed, requiring the total hydrogen production of all electrolyzers to be Not less than the flow threshold. For example, this constraint can be mathematically expressed as formula (14):

[0100]

[0101] Specifically, when determining the operating constraints of the second unit, the terminal first obtains a shutdown critical temperature (T Crit ). Then, in each time step t, the real-time internal temperature T of the purification unit is t The core logic of this constraint is: when the purification unit is in operation, its temperature can be higher than T Crit ; However, if you want to perform a shutdown operation (i.e. changes from 1 to 0), then its temperature T t Need to have been reduced to T in advance Crit the following.

[0102] To facilitate processing in a mixed integer linear programming (MILP) solver, this logic can be converted into a standard linear constraint expression using the big-M method, as shown in formula (15).

[0103]

[0104] Where M is a sufficiently large positive number. This expression can ensure that (at runtime), it is always true because M is large enough and does not impose any restrictions; (When the machine is stopped), the constraint is automatically tightened to T t ≤T crit , thereby strictly limiting the shutdown operation to a safe temperature range.

[0105] In this embodiment, the above method is used to concretize the fuzzy operating requirements of the purification unit into two precise and calculable mathematical constraints: the minimum hydrogen flow rate and the critical shutdown temperature. This makes the final output capacity configuration plan more realistic in engineering guidance and operational safety, thereby improving the operational stability of the integrated hydrogenation and production device.

[0106] In an exemplary embodiment, the adjustment directions corresponding to multiple candidate capacity configurations are determined according to the degree of excellence, including: determining the priorities corresponding to each of the multiple candidate capacity configurations based on the degree of excellence; the priorities include a first priority and a second priority lower than the first priority; if the priority is the second priority, the candidate capacity configuration corresponding to the second priority level is adjusted to the capacity configuration corresponding to the first priority; iteratively adjusting the configurations of the multiple candidate capacity configurations with different adjustment degrees in the adjustment direction until the iteration end condition is met and the target capacity configuration is determined, and also including: determining the adjustment degree of the candidate capacity configuration in the adjustment direction according to the priority corresponding to the candidate capacity configuration.

[0107] Among them, priority can be a level assigned according to the quality of each candidate capacity configuration, which is used to distinguish solutions of different qualities in the algorithm and establish a collaborative relationship of guidance and following. Specifically, the first priority is given to a few candidate configurations that rank at the top in terms of quality in the current solution set, which together constitute the leader echelon that guides the evolution of the population. The second priority is given to other candidate capacity configurations except the first priority. The degree of adjustment refers to the value or amplitude of the modification of each capacity parameter of a second-priority candidate configuration when it approaches the first-priority configuration. This value can be calculated and determined based on factors such as the distance between it and one or more first-priority configurations.

[0108] In one embodiment, a mechanism that simulates the social hierarchy and hunting behavior of gray wolves can be used to determine the direction and degree of adjustment. Specifically, when determining the priority, the terminal first sorts all candidate capacity configurations according to their pros and cons (for example, the lower the comprehensive cost value, the higher the pros and cons) at the beginning of each generation iteration. Then, the terminal designates the currently optimal candidate configuration as the α solution (leader) and determines its priority as the highest level in the first priority; the second-best and third-best candidate configurations are designated as the β solution (think tank team) and the δ solution (hub), respectively, and their priorities also belong to the first priority. All remaining candidate capacity configurations are uniformly designated as the ω solution (civilian), and their priority is determined to be the second priority.

[0109] When determining the direction and degree of adjustment, for each ω solution in the second priority, the terminal can calculate its distance from the three first priority solutions α, β, and δ in the multidimensional capacity parameter space. The distance is a multidimensional vector, each component of which represents the difference in a certain capacity parameter (such as electrolyzer power). Optionally, these three distance vectors are weighted and combined by a set of random coefficients to generate a final step vector that guides the ω solution to update its position. This step vector not only clarifies the direction of parameter adjustment (i.e., the direction of the vector), but also quantifies the degree of adjustment (i.e., the modulus of the vector), thereby driving all second-priority solutions to move collaboratively towards the areas where the current optimal, suboptimal, and third-optimal solutions are located under the collective guidance of the first-priority leadership echelon.

[0110] In an optional embodiment, the adjustment degree can be determined by a cuckoo algorithm. For example, the cuckoo algorithm iteration is expressed as formula (16):

[0111]

[0112] Where, i represents the number of host bird nests (candidate capacity configuration), α is the step size factor, Denotes the new position of the i-th candidate capacity configuration after the m-th iterative update, and Levy(η) is the step length of the random flight, which conforms to the distribution of the Levy flight. During the flight, short-distance walks with smaller step lengths alternate with long-distance walks with larger step lengths, which is conducive to expanding the search range and avoiding falling into the local optimum. For example, its functional expression is formula (17):

[0113] Levy~u=l -η ,(1<η<3), formula (17).

