Green hydrogen system capacity configuration method, device and platform and storage medium

Abstract

The invention relates to a renewable energy technology, and discloses a green hydrogen system capacity configuration method and device, a platform and a storage medium, and the method comprises the steps: obtaining renewable energy output data, system module parameters and business demand information of a target project; configuring a coupling system model based on the renewable energy output data, the system module parameters and the service demand information; wherein the coupling system model takes electricity-hydrogen power balance as a basic physical constraint, and integrates at least one system operation constraint; in response to at least one optimization target configured by the user based on the business demand information, constructing a combined optimization target function; and solving the coupling system model through a hybrid optimization algorithm to obtain a target capacity configuration scheme which meets basic physical constraints and system operation constraints and enables the combinatorial optimization target function to be optimal. According to the method, global optimization of green hydrogen system capacity configuration and operation simulation data can be realized, and the comprehensive hydrogen production cost can be reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of renewable energy technology, in particular to a green hydrogen system capacity configuration method, device, platform and storage medium. BACKGROUND

[0002] With the transformation of global energy structure towards low carbonization and cleanization, the penetration rate of renewable energy such as wind energy and solar energy in the power system continues to increase. However, due to the significant intermittency and volatility of its output, large-scale grid connection brings great challenges to the stable operation of the power grid. Under this background, hydrogen energy, as a high energy density and zero carbon emission secondary energy carrier, has gradually become an important technical path to realize efficient consumption of renewable energy and cross-time and space energy storage. Through water electrolysis hydrogen production technology, surplus wind power and photovoltaic power can be converted into green hydrogen storage, which not only can alleviate the problem of abandoned wind and light, but also can provide green fuel or raw materials for transportation, industry, chemical industry and other fields, and promote the process of deep decarbonization.

[0003] In a wind-solar coupled hydrogen production system, the capacity configuration between the power source (wind / solar), energy storage device and electrolytic hydrogen production load directly determines the economy, stability and energy utilization efficiency of the system. In particular, in off-grid or weakly connected green hydrogen projects, there is a lack of external grid support, and the system must rely on reasonable equipment selection and collaborative operation strategy to achieve dynamic balance of source-storage-load on the time scale of 8760 hours in a year, to ensure continuous and stable operation of the electrolyzer, and to minimize the loss of abandoned electricity.

[0004] At present, the experience-based or simplified analysis method commonly used in the industry still dominates in the preliminary planning and design of such projects. Typical practices include: estimating the equivalent utilization hours of wind and solar resources based on historical data, setting a fixed wind-solar ratio and electrolyzer scale ratio, and using a linear calculation model to calculate key indicators such as power generation, hydrogen production, energy storage demand and abandoned electricity rate item by item; then a small number of candidate schemes (usually no more than 5) are constructed, and the relatively suitable configuration for the client's needs is selected as the final recommended scheme after artificial comparison. This process is usually based on pre-set operating modes or reasonable assumptions about the proportion of device configuration, artificially generates a limited number of candidate schemes, and selects from them, which is essentially a mode of selecting the best from a limited set of feasible solutions, and has obvious limitations.

[0005] Research has found that the existing technology has at least the following three defects: First, the design logic is fragmented, and there is a lack of system-level collaborative modeling mechanism. The existing methods often perform power supply planning, energy storage configuration and hydrogen production system design independently in steps, such as determining the wind and light capacity according to the maximum output, preferentially selecting low-power PEM electrolytic cells, and configuring energy storage according to the ideal peak clipping and valley filling principle. There is a lack of unified coupling relationship between physical constraints and operating boundaries among the links. This fragmented selection idea is difficult to reflect the actual operating characteristics of the multi-energy coupling system, and is easy to cause equipment capacity mismatch, affecting the overall stability of the system.

[0006] Second, the modeling assumption is oversimplified, and the nonlinear complex relationship cannot be captured. The traditional method usually assumes that the output indicators such as hydrogen production capacity and abandoned electricity rate have an approximate linear relationship with the configuration of power supply / energy storage / electrolytic cell, and ignores the multi-peak, non-convex and strong coupling response characteristics under different component combinations. In fact, due to the combined effects of electrolytic cell start-stop characteristics, energy storage charging and discharging constraints, wind and light output uncertainty and other factors, the system performance indicators show a highly nonlinear response surface with configuration changes. It is difficult to accurately identify the global optimal solution through a few trial schemes, and even a locally feasible but overall inferior scheme may be misjudged as optimal, causing investment decision deviation.

[0007] Third, the process is reversed and the parameter reliability is low, and the scheme has poor landing performance. The current mainstream method adopts a reverse process of "first preset parameters, then simulation verification, and finally matching demand", that is, a series of boundary conditions (such as wind and light ratio, electrolytic cell load rate, energy storage utilization rate, etc.) are artificially assumed, and single-point or multi-point simulation is carried out, and finally whether the customer's target is met is evaluated in reverse according to the results. This method relies heavily on subjective experience, and the parameters set lack actual operation mechanism support. Especially when there are many parameter combinations, it is difficult to demonstrate its engineering feasibility and economic rationality, resulting in a large deviation of the design scheme in the actual construction and operation stage, high comprehensive cost, and lower-than-expected project return rate. SUMMARY

[0008] Therefore, the embodiments of the present application provide a green hydrogen system capacity configuration method, device, platform and storage medium to realize simultaneous optimization of capacity configuration and operation simulation data under the condition of essential safety and stability of the green hydrogen system, and to guarantee the strong coupling of the scheme.

[0009] In a first aspect, the embodiments of the present application provide a green hydrogen system capacity configuration method, comprising: obtaining renewable energy output data, system module parameters and business demand information of a target project; configuring a coupled system model based on the renewable energy output data, the system module parameters and the business demand information; wherein the coupled system model takes the power-hydrogen power balance as a basic physical constraint, and integrates at least one system operating constraint; constructing a combined optimization objective function in response to at least one optimization target configured by a user based on the business demand information; solving the coupled system model by a hybrid optimization algorithm to obtain a target capacity configuration scheme that satisfies the basic physical constraints and the system operation constraints and optimizes the combined optimization objective function.

[0010] In an optional embodiment, the solving the coupled system model by a hybrid optimization algorithm to obtain a target capacity configuration scheme that satisfies the basic physical constraints and the system operation constraints and optimizes the combined optimization objective function comprises: generating a plurality of candidate capacity configuration schemes by a preset rule; performing constraint feasibility screening on each of the candidate configuration schemes based on the basic physical constraints and the system operation constraints to determine at least one candidate feasible solution that satisfies a preset default threshold; optimizing the candidate feasible solution based on the coupled system model and the combined optimization objective function to obtain the target capacity configuration scheme, wherein the target capacity configuration scheme includes installed capacity of a power source, rated capacity and rated power of an energy storage system, and rated scale of a hydrogen production device.

[0011] In an optional embodiment, the basic physical constraint of the electric-hydrogen power balance is that total input power and total output power of the system are equal within a preset time step; wherein the total input power includes renewable energy power generation power, controllable power supply power, purchased power, and energy storage charging and discharging power; and the total output power includes total hydrogen production power, external transmission power, and power loss.

[0012] In an optional embodiment, the optimization target includes at least one of the following: lowest comprehensive hydrogen production cost, lowest unit hydrogen production power consumption, maximum hydrogen production amount, highest equipment capacity utilization rate, minimum energy storage configuration capacity, and lowest curtailment rate. The combined optimization objective function is constructed based on all the optimization targets configured by the user by a priority sorting method, a linear weighting method, or a hybrid method; wherein the hybrid method is a method of taking one of the optimization targets as a primary target, and taking the remaining optimization targets as secondary targets by the linear weighting method.

[0013] In an optional embodiment, the system operation constraints include device operation characteristic constraints, device life constraints, and business demand constraints. The equipment operation characteristic constraints include the minimum power ratio and maximum power ratio for stable operation of the electrolyzer; the equipment life constraints include the upper limit of the number of start-ups and shutdowns per year, the upper limit of the annual operating time of the electrolyzer, and the upper limit of the number of charge-discharge cycles per year of the energy storage system; the business demand constraints include the electricity-based hydrogen constraint targeting the total fixed power supply capacity, the electricity-based hydrogen constraint targeting the fixed capacity of various power sources, the hydrogen-based electricity constraint targeting the total fixed hydrogen production, and the hydrogen-based electricity constraint targeting the total fixed hydrogen production and the upper limit of renewable energy resources. The equipment operating characteristic constraints also include a lower limit constraint on the energy storage system capacity, which is used to ensure that the rated capacity of the energy storage system is not lower than a preset proportion of the system's critical load, so as to support the system's grid construction capability or short-term overload requirements.

[0014] In an optional implementation, the step of using the candidate feasible solution as an initial solution and optimizing the candidate feasible solution based on the coupled system model and the combined optimization objective function to obtain the target capacity configuration scheme includes: Call a mathematical solver that supports solving nonlinear mixed-integer programming or quadratic mixed-integer programming problems, and use the candidate feasible solution as the initial solution to perform iterative calculations until convergence to the final solution that satisfies all constraints of the coupled system model and makes the combined optimization objective function optimal, then the target capacity configuration scheme is obtained.

