Hydrogen production system scheduling method, device and non-volatile storage medium

Abstract

The present invention discloses a method, device and non-volatile storage medium for scheduling a hydrogen production system. The method comprises: determining the objective function of the hydrogen production system based on the total operation and maintenance cost and total hydrogen production income corresponding to the hydrogen production system, the first output power of the new energy power supply equipment in the hydrogen production system, the second output power of the energy storage equipment, the first input power of the water electrolysis hydrogen production equipment, and the second input power of the load; processing the objective function using the honey badger algorithm to obtain the initial optimal solution of the objective function; performing Gaussian variation processing on the initial optimal solution to obtain the target optimal solution of the objective function, and the target optimal value corresponding to the target optimal solution; determining the hydrogen production scheduling strategy of the hydrogen production system based on the target optimal value, so that the hydrogen production system meets the target optimal solution. The present invention solves the technical problems in the related art of unsatisfactory scheduling efficiency of new energy coupled hydrogen production, insufficient system operation stability, and premature system scheduling algorithm.

Description

Technical Field

[0001] The present invention relates to the field of hydrogen production technology, and in particular to a hydrogen production system scheduling method, device and non-volatile storage medium. Background Art

[0002] In recent years, with increasing pressure from both energy consumption and environmental governance, the demands on energy systems have also been constantly evolving. Wind and solar technologies are leading the global transition from fossil fuels to renewable energy generation. However, both major renewable energy sources are intermittent, and mitigating their adverse impact on the power grid is a pressing issue for renewable energy generation. Appropriately increasing energy storage can improve the stability of renewable energy generation. Hydrogen, as a clean energy carrier, can store excess energy from renewable sources such as wind and solar. Electrolysis equipment can be used to produce hydrogen for storage during low electricity consumption periods, while fuel cells or energy storage can be used to compensate for output shortfalls during peak electricity consumption periods. The addition of hydrogen significantly mitigates the impact of renewable energy on the power grid. Related technologies for hydrogen production systems coupled with renewable energy fail to balance operational efficiency, stability, production costs, and revenue. As a multi-objective problem, these systems are prone to premature algorithm maturation and poor convergence, resulting in suboptimal scheduling of hydrogen production systems, low operational efficiency, and poor robustness.

[0003] To address the above-mentioned problems, no effective solutions have been proposed so far. Summary of the Invention

[0004] The embodiments of the present invention provide a hydrogen production system scheduling method, device and non-volatile storage medium to at least solve the technical problems in the related art of unsatisfactory scheduling efficiency of new energy coupled hydrogen production, insufficient system operation stability and premature system scheduling algorithm.

[0005] According to one aspect of an embodiment of the present invention, a hydrogen production system scheduling method is provided, comprising: determining an objective function of the hydrogen production system based on the total operation and maintenance cost and total hydrogen production income corresponding to the hydrogen production system, the first output power of the new energy power supply equipment in the hydrogen production system, the second output power of the energy storage equipment in the hydrogen production system, the first input power of the water electrolysis hydrogen production equipment in the hydrogen production system, and the second input power of the load in the hydrogen production system, wherein the total operation and maintenance cost is the operation and maintenance cost generated by the hydrogen production system within a preset unit operating time, and the total hydrogen production income is the hydrogen production system generated within the unit operating time. The hydrogen production revenue generated, the objective function is used to represent the total cost of the hydrogen production system; the objective function is processed by the honey badger algorithm to obtain the initial optimal solution of the objective function; the initial optimal solution is subjected to Gaussian variation processing to obtain the target optimal solution of the objective function, and the target optimal value corresponding to the target optimal solution, wherein the target optimal solution makes the total cost of the hydrogen production system lowest, and the target optimal value is the control parameter of the hydrogen production system when the hydrogen production system reaches the target optimal solution; based on the target optimal value, the hydrogen production scheduling strategy of the hydrogen production system is determined so that the hydrogen production system meets the target optimal solution.

[0006] According to another aspect of an embodiment of the present invention, a hydrogen production system scheduling device is provided, comprising: a first determination module, configured to determine an objective function of the hydrogen production system based on the total operation and maintenance cost and total hydrogen production income corresponding to the hydrogen production system, the first output power of the new energy power supply equipment in the hydrogen production system, the second output power of the energy storage equipment in the hydrogen production system, the first input power of the water electrolysis hydrogen production equipment in the hydrogen production system, and the second input power of the load in the hydrogen production system, wherein the total operation and maintenance cost is the operation and maintenance cost generated by the hydrogen production system within a preset unit operating time, the total hydrogen production income is the hydrogen production income generated by the hydrogen production system within the unit operating time, and the The objective function is used to represent the total cost of the hydrogen production system; the first calculation module is used to process the objective function using the honey badger algorithm to obtain the initial optimal solution of the objective function; the second calculation module is used to perform Gaussian variation processing on the initial optimal solution to obtain the target optimal solution of the objective function, and the target optimal value corresponding to the target optimal solution, wherein the target optimal solution minimizes the total cost of the hydrogen production system, and the target optimal value is the control parameter of the hydrogen production system when the hydrogen production system reaches the target optimal solution; the second determination module is used to determine the hydrogen production scheduling strategy of the hydrogen production system based on the target optimal value, so that the hydrogen production system meets the target optimal solution.

[0007] According to another aspect of an embodiment of the present invention, a non-volatile storage medium is provided, wherein the non-volatile storage medium stores a plurality of instructions, wherein the instructions are suitable for being loaded by a processor and executed by any one of the hydrogen production system scheduling methods.

[0008] According to another aspect of an embodiment of the present invention, an electronic device is provided, comprising: one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement any one of the hydrogen production system scheduling methods.

[0009] In an embodiment of the present invention, an improved algorithm based on the honey badger algorithm is adopted, and the objective function of the hydrogen production system is determined based on the total operation and maintenance cost corresponding to the hydrogen production system, the total hydrogen production income, the first output power of the new energy power supply equipment in the hydrogen production system, the second output power of the energy storage equipment in the hydrogen production system, the first input power of the electrolytic water hydrogen production equipment in the hydrogen production system, and the second input power of the load in the hydrogen production system. The total operation and maintenance cost is the operation and maintenance cost generated by the hydrogen production system within a preset unit operating time, and the total hydrogen production income is the hydrogen production system generated within the unit operating time. The hydrogen production revenue, the objective function is used to represent the total cost of the hydrogen production system; the objective function is processed by the honey badger algorithm to obtain the initial optimal solution of the objective function; the initial optimal solution is subjected to Gaussian variation processing to obtain the target optimal solution of the objective function, and the target optimal value corresponding to the target optimal solution, wherein the target optimal solution makes the total cost of the hydrogen production system the lowest, and the target optimal value is the control parameter when the hydrogen production system reaches the target optimal solution; based on the target optimal value, the hydrogen production scheduling strategy of the hydrogen production system is determined so that the hydrogen production system meets the target optimal solution. The purpose of introducing Gaussian variation, avoiding the hydrogen production system scheduling algorithm from falling into local optimality, and improving scheduling efficiency is achieved, and the technical effect of taking into account the stability and economy of the hydrogen production system, improving the system operation stability and scheduling effect is achieved, thereby solving the technical problems in the related technology of unsatisfactory scheduling efficiency of new energy coupled hydrogen production, insufficient system operation stability, and premature system scheduling algorithm. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0011] Figure 1 is a flow chart of an optional hydrogen production system scheduling method provided according to an embodiment of the present invention;

[0012] Figure 2 is a schematic diagram of a hydrogen production system according to an optional hydrogen production system scheduling method provided in an embodiment of the present invention;

[0013] Figure 3 2. A schematic diagram of power efficiency-efficiency of hydrogen production by electrolysis of water according to an embodiment of the present invention;

[0014] Figure 4 This is a flow chart of an improved honey badger algorithm for an optional hydrogen production system scheduling method provided in an embodiment of the present invention;

[0015] Figure 5 Schematic diagram of wind and solar power output of an optional hydrogen production system scheduling method provided in an embodiment of the present invention;

[0016] Figure 6 Schematic diagram of wind, solar and load combination of an optional hydrogen production system scheduling method provided in an embodiment of the present invention;

[0017] Figure 7 is a schematic diagram of an algorithm for an optional hydrogen production system scheduling method provided according to an embodiment of the present invention;

[0018] Figure 8 1 is a power diagram of a water electrolysis hydrogen production device according to an optional hydrogen production system scheduling method provided in an embodiment of the present invention;

[0019] Figure 9 is a schematic diagram of an energy storage device according to an optional hydrogen production system scheduling method provided by an embodiment of the present invention;

[0020] Figure 10 Schematic diagram of an optional hydrogen production system scheduling device provided according to an embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0022] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0023] For ease of description, some nouns or terms involved in the embodiments of the present application are explained below:

[0024] In recent years, with increasing pressure from both energy consumption and environmental governance, the demands on energy systems have also been constantly changing. Wind and solar technologies are leading the global transition from fossil fuels to renewable energy generation. However, both major renewable energy sources are intermittent, and mitigating their adverse impact on the power grid is a pressing issue for renewable energy generation. Appropriately increasing energy storage can improve the stability of renewable energy generation. Hydrogen, as a clean energy carrier, can store excess energy from renewable sources such as wind and solar power. Electrolysis equipment can be used to produce hydrogen for storage during low electricity consumption periods, while fuel cells or energy storage can be used to compensate for shortfalls during peak electricity consumption periods. The addition of hydrogen significantly mitigates the impact of renewable energy on the power grid.

