Method and device for optimizing operation of multi-agent based electric-hydrogen coupling system, equipment and storage medium

Abstract

The present disclosure relates to the technical field of hydrogen energy optimization, and discloses a method, device and equipment for optimizing operation of an electricity-hydrogen coupling system based on multiple agents, and a storage medium. The method comprises obtaining a multiple-agent set of the electricity-hydrogen coupling system to be optimized, each agent in the multiple-agent set being obtained based on joint training of historical global information; obtaining local observation information required by each agent at every preset period, and determining an adjustment action of the agent based on the local observation information; obtaining preset constraint information corresponding to each agent and a preset action projection strategy corresponding thereto; and determining, for each agent, an optimized operation parameter of each device in the electricity-hydrogen coupling system in a preset time period based on the adjustment action of the agent, the preset constraint information and the preset action projection strategy. Based on centralized training and independent decision of the multiple-agent set, efficient and collaborative optimized operation of the electricity-hydrogen coupling system is achieved at a minute-level time scale.

Description

Technical Field

[0001] This disclosure relates to the field of hydrogen energy optimization technology, specifically to an optimized operation method, apparatus, equipment, and storage medium for an electro-hydrogen coupling system based on multiple agents. Background Technology

[0002] With the acceleration of the global energy transition, the proportion of renewable energy (such as wind and solar power) in the power system is gradually increasing, bringing complexity and uncertainty to power system dispatch. Electric-hydrogen coupling systems can provide inter-period energy storage through a process of electric hydrogen production-hydrogen storage-hydrogen power generation when facing renewable energy fluctuations. However, their high investment costs and low operating efficiency make them reliant on efficient dispatch optimization. Existing technologies typically utilize mixed-integer linear programming (MILP) or dynamic programming (DP) methods for dispatch optimization. However, MILP has high computational complexity and long processing time, making it unsuitable for minute-level optimization planning. DP's state space grows exponentially with the number of devices, making it difficult to handle the optimization planning of multi-device coupled systems. Therefore, existing dispatch optimization methods for electric-hydrogen coupling systems have untimely optimization responses and low optimization efficiency. Summary of the Invention

[0003] This disclosure addresses the problems existing in the prior art by providing an optimized operation method, apparatus, device, and storage medium for an electro-hydrogen coupling system based on multiple agents.

[0004] To achieve the above objectives, the technical solution adopted in this disclosure is as follows: A first aspect of this disclosure discloses a method for optimizing the operation of an electro-hydrogen coupling system based on a multi-agent approach, comprising: acquiring a set of multi-agents for the electro-hydrogen coupling system to be optimized, wherein the set of multi-agents includes agents corresponding to each device in the electro-hydrogen coupling system to be optimized, and each agent in the set of multi-agents is obtained through joint training based on historical global information, wherein the historical global information includes historical state information of each device in the electro-hydrogen coupling system to be optimized; acquiring local observation information required by each agent in the set of multi-agents at preset intervals, wherein the agent determines an adjustment action based on the local observation information; and so on. The preset period is less than or equal to one minute. The local observation information is the state information of the local devices in each device of the electro-hydrogen coupling system to be optimized, which is required when the agent makes a decision-making and adjustment action. The preset constraint information and the corresponding preset action projection strategy are obtained for each agent. For each agent, the optimized operating parameters of each device in the electro-hydrogen coupling system are determined based on the agent's adjustment action, the preset constraint information and the preset action projection strategy. The preset time period is a time period that starts at the current time and ends at a time later than the current time and equal to the preset period duration.

[0005] In some embodiments of this disclosure, the electro-hydrogen coupling system to be optimized includes at least an electrolyzer, a hydrogen gas turbine, and a hydrogen storage tank. The method further includes: acquiring multiple historical global information, including first historical observation state information of the electrolyzer, second historical observation state information of the hydrogen gas turbine, and third historical observation state information of the hydrogen storage tank; and using deep reinforcement learning to jointly train each initial agent in the initial multi-agent set based on the multiple historical global information to obtain the multi-agent set, which includes at least an electrolyzer agent corresponding to the electrolyzer, a hydrogen gas turbine agent corresponding to the hydrogen gas turbine, and a hydrogen storage tank agent corresponding to the hydrogen storage tank.

[0006] In some embodiments of this disclosure, obtaining the local observation information required by the intelligent agent includes: when the intelligent agent is the electrolyzer intelligent agent, obtaining first observation state information for the preset time period, the first observation state information including the preset output power of the renewable energy equipment supplying power to the electro-hydrogen coupling system during the preset time period, the preset power consumption of the load supplied by the electro-hydrogen coupling system during the preset time period, the expected hydrogen storage rate of the hydrogen storage tank equipment at the end of the preset time period, and the preset electricity price during the preset time period; when the intelligent agent is the hydrogen gas turbine intelligent agent, obtaining second observation state information for the preset time period, the second observation state information including the initial hydrogen production power of the electrolyzer equipment during the preset time period, the expected hydrogen consumption of the hydrogen gas turbine equipment during the preset time period, the preset power consumption, the expected hydrogen storage rate of the hydrogen storage tank equipment at the end of the preset time period, and the preset electricity price; when the intelligent agent is the hydrogen storage tank intelligent agent, obtaining third observation state information for the preset time period, the third observation state information including the initial hydrogen production power and the initial power generation power of the hydrogen gas turbine equipment during the preset time period.