[0015] In an optional implementation, when configuring the coupled system model, a modular constraint is applied to the installed capacity of the power source and / or the rated size of the hydrogen production device, wherein the modular constraint is an integer multiple of a preset modular number.

[0016] Secondly, this application provides a green hydrogen system capacity configuration device and an acquisition unit for acquiring renewable energy output data, system module parameters and business requirement information of a target project. A configuration unit is used to configure a coupled system model based on the renewable energy output data, the system module parameters, and the business requirement information; wherein the coupled system model uses the power balance of electricity and hydrogen as the basic physical constraint and integrates at least one system operation constraint; A construction unit is used to construct a combined optimization objective function in response to at least one optimization objective configured by the user based on the business requirement information; The solution unit is used to solve the coupled system model through a hybrid optimization algorithm to obtain a target capacity configuration scheme that satisfies the basic physical constraints and the system operation constraints, and makes the combined optimization objective function optimal.

[0017] Thirdly, embodiments of this application provide a green hydrogen system capacity configuration platform, a human-computer interaction module, and an information processing module; The human-computer interaction module is used to receive renewable energy output data, system module parameters, business requirement information and optimization targets of the target project input by the user. The information processing module is communicatively connected to the human-machine interaction module and is used to execute the above-described green hydrogen system capacity configuration method.

[0018] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed on a processor, implements the aforementioned green hydrogen system capacity configuration method.

[0019] The embodiments of this application have the following beneficial effects: By acquiring renewable energy output data, system module parameters, and business demand information of the target project, this application constructs a coupled system model based on the physical constraint of power-hydrogen power balance and integrating at least one system operation constraint. This model can realistically reflect the dynamic interaction between power source, energy storage, and hydrogen production load across the entire time scale. Based on this, a combined optimization objective function is constructed in response to the user-configured optimization objective, and the model is solved using a hybrid optimization algorithm. This yields an optimal capacity configuration scheme that simultaneously satisfies energy conservation and engineering operation constraints, as well as corresponding highly feasible power and production capacity operation simulation curves. Compared to traditional methods that rely on experience-based values ​​or limited trial calculations, this application overcomes the problem of unreasonable resource allocation caused by independent decision-making and fragmented constraints in existing technologies. It ensures that the recommended solution not only meets the basic requirements for safe and stable system operation but also effectively responds to the diverse business needs of users, providing a high-precision and high-efficiency decision support tool for the early planning of green hydrogen projects. This embodiment constructs a multi-component coupled system model covering power supply, energy storage, hydrogen production devices, and grid interaction, and performs global optimization by combining a combinatorial optimization objective function, thereby effectively reducing the overall cost of hydrogen production. Attached Figure Description

[0020] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 A schematic diagram of a green hydrogen system capacity configuration platform according to an embodiment of this application is shown; Figure 2 This paper illustrates a first flowchart of a green hydrogen system capacity configuration method according to an embodiment of this application. Figure 3 This paper illustrates a second flowchart of a green hydrogen system capacity configuration method according to an embodiment of this application. Figure 4 The following is a graph showing the annual photovoltaic and wind power power curves in a specific calculation example of an embodiment of this application; Figure 5 The diagram shows the electrolytic cell power curve in a specific calculation example of an embodiment of this application; Figure 6 The graph shows the power curtailment curve in a specific calculation example of an embodiment of this application; Figure 7 A schematic diagram of a green hydrogen system capacity configuration device according to an embodiment of this application is shown. Detailed Implementation

[0022] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0023] The components of the embodiments of this application described and illustrated in the accompanying drawings can be arranged and designed in a variety of different configurations. Therefore, the following detailed description of the embodiments of this application provided in the drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0024] In the following text, the terms "comprising," "having," and their cognates, which may be used in various embodiments of this application, are intended only to indicate a particular feature, number, step, operation, element, component, or combination thereof, and should not be construed as primarily excluding the presence of one or more other features, numbers, steps, operations, elements, components, or combinations thereof, or adding the possibility of one or more combinations thereof. Furthermore, the terms "first," "second," "third," etc., are used only for distinguishing descriptions and should not be construed as indicating or implying relative importance.

[0025] Unless otherwise specified, all terms used herein (including technical and scientific terms) shall have the same meaning as commonly understood by one of ordinary skill in the art to which the various embodiments of this application pertain. Terms (such as those defined in commonly used dictionaries) shall be interpreted as having the same meaning as in their contextual meaning in the relevant technical field and shall not be construed as having an idealized or overly formal meaning, unless clearly defined in the various embodiments of this application.

[0026] The following detailed description of some embodiments of this application is provided in conjunction with the accompanying drawings. Unless otherwise specified, the following embodiments and features can be combined with each other.

[0027] The capacity configuration platform of the green hydrogen system will be described below with reference to some specific embodiments.

[0028] like Figure 1 As shown, the green hydrogen system capacity configuration platform includes a human-machine interaction module 100, an information processing module 200, and a data storage module 300. These modules interact and collaborate through internal communication interfaces to achieve fully automated optimization from project input to the output of the optimal capacity configuration scheme.

[0029] The human-computer interaction module 100 receives renewable energy output data, system module parameters, business requirements, and optimization goals for the target project from the user's input. Serving as the user interface between the user and the platform, this module supports access via a web browser or local client, providing a graphical, wizard-driven workflow to lower the barrier to entry for non-professional users. Users can create new project plans through this module and set basic information such as plan name, administrative division, and project affiliation. It also supports saving, comparing, and archiving multiple plans. In the basic information configuration stage, users can select the power source type involved in the project, including but not limited to wind power, photovoltaic, hydropower, controllable power sources, and the power grid; set the energy storage deployment location, covering source-side energy storage, load-side energy storage, and independent energy storage stations; and determine the hydrogen production process combination, supporting multiple technology routes such as alkaline electrolyzers (ALK), proton exchange membrane electrolyzers (PEM), anion exchange membrane electrolyzers (AEM), and solid oxide electrolyzers (SOEC). Furthermore, users need to clarify the project's business requirement model, i.e., whether to adopt a planning orientation based on electricity demand for hydrogen or hydrogen demand for electricity.

[0030] To meet the needs of different data sources, the human-computer interaction module 100 provides multiple methods for acquiring renewable energy output data. On one hand, it supports importing annual 8760-hour output sequence data generated by external measurements or simulations. The file format can be CSV or Excel, and the data content includes timestamps (accurate to the hour), power type, installed capacity, and the actual output value at the corresponding time. On the other hand, for scenarios lacking historical data, the platform can call third-party meteorological and power generation forecasting services through API interfaces. After the user provides the latitude and longitude coordinates of the geographical location, it automatically obtains wind and solar power output forecast sequences under standard capacity for subsequent modeling and analysis.

[0031] The parameter setting interface can be presented in form, guiding users to configure the technical and economic parameters of various system modules one by one. These parameters include, but are not limited to, the average annual unit cost of various renewable energy sources and their maximum exploitable installed capacity limits; the charge and discharge efficiency, discharge multiple, end-of-life battery health, and maximum allowed annual charge and discharge cycles of the energy storage system; the unit power consumption of the hydrogen production unit, the minimum to maximum power ratio during stable operation, and the annual start-stop limit; and the relevant constraints on purchased and transmitted electricity, such as power ratio limits, electricity ratio limits, and electricity price structure (supporting peak-valley time-of-use pricing and two-part pricing). Users can also select one or more optimization objectives on the interface according to their actual business needs, such as pursuing the lowest overall hydrogen production cost, the lowest unit power consumption for hydrogen production, the highest hydrogen production output, the highest equipment capacity utilization rate, the lowest energy storage configuration capacity, or the lowest curtailment rate. The system further supports integrating multiple optimization objectives through priority ranking, linear weighting, or hybrid methods to construct a unified combined optimization objective function, thereby achieving synergistic optimization of multi-dimensional objectives. After all input information is configured, users can trigger the calculation task by clicking the "Start Optimization" button. The information processing module 200 then initiates the solution process. Once the results are generated, the platform will display key performance indicators in chart form, including the annual power output curve, the trend of remaining power in the energy storage system, and the power distribution of the hydrogen production unit. Simultaneously, it will output the final target capacity configuration scheme in tabular form and generate an analysis report containing overall evaluation indicators and technical details for download and review. This analysis report can be presented in formats such as EXCEL, WORD, and PDF. Thus, the human-computer interaction module 100 achieves a complete closed loop from project modeling and parameter setting to result visualization, thereby improving the scientific rigor and efficiency of the early-stage planning and design of the green hydrogen system.

[0032] The information processing module 200 communicates with the human-machine interaction module 100 to execute the green hydrogen system capacity configuration method. As the core computing engine of the platform, this module integrates a multi-component coupled modeling mechanism and an efficient hybrid optimization algorithm. After receiving user-input data and parameters, it can automatically complete the entire process of model construction, objective function generation, and global optimization. First, the information processing module 200 dynamically loads the corresponding sub-models based on the system composition selected by the user, constructing a multi-component coupled system model covering power supply, energy storage, hydrogen production devices, and grid interaction. This model establishes a dynamic operation simulation framework covering 8760 hours throughout the year, with an hourly time step. The basic physical constraint of the model is the power-hydrogen power balance, meaning that within any time step, the total input power of the system equals the total output power. Based on this, the model also integrates at least one system operation constraint, including constraints reflecting equipment operating characteristics, equipment lifespan-related limitations, and boundary conditions determined by business requirements.