[0025] In related technologies, the goal is to minimize the tracking plan error rate and the pressure fluctuation rate of the hydrogen storage system, thereby achieving day-ahead coordinated optimization scheduling within the wind, solar, and hydrogen multi-energy system. However, the cost indicator does not take into account the power grid's power shortage penalty for the wind, solar, and hydrogen multi-energy system. In another related technology, by studying the efficiency characteristics of the electrolysis equipment, the overall efficiency expression of the hydrogen production system is derived, and the hybrid renewable energy system is optimized to find the best combination of energy efficiency, hydrogen production quality, and cooling load. However, this study does not consider the overall cost of the system. In another related technology, the hydrogen production efficiency is improved by operating the electrolysis equipment in the optimal range, and the capacity of the wind-hydrogen system is configured by optimizing cost and reliability. However, the total cost description ignores the benefits brought by hydrogen products.

[0026] In response to the above problems, an embodiment of the present invention provides an embodiment of a method for scheduling a hydrogen production system. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0027] Figure 1 is a flow chart of an optional hydrogen production system scheduling method according to an embodiment of the present invention, such as Figure 1 As shown, the method includes the following steps:

[0028] Step S102: Determine the objective function of the hydrogen production system based on the total operation and maintenance cost and total hydrogen production income corresponding to the hydrogen production system, the first output power of the new energy power supply equipment in the hydrogen production system, the second output power of the energy storage equipment in the hydrogen production system, the first input power of the water electrolysis hydrogen production equipment in the hydrogen production system, and the second input power of the load in the hydrogen production system. The total operation and maintenance cost is the operation and maintenance cost generated by the hydrogen production system within a preset unit operating time, and the total hydrogen production income is the hydrogen production income generated by the hydrogen production system within the unit operating time. The objective function is used to represent the total cost of the hydrogen production system.

[0029] It can be understood that the scheduling of the hydrogen production system must consider not only the cost issue but also the stable operation. In order to establish an objective function for representing the total cost of the hydrogen production system, the objective function of the hydrogen production system is determined based on the total operation and maintenance cost generated by the hydrogen production system within the preset unit operating time, the total hydrogen production income generated by the hydrogen production system within the unit operating time, the first output power of the new energy power supply equipment in the hydrogen production system, the second output power of the energy storage equipment in the hydrogen production system, the first input power of the water electrolysis hydrogen production equipment in the hydrogen production system, and the second input power of the load in the hydrogen production system.

[0030] In an optional embodiment, the new energy power supply equipment includes: photovoltaic equipment, wind power generation equipment, and the water electrolysis hydrogen production equipment includes: proton exchange membrane electrolysis equipment, alkaline electrolysis equipment.

[0031] It is understood that the aforementioned new energy power supply equipment can be of various types, including photovoltaic equipment and wind power generation equipment. There are also various types of water electrolysis hydrogen production equipment, including proton exchange membrane electrolysis equipment and alkaline electrolysis equipment. The aforementioned proton exchange membrane can also be referred to as (PEM electrolysis equipment).

[0032] In an optional embodiment, the objective function of the hydrogen production system is determined based on the total operation and maintenance cost and total hydrogen production income corresponding to the hydrogen production system, the first output power of the new energy power supply equipment in the hydrogen production system, the second output power of the energy storage equipment in the hydrogen production system, the first input power of the water electrolysis hydrogen production equipment in the hydrogen production system, and the second input power of the load in the hydrogen production system, including: obtaining the cost function corresponding to the hydrogen production system based on the total operation and maintenance cost and the total hydrogen production income; determining the power shortage penalty cost and the excess power cost of the hydrogen production system; obtaining the power function corresponding to the hydrogen production system based on the first output power, the second output power, the first input power, and the second input power within the unit operating time; obtaining the reliability function corresponding to the hydrogen production system based on the power function, the power shortage penalty cost, and the excess power cost; and obtaining the objective function corresponding to the hydrogen production system based on the cost function and the reliability function.

[0033] It can be understood that since there are two problems: cost problem and stable operation problem, it is necessary to obtain corresponding cost function and reliability function to obtain the objective function. First, based on the total operation and maintenance cost and the total hydrogen production income, the cost function corresponding to the hydrogen production system is obtained. Secondly, in order to obtain the reliability function, the power shortage penalty cost and the excess electricity cost of the hydrogen production system are determined. Based on the first output power, the second output power, the first input power, and the second input power within the unit operating time, the power function corresponding to the hydrogen production system is obtained. Based on the power function, the power shortage penalty cost, and the excess electricity cost, the reliability function corresponding to the hydrogen production system is obtained. Through the above processing, the cost function and the reliability function are obtained, and based on the cost function and the reliability function, the objective function corresponding to the hydrogen production system is obtained.

[0034] In an optional embodiment, the above-mentioned cost function corresponding to the above-mentioned hydrogen production system is obtained based on the above-mentioned total operation and maintenance cost and the above-mentioned total hydrogen production income corresponding to the above-mentioned hydrogen production system, including: determining the first operation and maintenance cost, the first number of systems, and the above-mentioned first output power corresponding to the above-mentioned new energy power supply equipment, the second operation and maintenance cost, the second number of systems, and the above-mentioned second output power corresponding to the above-mentioned energy storage equipment, the third operation and maintenance cost, the third number of systems, and the third output power corresponding to the above-mentioned water electrolysis hydrogen production equipment, and the fourth operation and maintenance cost, the fourth number of systems, and the fourth output power corresponding to the above-mentioned load; obtaining the above-mentioned total operation and maintenance cost based on the above-mentioned first operation and maintenance cost, the above-mentioned first number of systems, the above-mentioned first output power, the above-mentioned second operation and maintenance cost, the above-mentioned second number of systems, the above-mentioned second output power, the above-mentioned third operation and maintenance cost, the above-mentioned third number of systems, the above-mentioned third output power, the above-mentioned fourth operation and maintenance cost, the above-mentioned fourth number of systems, and the above-mentioned fourth output power; obtaining the above-mentioned total hydrogen production income based on the preset hydrogen price and the above-mentioned hydrogen sales volume within the above-mentioned unit operating time; obtaining the above-mentioned cost function according to the above-mentioned total operation and maintenance cost and the above-mentioned total hydrogen production income.

[0035] It can be understood that to establish a cost function, the hydrogen production system includes multiple subsystems: new energy power supply equipment, energy storage equipment, loads, and water electrolysis hydrogen production equipment. The first operation and maintenance cost, first number of systems, and first output power corresponding to the new energy power supply equipment are determined; the second operation and maintenance cost, second number of systems, and second output power corresponding to the energy storage equipment; the third operation and maintenance cost, third number of systems, and third output power corresponding to the water electrolysis hydrogen production equipment; and the fourth operation and maintenance cost, fourth number of systems, and fourth output power corresponding to the loads are determined. Based on the first operation and maintenance cost, first number of systems, first output power, second operation and maintenance cost, second number of systems, second output power, third operation and maintenance cost, third number of systems, third output power, fourth operation and maintenance cost, fourth number of systems, and fourth output power, the total operation and maintenance cost of the hydrogen production system is calculated. Based on the preset hydrogen price and the hydrogen sales volume per unit operating time, the total hydrogen production revenue of the hydrogen production system is calculated. Through the above process, the total operation and maintenance cost and total hydrogen production revenue are obtained. Based on the total operation and maintenance cost and total hydrogen production revenue, a cost function is derived.

[0036] Step S104: Process the objective function using the Honey Badger algorithm to obtain an initial optimal solution of the objective function.

[0037] It can be understood that the Honey Badger algorithm is used to obtain the initial optimal solution of the objective function. When the objective function is used to represent the total cost of the hydrogen production system, the optimal solution is expected to be the one with the minimum total cost.

[0038] In an optional embodiment, the honey badger algorithm is used to process the objective function to obtain the initial optimal solution of the objective function, including: based on the first output power, the second output power, the first input power, and the second input power, the power balance constraint of the objective function is obtained; based on the power upper limit and power lower limit of the new energy power supply equipment, the power output constraint of the new energy power supply equipment is obtained; based on the power upper limit, power lower limit, state of charge, and remaining power of the energy storage equipment, the energy storage equipment constraint is obtained; based on the efficiency upper limit, efficiency lower limit, and climbing rate of the water electrolysis hydrogen production equipment, the water electrolysis hydrogen production equipment constraint is obtained, wherein the above The ramp rate is the rate at which the efficiency of the above-mentioned water electrolysis hydrogen production equipment increases with power; based on the minimum start and stop time of the above-mentioned water electrolysis hydrogen production equipment, the number of starts within the above-mentioned unit operating time, the preset maximum number of starts, the number of shutdowns within the above-mentioned unit operating time, and the preset maximum number of shutdowns, the start and stop constraints of the above-mentioned water electrolysis hydrogen production equipment are obtained; the above-mentioned power balance constraint, the above-mentioned power supply output constraint, the above-mentioned energy storage device constraint, the above-mentioned water electrolysis hydrogen production equipment constraint, and the above-mentioned start and stop constraint are used to constrain the above-mentioned objective function to obtain the constrained objective function; the above-mentioned honey badger algorithm is used to process the above-mentioned constrained objective function to obtain the above-mentioned initial optimal solution of the above-mentioned constrained objective function.