[0114] Among them, l is the distance step, u is the probability of obeying the Levy distribution, which represents the probability of going out of l.

[0115] In this embodiment, by dividing candidate configurations into different priorities and establishing a mechanism for adjusting low-priority solutions to a set of high-priority solutions, an efficient search paradigm that imitates biological social collaborative behavior is introduced into the optimization process. This can not only ensure rapid convergence to the discovered high-quality solution area, but also avoid falling into the local optimal trap prematurely due to the limitations of a single optimal solution through the combined effect of multiple guiding points, thereby improving the stability and robustness of the optimization process.

[0116] In an exemplary embodiment, multiple candidate capacity configurations are iteratively adjusted with different degrees of adjustment according to various adjustment directions until an iterative end condition is met, thereby determining target capacity configurations for the electrolyzer hydrogen production unit, the hydrogen purification unit, and the hydrogen storage unit, including:

[0117] Iteratively adjust the configuration with different adjustment degrees in the adjustment direction to obtain multiple adjusted candidate capacity configurations; for each adjusted candidate capacity configuration, compare the corresponding quality of the adjusted candidate capacity configuration with the candidate capacity configuration before adjustment; use the candidate capacity configuration corresponding to the highest quality as the starting point of the next iteration, and return to perform iterative adjustment of the configuration with different adjustment degrees in the adjustment direction until the iteration end condition is met and the target capacity configuration is determined.

[0118] For example, as shown in formula (18), in an iterative adjustment process, an adjusted corresponding candidate capacity configuration X is generated for the candidate capacity configuration X(m) in the current population. new (m).

[0119] For each individual in the population, the terminal can call the objective function corresponding to the optimization target and calculate the quality f(X(m)) of the configuration X(t) before adjustment and the quality f(X(m)) of the configuration X(t) after adjustment. new The degree of quality f(X new (m)). If the adjusted configuration X new (m) is higher than or equal to the configuration X(m) before adjustment, the terminal will adopt the new configuration, that is, X new (m) is the starting point X(m+1) of the individual in the next iteration t+1. On the contrary, if the adjusted new configuration X new If the new configuration (X(m)) does not bring improvement or even worsens, the terminal will discard the new configuration and retain the old configuration before the adjustment, X(m), as the starting point X(m+1) for the next iteration. By performing this survival of the fittest operation on all individuals in the population, the average quality of the entire population entering the next iteration will not decrease, thus achieving a stable, one-way optimization process.

[0120]

[0121] In this embodiment, by comparing the advantages and disadvantages of the new and old configurations after each iteration and always retaining the better solution as the starting point of the next iteration, this greedy selection strategy greatly enhances the algorithm's local search capability and convergence stability. It can ensure that after the algorithm finds a high-quality solution, it can continue to explore in detail on this basis, thereby effectively improving the reliability of ultimately finding a high-quality solution.

[0122] In an exemplary embodiment, obtaining an optimization target for capacity configuration based on operating resources consumed during the operation of the hydrogen production system includes:

[0123] The initial investment cost, cumulative operation and maintenance cost, and replacement cost of key components of the hydrogen production system within the preset operating time are determined as the full life cycle cost sub-goals; the penalty cost corresponding to the amount of abandoned photovoltaic power due to the photovoltaic power generation exceeding the system's absorption capacity is determined as the abandoned photovoltaic penalty cost sub-goal; the electricity purchase cost corresponding to the electricity purchased from the external power grid to meet the operation of the hydrogen production system is determined as the electricity purchase cost sub-goal; the full life cycle cost sub-goal, abandoned photovoltaic penalty cost sub-goal, and electricity purchase cost sub-goal are normalized, and the normalized sub-goals are weighted according to the preset weights to combine them into the optimization goal of capacity configuration.

[0124] Specifically, the life cycle cost sub-goal f1 includes initial investment cost, operating cost and replacement cost, as shown in formula (19) for example:

[0125] f1=C in +C O +C re , formula (19).

[0126] Among them, C in is the initial investment cost, which represents the one-time cost required for the initial construction, procurement, installation and commissioning of the system; C O is the operating cost; C re is the replacement cost, which refers to the cost of replacing each component in this configuration after it reaches its service life.

[0127] For the initial investment cost C in , for example, as shown in formula (20):

[0128] C in =C in,PV +C in,ELE +C in,H2 +C in,SC , formula (20).