[0033] After the model configuration is completed, the information processing module 200, based on the user-defined optimization objectives, uses one of the following methods—priority ranking, linear weighting, or a hybrid approach—to transform multiple independent objectives into a computable combined optimization objective function. This is followed by the solution phase of the hybrid optimization algorithm. In the initial stage, the system generates multiple candidate capacity configuration schemes using preset rules. These rules can be based on empirical ratios of regional resource endowments, random sampling strategies, or Latin hypercube sampling methods to generate an initial solution set. Next, each candidate scheme is substituted into the coupled system model for hourly simulation, and constraint feasibility is screened based on the power balance of electricity and hydrogen and other system operating constraints. One or more candidate feasible solutions with fewer than a preset default threshold are retained. These candidate feasible solutions are then input as initial solutions into the mathematical programming solver, which calls commercial or open-source solvers (such as Gurobi, CPLEX, or COPT) that support solving nonlinear mixed-integer programming or quadratic mixed-integer programming problems for iterative optimization calculations. After a finite number of iterations, the algorithm converges to a solution that satisfies all constraints and optimizes the combined objective function. The final output is the target capacity configuration scheme, which includes core design parameters such as the installed capacity of various power sources, the rated power and rated capacity of the energy storage system, and the rated scale of various hydrogen production devices. It also outputs highly feasible power and production capacity operation data, including simulation data such as hourly power and hourly hydrogen production of each module.

[0034] After the solution is completed, the information processing module 200 returns the optimal result to the human-computer interaction module 100 for visualization. Simultaneously, it writes the complete configuration scheme and detailed operational data into the data storage module 300, ensuring the results are traceable and reusable. This method in this embodiment compresses the traditional method, which relied on manual calculations and took tens of hours, into a few minutes, thereby improving the speed and accuracy of decision-making in the feasibility study phase of the green hydrogen project.

[0035] The data storage module 300 is connected to both the human-computer interaction module 100 and the information processing module 200, and is used for persistent storage and unified management of various types of data generated during platform operation. This module can use a relational database (such as MySQL or PostgreSQL) or a time-series database (such as InfluxDB) to implement structured storage, ensuring data security, consistency, and efficient query capabilities. The stored data categories include basic project information, such as the project name, administrative division code, project affiliation, creator, creation time, and update records; renewable energy output sample data, covering power source type, installed capacity, and 8760-hour hourly output sequence (including timestamps and output values), and supports independent storage and associated management of different power source types such as wind power and photovoltaic power; system module parameters and business requirement information, i.e., the set of all input parameters configured by the user at the front end, including cost, efficiency, operating limits, electricity pricing policies, and optimization preferences.

[0036] Furthermore, the platform archives the optimal configuration schemes generated by the calculations, recording key output indicators such as the installed capacity of various power sources, the rated power and rated capacity of energy storage systems (distinguishing between source and load sides), the rated scale of various hydrogen production devices, and the amount of electricity transmitted and purchased. More importantly, the platform retains detailed 8760 hours of operational simulation data, including hourly renewable energy generation power, the charging and discharging power of energy storage systems and their remaining power (SOC), the actual power consumption of various hydrogen production devices, the amount of electricity transmitted and purchased, and fine-grained operational information such as power curtailment and line loss. This data can not only be used as a reference for subsequent engineering design but also as a basic input for control system strategy simulation and verification.

[0037] To ensure the traceability of the operation process and the maintainability of the system, the data storage module 300 also records user operation logs and system calculation logs. The operation logs cover key events such as user login behavior, parameter modification records, and the start and termination of optimization tasks; the calculation logs include internal execution information such as algorithm execution time, number of iterations, convergence status, and trends in intermediate solutions. Through these methods, the platform achieves closed-loop data management throughout the entire lifecycle, from data input and model calculation to result output, providing solid data support for enterprises to accumulate project experience and optimize model parameters.

[0038] The following examples illustrate the capacity configuration method for this green hydrogen system.

[0039] Figure 2 A schematic flowchart of a green hydrogen system capacity configuration method according to an embodiment of this application is shown. Exemplarily, the green hydrogen system capacity configuration method includes steps S100-S400: Step S100: Obtain renewable energy output data, system module parameters, and business requirement information for the target project. In this step, renewable energy output data is the core basis for reflecting the wind and solar energy resource endowment of the project site, and is used to drive the dynamic operation simulation for 8760 hours per year. This data can be obtained in two ways: data import or interface call.

[0040] In the data import method, users can upload existing historical operational data from their local systems, such as actual power generation records from similar wind farms or photovoltaic power stations in the target project area or neighboring regions, in standard file formats (such as CSV and Excel) to the human-computer interaction module 100. The submitted data should include a timestamp accurate to the hour, power type identifier, installed capacity, and the actual output value at the corresponding time, totaling 8760 data points. Upon receiving the data, the system will automatically perform validity checks, including but not limited to checking whether the number of data entries completely covers all 8760 hours of the year, verifying that the output value for each hour is non-negative and does not exceed its corresponding installed capacity, and correcting abnormal data, such as adjusting negative values ​​to 0 and truncating output values ​​exceeding the installed capacity at the upper limit. These checks ensure that the input data conforms to physical laws and the requirements of the calculation model, avoiding distortion of simulation results due to data quality issues.

[0041] In the interface call method, when historical measured data is lacking, users can input the geographical latitude and longitude coordinates of the proposed facility in the human-computer interaction module 100. The platform establishes a communication connection with external wind / solar energy resource big data platforms (such as Meteonorm, NASA POWER, meteorological data centers, etc.) through a pre-defined application programming interface. Based on the provided geographical location, the big data platform combines long-term meteorological observation data and numerical weather prediction models to generate an annual hourly power output forecast curve based on a standard capacity (usually set at 1MW), and returns it to this platform. This method can quickly obtain representative wind and solar power output sequences in the early stages of a project, supporting planning decisions under conditions where measured data is unavailable.

[0042] System module parameters define the technical performance indicators and economic cost characteristics of each functional unit constituting the green hydrogen system, and are key inputs for constructing the coupled system model. Users need to fill in the relevant values ​​one by one in the parameter setting interface of the human-machine interface module 100, according to the actual project situation or the technical specifications provided by the equipment supplier. These parameters cover multiple subsystems, specifically including but not limited to the following four categories: For renewable energy units, users can set parameters such as maximum installed capacity, average annual unit construction and operation and maintenance cost, and output limitation ratio (power generation efficiency) for power sources such as wind and solar power. In addition, a capacity modulus can be set to constrain the final recommended installed capacity (e.g., 100kW, 1MW) and / or the rated scale of hydrogen production units (e.g., [missing information]). ,all () is a specific integer value to match engineering design conventions and equipment manufacturing specifications.

[0043] For controllable power supply and grid interaction units, if the project connects to gas turbines, diesel generators, or other controllable power sources, it is necessary to set their power supply capacity, ramp rate, allowed power supply periods, and average annual connection cost. For grid-connected or external transmission scenarios, it is necessary to set policy and economic constraints such as the external power purchase limit ratio (as a percentage of total load), the external power transmission limit ratio (as a percentage of renewable energy installed capacity), the external power purchase limit ratio, the external power transmission limit ratio, peak-valley electricity price structure, and basic demand electricity price.

[0044] Energy Storage Units: Users can configure parameters for source-side energy storage, load-side energy storage, or independent energy storage stations. Key parameters include charge / discharge efficiency (system-level overall efficiency considering battery, converter, transformer, and line losses), maximum depth of charge / discharge (typically 80%-90%), cycle life, end-of-life battery health (typically 60%-80%), discharge ratio (e.g., 0.5C or 1C), and average annual unit cost. Furthermore, to meet the design requirements of grid-based energy storage, a minimum capacity ratio (CLL) setting is supported to ensure the energy storage system has short-term overload capability to support stable system operation.

[0045] For hydrogen production units, users need to set key parameters for different technologies such as alkaline electrolyzers (ALK), proton exchange membrane electrolyzers (PEM), anion exchange membrane electrolyzers (AEM), or solid oxide electrolyzers (SOEC). These parameters include unit power consumption, minimum and maximum power ratios during stable operation, cold start ramp-up rate, annual start / stop limit, average annual comprehensive cost corresponding to rated capacity, and average annual operating hours. The unit also supports setting a capacity modulus to ensure the recommended electrolyzer size matches the actual procurement specifications (e.g., a whole 100). ).

[0046] Business requirements information reflects users' business goals, resource allocation preferences, and policy constraints, serving as a core input for determining optimization directions. Users can select preset business scenario templates in the human-computer interaction module 100 and fill in the corresponding parameters. The platform offers a variety of typical scenarios for selection, including electricity-based hydrogen determination (total volume), electricity-based hydrogen determination (specific items), hydrogen-based electricity determination (total volume), and hydrogen-based electricity determination (limited quantity).