[0039] It can be understood that the above objective function needs to be constrained. The purpose of establishing the constraints is to make the mathematical model conform to the operating rules of the actual hydrogen production system and to obtain a more reasonable optimal solution. Based on the first output power, the second output power, the first input power, and the second input power, the power balance constraint of the objective function is obtained. Based on the power upper limit and power lower limit of the new energy power supply equipment, the power output constraint of the new energy power supply equipment is obtained. Based on the power upper limit, power lower limit, state of charge, and remaining power of the energy storage equipment, the energy storage equipment constraint is obtained. Based on the efficiency upper limit, efficiency lower limit, and ramp rate of the water electrolysis hydrogen production equipment, the water electrolysis hydrogen production equipment constraint is obtained, where the ramp rate is the rate at which the efficiency of the water electrolysis hydrogen production equipment increases with power. Based on the minimum start and stop time of the water electrolysis hydrogen production equipment, the number of starts per unit operating time, the preset maximum number of starts, the number of shutdowns per unit operating time, and the preset maximum number of shutdowns, the start and stop constraints of the water electrolysis hydrogen production equipment are obtained. Through the above processing, the power balance constraint, power output constraint, energy storage equipment constraint, water electrolysis hydrogen production equipment constraint, and start and stop constraint are obtained. The objective function is constrained using power balance constraints, power output constraints, energy storage equipment constraints, water electrolysis hydrogen production equipment constraints, and start-stop constraints to obtain a constrained objective function. The Honey Badger algorithm is used to solve the constrained objective function and obtain the initial optimal solution for the constrained objective function.

[0040] In an optional embodiment, the honey badger algorithm is used to process the objective function to obtain the initial optimal solution of the objective function, including: determining the feasible domain of the objective function; performing population initialization processing on the honey badger algorithm using the reverse learning method to obtain a processed honey badger population; using the objective function to obtain the fitness function values corresponding to the multiple honey badgers included in the processed honey badger population; determining the honey badger with the smallest fitness function value among the multiple honey badgers as the target honey badger, and the individual position of the target honey badger in the feasible domain; and using the individual position as the initial optimal solution.

[0041] It can be understood that the feasible domain of the objective function is determined, and the feasible domain is the feasible range of values of the parameters included in the objective function. Using the reverse learning method to initialize the population of the honey badger algorithm is beneficial to expanding the diversity of the population and improving the search efficiency of the algorithm, thereby obtaining a processed honey badger population. Using the objective function, the fitness function values corresponding to the multiple honey badgers included in the processed honey badger population are obtained. The honey badger with the smallest fitness function value among the multiple honey badgers is determined as the target honey badger, as well as the individual position of the target honey badger in the feasible domain, and the individual position is used as the initial optimal solution.

[0042] To facilitate understanding of the terminology used in the honey badger algorithm, let's use a specific example: the objective function is Z(x), where Z is the function's value (also called its solution), x is the independent variable, the range of x is the feasible domain, and the fitness function represents the value of Z for different values of x. In this example, x is a 288-dimensional parameter, and the target honey badger's individual position can be understood as the 288-dimensional value of x that minimizes the fitness function. When the objective function represents the total cost, the desired minimum Z is desired.

[0043] Step S106, performing Gaussian mutation processing on the above-mentioned initial optimal solution to obtain the target optimal solution of the above-mentioned objective function and the target optimal value corresponding to the above-mentioned target optimal solution, wherein the above-mentioned target optimal solution minimizes the total cost of the above-mentioned hydrogen production system, and the above-mentioned target optimal value is the control parameter when the above-mentioned hydrogen production system reaches the above-mentioned target optimal solution.

[0044] It is understandable that since the Honey Badger Algorithm is prone to falling into local optimal solutions, Gaussian mutation processing is performed on the initial optimal solution to obtain the target optimal solution of the objective function (i.e., the value of the function) and the target optimal value corresponding to the target optimal solution (i.e., the value of the parameter in the function). The target optimal solution minimizes the total cost of the hydrogen production system, and the target optimal value is the control parameter when the hydrogen production system reaches the target optimal solution. Through the above processing, it can be seen that the target optimal solution is the minimum cost obtained by the objective function, and the target optimal value is the value of the control parameter in the objective function in order to achieve the minimum cost.

[0045] In an optional embodiment, the above-mentioned initial optimal solution is subjected to Gaussian mutation processing to obtain the target optimal solution of the objective function, including: performing Gaussian mutation processing on the initial optimal value of the above-mentioned initial optimal solution to obtain the initial optimal value after Gaussian processing; determining the initial optimal solution of the fitness function value corresponding to the initial optimal value after Gaussian processing; when the above-mentioned fitness function value is less than the above-mentioned initial optimal solution, taking the above-mentioned fitness function value as the first optimal solution; when the above-mentioned fitness function value is not less than the above-mentioned initial optimal solution, taking the above-mentioned initial optimal solution as the above-mentioned first optimal solution; when the current number of iterations of the above-mentioned honey badger algorithm reaches a preset maximum number of iterations, taking the above-mentioned first optimal solution as the above-mentioned target optimal solution.

[0046] It can be understood that the Gaussian mutation process is used to search for the best solution near the initial optimal solution, that is, the initial optimal value of the initial optimal solution is processed using Gaussian mutation, and the fitness function value corresponding to the initial optimal value after Gaussian mutation is determined. It should be noted that the initial optimal value that has not been processed by Gaussian mutation corresponds to the initial optimal solution, and the initial optimal value after Gaussian mutation has changed, so the initial optimal solution is no longer obtained, but the fitness function value is obtained. In the case where the above-mentioned fitness function value is less than the above-mentioned initial optimal solution, it is regarded that the fitness function value has a better performance in the hydrogen production system, that is, the total cost is minimized, and the above-mentioned fitness function value is used as the first optimal solution. In the case where the above-mentioned fitness function value is not less than the above-mentioned initial optimal solution, the initial optimal solution is regarded as the one with the lowest total cost, and the above-mentioned initial optimal solution is used as the above-mentioned first optimal solution. In the case where the current number of iterations of the above-mentioned honey badger algorithm reaches the preset maximum number of iterations, the above-mentioned first optimal solution is used as the above-mentioned target optimal solution.

[0047] Step S108: Based on the above target optimal value, determine the hydrogen production scheduling strategy of the above hydrogen production system so that the above hydrogen production system meets the above target optimal solution.

[0048] It can be understood that the target optimal value is a control parameter. Under the control parameter of the target optimal value, the target optimal solution can be obtained. Based on the target optimal value, the hydrogen production strategy of the hydrogen production system is determined to minimize the total cost of the hydrogen production system and meet the target optimal solution.

[0049] Through the above steps, Gaussian variation can be introduced to avoid the hydrogen production system scheduling algorithm from falling into local optimality, thereby improving the scheduling efficiency, achieving the technical effect of improving the system operation stability and scheduling effect, and thus solving the technical problems in related technologies such as unsatisfactory scheduling efficiency of new energy coupled hydrogen production, insufficient system operation stability, and premature system scheduling algorithm.

[0050] Based on the above embodiments and optional embodiments, the present invention proposes an optional implementation method, which is applied to an island-type renewable energy hydrogen production system. Figure 2 Schematic diagram of a hydrogen production system according to an optional hydrogen production system scheduling method provided in an embodiment of the present invention, such as Figure 2 As shown, the islanded renewable energy hydrogen production system consists of three components: a distributed power source (DG), an AC / DC converter, and an energy storage unit. The DGs include wind farms and photovoltaic power plants, while the energy storage unit includes both battery and hydrogen storage. The hydrogen storage includes at least an alkaline electrolysis unit and a proton membrane exchange (PME) electrolysis unit. This islanded renewable energy hydrogen production system enables internal "electricity-to-hydrogen" energy conversion, making renewable energy sources like wind and solar power controllable and adjustable. When wind and solar power output exceeds the load, the electrolysis unit produces hydrogen, and the energy storage unit stores energy. When the load is insufficient, the energy storage unit discharges to compensate for the energy shortfall. This mitigates the volatility and intermittency of renewable energy and improves system power supply stability. Considering the low cost of alkaline electrolysis equipment and the high current density, wide power load range, and flexible operation of PME, combining the two offers enhanced benefits. By using the alkaline electrolysis unit to continuously and stably produce hydrogen, and adjusting the PME electrolysis unit to absorb excess power when wind and solar power are in excess, this system can reduce wind and solar curtailment while ensuring economic efficiency. In addition, the abundant hydrogen produced can also be used to generate revenue, which will also reduce the cost of hydrogen production and further improve the economic efficiency of the system. The byproduct oxygen obtained from hydrogen production will be directly discharged into the atmosphere without causing environmental pollution. The following is a detailed description of the mathematical modeling of the various subsystems included in the island-type renewable energy hydrogen production system, an optional embodiment of the present invention.