[0129] Among them, C in,PV 、C in,ELE 、C in,H2 、Cin,SC It can be expressed by formula (21):

[0130]

[0131] Among them, C in,PV 、C in,ELE 、C in,H2 、C in,SC are the initial investment costs of the photovoltaic array, electrolyzer, hydrogen storage tank, and battery respectively; ρ1, ρ2, ρ3, and ρ4 are the investment cost coefficients of the photovoltaic array, electrolyzer, hydrogen storage tank, and battery respectively; R PV is the configuration capacity of the photovoltaic array; R ELE is the configuration capacity of the electrolytic cell; R H2 is the configuration capacity of the hydrogen storage tank; R H2 is the configured capacity of the battery; r is the annual interest rate; N is the operating life of the system.

[0132] For the cumulative operation and maintenance cost C O , for example, as shown in formula (22):

[0133]

[0134] Among them, C O,PV 、C O,eLE 、C O,H2 、C O,SC They are the annual operation and maintenance costs of the photovoltaic array, electrolyzer, hydrogen storage tank, and battery respectively.

[0135] For the system replacement cost C re , for example, as shown in formula (23):

[0136] C re =C re,PV +C re,ELE +C re,H2 +C re,SC , formula (23).

[0137] Among them, C re,PV 、C re,ELE 、C re,H2 、C re,SC It can be expressed by formula (24):

[0138]

[0139] Among them, n1, n2, n3, and n4 are the service life of the photovoltaic array, electrolyzer, hydrogen storage tank, and battery respectively; C re,PV 、C re,ELE 、C re,H2 、C re,SCare the replacement costs of the photovoltaic array, electrolyzer, hydrogen storage tank and battery respectively.

[0140] Specifically, photovoltaic output fluctuates with changes in sunlight intensity. When photovoltaic output exceeds load demand, it may lead to curtailment. Therefore, rationally planning the capacity of the hydrogen energy storage system can effectively reduce the cost of curtailment. The curtailment penalty cost f2 can be expressed by formula (25).

[0141]

[0142] Among them, P excess (t) is the amount of abandoned light at time t; P rice (t) is the time-of-use electricity price of the power grid at time t.

[0143] Specifically, power supply reliability is an important indicator to characterize the stability of system operation. External power purchase is the key to achieving reliability. The external power purchase cost f3 can be calculated using formula (26).

[0144]

[0145] Among them, P buy (t) is the electricity purchase amount at time t.

[0146] Finally, the terminal normalizes and weights the three sub-goals f1, f2, and f3 to obtain the optimization goal f, which is shown in formula (27) as follows:

[0147]

[0148] Among them, w1, w2 and w3 are the weight coefficients of the whole life cycle cost, the penalty cost of curtailed solar power and the cost of purchased electricity respectively; are the minimum values ​​of f1, f2 and f3 respectively.

[0149] In this embodiment, by decomposing the optimization objective into three specific and key sub-goals: full life cycle cost, curtailment penalty, and electricity purchase cost, and scientifically combining them using normalization and weighted summation, the evaluation dimension of the system configuration plan is transformed from a single perspective to a multi-dimensional comprehensive perspective, which can comprehensively balance the three core performance indicators of the system: long-term economic efficiency, renewable energy absorption rate, and energy independence.

[0150] In an exemplary embodiment, the hydrogen purification unit model is established by the following steps:

[0151] Based on the temperature of the hydrogen purification unit and the heat exchange rate during each operating phase of the unit, a temperature dynamic equation is determined to describe the temperature changes of the hydrogen purification unit. A timer model is established to track the operating phase of the hydrogen purification unit. The timer model's segmented operation logic is converted into a predefined form by introducing auxiliary binary variables, resulting in a predefined timer model. The hydrogen purification unit model is then determined based on the temperature dynamic equation, the predefined timer model, and the unit's operating constraints. The temperature dynamic equation can be a differential or difference equation describing the temporal variation of the internal temperature of the hydrogen purification unit. It comprehensively considers multiple heat exchange processes, including heat input, heat output, and natural heat dissipation to the environment, during the unit's heating and cooling phases. The timer model can be a virtual clock used to track and record the specific phase of the hydrogen purification unit's complex, cyclical workflow. The predefined form can be achieved by converting the nonlinear segmented logic in the timer model into a standard mixed-integer linear form that can be directly processed by introducing auxiliary binary variables and applying the Big-M method.

[0152] For example, due to the internal working logic of the hydrogen purification unit, it cannot be shut down at any time during high-temperature regeneration. A certain air flow rate must be maintained to prevent damage to the device or degradation of its life. However, the traditional purification process for a stable hydrogen production process may be difficult to match with the random and volatile renewable energy hydrogen production process. The purification device lacks sufficient operational flexibility, which makes production scheduling difficult. This embodiment additionally considers the operational constraints of the hydrogen purification device and divides it into three stages: adsorption, heating regeneration, and cooling, which are performed alternately to ensure high-purity hydrogen production.