[0047] The "Electricity-Determined Hydrogen - Total Amount" approach uses the total installed capacity of renewable energy as a fixed boundary condition for the user. Under this premise, the system optimizes the configuration of energy storage and hydrogen production devices to pursue the optimal overall benefits. The "Electricity-Determined Hydrogen - Itemized" approach further subdivides the installed capacity of various renewable energy sources for the user, such as setting specific values ​​for wind power and photovoltaics, which is suitable for projects with a clear power supply layout. The "Hydrogen-Determined Electricity - Total Amount" approach refers to the user setting the expected annual hydrogen production, and the system uses this to deduce the required power supply and energy storage configuration, which is suitable for application scenarios with a clear hydrogen consumption market. The "Hydrogen-Determined Electricity - Limited Amount" approach refers to the user setting both the upper limit of available renewable energy resources and the target hydrogen production, and the system seeks the optimal solution under dual constraints, which is suitable for projects with limited resources but rigid production needs.

[0048] After selecting the scenario, users need to set the optimization objectives for this optimization search. The platform provides a set of preset objective options, including lowest overall hydrogen production cost, lowest unit hydrogen production power consumption, maximum hydrogen production, highest equipment capacity utilization, minimum energy storage capacity, and lowest power curtailment rate. Users can select one or more objectives based on the project's priorities and construct a combined optimization objective function using priority ranking, linear weighting, or a hybrid method. For example, in projects prioritizing economic efficiency, overall hydrogen production cost can be set as the primary objective; in scenarios focusing on equipment utilization, capacity utilization can be optimized first. After all the above input information is confirmed by the user, the platform proceeds to the next stage of the coupled system model construction and optimization solution process.

[0049] Step S200: Configure the coupled system model based on renewable energy output data, system module parameters, and business requirement information.

[0050] The coupled system model uses the power balance of electricity and hydrogen as the basic physical constraint and integrates at least one system operation constraint.

[0051] The fundamental physical constraint for power balance is that the total input power of the system is equal to the total output power within a preset time step; where the total input power includes renewable energy generation power, controllable power supply power, purchased power, and energy storage charging and discharging power; the total output power includes total hydrogen production power, external power transmission power, and power loss.

[0052] Specifically, based on the input information obtained in step S100, the platform constructs a multi-component coupled system model covering power supply, energy storage, hydrogen production devices, and grid interaction. This model uses the power-hydrogen power balance as the basic physical constraint and integrates at least one system operation constraint reflecting the actual engineering operation law, thereby ensuring that the generated capacity configuration scheme satisfies both the principle of energy conservation and the equipment performance boundaries and project implementation requirements.

[0053] The power balance between electricity and hydrogen is a crucial foundation for the entire coupled system model, ensuring that the system satisfies the law of conservation of energy at all times. In this embodiment, a dynamic simulation framework covering 8760 discrete moments throughout the year is established with an hourly preset time step. Based on this, the following power balance equation can be established: ;in, That is, the total input power of the system. t is the total output power of the system. .

[0054] This represents the total output of the renewable energy power generation unit at time t. The installed capacity can be determined by the renewable energy output data obtained in step S100 and the installed capacity set by the user. The obtained calculation formula is: ;in, The actual installed capacity set for the user. This is the output value under standard capacity. This is the standard capacity. If multiple power types exist simultaneously, then... Contributing to various types of renewable energy.

[0055] This represents the power output of a controllable power source (such as a gas turbine or diesel generator) at time t. It can be constrained by parameters such as the maximum power supply capacity (OPL), ramp rate (RR), and allowable power supply time (STI) input by the user, and must meet the safety requirements for continuous operation.

[0056] This represents the power purchased from the external power grid at time t, which is subject to policy and economic factors such as the power purchase limit ratio and basic demand set by the user.

[0057] This represents the charging and discharging power of the energy storage system at time t, where the power is at time t when the energy storage is in the charging state. When the energy storage is in a discharging state Its absolute value is affected by a combination of factors, including the rated power of the energy storage, the current remaining charge (SOC), the charge and discharge efficiency, and the battery health.

[0058] This represents the total electrical power consumption of the hydrogen production system at time t, which is the main power-consuming unit on the load side. According to industry experience, the hydrogen production unit (electrolyzer) accounts for approximately 90% of the total plant power consumption, with the remaining 10% coming from auxiliary equipment. Therefore, ,in, This represents the sum of DC power consumption for all types of electrolyzers at time t. It can be understood that setting the DC power consumption for hydrogen production to 90% of the total plant power consumption is a simplification based on industry experience, used to reduce model complexity while ensuring accuracy. In actual projects, this proportion can be adjusted according to the specific configuration of auxiliary equipment. For example, when adding air compressors, cooling systems, or hydrogen refueling units, this proportion can be reduced to 85% or 80% to more accurately reflect the true energy consumption distribution.

[0059] It represents the power transmitted to the external power grid at time t. It is subject to the power transmission limit ratio (as a percentage of renewable energy installed capacity) and the annual power transmission limit ratio, and cannot occur simultaneously with the purchase of electricity at the same time.

[0060] This represents the power loss at time t. This includes line technical losses, management losses, and the power that is abandoned due to inability to absorb it. This value is calculated using the difference and participates as a non-negative variable in the constraints during the optimization process.

[0061] To further avoid spurious solutions that violate energy conservation during the optimization process (such as discharge behavior despite no input power), this embodiment introduces an upper limit constraint on the proportion of abandoned power: PLOSSL is typically set to 100% as a soft boundary to prevent extreme values ​​from overflowing, ensuring that all curtailed power comes from actual generation surplus.

[0062] The power balance equations described above will be verified at each time point t (t=1, 2, ..., 8760) during the subsequent optimization process. Any feasible configuration scheme must satisfy this basic physical constraint.

[0063] When constructing a coupled system model, in addition to ensuring the fundamental physical constraint of energy conservation, it is also necessary to incorporate various system operation constraints that reflect actual engineering, equipment characteristics, and business decisions. These system operation constraints include, but are not limited to, equipment operation characteristic constraints, equipment lifespan constraints, and business requirement constraints.

[0064] Equipment operating characteristic constraints are crucial for ensuring the safe and stable operation of the system. These include the minimum and maximum power ratios for stable operation of the electrolyzer, as well as the capacity constraints for grid-based energy storage. Equipment lifespan constraints include the annual maximum number of start-ups and shutdowns, the annual maximum operating time for the electrolyzer, and the annual maximum number of charge-discharge cycles for the energy storage system. Business demand constraints include constraints based on the total fixed power supply capacity (electricity-to-hydrogen - total amount), constraints based on the fixed capacity of various power sources (electricity-to-hydrogen - specific items), constraints based on the fixed total hydrogen production (hydrogen-to-electricity - total amount), and constraints based on the fixed total hydrogen production and renewable energy resource limits (hydrogen-to-electricity - limited quantity). Equipment operating characteristic constraints also include grid-based energy storage capacity constraints, used to ensure that the rated capacity of the energy storage system is not lower than a preset minimum proportion of the system design load. The design basis for this preset minimum proportion also includes the short-term overload capacity requirements of the energy storage system. In off-grid or weak grid scenarios, energy storage systems must be able to operate continuously at 150% of rated current for at least 2 minutes, or briefly at 300% of rated current for 10 seconds, to cope with transient disturbances such as load changes and power fluctuations, and maintain the stability of microgrid voltage and frequency. Therefore, the rated capacity of the energy storage system should not be too small; otherwise, it will not provide sufficient inertia support and rapid response capability. This embodiment indirectly ensures the grid-connected performance of the energy storage system by setting a minimum capacity ratio.

[0065] Furthermore, for projects connected to gas-fired power generation or other controllable power sources, power supply ratio constraints can be set to meet green energy ratio policy requirements. Let the annual direct power supply from controllable sources be... The total renewable energy generation is Purchased electricity volume is Then we have: QSL is the maximum controllable power supply ratio set by the user (e.g., 10%), used to ensure that the green electricity usage ratio of the system is not lower than the specified threshold.

[0066] Specifically, for electrolytic cells, their operating power must be maintained within a specific range to ensure efficient and long-life operation. If the operating power is too low, it may lead to uneven electrode reactions, decreased gas purity, or even localized dry burning; if it exceeds the upper limit, it may cause overheating or material damage. Therefore, during the optimization process, for any time t, the operating power of the j-th type of electrolytic cell... The following constraints must be met: ,in, and These are the minimum and maximum power ratios for this type of electrolytic cell, respectively. For its rated size, This is determined by their power consumption per unit. For example, the typical operating range of an alkaline electrolyzer (ALK) is 30% to 110% of its rated power, while a proton exchange membrane electrolyzer (PEM), due to its excellent dynamic response, can operate as low as 10% of its rated power.