[0051] 1. Establish the output power model of the wind turbine:

[0052]

[0053] Among them, P WT is the output power of the wind turbine, v is the current wind speed, V in Cut-in wind speed and V out is the cut-out wind speed, V rat is the rated wind speed, P rat is the rated output power of the wind turbine.

[0054] 2. Establish the output power model of photovoltaic power generation. Formula 2 is:

[0055]

[0056] Among them, P PV is the photovoltaic power output power, P sTC Output power under standard test conditions, K DF is the photovoltaic derating factor, G ING is the actual light intensity, G STCis the light intensity under standard test conditions, α is the power temperature coefficient, T SP is the panel operating temperature, T RT is the reference temperature.

[0057] 3. The present invention adopts two hydrogen energy storage methods, including alkaline electrolysis equipment and proton membrane exchange electrolysis equipment, and combines the alkaline electrolysis equipment and proton membrane exchange electrolysis equipment with hydrogen production for modeling.

[0058] First, the input power of the proton membrane exchange electrolysis device is modeled to obtain Equation 3:

[0059] P ele =V ele I ele (Formula 3)

[0060] Among them, P ele Input power for the proton membrane exchange electrolysis device, V ele is the voltage of the proton membrane exchange electrolysis device, I ele To obtain the current of the proton membrane exchange electrolysis device, I ele Expressed as formula 4:

[0061] I ele =i den S ele (Formula 4)

[0062] Among them, i den is the current density of the proton membrane exchange electrolysis device, S ele is the electrode area of the proton membrane exchange electrolysis device.

[0063] In order to obtain the voltage of the proton membrane exchange electrolysis device, V ele Expressed as formula 5:

[0064] V ele =V rev +η act +η ohm +η con (Formula 5)

[0065] Among them, V rev is the reversible potential of the proton membrane exchange electrolysis device. In general, the reversible potential V rev =1.23V, η act is the activation overpotential of the proton membrane exchange electrolysis device, η ohm is the ohmic overpotential of the proton membrane exchange electrolysis device, η con is the concentration overpotential of the proton membrane exchange electrolysis device.

[0066] In order to ensure the safety and efficiency of the proton membrane exchange electrolysis equipment in the hydrogen production process, the efficiency characteristics of the proton membrane exchange electrolysis equipment are analyzed. The efficiency η of the proton membrane exchange electrolysis equipment ele Depends on the Faraday efficiency and the voltage efficiency η of the proton membrane exchange electrolysis device V , establish the efficiency η of the proton membrane exchange electrolysis device ele Mathematical expression 6:

[0067]

[0068] And establish the voltage efficiency η of the proton membrane exchange electrolysis device V Mathematical expression 7:

[0069] η ele =η f η V (Equation 7)

[0070] Among them, V th is the thermal neutral potential of the proton membrane exchange electrolysis device, and V is taken under standard conditions. th =1.48V,η f is the Faraday efficiency.

[0071] Afterwards, a mathematical expression for the power of the alkaline electrolysis equipment was established, P cell It can be expressed as formula 8:

[0072] P cell =V cell I cell (Equation 8)

[0073] Among them, P cell Input power for alkaline electrolysis equipment, V cell is the input voltage of the alkaline electrolysis equipment, I cell is the input current of the alkaline electrolysis equipment.

[0074] In order to obtain the voltage V of the alkaline electrolysis equipment cell Create mathematical expression 9:

[0075]

[0076] Among them, r1, r2, s, q1, q2, q3 are empirical coefficients, A is the electrode area of the alkaline electrolysis equipment, T is the operating temperature of the alkaline electrolysis equipment, I cell is the current of the alkaline electrolysis equipment.

[0077] Energy efficiency η of alkaline electrolysis equipment cell It can be calculated from the thermal neutral potential of the alkaline electrolysis device and the cell voltage of the alkaline electrolysis device to establish a mathematical expression 10:

[0078]

[0079] Among them, V cell is the battery voltage of the alkaline electrolysis equipment, V th It is the thermal neutral potential of alkaline electrolysis equipment.

[0080] In order to obtain the thermoneutral potential V of the alkaline electrolysis device th , establish mathematical expression 11:

[0081]

[0082] Where ΔH is the reaction enthalpy change and F is the Faraday constant.

[0083] Figure 3 : is a power efficiency-efficiency diagram of hydrogen production by electrolysis of water provided according to an embodiment of the present invention, such as Figure 3 The two curves shown are the power-efficiency curve for the alkaline electrolysis equipment and the power-efficiency curve for the proton membrane exchange electrolysis equipment. The operating efficiency of the proton membrane exchange electrolysis equipment is slightly higher than that of the alkaline electrolysis equipment. The efficiency peaks of both electrolysis equipment are around 0.2 pu (pu is the per-unit value). However, too low a power output will lead to reduced hydrogen production. To ensure overall scheduling stability and minimize total cost, considering the operating efficiency and hydrogen production of the electrolysis equipment, the optimal operating range of both electrolysis equipment should be in the right half of the efficiency peak, and a reasonable constraint solution should be designed.

[0084] 4. In the case where the energy storage device selected for the island-type renewable energy hydrogen production system of this embodiment is a lithium iron phosphate battery, establish the remaining power C at time t soc Mathematical expression of (t)12:

[0085]

[0086] Among them, η + is the charging efficiency of the energy storage device, η - is the discharge efficiency of the energy storage device, P SB (t) is the charging or discharging power of the energy storage device at time t, P SB (t)<0 means the energy storage device is discharging, P SB (t)>0 means the energy storage device is charging.

[0087] In order to balance the cost minimization and stable operation of the islanded renewable energy hydrogen production system, at least two objectives are included. A cost function (Equation 13) is established to minimize the comprehensive operation and maintenance cost f1 of the system within one day, which includes the operation and maintenance costs of wind and solar units, lithium iron phosphate batteries, and two electrolysis equipment (Equation 14) and the hydrogen sales revenue (Equation 15):

[0088]

[0089] Among them, C d is the daily operation and maintenance cost of the system, K is the revenue from hydrogen sales. i is the unit operation and maintenance cost of each unit in the system, N i is the number of units in the system, P i (t) is the output power of each unit at time t, C1 is the price of hydrogen, is the volume of hydrogen sold at time t.

[0090] In order to evaluate the reliability of system operation, under the premise of meeting the load demand, wind power and photovoltaic power are absorbed as much as possible to ensure a small power shortage and minimize the surplus of wind and photovoltaic power. Therefore, the power function is selected to minimize the absolute value f2 of the difference between the system output and the load. The mathematical expression of the power function is established as Equation 16:

[0091]

[0092] Among them, P e&g (t) is the output power of the power generation system and energy storage system at time t, P e&c (t) is the power absorbed by the power system at time t, P load (t) is the load demand at time t.

[0093] In order to obtain the output power of the power generation system and the energy storage system at time t, mathematical expression 17 is established:

[0094] P e&g (t) = P WT (t)+P PV (t)-P SB (t) (Equation 17)

[0095] Among them, P WT is the output power of the wind turbine, P SB (t) is the charging and discharging power of the energy storage device at time t, P PV Output power for photovoltaic power generation.

[0096] P e&c (t) = P load (t)+P ele (t)+P cell (t) (Equation 18)

[0097] Among them, P ele is the input power of the proton membrane exchange electrolysis device at time t, P load (t) is the load demand at time t, P cell is the power of the alkaline electrolysis equipment at time t.

[0098] The power function f2 is converted into a reliability cost model, and the new mathematical expression is the reliability function (Equation 19):

[0099]

[0100] Among them, C(t) is the penalty cost at time t.

[0101] In order to obtain the penalty cost at time t, the insufficient power penalty cost C is introduced. In&p and the remaining penalty cost C sur&p , establish the mathematical expression of C(t)20:

[0102]

[0103] Among them, C In&p is the penalty cost for insufficient power, C sur&p is the remaining penalty cost of electricity, C In&p The mathematical expression of is Equation 21:

[0104] C In&p =BC ave (Equation 21)

[0105] Among them, B is the power shortage penalty coefficient, C ave is the average electricity price.

[0106] Combining the transformed reliability model with the total cost, combining the cost function with the reliability function, and transforming the multi-objective function into a single-objective function, we obtain the objective function (Equation 22):

[0107] Z = f1 + f2′ (Equation 22)

[0108] Where Z is the total system cost, and the objective function (Equation 22) is composed of the f1 cost function representing the daily operation and maintenance cost and the f2′ reliability function representing the reliability cost.

[0109] The objective function (Equation 22) consists of multiple constraints, including at least: the objective function's power balance constraint, the power output constraint of the renewable energy power supply equipment, the energy storage equipment constraint, the water electrolysis hydrogen production equipment constraint, and the start / stop constraint of the water electrolysis hydrogen production equipment. The various constraints are described in detail below.

[0110] (1) Establish the mathematical expression of the power balance constraint of the objective function 23:

[0111] P WT +P PV -P ele -P cell -P SB =P load (Equation 23)

[0112] Among them, P WT is the output power of the wind turbine, P SB (t) is the charging or discharging power at time t, P PV is the photovoltaic power output power, P cell Input power for alkaline electrolysis equipment, P ele is the input power of the proton membrane exchange electrolysis device, P load (t) is the load demand at time t.