[0153] Specifically, the temperature of the drying tower is described using a first-order temperature dynamic model, as shown in formula (28):

[0154]

[0155] The temperature change T of the purification unit in each discrete time step Δt t+1 -T t Described as heating power Cooling power and natural heat dissipation to the environment The result of the combined effect of the three factors is shown in formulas (29) to (31).

[0156]

[0157] Among them, C Aux 、T t are the heat capacity and temperature of the drying tower respectively; They are heating and cooling heat respectively; To dissipate heat; H t 、C t are the state variables of the purification device startup, heating, and cooling respectively; M is a large constant; P Aux,0 is the power consumption of the remaining auxiliary machines, which is assumed to be constant here.

[0158] The terminal establishes a timer variable τ for the cyclical workflow of the purification unit (for example, a cycle is defined as heating for 10 hours → cooling for 8 hours → heating for 3 hours → cooling for 3 hours), as shown in equations (32)-(34). When the purification system is operating, the timer starts; when it stops, the timer stops and remains on; when it resumes operation, the timer continues counting based on the last time it stopped.

[0159]

[0160] H t +C t ≤1, formula (34).

[0161] To convert this piecewise, nonlinear timing logic into a predefined form (i.e., a mixed-integer linear form) that can be processed by the optimization solver, the terminal can introduce multiple auxiliary binary variables, such as Z1, Z2, Z3, and Z4, corresponding to different heating or cooling intervals. The terminal then uses the Big M method to bind the value range of the timer variable τ to these binary variables through a series of inequality constraints, thereby successfully linearizing the original piecewise logic. For example, as shown in Equations (35)-(37),

[0162]

[0163] Where: Z1, Z2, Z3, and Z4 represent the purification device operating in heating interval 1, cooling interval 1, heating interval 2, and cooling interval 2, respectively.

[0164] The terminal integrates the obtained temperature dynamic equation, the preset timer model after linearization, and the unit operation constraints defined above (i.e., minimum flow constraint and shutdown temperature constraint) into a complete operation model. This model is a model that can accurately characterize the operating characteristics of the hydrogen purification unit.

[0165] In this embodiment, by establishing a refined hydrogen purification unit model that includes temperature dynamics, periodic timing, and key operating constraints, and converting it into a unified preset form, accurate operational characterization of key equipment in the hydrogen production system that was often oversimplified or directly ignored in the past is achieved, fundamentally improving the fidelity and accuracy of the entire system operation model.

[0166] In an exemplary implementation, after establishing the system operation model and optimization target of the hydrogen production system, the present application provides an improved Grey Wolf Optimizer and Cuckoo Search algorithm (GWO-CS) to determine the target capacity configuration, such as Figure 4 As shown, specifically, the position of the gray wolf, that is, the configuration capacity of the photovoltaic array electrolyzer hydrogen storage tank and the battery, is defined, the coefficient vector convergence factor and other related parameters of the algorithm itself are input, the objective function and constraints to be optimized by the system are determined, the position of the wolf pack is initialized using Kent mapping, the leader α, think tank β, hub δ and civilian ω in the wolf pack are selected according to fitness, and the position of the gray wolf individual is updated according to the wolf pack's encirclement hunting mechanism and greedy selection strategy to reach the number of iterations and output the optimal result.

[0167] In an exemplary embodiment, when facing different application problems of water electrolysis hydrogen production equipment in the power system, the existing technology provides some solutions, such as reducing operating costs through the day-ahead optimization method of the start-stop characteristics of the electrolyzer; improving hydrogen production efficiency and flexibility through photovoltaic absorption and impurity impact analysis; expanding active power scheduling to reactive power to achieve coordinated management of the entire system; improving hydrogen production safety and power balance from the perspectives of intraday rotation and real-time control, and proposing a multi-time scale framework and dynamic hydrogen price strategy to promote new energy absorption and economic benefits. On the other hand, a novel wind-solar hybrid hydrogen production scheme was proposed, based on the coordinated operation of multiple electrolysis hydrogen production technologies. Software was used to analyze photovoltaic / battery / hydrogen projects, taking into account factors such as initial investment, net present value cost, unit energy cost, and capacity shortage. The energy stored in hydrogen was analyzed to meet demand under minimum power load, and the software was used to solve related problems. A sparrow search algorithm was used to optimize the configuration of the various components of the hydrogen production system with the goal of reducing unit power generation cost. An improved cat swarm algorithm was proposed, which, through set weight coefficients, integrated the three optimization objectives of economic efficiency, wind curtailment rate, and power shortage rate into a single optimization objective, solving the configuration problem of the wind-solar hybrid hydrogen production system. A solver was used to solve multiple supercapacitor configuration models to explore solution frontiers. To reduce system operating costs and maximize wind and solar power consumption, a multi-objective particle swarm algorithm was used to solve the configuration optimization problem of the wind-solar hybrid power generation hydrogen storage system. However, most existing methods focus on single-objective optimization, and most use a single objective to solve capacity configuration, with only a few studies using multi-objective optimization. However, these multi-objective optimization methods face a small search space, resulting in insufficient coverage of the solution space and easily falling into local optimal solutions.