[0067] Furthermore, for green hydrogen projects that are off-grid or weakly connected to the grid, the energy storage system not only needs to perform energy buffering functions but also needs to have grid-connection capabilities to maintain the voltage and frequency stability of the microgrid. Based on this, this embodiment introduces a grid-connected energy storage capacity constraint, requiring that the rated capacity of the energy storage system not be less than a preset minimum proportion of the system design load. System design load The calculation formula is: Among them, the summation term Covering all types of hydrogen production devices, the denominator 0.9 corresponds to an empirical value for the proportion of electricity used in hydrogen production. This preset minimum proportion can be set from 5% to 20% according to project requirements. This constraint is incorporated into the optimization model as a hard boundary condition, directly determining the lower limit of energy storage configuration and preventing system instability due to insufficient energy storage capacity.

[0068] Equipment life constraints are primarily used to extend the economic lifespan of critical equipment and reduce operation and maintenance costs. These constraints include the annual start-up and shutdown limits for electrolyzers and the annual charge-discharge limits for energy storage systems.

[0069] Frequent start-ups and shutdowns of electrolyzers can induce thermal and mechanical stresses, accelerating membrane module aging and significantly shortening equipment lifespan. Therefore, an upper limit is set on the number of start-ups and shutdowns per year in the model. This limits the number of state changes per year for various types of electrolyzers. For example, the annual start-up limit for alkaline electrolyzers (ALK) and proton exchange membrane electrolyzers (PEM) can be set to 1000 and 2000 times, respectively. During the optimization process, the system statistically analyzes data from various sources throughout the year... arrive The number of state transitions is controlled within a preset threshold.

[0070] Furthermore, energy storage batteries have a limited cycle life, typically measured by the equivalent deep charge-discharge cycles over their entire lifespan. To avoid overuse, the model sets an annual maximum allowable charge-discharge cycle limit (CDSL). For example, the average annual charge-discharge cycle for lithium iron phosphate batteries can be set to 2000 cycles. The optimization algorithm will prioritize a smooth charge-discharge strategy, while meeting scheduling requirements, to reduce the equivalent losses caused by shallow charging and discharging, thereby extending the lifespan of the energy storage system.

[0071] Business demand constraints reflect the user's business decision-making orientation and determine the basic boundary conditions of the optimization problem. Based on different planning objectives, scenarios can be divided into two categories: "electricity-driven hydrogen production" and "hydrogen-driven electricity production." In the "electricity-driven hydrogen production" scenario, the user has determined the scale of renewable energy investment, aiming to maximize the benefits of hydrogen production under fixed power supply conditions. In this case, the business demand constraint means that the total installed capacity of renewable energy or the individual installed capacity of various power sources must equal the fixed value input by the user. For example, in the "electricity-driven hydrogen production - total capacity" model... In the "hydrogen determination by electricity - sub-item" model, Under these constraints, the optimization objective is usually to minimize the overall hydrogen production cost, increase capacity utilization, or reduce the curtailment rate.

[0072] In a "hydrogen-driven power generation" scenario, the primary goal for users is to meet specific hydrogen energy market demands, requiring the reverse derivation of necessary power supply and energy storage configurations. In this case, the business demand constraint manifests as the annual total hydrogen production SEE (Self-Effective Energy Output) must reach or exceed a preset target value. For example, in the "hydrogen-driven power generation - total output" model, SEE = target value; in the "hydrogen-driven power generation - limited output" model, an additional constraint of renewable energy resource caps is added. In this scenario, the optimization objective is usually to find a power source and energy storage combination that can meet production requirements, has the lowest overall cost, or the highest resource utilization rate.

[0073] In some implementations, when configuring the coupled system model, a modular constraint is imposed on the installed capacity of the power source and / or the rated size of the hydrogen production unit. The modular constraint is an integer multiple of a preset modulus, so that the optimization results conform to the basic scale of equipment selection.

[0074] Exemplary, this modular constraint is used to adjust the continuous or arbitrary capacity recommendations obtained during the optimization process to discretized specifications that conform to actual engineering procurement and construction practices. In real-world projects, wind turbine generators, photovoltaic modules, and electrolytic cell equipment are manufactured and supplied in standardized units (e.g., wind turbine units are typically 3MW or 5MW; electrolytic cell modules are commonly 500 units). 1000 Therefore, its total installed capacity or rated capacity must be an integer multiple of a certain basic unit. Without this restriction, the optimization algorithm might output something like 47.6MW photovoltaic or 823MW. Design schemes such as AL electrolyzers, which cannot be directly implemented, result in theoretically optimal but impractical outcomes. Therefore, introducing modular constraints as a hard boundary condition when constructing the coupled system model ensures the engineering feasibility of the final output target capacity configuration scheme.

[0075] In this embodiment, the modulus constraint can be expressed as: or ,in, For the power generation capacity or hydrogen production unit rated capacity to be determined, X is a preset modulus. This expression means that CAP must be an integer multiple of X. For example, when X=100, the recommended capacity can only be 100kW, 200kW, ..., 16,600kW, etc., and cannot be 16,650kW. This discretization method ensures that the output results match the actual equipment specifications.

[0076] Step S300: In response to at least one optimization objective configured by the user based on business requirement information, construct a combined optimization objective function.

[0077] The combined optimization objective function is constructed based on all user-configured optimization objectives using a priority ranking method, a linear weighting method, or a hybrid method. The hybrid method involves taking one optimization objective as the primary objective and using a linear weighting method to form secondary objectives for the remaining optimization objectives.

[0078] As an example, after configuring the coupled system model, the process proceeds to step S300, where a combinatorial optimization objective function is constructed to guide the optimization direction based on the user's decision preferences. Since the planning of a green hydrogen system involves multiple dimensions of objectives, including economics, energy efficiency, production capacity, and equipment utilization, and these objectives are often interdependent (for example, pursuing the lowest cost may lead to reduced energy storage but increased power curtailment, or increasing hydrogen production may result in higher start-up and shutdown frequencies), a mechanism is needed to integrate multiple independent optimization objectives into a quantifiable, comparable, and solvable unified evaluation standard.

[0079] When selecting optimization objectives, users can choose at least one from a set of preset core indicators as the optimization objective for this search. These objectives are all derived from the business requirement information input in step S100, and specifically include, but are not limited to, at least one of the following: lowest overall hydrogen production cost, lowest unit hydrogen production power consumption, maximum hydrogen production, highest equipment capacity utilization rate, minimum energy storage configuration capacity, and lowest power curtailment rate.

[0080] Minimizing the overall hydrogen production cost, which aims to reduce the total cost of producing each kilogram of hydrogen, is the primary objective of most commercial projects. This cost encompasses the average annual comprehensive cost of renewable energy generation units, energy storage systems, and various electrolyzer devices (including amortization of construction investment and operation and maintenance costs), purchased electricity expenses, and potential revenue from electricity transmission. The formula for calculating the overall hydrogen production cost can be: ,in, The sum of the average annual comprehensive costs of all modules (comprehensive cost refers to the average actual full-cycle cost of similar projects), and EC is the annual purchased electricity cost. The revenue generated from electricity fed into the grid is represented by SEE, where SEE is the total annual hydrogen production, and 11.2 is the standard density conversion factor for hydrogen. If data on the overall cost is unavailable, the Levelized Cost of Hydrogen (LCOH) can be used as a substitute. This objective directly reflects the overall economic feasibility of the project.

[0081] The goal of minimizing electricity consumption per unit of hydrogen production is to maximize energy conversion efficiency, i.e., producing a unit volume of hydrogen with the least amount of electricity. This indicator is divided into two aspects: electricity consumption per unit of hydrogen production and overall electricity consumption per unit. Specifically, electricity consumption per unit of hydrogen production... ,in, The total annual electricity consumption of hydrogen production units is the sum of DC electricity consumption of all types of electrolyzers (such as ALK, PEM, etc.) over 8760 hours. SEE represents the total annual hydrogen production, which is the sum of the volume of hydrogen produced by all hydrogen production units within a year; in this case, only the DC electricity consumption of electrolyzers and their auxiliary systems is included. The comprehensive unit electricity consumption is also included. ,in, This refers to the total annual electricity generation from renewable energy sources, specifically the sum of electricity generated by green power sources such as wind and solar power over 8760 hours. This refers to the annual electricity supplied directly to the system by a controllable power source (such as a gas turbine). This refers to the annual electricity purchased by the system from the external power grid. This refers to the annual electricity that the system sends to the external power grid.

[0082] Maximizing hydrogen production aims to maximize the total annual hydrogen output, provided resources allow, and is suitable for projects with clear production quotas or market demand.

[0083] The goal of maximizing equipment capacity utilization is to increase the actual operating time of core equipment such as electrolyzers, bringing it as close as possible to their design lifespan (e.g., 8000 hours / year). Capacity utilization rate ,in, This refers to the rated capacity of a Class j hydrogen production unit, i.e., the volume of hydrogen it can produce per hour when operating at full load. This represents the sum of the theoretical maximum hydrogen production capacities of all hydrogen production units, signifying the system's rated total capacity. The highest equipment capacity utilization rate reflects the efficiency of the return on investment for fixed assets; high utilization helps to reduce fixed costs, thereby improving the project's economic viability.