[0113] (2) Establish mathematical expressions 24 and 25 for the power output constraints of new energy power supply equipment:

[0114] P WT，min ≤P WT (t)≤P WT，max (Equation 24)

[0115] P PV，min ≤P PV (t)≤P PV，max (Equation 25)

[0116] Among them, P wT，max is the upper limit of fan output, P WT，min is the lower limit of fan output, P PV，max is the upper limit of photovoltaic cell output, P PV，min It is the lower limit of photovoltaic cell output.

[0117] (3) Establish mathematical expressions 25, 26, and 27 for energy storage device constraints:

[0118] P SB，min ≤P SB ≤P SB，max (Equation 25)

[0119] SOC min ≤SOC≤SOC max (Equation 26)

[0120] C soc (0) = C soc (T) (Equation 27)

[0121] Among them, P SB，max is the upper limit of the energy storage device power interaction, P SB，min is the lower limit of the energy storage device power interaction, SOC max SOC is the upper limit of the state of charge of the energy storage device. min is the lower limit of the charge state of the energy storage device, and formula (27) is the periodic operation limit of the energy storage device, ensuring that it can perform periodic work.

[0122] (4) Establish mathematical expressions 28, 29, 30a, and 30b for the constraints of the water electrolysis hydrogen production equipment:

[0123] η ele,min ≤η ele ≤η ele,max (Equation 28)

[0124] η cell,min ≤n≤η cell ≤c ell,max (Equation 29)

[0125] |P ele (t+1)-P ele (t)|≤ΔP ele,max (Formula 30a)

[0126] |P cell (t+1)-P cell (t)|≤P cell，max (Formula 30b)

[0127] Among them, η ele，max is the upper limit of the efficiency of the proton membrane exchange electrolysis equipment, η ele，min is the lower limit of the efficiency of the proton membrane exchange electrolysis equipment, η cell，max is the upper limit of alkaline electrolysis equipment efficiency, η cell，min is the lower limit of alkaline electrolysis equipment efficiency, ΔP ele，max is the maximum ramp rate of the proton membrane exchange electrolysis equipment, ΔP cell，max It is the maximum ramp rate of alkaline electrolysis equipment.

[0128] (5) Establish the mathematical expression 31 for the start and stop constraints of the water electrolysis hydrogen production equipment:

[0129]

[0130] Among them, T on is the minimum startup time of the proton membrane exchange electrolysis equipment, T off is the minimum stop time of the proton membrane exchange electrolysis equipment, u(t) is the start and stop state of the proton membrane exchange electrolysis equipment at time t, and takes the value 0 or 1 (0 means shutdown, 1 means start), S on is the number of daily starts, S on，max is the maximum number of daily starts, S off is the number of daily shutdowns, S off，max The maximum number of daily shutdowns. Considering the start-stop characteristics of the alkaline electrolysis equipment, it is set to be always on. At the same time, to avoid intermittent operation of the proton membrane exchange electrolysis equipment, start-stop constraints are set for it.

[0131] (6) The operation control strategy of the isolated renewable energy hydrogen production system will affect the power distribution and directly affect the operation efficiency of the system. When the system is working, the wind turbine, photovoltaic output and energy storage device discharge sometimes cannot meet the requirements of the load and the two electrolysis equipment to operate within the optimal range. In order to ensure the economy and reliability of the system operation as much as possible, two working states are set so that the isolated renewable energy hydrogen production system can select different operation control strategies under different circumstances. Because the alkaline electrolysis equipment is inconvenient to start and stop, it is set to be normally open, while the proton membrane exchange electrolysis equipment is more flexible in control, so the following two working states are set as operation state constraints:

[0132] ① Working state 1: When the output of wind turbine and photovoltaic cannot meet the load demand, that is, P WT (t)+P PV (t)≤P load At (t), the proton membrane exchange electrolysis equipment is shut down, the alkaline electrolysis equipment operates in the optimal operating range to continuously produce hydrogen, and the energy storage device is discharged. WT is the output power of the wind turbine, P PV is the photovoltaic power output power, P load (t) is the load demand at time t.

[0133] ② Working state 2: When the output of wind turbine and photovoltaic is greater than the load demand, that is, P WT (t)+P PV (t)>P load (t), the alkaline electrolysis equipment works in the optimal operating range, and the proton membrane exchange electrolysis equipment absorbs the remaining power. If P WT (t)+P PV (t)>P load (t)+P ele (t)+P cell (t), the energy storage device is charged; if P WT (t)+P PV (t) <P load (t)+P ele (t)+P cell (t), the energy storage device discharges. Where, P WT is the output power of the wind turbine, P SB (t) is the charging or discharging power at time t, P PV is the photovoltaic power output power, P cell Input power for alkaline electrolysis equipment, P ele is the input power of the proton membrane exchange electrolysis device, P load (t) is the load demand at time t.

[0134] The constrained objective function (Equation 22) is processed using the honey badger algorithm to obtain the initial optimal solution. Gaussian mutation is then performed on this initial optimal solution to obtain the target optimal solution and the target optimal value corresponding to the target optimal solution. The honey badger algorithm is a biomimetic intelligent optimization algorithm that primarily simulates the digging and honey-seeking behavior of honey badgers to obtain food sources. Generally speaking, a honey badger can continuously locate its prey through its sense of smell and continuously dig to obtain it. Honey badgers love honey but are not good at locating beehives, so they follow honey guides to obtain honey. Therefore, to find honey, honey badgers either sniff and dig frantically or follow a guide. Therefore, the algorithm's dynamic search can be divided into two modes: digging mode and honey-seeking mode. In other words, the honey badger algorithm is used to solve the objective function and obtain the optimal solution and the optimal value under the optimal solution. This is explained in detail below.

[0135] Figure 4 This is a flow chart of an improved honey badger algorithm for an optional hydrogen production system scheduling method provided in an embodiment of the present invention, such as Figure 4 As shown, the following steps are:

[0136] Step S1, set basic parameters. Number of honey badgers n, variable space dimension DIM, maximum number of iterations t max , the upper bound of feasible solution ub, the lower bound of feasible solution lb.

[0137] In the Honey Badger algorithm, the candidate values corresponding to multiple candidate solutions can be expressed as:

[0138]

[0139] Where D is the dimension of candidate solutions in the variable space dimension DIM, n is the number of candidate solutions, i is the identifier of the honey badger in the population, and the position of the i-th honey badger can be expressed as That is, the candidate value of the i-th candidate solution among n candidate solutions.

[0140] Step S2: Population initialization. Randomly generate an initial population within the feasible region, generate the corresponding dynamic reverse solution, and finally retain the optimized initial population to enter the iteration.

[0141] It should be noted that the initial population of the standard Honey Badger algorithm is randomly generated, resulting in a significant degree of randomness. This can lead to the inability to capture the optimal points during initialization, increasing the range of feasible solutions and lengthening the search time, thus affecting the algorithm's search capability and convergence efficiency. To address this issue, an elitist reverse learning strategy (also known as a reverse learning algorithm) is incorporated into the initialization of the standard Honey Badger algorithm.

[0142] In the standard honey badger algorithm, the feasible domain of candidate values corresponding to multiple candidate solutions is determined based on the upper bound ub and the lower bound lb of the feasible solution. Using random initialization, the number and individual positions of honey badgers in the feasible domain are initialized, and the mathematical expression is established as Equation 32:

[0143] x i =lb i +r1(ub i -lb i ) (Equation 32)

[0144] Among them, x i is the position of the i-th honey badger, ub i is the upper bound of the feasible region of the i-th honey badger, lb i is the lower bound of the feasible region of the i-th honey badger, and r1 is a random number in (0, 1).

[0145] On the basis of the standard honey badger algorithm, an elite reverse learning strategy is adopted. When the algorithm initializes the population, a set of random solutions and their corresponding dynamic reverse learning solutions are generated at the same time. The fitness function value of each individual and its dynamic reverse solution is calculated separately, and the individuals with better fitness values are retained. Finally, the remaining individuals constitute the initial population of the algorithm.

[0146] Let X = (x1, x2, ... x n ) is a random solution in n-dimensional space, then the mathematical expression for generating its dynamic reverse solution is 33:

[0147]

[0148] Among them, X′ is the dynamic reverse solution corresponding to X, rand(0,1) is a random number between (0,1), and x max is the maximum feasible solution, x min is the minimum value of the feasible solution, x′ i ∈[x min , x max ].

[0149] Let f(X) be the solution X=(x1,x2,...,x n ), after generating its dynamic reverse solution X′, the following elite reverse learning strategy is used to optimize the random initialization population and establish mathematical expression 34:

[0150]

[0151] X new These are the better individuals that remain after elite reverse learning optimization. Adding elite reverse learning optimization increases the diversity of the initial population and improves the coverage of better points to a certain extent.

[0152] Step S3: Calculate and sort the fitness function values of each honey badger in the current population. Sort the honey badgers according to their fitness function values, and then compare the function values to obtain the current optimal solution and optimal value. In the application scenario of this objective function (Equation 22), the fitness function value is expected to be as small as possible.