[0168] Based on this, the present application provides a capacity configuration method for a hydrogen production system that can solve the above-mentioned technical problems. Figure 5As shown, specifically including:

[0169] Step S501 establishes a system operation model for the hydrogen production system. This model comprises three units: the electrolyzer hydrogen production unit, the hydrogen purification unit, and the hydrogen storage unit. To establish the hydrogen purification unit model, the terminal establishes a temperature dynamics equation based on the unit's physical heat capacity. This equation describes the change in internal unit temperature within each time step, as a function of multiple heat exchange rates, including heating, cooling, and heat dissipation to the environment. Furthermore, to track the purification unit's position during alternating operation phases, such as heating and cooling, the terminal also establishes a timer model. To facilitate subsequent unified solutions, the terminal successfully converts the inherent segmented operation logic of the timer model into a standard, pre-set form by introducing auxiliary binary variables. During the model establishment process, the terminal also defines unit constraints for the hydrogen purification unit. The first unit operation constraint is defined as follows: as long as the purification unit is operating, the hydrogen flow rate from the electrolyzer hydrogen production unit must be greater than or equal to a preset hydrogen flow threshold, ensuring internal process stability. Meanwhile, the second operating constraint is temperature-related: the terminal first determines a shutdown threshold temperature and sets a shutdown limit for the purification unit only if its internal temperature remains below that threshold. This completes a complete hydrogen purification unit model, encompassing temperature dynamics equations, a pre-defined timer model, and the unit's operating constraints. Together with the electrolyzer and hydrogen storage unit models, this model forms the system's operational model.

[0170] Step S502, obtain the optimization target of capacity configuration. The terminal uses the system's full life cycle cost sub-target, the abandoned photovoltaic penalty cost sub-target, and the electricity purchase cost sub-target as the three core evaluation dimensions. Among them, the full life cycle cost sub-target is composed of the sum of the system's initial investment cost, the long-term accumulated operation and maintenance cost, and the replacement cost of key components after reaching the end of their service life. The abandoned photovoltaic penalty cost sub-target is to accumulate the economic losses corresponding to all abandoned photovoltaic power that cannot be utilized by the system. The electricity purchase cost sub-target is to accumulate all the electricity costs purchased from the external power grid to maintain system operation. In order to comprehensively evaluate these three sub-targets of different nature, the terminal first normalizes them to eliminate the differences in their numerical magnitudes. Then, the terminal performs a weighted summation on the three normalized sub-targets according to a set of pre-set weights, thereby combining them into a multi-dimensional and comprehensive optimization target for capacity configuration.

[0171] In step S503, based on the system operation model and optimization objectives, the target capacity configuration is determined using the Grey Wolf-Cuckoo optimization algorithm. Multiple candidate capacity configurations are first generated as an initial solution set. The core step then involves the terminal determining the adjustment direction for each candidate capacity configuration based on the relative merits of all candidate capacity configurations. Specifically, the terminal prioritizes each candidate capacity configuration based on the optimization objective calculation results corresponding to each candidate capacity configuration. The few candidate configurations with the highest relative merits are assigned first priority, while the remaining configurations are assigned second priority. This determines the adjustment direction: all candidate configurations with second priority must be adjusted toward the candidate configuration with first priority. Furthermore, the degree of adjustment—the magnitude of parameter modification—is determined by factors such as the distance between the candidate configuration and the first priority configuration. The terminal then enters a loop of iterative configuration adjustment. In each iteration, the terminal first obtains multiple adjusted candidate capacity configurations based on the aforementioned adjustment directions and degrees. The terminal then compares the relative merits of each adjusted candidate capacity configuration with its predecessor. The terminal can always select and retain the configuration with the highest performance as the starting point for the next iteration. The terminal repeats this iterative adjustment and selection process until a preset end-of-iteration condition is met, such as when the number of iterations reaches a set upper limit. When the iteration ends, the terminal selects the globally optimal solution from the optimal solutions recorded throughout all iterations and determines it as the final target capacity configuration.