[0084] Minimizing energy storage configuration capacity aims to reduce reliance on energy storage systems by optimizing the dynamic matching between power output and load demand. This objective is reflected in minimizing the rated capacity of energy storage. or its proportion relative to the installed capacity of renewable energy , The total installed capacity of renewable energy refers to the sum of the rated power of all renewable power sources such as wind power, photovoltaic power, and hydropower in the project. The energy storage configuration capacity is suitable for projects that wish to reduce initial investment or simplify the system structure.

[0085] The goal of a minimum curtailment rate is to maximize the utilization of renewable energy generation and reduce the amount of electricity that is forcibly abandoned due to unavailability. Curtailment Rate LOSS% = ,in, This represents the total amount of electricity curtailed throughout the year. The lowest curtailment rate directly reflects the green attributes and resource utilization rate of a project, which is very important for regions with strict carbon emission reduction assessments.

[0086] To effectively handle the trade-offs between the aforementioned multiple objectives, this embodiment provides three strategies for constructing a combined optimization objective function, which users can choose according to their actual decisions. These methods are all integrated into the information processing module 200 and can be configured through a human-computer interaction interface.

[0087] The first strategy is the priority ranking method. The user specifies a clear priority order for the selected optimization objectives (e.g., first priority, second priority, etc.). The algorithm first optimizes the first priority objective, searching for the optimal solution set among all feasible solutions that satisfy the constraints. Then, it further optimizes the second priority objective within this solution set, and so on, until all objectives have been addressed. This method employs hierarchical minimization logic, ensuring that high-priority objectives always outperform low-priority objectives. It is suitable for scenarios where there is a clear hierarchy among objectives, such as when economic efficiency is the absolute dominant objective.

[0088] The second strategy is the linear weighting method. The user assigns a weight coefficient to each selected optimization objective. The sum of all weights is usually normalized to 1. The combinatorial optimization objective function is constructed in the following weighted summation form: ,in, This is the normalized value of the i-th objective (e.g., processed to the [0,1] interval by range standardization). This indicates their relative importance. By adjusting the weight distribution, the focus of different stakeholders can be flexibly reflected. For example, in projects that emphasize economic benefits, a higher weight can be assigned to the overall hydrogen production cost; while in scientific research demonstration projects, the weight of the curtailment rate or electricity consumption per unit can be emphasized. This method is simple to calculate and facilitates global optimization solutions.

[0089] The third strategy is a hybrid approach, a composite optimization strategy combining priority ranking and linear weighting. The user first specifies a primary optimization objective (e.g., minimizing overall hydrogen production cost), and then merges the remaining one or more optimization objectives into a secondary objective using a linear weighting method. For example, if four optimization objectives are selected, one is chosen as the primary objective, and the other three objectives are transformed into a single objective using a linear weighted sum method. The weighting coefficients can be {0.6, 0.3, 0.1} or {0.4, 0.3, 0.3}, etc. The primary and secondary objectives can be solved using a hierarchical approach.

[0090] The final solution process still employs a priority mechanism, that is, first finding the solution set that optimizes the primary objective among all feasible solutions, and then optimizing the secondary objectives within this solution set. This method ensures the priority of the core objective while also taking into account the overall performance of the secondary objectives, making it suitable for engineering projects with complex objective systems that are difficult to rank simply or are sensitive to multiple weights.

[0091] This step, by introducing three optional mechanisms—priority ranking, linear weighting, and a hybrid approach—can transform a multi-dimensional, dispersed objective into a single, executable optimization function. This combined optimization objective function not only reflects the user's business decisions but also provides a clear search direction for subsequent hybrid optimization algorithms, thereby enhancing the scientific rigor and practicality of the green hydrogen system capacity configuration scheme.

[0092] Step S400: Solve the coupled system model using a hybrid optimization algorithm to obtain a target capacity configuration scheme that satisfies the basic physical constraints and system operation constraints, and optimizes the combined optimization objective function.

[0093] Exemplary approach: After constructing the coupled system model and setting the combinatorial optimization objective function, step S400 is taken, where a hybrid optimization algorithm is used to solve the model to search for the optimal equipment capacity configuration scheme that satisfies all physical and engineering constraints, thereby maximizing the combinatorial optimization objective function. Since this optimization problem involves numerous discrete decision variables (such as power generation capacity and hydrogen production unit rated scale), continuous variables (such as hourly power allocation), and complex nonlinear constraints (such as power-hydrogen balance and start-stop switching), it is essentially a large-scale non-convex nonlinear mixed integer programming problem. Directly solving it using traditional global search methods could take tens of hours or even days, failing to meet the timeliness requirements of early-stage project planning. Therefore, this embodiment employs a phased hybrid optimization strategy to improve solution efficiency while ensuring solution quality.

[0094] Specifically, in some implementations, such as Figure 3 As shown, step S400 includes steps S410-S430: Step S410: Generate multiple candidate capacity configuration schemes through preset rules.

[0095] In this step, the information processing module 200 first generates a diverse set of initial solutions, which serve as the basis for subsequent screening and refinement. These candidate capacity configuration schemes cover different combinations of key decision variables such as power generation capacity, rated power and capacity of energy storage, and rated scale of various hydrogen production devices.

[0096] To improve the quality of the initial solution and avoid a large number of infeasible solutions caused by blind random sampling, this embodiment uses preset rules to guide the generation of candidate solutions. These preset rules can be flexibly set according to project characteristics, and include, but are not limited to, the following methods: experience-based allocation rules based on regional resource endowment, for example, in wind-solar hybrid projects, setting the capacity ratio range of wind power and photovoltaic power (e.g., 3:7 to 5:5) based on the local wind / solar output correlation; random sampling combined with boundary truncation, i.e., sampling uniformly or normally distributed within the user-defined maximum installed capacity range, and truncating values ​​exceeding the boundary to an allowable range; and analogical recommendations based on a typical project database, i.e., calling similar cases from the historical project database as initial configuration references. The number of generated candidate capacity configuration schemes can be set by the system default (e.g., 100 groups) or customized by the user, ensuring that a sufficiently wide search space is covered without causing excessive computational burden.

[0097] Step S420: For each candidate configuration scheme, constrained feasibility screening is performed based on basic physical constraints and system operation constraints to determine at least one set of candidate feasible solutions that meet the preset default threshold.

[0098] In this step, the system substitutes each candidate capacity configuration scheme into the coupled system model, performs an hourly simulation of 8760 hours throughout the year, and evaluates whether it violates various constraints during dynamic operation.

[0099] Specifically, the system checks whether the power balance between electricity and hydrogen is valid at each time step, and simultaneously calculates the frequency or severity of the following violations: electrolyzer operating power exceeding the minimum / maximum power ratio limit; energy storage SOC exceeding the limit or charge / discharge power exceeding the product of the final capacity and discharge multiple; annual cumulative start-stop count exceeding the set upper limit; purchased / exported electricity exceeding the policy-limited proportion; curtailment rate or line loss rate exceeding the preset threshold, etc. Subsequently, the system calculates the total violation degree for each group of candidate solutions, which can be quantified by weighted summation of the number of violations, maximum deviation value, cumulative exceedances, etc. Then, a preset violation threshold is set, and only one or more candidate solutions with a violation degree below this threshold are retained as input for the next stage. For example, a maximum of three minor violations without hard constraint breaches can be set as the screening criterion. This process is essentially a heuristic initial screening mechanism, aiming to quickly identify high-quality initial solutions close to the feasible region from the original candidate set, thereby significantly narrowing the search range for subsequent precise solutions.

[0100] Step S430: Using the candidate feasible solution as the initial solution, optimize the candidate feasible solution based on the coupled system model and the combined optimization objective function to obtain the target capacity configuration scheme.

[0101] The target capacity configuration scheme includes the installed capacity of the power source, the rated capacity and rated power of the energy storage system, and the rated scale of the hydrogen production unit.

[0102] Specifically, this step involves calling a mathematical solver that supports solving nonlinear mixed-integer programming or quadratic mixed-integer programming problems, using candidate feasible solutions as initial solutions, and performing iterative calculations until convergence to the final solution that satisfies all constraints of the coupled system model and makes the combinatorial optimization objective function optimal, thus obtaining the target capacity configuration scheme.

[0103] Specifically, the system takes the candidate feasible solutions selected in step S420 as the initial solutions, inputs them into the mathematical programming solver, and then starts the high-precision optimization calculation process.

[0104] The system can invoke commercial or open-source mathematical solvers that support solving nonlinear mixed-integer programming or quadratic mixed-integer programming problems, such as Gurobi, CPLEX, COPT, and SCIP, for iterative optimization. These solvers are capable of handling large-scale complex optimization problems and can effectively handle nonlinear terms in the objective function (such as cost piecewise functions) and integer constraints in the decision variables (such as modulus constraints). During the solution process, starting from candidate feasible solutions, the solver continuously explores the neighboring solution space through advanced algorithms such as branch and bound, interior point methods, and cutting planes. Under the premise of satisfying all basic physical constraints and system operation constraints in the coupled system model, it gradually approaches the final solution that optimizes the combinatorial optimization objective function.