[0153] Step S4, calculate the current density factor α. The density factor α controls the time-varying randomization and ensures a smooth transition from search to acquisition. Its size decreases as the number of iterations increases. The mathematical expression 35 for the density factor α is:

[0154]

[0155] Among them, C is a constant 2, t is the current iteration number, t max is the maximum number of iterations.

[0156] Step S5, calculate the concentration I of the current n honey badger individuals i (i=1, ..., n) The concentration of the prey (honey) odor I i It is related to the concentration of the honey badger and the distance between the prey and the honey badger. The greater the concentration, the faster the movement speed. The following mathematical expressions are established: Equation 36, Equation 37 and Equation 38:

[0157]

[0158] S=(x i -x i+1 ) 2 (Equation 37)

[0159] d i =x prey -x i (Equation 38)

[0160] Among them, r2 is a random number (0, 1), S is the concentration intensity of prey, d i is the distance between the i-th honey badger and its prey, x prey The location of the prey.

[0161] Step S6: Calculate the directional parameter F for each honey badger. During the digging phase, honey badgers rely heavily on the concentration of the prey's odor, the distance to the prey, and the density factor. The range of individual position updates is similar to a cardioid, and its motion expression can be simulated as Equation 39:

[0162] x new =x prey +FβIx prey +Fr3αd i |cos(2πr4)[-cos(2πr5)]| (Equation 39)

[0163] Where β represents the ability of the honey badger to obtain food, the default value is 6, r3, r4, and r5 are random numbers (0, 1), and F is a parameter for controlling the direction. The mathematical expression 40 is established:

[0164]

[0165] Among them, r6 is a random number (0, 1).

[0166] During the honey collection phase, the honey badger follows the honey guide to the hive. Its behavior is affected by the density factor, and the motion expression can be simulated as Equation 41:

[0167] x new =x prey +Fr7αd i (Equation 41)

[0168] Among them, r7 is a random number (0, 1).

[0169] Step S7: Update the individual honey badger's position. Based on Equation 40, if r6 ≤ 0.5, it indicates that the individual is in the digging phase, and its position is updated according to Equation 39. If r6 > 0.5, it indicates that the individual is in the honey-collecting phase, and its position is updated according to Equation 41.

[0170] Step S8, calculate the fitness function values of the updated population individuals and sort them, update the optimal solution and optimal value, and obtain the initial optimal solution.

[0171] Step S9 performs Gaussian mutation on the initial optimal solution. In one iteration of the standard honey badger algorithm, each honey badger individual moves towards the location of the honey (optimal solution), but there may be a better solution near the honey location. Therefore, a Gaussian mutation operator is added to the algorithm to enable the honey badger individual to search near the current optimal solution in order to find a better location and update the optimal solution in time. In this way, the local optimum can be jumped out in time during the algorithm search process, thereby improving the accuracy of its convergence. Gaussian mutation refers to the use of a mean of μ and a variance of σ when performing a mutation operation. 2 A random value from a normal distribution replaces the original value. Gaussian mutation is based on the Gaussian probability density function 42:

[0172]

[0173] Where g(x; μ, σ) is a Gaussian distribution, μ is the mean, and σ is the standard deviation. When μ = 0 and σ = 1, it is a standard Gaussian distribution, denoted as Gauss(0,1). Using Gaussian mutation to update the optimal point, mathematical expressions 43 and 44 are established:

[0174] x gauss =x prey +Gauss(0,1)x prey (Equation 43)

[0175]

[0176] Among them, x gauss is the value after Gaussian mutation of the optimal solution, x prey，new is the optimal individual position after update.

[0177] By incorporating Gaussian mutation into the algorithm, the perturbation function of the Gaussian operator is utilized, allowing for focused searches in local areas near the original optimal individual, enabling more efficient and accurate searches for local extreme points. This, to a certain extent, prevents the algorithm from falling into local optimality and enhances its global optimization capabilities.

[0178] Step S10 calculates the fitness function value after Gaussian mutation of the initial optimal solution, updates the initial optimal solution according to formula 44, and obtains the target optimal solution and target optimal value.

[0179] Step S11 determines whether the maximum number of iterations has been reached. If so, the iteration is terminated and the target optimal solution and the target optimal value corresponding to the target optimal solution are output. Otherwise, the process jumps to step S4.

[0180] To facilitate understanding, a specific example is provided below: A system model is constructed in a microgrid simulation system containing a 64-kW proton membrane exchange electrolysis device, a 64-kW alkaline electrolysis device, and three 125-kWh lithium iron phosphate battery packs, where the initial state of charge of the lithium iron phosphate battery is 0.6. Table 1 shows the parameter settings for each subsystem in the microgrid simulation system, and Table 2 shows the fixed parameter settings. The specific data in Tables 1 and 2 are for illustrative purposes only and do not limit the present invention.

[0181] Table 1

[0182]

[0183]

[0184] Table 2

[0185]

[0186] Because alkaline electrolysis equipment has a narrow tolerance for power fluctuations, a smaller operating efficiency range was set to reduce fluctuations while ensuring efficient hydrogen production. The algorithm parameters were set to 50 honey badgers and a maximum number of iterations of 800. Data from a typical day was used for the experiment, with 24 hours divided into 96 time periods and recorded every 15 minutes. Figure 5Schematic diagram of wind and solar power output of an optional hydrogen production system scheduling method provided in an embodiment of the present invention, such as Figure 5 The figure shows the output power variation of wind power and photovoltaic power over the 24 hours of a typical day. kW is kilowatt and h is hour. Figure 6 This is a schematic diagram of wind, solar and load combination of an optional hydrogen production system scheduling method provided by an embodiment of the present invention. The local load is taken as the system load. The wind, solar and load output power is as follows: Figure 6 As shown. Figure 5 and Figure 6 It can be seen that between 0:00 and 3:00 and 15:00 and 20:00, the combined output power of wind and solar power is slightly lower than the load power, and reaches the valley value around 3:00; between 3:00 and 15:00 and 20:00 to 24:00, the combined output power of wind and solar power is higher than the load power, and reaches the peak value around 12:00.

[0187] Figure 7 is an algorithm diagram of an optional hydrogen production system scheduling method provided according to an embodiment of the present invention, such as Figure 7 As shown, to verify the effectiveness of the improved Honey Badger algorithm, the established model was tested on the Honey Badger algorithm, the improved Honey Badger algorithm, and the atomic search algorithm. To verify the stability of the improved Honey Badger algorithm, 10 repeated experiments were performed on each of the three algorithms, and the average and variance values were calculated. The average values were then used to plot the optimization process curve. Table 3 shows the experimental results. The specific data in Table 3 are for illustrative purposes only and do not limit the present invention.

[0188] Table 3

[0189]

[0190] Analysis shows that the optimization results of the improved Honey Badger algorithm outperform those of the Honey Badger algorithm and the Atomic Search Algorithm. The Atomic Search Algorithm reached its optimal state around the 500th iteration, the Honey Badger algorithm around the 450th iteration, and the improved Honey Badger algorithm around the 300th iteration. Although the improved Honey Badger algorithm's convergence speed was slower than those of the Honey Badger and Atomic Search Algorithms in the early stages, it converged significantly faster in the middle and late stages. The Honey Badger algorithm ultimately converged to 6148.98 yuan, the Atomic Search Algorithm to 6740.83 yuan, and the improved Honey Badger algorithm to 4607.19 yuan. This indicates that the improved Honey Badger algorithm achieved the best convergence accuracy, improving by 25.07% compared to the original results. A comparison of variances shows that the improved Honey Badger algorithm had the smallest variance, indicating the most stable algorithm. The optimization results prove that this paper greatly improves the convergence speed and search accuracy of the algorithm by improving the initialization method of the Honey Badger algorithm and introducing the Gaussian mutation strategy, avoids the algorithm from falling into local optimality to a certain extent, and makes the algorithm more stable and robust.

[0191] Figure 8 FIG. 1 is a power diagram of a water electrolysis hydrogen production device according to an optional hydrogen production system scheduling method provided in an embodiment of the present invention. Figure 8 The figure shows the output power curves of the alkaline electrolysis system and the proton membrane exchange electrolysis system. Due to insufficient wind and solar power output from 0:00 to 8:00 and sometimes failing to meet load demand, the alkaline electrolysis system operates at its lower power limit. From 8:00 to 12:00, the system shows an upward trend as wind and solar power output increases, reaching a peak around 12:00. From 12:00 to 15:00, the system shows a downward trend due to reduced photovoltaic power generation. Due to insufficient wind and solar power output from 20:00 to 24:00, the alkaline electrolysis system's operating power drops significantly. The proton membrane exchange electrolysis system is shut down from 0:00 to 4:00 and 15:00 to 20:00 due to insufficient wind and solar power output. From 4:00 to 12:00, the system's power rises rapidly, peaking around 12:00. It then declines from 12:00 to 15:00. To minimize grid power losses, the system operates at its lower power limit from 20:00 to 24:00. The overall power trend shows that the alkaline electrolysis system has a narrower operating range than the proton membrane exchange electrolysis system, and its power rises and falls more slowly.