[0172] In this example, by modeling the integrated hydrogenation system, incorporating purification temperature and timing into the scheduling framework, and considering purification heating and cooling logic constraints, we can avoid the situation where purification cannot be shut down at high temperatures, resulting in high-cost hydrogen production, thereby enhancing the operational stability of the capacity-configured system. By combining an improved Grey Wolf optimization algorithm with a Cuckoo algorithm for optimization and solution, the stability of the system solution and global search capabilities are significantly improved. This allows for more rapid and accurate identification of optimal values ​​for the cost and operational efficiency of the integrated hydrogenation system, thereby improving the effectiveness and speed of the power generation system.

[0173] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily performed in sequence in the order indicated by the arrows. Unless clearly stated herein, the execution of these steps is not strictly limited in order, and these steps can be performed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above may include multiple steps or multiple stages, and these steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of the steps or stages in other steps or other steps. It is understandable that the various steps in different embodiments can be freely combined as needed, and the various non-contradictory schemes formed by the combination all fall within the scope of protection of this application.

[0174] Based on the same inventive concept, embodiments of the present application also provide a capacity configuration device for a hydrogen production system for implementing the aforementioned capacity configuration method for a hydrogen production system. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more of the following embodiments of the capacity configuration device for a hydrogen production system can be found in the aforementioned limitations of the capacity configuration method for a hydrogen production system, and will not be further elaborated here.

[0175] In an exemplary embodiment, Figure 6 As shown, a capacity configuration device for a hydrogen production system is provided, comprising: a system operation model establishment module 610, an optimization target acquisition module 620, a candidate capacity configuration determination module 630, a configuration adjustment direction determination module 640, and a target capacity configuration determination module 650, wherein:

[0176] The system operation model establishment module 610 is used to establish a system operation model for characterizing the operating state of the hydrogen production system; the system operation model includes an electrolyzer hydrogen production unit, a hydrogen purification unit, and a hydrogen storage unit; the hydrogen purification unit is used to receive and purify the hydrogen produced by the electrolyzer hydrogen production unit, and the hydrogen storage unit is used to store the purified hydrogen; the hydrogen purification unit operates under unit constraints determined by the temperature in the hydrogen purification unit and the hydrogen flow rate of the electrolyzer hydrogen production unit;

[0177] The optimization target acquisition module 620 is used to obtain the optimization target of the capacity configuration according to the operating resources consumed during the operation of the hydrogen production system;

[0178] A candidate capacity configuration determination module 630 is configured to determine, based on the system operation model and the optimization objective, candidate capacity configurations for the electrolyzer hydrogen production unit, the hydrogen purification unit, and the hydrogen storage unit; the candidate capacity configurations include power capacity configurations or hydrogen capacity configurations;

[0179] a configuration adjustment direction determining module 640 for determining, based on the target quantized values ​​of the plurality of candidate capacity configurations relative to the optimization target of the capacity configuration, the corresponding superiority or inferiority of the plurality of candidate capacity configurations, and determining, based on the superiority or inferiority, the corresponding adjustment directions of the plurality of candidate capacity configurations;

[0180] The target capacity configuration determination module 650 is used to iteratively adjust the configurations of the multiple candidate capacity configurations with different adjustment degrees according to each of the adjustment directions until the iteration end conditions are met, thereby determining the target capacity configurations of the electrolyzer hydrogen production unit, the hydrogen purification unit and the hydrogen storage unit.

[0181] In one embodiment, the system operation model establishment module 610 is further used to use the hydrogen flow rate of the electrolyzer hydrogen production unit being greater than or equal to a preset hydrogen flow rate threshold as a first unit operation constraint condition of the hydrogen purification unit; and to obtain the shutdown critical temperature of the hydrogen purification unit; and to determine the second operation constraint condition of the hydrogen purification unit based on the temperature, the shutdown critical temperature and the preset temperature tolerance value.

[0182] In one embodiment, the configuration adjustment direction determination module 640 is also used to determine the priorities corresponding to each of the multiple candidate capacity configurations based on the degree of superiority or inferiority; the priorities include a first priority and a second priority lower than the first priority; if the priority is the second priority, the candidate capacity configuration corresponding to the second priority level is adjusted to the capacity configuration corresponding to the first priority level.

[0183] In one embodiment, the configuration adjustment direction determining module 640 is further configured to determine the degree of adjustment of the candidate capacity configuration in the adjustment direction according to the priority corresponding to the candidate capacity configuration.