[0105] The algorithm terminates and outputs the result when any of the following convergence conditions are met. For example, the convergence condition can be that the change in the objective function value is less than a preset tolerance (e.g., ...). The methods include: reaching the maximum number of iterations or the longest solution time (e.g., 5 minutes), finding the global optimal solution or an approximate optimal solution that satisfies the gap tolerance, etc.

[0106] The final target capacity configuration scheme includes, but is not limited to, the installed capacity of various power sources (such as wind power and photovoltaic), the rated power and rated capacity of energy storage systems, the distinction between the source side and the load side, and the rated scale of various hydrogen production devices; and can further output the power operation curve for 8760 hours a year, key evaluation indicators (such as comprehensive hydrogen production cost, curtailment rate, capacity utilization rate, etc.).

[0107] Through this optimized process, this embodiment can compress the full search problem, which originally required tens of hours to complete, into convergence within minutes, achieving minute-level optimization. This not only greatly improves the work efficiency of the feasibility study phase of the green hydrogen project, but also ensures that the recommended solution meets the requirements for safe and stable operation while closely aligning with actual engineering application scenarios.

[0108] To more clearly illustrate the practical application effect of the green hydrogen system capacity configuration method provided in this embodiment, a specific calculation case is described in detail below. This embodiment takes a wind-solar hybrid off-grid green hydrogen demonstration project as an example, with a total renewable energy installed capacity set at 40 megawatts (MW). The goal is to optimize the equipment scale of photovoltaic power generation units, wind power generation units, alkaline electrolyzers (ALK), proton exchange membrane electrolyzers (PEM), and energy storage systems through the method of this embodiment, while meeting multiple physical and engineering constraints, and generate an annual 8760-hour operation scheduling strategy, ultimately outputting key performance indicators and typical daily operating characteristics.

[0109] (1) Input data First, collect wind and solar energy resource data, technical and economic parameters of each system module, and business requirements information of the project site as model inputs.

[0110] The renewable energy output data used comes from the annual measured power generation records of an actual operating wind farm and photovoltaic power station in the region, with a time resolution of once per hour, totaling 8760 data points, representing the hourly output characteristics of wind power and photovoltaic power under different meteorological conditions (see [link]). Figure 4 Based on this data, the platform constructed a power output sequence that reflects local resource endowment.

[0111] The system module parameters set by the user are as follows: The demand-based electricity price is 30.4 yuan per kilowatt per month. The transmission network's external power price is 0.36 yuan per kilowatt-hour. The feed-in tariff for renewable energy is 0.37 yuan per kilowatt-hour. The average annual unit construction and operation and maintenance cost of photovoltaic power generation is 163.7 yuan per kilowatt per year. Wind power generation costs 146 yuan per kilowatt per year. The average annual unit cost of the energy storage system is 121.73 yuan per kilowatt-hour per year. The charging and discharging efficiency is set at 95%, the maximum depth of charge and discharge is 80%, and the annual maximum number of charge and discharge cycles is 2000. The installed capacity of source-side energy storage is set to account for 10% to 20% of the total installed capacity of renewable energy.

[0112] For hydrogen production units, the power consumption per unit volume of an alkaline electrolyzer (ALK) is taken as 4.5 kWh per standard cubic meter. The stable operating power range is 30% to 110% of its rated power; the power consumption of the proton exchange membrane electrolyzer (PEM) is 5.0 kWh per standard cubic meter. The operating power range is 10% to 110% of the rated power. The annual start-up and shutdown limit for both types of electrolyzers is set at 1000 times. The average annual comprehensive cost of an ALK electrolyzer is 107 yuan per kilowatt per year. PEM is 445 yuan per kilowatt per year. The hydrogen production unit consumes approximately 90% of the plant's total DC power, with the remaining 10% used for auxiliary equipment and other plant power loads. The average annual cost of the substation system is 75 yuan per kilowatt per year. The maximum allowable curtailment rate of the system shall not exceed 5% of the total annual power generation. The reasonable range for the average annual effective operating hours of the electrolyzer is 3,000 to 9,000 hours.

[0113] Furthermore, to conform to equipment selection practices in engineering, all power supply capacity and hydrogen production unit rated capacity are based on 100 kilowatts (kW) or 100 standard cubic meters per hour (kWh). The values ​​are taken as integer multiples of ), i.e., modulo constraints are applied to ensure that the output solution is procureable and feasible.

[0114] The business requirement scenario is set as "hydrogen production determined by electricity - total capacity", that is, the total installed capacity of wind power and photovoltaic power is known to be 40 megawatts. The goal is to find the optimal equipment configuration scheme that minimizes the overall cost of hydrogen production under this condition, while taking into account the capacity utilization rate and the curtailment rate.

[0115] (2) Model building Based on the input data, the platform automatically configures a multi-component coupled system model covering power supply, energy storage, hydrogen production devices, and grid interaction. This model uses an hourly time step, covering 8760 time periods throughout the year, to construct a dynamic energy balance relationship.

[0116] The core physical constraint is the electro-hydrogen power balance, meaning that at any given time t, the total input power of the system equals the total output power. System operation constraints include several aspects: equipment operation characteristic constraints require that the operating power of the ALK electrolyzer must be maintained within 30% to 110% of its rated power, while that of the PEM electrolyzer is 10% to 110%. Equipment lifespan constraints stipulate that the annual start-up and shutdown counts for ALK and PEM electrolyzers must not exceed 1000 times, and the annual charge-discharge counts for the energy storage system must not exceed 2000 times. Capacity boundary constraints limit the total rated capacity of source-side energy storage to between 10% and 20% of the total installed capacity of renewable energy. Curtailment rate constraints ensure that the annual curtailment does not exceed 5% of the total power generation. Modulus constraints guarantee that all decision variables are integer multiples of a preset modulus.

[0117] The combined optimization objective function is set as the primary objective of minimizing the overall hydrogen production cost, supplemented by the secondary objectives of minimizing the curtailment rate and maximizing the capacity utilization rate. A hybrid method is used to transform the multi-objective problem into a computable form.

[0118] The above model is expressed as a large-scale nonlinear mixed integer programming problem (MINLP) and embedded in the platform information processing module 200 for solution.

[0119] (3) Solution and optimization The platform uses a hybrid optimization algorithm to solve the model. The specific process is as follows: First, 1000 candidate capacity configuration schemes were generated using preset rules, covering different wind-solar ratios, electrolyzer combinations, and energy storage scales. Next, each scheme underwent 8760 hours of operational simulation, and feasibility was screened based on the power balance of electricity and hydrogen and other system operational constraints, retaining 87 candidate feasible solutions with fewer than three defaults and no hard constraint breaches. Finally, these candidate feasible solutions were used as initial solutions and input into a mathematical solver (supporting nonlinear mixed integer programming) to initiate precise optimization iterations. After approximately 4 minutes and 30 seconds of computation, the algorithm converged to a Pareto optimal solution, yielding the recommended capacity configuration scheme: 16,600 kW of photovoltaic power generation capacity, 23,500 kW of wind power generation capacity, 11,600 kW of rated alkaline electrolyzer capacity, and 6,800 kW of rated proton exchange membrane electrolyzer capacity. The capacity ratio of ALK to PEM is approximately 1.7:1, reflecting the design concept of synergistic complementarity between the two, with ALK handling the base load and PEM handling peak fluctuations. The rated capacity of the source-side energy storage is 4,000 kWh, and the rated capacity of the load-side energy storage is 1,900 kWh.

[0120] Key performance indicators are summarized as follows: Total annual power generation is 64,130,231.42 kWh; total annual hydrogen production is 11,679,317.08 standard cubic meters; comprehensive power consumption per unit is 5.491 kWh per standard cubic meter; renewable energy utilization hours are 2,980 hours; and annual abandoned electricity is 3,206,511.57 kWh, accounting for 5.00% of total power generation, just above the upper limit of the constraint. The DC power consumption per unit in the hydrogen production process is 5.216 kWh per standard cubic meter, with an effective hydrogen production time of 7,275 hours. The unit comprehensive hydrogen production cost is 9.672 yuan per kilogram of hydrogen. The average annual cost of the total project investment is 10.0857 million yuan, including 2.7096 million yuan for photovoltaic power, 3.4242 million yuan for wind power, 250,200 yuan for the ALK system, 673,300 yuan for the PEM system, and 2.3175 million yuan for the substation system.

[0121] (4) Simulation results Substituting the above optimized configuration scheme into the time-by-time scheduling simulation, the results are as follows: Figure 5 and Figure 6 As shown.

[0122] The results show that the alkaline electrolyzer and PEM electrolyzer, when operating in tandem, enhance hydrogen production and improve capacity utilization. The total daily wind and solar power generation was approximately 620,000 kWh, with curtailment occurring during peak periods, amounting to approximately 26,000 kWh, resulting in a curtailment rate of 4.3%, below the 5% constraint limit. The alkaline electrolyzer's start-up and shutdown frequency was limited to less than 1700 times / year, and the proton exchange membrane electrolyzer's frequency was significantly lower than the 3000 times / year limit, contributing to extended equipment lifespan. The entire system achieved continuous and stable hydrogen production, effectively supporting the continuity and reliability of hydrogen energy production.