[0192] Figure 9 Schematic diagram of an energy storage device according to an optional hydrogen production system scheduling method provided in an embodiment of the present invention, such as Figure 9 The figure shows the total interactive power and state of charge (SOC) of the lithium iron phosphate battery pack over a typical 24-hour day. Analysis shows that the operating power and depth of charge / discharge of the lithium iron phosphate batteries are within the specified range. From 0:00 to 8:00, to ensure grid stability, the lithium iron phosphate batteries are in a discharging state, and the SOC shows an overall downward trend. From 8:00 to 15:00 and from 21:00 to 24:00, due to abundant wind and solar power and the cyclical operation of the lithium iron phosphate batteries, the batteries continue to charge, and the SOC shows an upward trend. From 15:00 to 21:00, to ensure grid stability and optimal operation of the electrolysis equipment, the lithium iron phosphate batteries continue to discharge, and the SOC decreases. The lithium iron phosphate batteries reach the lower limit of the SOC around 5:00 and 21:00, and the upper limit of the SOC around 15:00, indicating high battery utilization.

[0193] The above optional implementation methods achieve at least the following effects: a mathematical model of a hydrogen production system containing wind turbines, photovoltaics, energy storage and various types of electrolysis equipment is established, and the advantages of proton membrane exchange electrolysis equipment, such as flexible operation, high current density, and low cost and sustainable and stable hydrogen production, of alkaline electrolysis equipment are utilized, and a combination of two electrolysis equipment is used to produce hydrogen. And by improving the honey badger algorithm, the output of each part of the system is reasonably distributed, while ensuring the economic efficiency of operation and taking into account the reliability of power supply to local loads. In the population initialization of the honey badger algorithm, the elite reverse learning strategy is introduced to replace the random initialization in the original algorithm, which effectively expands the diversity of the population and improves the search efficiency of the algorithm. In addition, the Gaussian mutation strategy is introduced to avoid premature algorithm maturation and improve the convergence accuracy. The above analysis shows that the convergence performance of the improved honey badger algorithm provided by the present invention is improved by 25.07% compared with the standard honey badger algorithm, which can effectively solve complex engineering problems with multiple constraints and has better robustness.

[0194] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0195] This embodiment also provides a hydrogen production system scheduling device, which is used to implement the above-mentioned embodiments and preferred embodiments. Details that have already been described will not be repeated. As used below, the terms "module" and "device" may refer to a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation using hardware, or a combination of software and hardware, is also possible and contemplated.

[0196] According to an embodiment of the present invention, there is also provided an embodiment of a device for implementing a hydrogen production system scheduling method. Figure 10 is a schematic diagram of a hydrogen production system scheduling device according to an embodiment of the present invention, such as Figure 10 As shown, the above-mentioned hydrogen production system scheduling device includes: a first determination module 1002, a first calculation module 1004, a second calculation module 1006, and a second determination module 1008. The device is described below.

[0197] A first determination module 1002 is configured to determine an objective function of the hydrogen production system based on a total operation and maintenance cost and a total hydrogen production income corresponding to the hydrogen production system, a first output power of the new energy power supply device in the hydrogen production system, a second output power of the energy storage device in the hydrogen production system, a first input power of the water electrolysis hydrogen production device in the hydrogen production system, and a second input power of the load in the hydrogen production system, wherein the total operation and maintenance cost is the operation and maintenance cost generated by the hydrogen production system within a preset unit operating time, the total hydrogen production income is the hydrogen production income generated by the hydrogen production system within the unit operating time, and the objective function is used to represent the total cost of the hydrogen production system;

[0198] A first calculation module 1004 is connected to the first determination module 1002 and is used to process the objective function using a honey badger algorithm to obtain an initial optimal solution of the objective function;

[0199] A second calculation module 1006 is connected to the first calculation module 1004 and is used to perform Gaussian variation processing on the initial optimal solution to obtain a target optimal solution of the objective function and a target optimal value corresponding to the target optimal solution, wherein the target optimal solution minimizes the total cost of the hydrogen production system, and the target optimal value is a control parameter when the hydrogen production system achieves the target optimal solution;

[0200] The second determination module 1008 is connected to the second calculation module 1006 and is used to determine the hydrogen production scheduling strategy of the hydrogen production system based on the target optimal value, so that the hydrogen production system meets the target optimal solution.

[0201] In a hydrogen production system scheduling device provided in an embodiment of the present invention, a first determination module 1002 is used to determine the objective function of the hydrogen production system based on the total operation and maintenance cost and total hydrogen production income corresponding to the hydrogen production system, the first output power of the new energy power supply equipment in the hydrogen production system, the second output power of the energy storage equipment in the hydrogen production system, the first input power of the water electrolysis hydrogen production equipment in the hydrogen production system, and the second input power of the load in the hydrogen production system, wherein the total operation and maintenance cost is the operation and maintenance cost generated by the hydrogen production system within a preset unit operating time, the total hydrogen production income is the hydrogen production income generated by the hydrogen production system within the unit operating time, and the objective function is used to represent the total cost of the hydrogen production system; a first calculation module 1004, The first determining module 1002 is connected to the first determining module 1002 and is used to process the objective function using the honey badger algorithm to obtain the initial optimal solution of the objective function. The second calculating module 1006 is connected to the first calculating module 1004 and is used to perform Gaussian variation processing on the initial optimal solution to obtain the target optimal solution of the objective function and the target optimal value corresponding to the target optimal solution, wherein the target optimal solution minimizes the total cost of the hydrogen production system, and the target optimal value is the control parameter when the hydrogen production system reaches the target optimal solution. The second determining module 1008 is connected to the second calculating module 1006 and is used to determine the hydrogen production scheduling strategy of the hydrogen production system based on the target optimal value so that the hydrogen production system meets the target optimal solution. The purpose of introducing Gaussian variation, avoiding the hydrogen production system scheduling algorithm from falling into local optimality, and improving scheduling efficiency is achieved, achieving the technical effect of taking into account the stability and economy of the hydrogen production system, improving system operation stability and scheduling effect, and thus solving the technical problems in the related art of unsatisfactory scheduling efficiency of hydrogen production coupled with new energy, insufficient system operation stability, and premature system scheduling algorithm.

[0202] It should be noted that the above modules can be implemented by software or hardware. For example, for the latter, it can be implemented in the following ways: the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0203] It should be noted that the first determination module 1002, the first calculation module 1004, the second calculation module 1006, and the second determination module 1008 correspond to steps S102 to S108 in the embodiment. The examples and application scenarios implemented by these modules and the corresponding steps are the same, but are not limited to the contents disclosed in the above embodiment. It should be noted that the above modules, as part of the device, can be run on a computer terminal.

[0204] It should be noted that the optional or preferred implementation of this embodiment can be found in the relevant description in the embodiment, which will not be repeated here.

[0205] The above-mentioned hydrogen production system scheduling device may also include a processor and a memory. The first determination module 1002, the first calculation module 1004, the second calculation module 1006, the second determination module 1008, etc. are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to realize the corresponding functions.

[0206] The processor includes a kernel, which retrieves the corresponding program unit from memory. There can be one or more kernels. Memory may include non-permanent memory in a computer-readable medium, random access memory (RAM), and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory includes at least one memory chip.

[0207] An embodiment of the present invention provides a non-volatile storage medium on which a program is stored. When the program is executed by a processor, a method for scheduling a hydrogen production system is implemented.

[0208] An embodiment of the present invention provides an electronic device, which includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, the following steps are implemented: based on the total operation and maintenance cost and total hydrogen production income corresponding to the hydrogen production system, the first output power of the new energy power supply device in the hydrogen production system, the second output power of the energy storage device in the hydrogen production system, the first input power of the water electrolysis hydrogen production device in the hydrogen production system, and the second input power of the load in the hydrogen production system, the objective function of the hydrogen production system is determined, wherein the total operation and maintenance cost is the operation and maintenance cost generated by the hydrogen production system within a preset unit operating time, and the total hydrogen production income is The hydrogen production revenue generated by the above-mentioned hydrogen production system within the above-mentioned unit operating time, the above-mentioned objective function is used to represent the total cost of the above-mentioned hydrogen production system; the above-mentioned objective function is processed by the honey badger algorithm to obtain the initial optimal solution of the above-mentioned objective function; the above-mentioned initial optimal solution is subjected to Gaussian mutation processing to obtain the target optimal solution of the above-mentioned objective function, and the target optimal value corresponding to the above-mentioned target optimal solution, wherein the above-mentioned target optimal solution minimizes the total cost of the above-mentioned hydrogen production system, and the above-mentioned target optimal value is the control parameter when the above-mentioned hydrogen production system reaches the above-mentioned target optimal solution; based on the above-mentioned target optimal value, the hydrogen production scheduling strategy of the above-mentioned hydrogen production system is determined so that the above-mentioned hydrogen production system meets the above-mentioned target optimal solution. The device in this article can be a server, PC, etc.