[0184] In one embodiment, the target capacity configuration determination module 650 is further used to perform iterative adjustment of the configuration with different adjustment degrees in the adjustment direction to obtain multiple adjusted candidate capacity configurations; for each of the adjusted candidate capacity configurations, compare the corresponding superiority or inferiority of the adjusted candidate capacity configuration with the candidate capacity configuration before adjustment; use the candidate capacity configuration corresponding to the highest superiority or inferiority as the starting point of the next iteration, return to perform iterative adjustment of the configuration with different adjustment degrees in the adjustment direction, until the iteration end condition is met, and determine the target capacity configuration.

[0185] In one embodiment, the optimization target acquisition module 620 is further used to determine the initial investment cost, cumulative operation and maintenance cost, and replacement cost of key components of the hydrogen production system after reaching the end of their service life within the preset operating time as full life cycle cost sub-targets; determine the penalty cost corresponding to the amount of abandoned photovoltaic power due to the photovoltaic power generation exceeding the system's absorption capacity as the abandoned photovoltaic penalty cost sub-target; determine the electricity purchase cost corresponding to the electricity purchased from the external power grid to meet the operation of the hydrogen production system as the electricity purchase cost sub-target; normalize the full life cycle cost sub-target, the abandoned photovoltaic penalty cost sub-target, and the electricity purchase cost sub-target, and weight each normalized sub-target according to preset weights to combine them into the optimization target of the capacity configuration.

[0186] In one embodiment, the system operation model building module 610 is further configured to determine a temperature dynamic equation for describing temperature changes of the hydrogen purification unit based on the temperature of the hydrogen purification unit and the heat exchange rate of each operation stage of the hydrogen purification unit;

[0187] A timer model is established for tracking the operating stage of the hydrogen purification unit, and the segmented operation logic of the timer model is converted into a preset form by introducing an auxiliary binary variable to obtain a timer model in the preset form; the hydrogen purification unit model is determined based on the temperature dynamic equation, the preset timer model and the unit operation constraints.

[0188] Each module in the capacity configuration device of the hydrogen production system can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in hardware form, or can be stored in a computer device memory in software form, so that the processor can call and execute the corresponding operations of each module.

[0189] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 7As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface, the display unit and the input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, near field communication (NFC) or other technologies. When the computer program is executed by the processor, a capacity configuration method for a hydrogen production system is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device casing, or an external keyboard, touchpad or mouse.

[0190] Those skilled in the art will understand that Figure 7 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0191] In one embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0192] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0193] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0194] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0195] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0196] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile memory and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in the various embodiments provided herein may be, but are not limited to, a general-purpose processor, a central processing unit (CPU), a graphics processing unit (GPU), a digital signal processor (DSP), a programmable logic unit (PLC), a data processing logic unit based on quantum computing, an artificial intelligence (AI) processor, and the like.

[0197] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0198] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A capacity configuration method for a hydrogen production system, characterized in that: The method comprises: Establish a system operation model for characterizing the operating state of the hydrogen production system; the system operation model includes an electrolyzer hydrogen production unit, a hydrogen purification unit, and a hydrogen storage unit; the hydrogen purification unit is used to receive and purify hydrogen produced by the electrolyzer hydrogen production unit, and the hydrogen storage unit is used to store the purified hydrogen; the hydrogen purification unit operates under unit constraints determined by the temperature in the hydrogen purification unit and the hydrogen flow rate of the electrolyzer hydrogen production unit; Obtaining an optimization target for capacity configuration based on the operating resources consumed during the operation of the hydrogen production system; Determining candidate capacity configurations for the electrolyzer hydrogen production unit, the hydrogen purification unit, and the hydrogen storage unit, respectively, based on the system operation model and the optimization objective; the candidate capacity configurations include power capacity configurations or hydrogen capacity configurations; Determining, based on the target quantified values ​​of the plurality of candidate capacity configurations relative to the optimization target of the capacity configuration, corresponding degrees of superiority or inferiority of the plurality of candidate capacity configurations, and determining, based on the degrees of superiority or inferiority, corresponding adjustment directions of the plurality of candidate capacity configurations; According to each of the adjustment directions, the multiple candidate capacity configurations are iteratively adjusted with different adjustment degrees until the iteration end condition is met, and the target capacity configurations of the electrolyzer hydrogen production unit, the hydrogen purification unit and the hydrogen storage unit are determined.

2. The method according to claim 1, characterized in that The unit constraints of the hydrogen purification unit are determined by the following steps: The hydrogen flow rate of the electrolyzer hydrogen production unit is greater than or equal to a preset hydrogen flow rate threshold as a first unit operation constraint condition of the hydrogen purification unit; as well as, Obtaining a shutdown critical temperature of the hydrogen purification unit; A second operating constraint condition of the hydrogen purification unit is determined based on the temperature, the shutdown critical temperature, and a preset temperature tolerance value.