[0123] Therefore, the method in this embodiment not only achieves the goals of low power curtailment and low cost, but also significantly reduces the frequency of electrolytic cell start-up and shutdown, thereby improving equipment lifespan and operational stability. Compared to traditional empirical methods or multi-scheme trial calculation methods, this embodiment significantly improves the scientific and economic efficiency of resource allocation while ensuring safety and stability.

[0124] This embodiment constructs a multi-component coupled system model encompassing power supply, energy storage, hydrogen production devices, and grid interaction, and performs global optimization using a combined optimization objective function, thereby effectively reducing the overall hydrogen production cost. Actual calculations show that, under the premise of meeting the same hydrogen production demand, the method in this embodiment can reduce the unit hydrogen production cost by 15% to 35% compared to traditional empirical configuration methods, thus improving the commercial viability of the project. Secondly, regarding energy utilization efficiency, this embodiment, based on hourly operation simulations over 8760 hours per year, fully leverages the output characteristics of wind and solar resources, optimizes the dynamic matching relationship between power supply and load, achieving a low curtailment rate while keeping the overall electricity consumption per unit at a low level, demonstrating good green attributes and resource utilization efficiency. Thirdly, regarding equipment operational reliability, by introducing lifespan constraints such as the upper limit of electrolyzer start-up and shutdown times and minimum / maximum power operating ranges, the optimized scheduling strategy significantly reduces the frequency of electrolyzer start-up and shutdown and inefficient operating time.

[0125] Figure 7 A schematic diagram of a green hydrogen system capacity configuration device according to an embodiment of this application is shown. Exemplarily, the green hydrogen system capacity configuration device includes: Acquisition unit 10 is used to acquire renewable energy output data, system module parameters, and business requirement information of the target project; Configuration unit 20 is used to configure a coupled system model based on renewable energy output data, system module parameters and business requirements information; wherein, the coupled system model uses the power balance of electricity and hydrogen as the basic physical constraint and integrates at least one system operation constraint; Construction unit 30 is used to construct a combined optimization objective function in response to at least one optimization objective configured by the user based on business requirement information; Solver 40 is used to solve the coupled system model through a hybrid optimization algorithm to obtain a target capacity configuration scheme that satisfies the basic physical constraints and system operation constraints and optimizes the combined optimization objective function.

[0126] It is understood that the device in this embodiment corresponds to the green hydrogen system capacity configuration method in the above embodiment, and the options in the above embodiment are also applicable to this embodiment, so they will not be described again here.

[0127] This application also provides a terminal device, exemplary of which includes a processor and a memory, wherein the memory stores a computer program, and the processor executes the computer program to enable the terminal device to perform the functions of the various modules in the above-described green hydrogen system capacity configuration method or the above-described green hydrogen system capacity configuration device.

[0128] The processor can be an integrated circuit chip with signal processing capabilities. The processor can be a general-purpose processor, including at least one of a Central Processing Unit (CPU), Graphics Processing Unit (GPU), Network Processor (NP), Digital Signal Processor (DSP), Application-Specific Integrated Circuit (ASIC), Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The general-purpose processor can be a microprocessor or any conventional processor, capable of implementing or executing the methods, steps, and logic block diagrams disclosed in the embodiments of this application.

[0129] The memory can be, but is not limited to, Random Access Memory (RAM), Read Only Memory (ROM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), etc. The memory is used to store computer programs, and the processor can execute the computer programs accordingly after receiving execution instructions.

[0130] This application also provides a computer-readable storage medium for storing the computer program used in the aforementioned terminal device. For example, the computer-readable storage medium may include, but is not limited to, various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0131] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that, in alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0132] In addition, the functional modules or units in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0133] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a smartphone, personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application.

[0134] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

Claims

1. A method for configuring the capacity of a green hydrogen system, characterized in that, include: Obtain renewable energy output data, system module parameters, and business requirements information for the target project; Based on the renewable energy output data, the system module parameters, and the business requirement information, a coupled system model is configured; wherein, the coupled system model uses the power balance of electricity and hydrogen as the basic physical constraint and integrates at least one system operation constraint; In response to at least one optimization objective configured by the user based on the business requirement information, a combined optimization objective function is constructed; The coupled system model is solved by a hybrid optimization algorithm to obtain a target capacity configuration scheme that satisfies the basic physical constraints and the system operation constraints, and optimizes the combined optimization objective function.

2. The green hydrogen system capacity configuration method according to claim 1, characterized in that, The step of solving the coupled system model using a hybrid optimization algorithm to obtain a target capacity configuration scheme that satisfies the fundamental physical constraints and the system operational constraints, and optimizes the combined optimization objective function, includes: Multiple candidate capacity configuration schemes are generated using preset rules; For each of the candidate capacity configuration schemes, constraint feasibility screening is performed based on the basic physical constraints and the system operation constraints to determine at least one set of candidate feasible solutions that meet the preset default threshold. The candidate feasible solution is used as the initial solution, and the candidate feasible solution is optimized based on the coupled system model and the combined optimization objective function to obtain the target capacity configuration scheme; wherein, the target capacity configuration scheme includes the installed capacity of the power source, the rated capacity and rated power of the energy storage system, and the rated scale of the hydrogen production unit.

3. The green hydrogen system capacity configuration method according to claim 1, characterized in that, The fundamental physical constraint for the electro-hydrogen power balance is that the total input power of the system is equal to the total output power within a preset time step; wherein, the total input power includes renewable energy generation power, controllable power supply power, purchased power, and energy storage charging and discharging power; and the total output power includes total hydrogen production power, external power transmission power, and power loss.

4. The green hydrogen system capacity configuration method according to claim 1, characterized in that, The optimization objectives include at least one of the following: lowest overall hydrogen production cost, lowest unit hydrogen production power consumption, maximum hydrogen production, highest equipment capacity utilization, minimum energy storage capacity, and lowest power curtailment rate. The combined optimization objective function is constructed based on all the optimization objectives configured by the user through a priority ranking method, a linear weighting method, or a hybrid method; wherein, the hybrid method is a method of taking one optimization objective as the primary objective and forming secondary objectives by linear weighting the remaining optimization objectives.

5. The green hydrogen system capacity configuration method according to claim 1, characterized in that, The system operation constraints include equipment operation characteristic constraints, equipment lifespan constraints, and business requirement constraints. The equipment operation characteristic constraints include the minimum power ratio and maximum power ratio for stable operation of the electrolyzer; the equipment life constraints include the upper limit of the number of start-ups and shutdowns per year, the upper limit of the annual operating time of the electrolyzer, and the upper limit of the number of charge-discharge cycles per year of the energy storage system; the business demand constraints include the electricity-based hydrogen constraint targeting the total fixed power supply capacity, the electricity-based hydrogen constraint targeting the fixed capacity of various power sources, the hydrogen-based electricity constraint targeting the total fixed hydrogen production, and the hydrogen-based electricity constraint targeting the total fixed hydrogen production and the upper limit of renewable energy resources. The equipment operating characteristic constraints also include a lower limit constraint on the energy storage system capacity, which is used to ensure that the rated capacity of the energy storage system is not lower than a preset proportion of the system's critical load, so as to support the system's grid construction capability or short-term overload requirements.

6. The green hydrogen system capacity configuration method according to claim 2, characterized in that, The step of using the candidate feasible solution as the initial solution and optimizing the candidate feasible solution based on the coupled system model and the combined optimization objective function to obtain the target capacity configuration scheme includes: Call a mathematical solver that supports solving nonlinear mixed-integer programming or quadratic mixed-integer programming problems, and use the candidate feasible solution as the initial solution to perform iterative calculations until convergence to the final solution that satisfies all constraints of the coupled system model and makes the combined optimization objective function optimal, then the target capacity configuration scheme is obtained.

7. The green hydrogen system capacity configuration method according to claim 2, characterized in that, When configuring the coupled system model, a modular constraint is applied to the installed capacity of the power source and / or the rated size of the hydrogen production unit, wherein the modular constraint is an integer multiple of a preset modular number.

8. A capacity configuration device for a green hydrogen system, characterized in that, The acquisition unit is used to acquire renewable energy output data, system module parameters, and business requirement information of the target project. A configuration unit is used to configure a coupled system model based on the renewable energy output data, the system module parameters, and the business requirement information; wherein the coupled system model uses the power balance of electricity and hydrogen as the basic physical constraint and integrates at least one system operation constraint; A construction unit is used to construct a combined optimization objective function in response to at least one optimization objective configured by the user based on the business requirement information; The solution unit is used to solve the coupled system model through a hybrid optimization algorithm to obtain a target capacity configuration scheme that satisfies the basic physical constraints and the system operation constraints, and makes the combined optimization objective function optimal.

9. A green hydrogen system capacity configuration platform, characterized in that, Human-computer interaction module and information processing module; The human-computer interaction module is used to receive renewable energy output data, system module parameters, business requirement information and optimization targets of the target project input by the user. The information processing module is communicatively connected to the human-machine interaction module and is used to execute the green hydrogen system capacity configuration method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed on a processor, implements the green hydrogen system capacity configuration method according to any one of claims 1-7.

Images