[0209] The present invention also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program initialized with the following method steps: based on the total operation and maintenance cost and total hydrogen production income corresponding to the hydrogen production system, the first output power of the new energy power supply equipment in the above hydrogen production system, the second output power of the energy storage equipment in the above hydrogen production system, the first input power of the water electrolysis hydrogen production equipment in the above hydrogen production system, and the second input power of the load in the above hydrogen production system, the objective function of the above hydrogen production system is determined, wherein the above total operation and maintenance cost is the operation and maintenance cost generated by the above hydrogen production system within a preset unit operating time, and the above total hydrogen production income is the above hydrogen production system in the above The hydrogen production revenue generated per unit operating time, the above objective function is used to represent the total cost of the above hydrogen production system; the honey badger algorithm is used to process the above objective function to obtain the initial optimal solution of the above objective function; the Gaussian mutation processing is performed on the above initial optimal solution to obtain the target optimal solution of the above objective function, and the target optimal value corresponding to the above target optimal solution, wherein the above target optimal solution makes the total cost of the above hydrogen production system the lowest, and the above target optimal value is the control parameter of the above hydrogen production system when the above target optimal solution is achieved; based on the above target optimal value, the hydrogen production scheduling strategy of the above hydrogen production system is determined so that the above hydrogen production system meets the above target optimal solution.

[0210] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0211] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0212] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0213] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0214] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0215] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0216] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0217] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0218] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0219] The above are merely embodiments of the present invention and are not intended to limit the present invention. It will be apparent to those skilled in the art that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention are intended to be included within the scope of the claims of the present invention.

Claims

1. A hydrogen production system scheduling method, characterized in that: include: Based on the total operation and maintenance cost and total hydrogen production income corresponding to the hydrogen production system, the first output power of the new energy power supply equipment in the hydrogen production system, the second output power of the energy storage equipment in the hydrogen production system, the first input power of the water electrolysis hydrogen production equipment in the hydrogen production system, and the second input power of the load in the hydrogen production system, the objective function of the hydrogen production system is determined, wherein the total operation and maintenance cost is the operation and maintenance cost generated by the hydrogen production system within a preset unit operating time, and the total hydrogen production income is the hydrogen production income generated by the hydrogen production system within the unit operating time, and the objective function is used to represent the total cost of the hydrogen production system; The objective function is processed using a honey badger algorithm to obtain an initial optimal solution of the objective function; Performing Gaussian mutation processing on the initial optimal solution to obtain a target optimal solution of the objective function and a target optimal value corresponding to the target optimal solution, wherein the target optimal solution minimizes the total cost of the hydrogen production system, and the target optimal value is a control parameter when the hydrogen production system achieves the target optimal solution; Based on the target optimal value, determining a hydrogen production scheduling strategy for the hydrogen production system so that the hydrogen production system meets the target optimal solution; The objective function of the hydrogen production system is determined based on the total operation and maintenance cost and total hydrogen production income corresponding to the hydrogen production system, the first output power of the new energy power supply equipment in the hydrogen production system, the second output power of the energy storage equipment in the hydrogen production system, the first input power of the water electrolysis hydrogen production equipment in the hydrogen production system, and the second input power of the load in the hydrogen production system, including: obtaining a cost function corresponding to the hydrogen production system based on the total operation and maintenance cost and the total hydrogen production income; determining a power shortage penalty cost and an excess power cost of the hydrogen production system; obtaining an electricity function corresponding to the hydrogen production system based on the first output power, the second output power, the first input power, and the second input power within the unit operating time; obtaining a reliability function corresponding to the hydrogen production system based on the electricity function, the power shortage penalty cost, and the excess power cost; and obtaining the objective function corresponding to the hydrogen production system based on the cost function and the reliability function.

2. The method according to claim 1, characterized in that The obtaining of a cost function corresponding to the hydrogen production system based on the total operation and maintenance cost and the total hydrogen production income corresponding to the hydrogen production system includes: Determine a first operation and maintenance cost, a first number of systems, and a first output power corresponding to the new energy power supply equipment, a second operation and maintenance cost, a second number of systems, and a second output power corresponding to the energy storage equipment, a third operation and maintenance cost, a third number of systems, and a third output power corresponding to the water electrolysis hydrogen production equipment, and a fourth operation and maintenance cost, a fourth number of systems, and a fourth output power corresponding to the load; Obtaining the total operation and maintenance cost based on the first operation and maintenance cost, the first number of systems, the first output power, the second operation and maintenance cost, the second number of systems, the second output power, the third operation and maintenance cost, the third number of systems, the third output power, the fourth operation and maintenance cost, the fourth number of systems, and the fourth output power; Based on the preset hydrogen price and the hydrogen sales volume within the unit operating time, the total hydrogen production revenue is obtained; The cost function is obtained according to the total operation and maintenance cost and the total hydrogen production income.

3. The method according to claim 1, characterized in that The honey badger algorithm is used to process the objective function to obtain an initial optimal solution of the objective function, including: Obtaining a power balance constraint of the objective function based on the first output power, the second output power, the first input power, and the second input power; Obtaining a power output constraint of the new energy power supply device based on the power upper limit and the power lower limit of the new energy power supply device; Obtaining energy storage device constraints based on the power upper limit, power lower limit, state of charge, and remaining capacity of the energy storage device; Obtain constraints for the electrolysis hydrogen production equipment based on the upper efficiency limit, the lower efficiency limit, and the ramp rate of the electrolysis hydrogen production equipment, wherein the ramp rate is the rate at which the efficiency of the electrolysis hydrogen production equipment increases with power; Based on the minimum start and stop time of the water electrolysis hydrogen production equipment, the number of starts within the unit operating time, the preset maximum number of starts, the number of shutdowns within the unit operating time, and the preset maximum number of shutdowns, the start and stop constraints of the water electrolysis hydrogen production equipment are obtained; The objective function is constrained by using the power balance constraint, the power output constraint, the energy storage device constraint, the water electrolysis hydrogen production device constraint, and the start-stop constraint to obtain a constrained objective function; The constrained objective function is processed using the honey badger algorithm to obtain the initial optimal solution of the constrained objective function.

4. The method according to claim 1, wherein The honey badger algorithm is used to process the objective function to obtain an initial optimal solution of the objective function, including: Determining the feasible region of the objective function; The reverse learning method is used to perform population initialization processing on the honey badger algorithm to obtain a processed honey badger population; Using the objective function, obtaining fitness function values corresponding to a plurality of honey badgers included in the processed honey badger population; Determine the honey badger with the smallest fitness function value among the multiple honey badgers as the target honey badger, and the individual position of the target honey badger in the feasible domain; The individual position is taken as the initial optimal solution.

5. The method according to claim 1, wherein The performing Gaussian mutation processing on the initial optimal solution to obtain the target optimal solution of the objective function includes: Performing Gaussian mutation processing on the initial optimal value of the initial optimal solution to obtain the Gaussian-processed initial optimal value; Determine an initial optimal solution of the fitness function value corresponding to the initial optimal value after Gaussian processing; When the fitness function value is less than the initial optimal solution, taking the fitness function value as the first optimal solution; When the fitness function value is not less than the initial optimal solution, taking the initial optimal solution as the first optimal solution; When the current number of iterations of the Honey Badger algorithm reaches a preset maximum number of iterations, the first optimal solution is used as the target optimal solution.

6. The method according to any one of claims 1 to 5, characterized in that The new energy power supply equipment includes: photovoltaic equipment, wind power generation equipment, and the water electrolysis hydrogen production equipment includes: proton exchange membrane electrolysis equipment, alkaline electrolysis equipment.

7. A hydrogen production system scheduling device, characterized in that: include: a first determination module, configured to determine an objective function of the hydrogen production system based on a total operation and maintenance cost and a total hydrogen production income corresponding to the hydrogen production system, a first output power of a new energy power supply device in the hydrogen production system, a second output power of an energy storage device in the hydrogen production system, a first input power of a water electrolysis hydrogen production device in the hydrogen production system, and a second input power of a load in the hydrogen production system, wherein the total operation and maintenance cost is the operation and maintenance cost generated by the hydrogen production system within a preset unit operating time, the total hydrogen production income is the hydrogen production income generated by the hydrogen production system within the unit operating time, and the objective function is used to represent the total cost of the hydrogen production system; A first calculation module is used to process the objective function using a honey badger algorithm to obtain an initial optimal solution of the objective function; a second calculation module, configured to perform Gaussian variation processing on the initial optimal solution to obtain a target optimal solution of the objective function and a target optimal value corresponding to the target optimal solution, wherein the target optimal solution minimizes the total cost of the hydrogen production system, and the target optimal value is a control parameter when the hydrogen production system achieves the target optimal solution; A second determining module is configured to determine a hydrogen production scheduling strategy for the hydrogen production system based on the target optimal value, so that the hydrogen production system satisfies the target optimal solution; The first determination module is also used to: obtain a cost function corresponding to the hydrogen production system based on the total operation and maintenance cost and the total hydrogen production income; determine the power shortage penalty cost and the excess electricity cost of the hydrogen production system; obtain an electricity function corresponding to the hydrogen production system based on the first output power, the second output power, the first input power, and the second input power within the unit operating time; obtain a reliability function corresponding to the hydrogen production system based on the electricity function, the power shortage penalty cost, and the excess electricity cost; and obtain the objective function corresponding to the hydrogen production system based on the cost function and the reliability function.

8. A non-volatile storage medium, characterized in that: The non-volatile storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executed by the hydrogen production system scheduling method according to any one of claims 1 to 6.

9. An electronic device, characterized in that: include: One or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the hydrogen production system scheduling method described in any one of claims 1 to 6.

Images