3. The method according to claim 1, characterized in that The determining, based on the degree of quality, the adjustment directions corresponding to the plurality of candidate capacity configurations includes: Determining priorities corresponding to the plurality of candidate capacity configurations based on the pros and cons, wherein the priorities include a first priority and a second priority lower than the first priority; If the priority is the second priority, adjusting the candidate capacity configuration corresponding to the second priority level toward the capacity configuration corresponding to the first priority level; The iterative adjustment of the plurality of candidate capacity configurations with different adjustment degrees in the adjustment direction until an iteration end condition is satisfied and the target capacity configuration is determined further includes: An adjustment degree of the candidate capacity configuration in the adjustment direction is determined according to the priority corresponding to the candidate capacity configuration.

4. The method according to claim 3, characterized in that The iterative adjustment of the plurality of candidate capacity configurations with different adjustment degrees according to the respective adjustment directions until an iterative end condition is satisfied, thereby determining target capacity configurations of the electrolyzer hydrogen production unit, the hydrogen purification unit, and the hydrogen storage unit, respectively, includes: Performing iterative configuration adjustments with different adjustment degrees in the adjustment direction to obtain multiple adjusted candidate capacity configurations; For each of the adjusted candidate capacity configurations, comparing the respective corresponding superiority or inferiority of the adjusted candidate capacity configuration and the candidate capacity configuration before the adjustment; The candidate capacity configuration corresponding to the highest degree of quality is used as the starting point of the next iteration, and configuration iterative adjustment with different degrees of adjustment is performed in the adjustment direction until the iteration end condition is met to determine the target capacity configuration.

5. The method according to claim 1, wherein The obtaining of an optimization target for capacity configuration according to the operating resources consumed during the operation of the hydrogen production system includes: The initial investment cost, accumulated operation and maintenance costs, and replacement costs of key components of the hydrogen production system after reaching the end of their service life are determined as sub-goals for the life cycle cost; The penalty cost corresponding to the amount of abandoned photovoltaic power caused by the photovoltaic power generation exceeding the system's absorption capacity is determined as the abandoned photovoltaic penalty cost sub-target; The electricity purchase cost corresponding to the electricity purchased from the external power grid to meet the operation of the hydrogen production system is determined as the electricity purchase cost sub-target; The full life cycle cost sub-target, the curtailment penalty cost sub-target and the electricity purchase cost sub-target are normalized, and each normalized sub-target is weighted according to a preset weight to combine them into the optimization target of the capacity configuration.

6. The method according to any one of claims 1 to 5, characterized in that The hydrogen purification unit model is established by the following steps: determining a temperature dynamic equation for describing temperature changes of the hydrogen purification unit according to the temperature of the hydrogen purification unit and the heat exchange rate of each operating stage of the hydrogen purification unit; Establishing a timer model for tracking the operating stage of the hydrogen purification unit, and converting the segmented operation logic of the timer model into a preset form by introducing an auxiliary binary variable to obtain a timer model in the preset form; The hydrogen purification unit model is determined according to the temperature dynamic equation, the preset timer model and the unit operation constraint conditions.

7. A capacity configuration device for a hydrogen production system, characterized in that: The device comprises: A system operation model establishment module is used to establish a system operation model for characterizing the operating state of the hydrogen production system; the system operation model includes an electrolyzer hydrogen production unit, a hydrogen purification unit, and a hydrogen storage unit; the hydrogen purification unit is used to receive and purify the hydrogen produced by the electrolyzer hydrogen production unit, and the hydrogen storage unit is used to store the purified hydrogen; the hydrogen purification unit operates under unit constraints determined by the temperature in the hydrogen purification unit and the hydrogen flow rate of the electrolyzer hydrogen production unit; An optimization target acquisition module, configured to acquire an optimization target for capacity configuration according to the operating resources consumed during the operation of the hydrogen production system; a candidate capacity configuration determination module, configured to determine, based on the system operation model and the optimization objective, candidate capacity configurations for the electrolyzer hydrogen production unit, the hydrogen purification unit, and the hydrogen storage unit; the candidate capacity configurations include power capacity configurations or hydrogen capacity configurations; a configuration adjustment direction determining module, configured to determine, based on target quantified values ​​of the plurality of candidate capacity configurations relative to the optimization target of the capacity configuration, the corresponding degrees of excellence of the plurality of candidate capacity configurations, and determine, based on the degrees of excellence, the corresponding adjustment directions of the plurality of candidate capacity configurations; The target capacity configuration determination module is used to iteratively adjust the configurations of the multiple candidate capacity configurations with different adjustment degrees according to each of the adjustment directions until the iteration end conditions are met, thereby determining the target capacity configurations of the electrolyzer hydrogen production unit, the hydrogen purification unit and the hydrogen storage unit.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images