[0007] In some embodiments of this disclosure, the determination of optimized operating parameters for each device in the electro-hydrogen coupling system within a preset time period based on the adjustment actions of the intelligent agent, the preset constraint information, and the preset action projection strategy includes: when the intelligent agent is the electrolyzer intelligent agent, the preset constraint information includes the first maximum ramp rate of the electrolyzer device, the maximum and minimum hydrogen production power thresholds of the electrolyzer device, the maximum hydrogen storage rate of the hydrogen storage tank device, and the maximum hydrogen storage capacity of the hydrogen storage tank device; obtaining the historical hydrogen storage rate of the hydrogen storage tank device at the time preceding the start time of the preset time period; obtaining the hydrogen production efficiency of the electrolyzer device; and using the preset action projection strategy corresponding to the electrolyzer intelligent agent, combined with the duration of the preset time period in the preset constraint information and the first maximum ramp rate, to optimize the operating parameters of the electrolyzer device. The adjustment actions of the cell agent are processed through action mapping to obtain the hydrogen production power adjustment amount; the historical hydrogen production power of the electrolyzer equipment in the previous preset cycle is obtained; based on the historical hydrogen production power and the hydrogen production power adjustment amount, the target hydrogen production power of the electrolyzer equipment in the preset time period is determined by the cell agent based on the first observation state information of the preset time period; the target hydrogen production power is constrained by the maximum hydrogen production power threshold, the minimum hydrogen production power threshold, the maximum hydrogen storage rate, the maximum hydrogen storage capacity, the historical hydrogen storage rate, the duration of the preset time period, and the hydrogen production efficiency to obtain the updated target hydrogen production power, which conforms to the preset constraint information; the updated target hydrogen production power is used as the optimized operating parameter of the electrolyzer equipment.

[0008] In some embodiments of this disclosure, the determination of optimized operating parameters for each device in the electro-hydrogen coupling system within a preset time period based on the agent's adjustment actions, the preset constraint information, and the preset action projection strategy includes: when the agent is the hydrogen gas turbine agent, the preset constraint information includes the second maximum ramp rate of the hydrogen gas turbine device, the maximum and minimum power generation thresholds of the hydrogen gas turbine device, the minimum hydrogen storage rate of the hydrogen storage tank device, and the maximum hydrogen storage capacity of the hydrogen storage tank device; obtaining the historical hydrogen storage rate of the hydrogen storage tank device at the time preceding the start time of the preset time period; obtaining the hydrogen consumption efficiency of the hydrogen gas turbine device; and using the preset action projection strategy corresponding to the hydrogen gas turbine agent, combined with the second maximum ramp rate in the preset constraint information and the duration of the preset time period, to optimize the operating parameters of the hydrogen gas turbine device. The adjustment actions of the machine intelligence agent are processed through action mapping to obtain the power adjustment amount of the hydrogen gas turbine; the historical power generation of the hydrogen gas turbine equipment in the previous preset cycle is obtained; based on the historical power generation and the power adjustment amount of the hydrogen gas turbine, the target power generation of the hydrogen gas turbine equipment in the preset time period is determined by the hydrogen gas turbine intelligence agent based on the second observation state information of the preset time period; the target power generation is constrained by the maximum power generation threshold, the minimum power generation threshold, the minimum hydrogen storage rate, the maximum hydrogen storage capacity, the historical hydrogen storage rate, the duration of the preset time period, and the hydrogen consumption efficiency to obtain an updated target power generation, which conforms to the preset constraint information; the updated target power generation is used as the optimized operating parameter of the hydrogen gas turbine equipment.

[0009] In some embodiments of this disclosure, determining the optimized operating parameters of each device in the electro-hydrogen coupling system within a preset time period based on the adjustment actions of the intelligent agent, the preset constraint information, and the preset action projection strategy includes: when the intelligent agent is the hydrogen storage tank intelligent agent, the preset constraint information includes the minimum unit hydrogen storage capacity, maximum unit hydrogen storage capacity, maximum hydrogen storage rate, and minimum hydrogen storage rate of the hydrogen storage tank device within the preset time period; using the preset action projection strategy corresponding to the hydrogen storage tank intelligent agent, combined with the minimum unit hydrogen storage capacity and maximum unit hydrogen storage capacity in the preset constraint information, to optimize the hydrogen storage... The adjustment actions of the tank agent are processed through action mapping to obtain the optimized unit hydrogen storage capacity and optimized unit hydrogen release capacity of the hydrogen storage tank equipment; the maximum hydrogen storage capacity of the electrolyzer equipment and the historical hydrogen storage rate at the previous moment before the start time of the preset time period are obtained; based on the historical hydrogen storage rate, the maximum hydrogen storage capacity, the optimized unit hydrogen storage capacity, and the optimized unit hydrogen release capacity, combined with the maximum hydrogen storage rate and the minimum hydrogen storage rate in the preset constraint information, the target hydrogen storage rate of the hydrogen storage tank equipment at the end time of the preset time period is calculated; the target hydrogen storage rate is used as the optimized operating parameter of the hydrogen storage tank equipment.

[0010] In some embodiments of this disclosure, the method further includes: determining the cost reward value of the multi-agent set based on the preset output power, the preset power consumption, the preset electricity price, the optimized operating parameters of the hydrogen gas turbine equipment in the electro-hydrogen coupling system, the duration of the preset time period, and the optimized operating parameters of the electrolyzer equipment; obtaining the maximum and minimum hydrogen storage rates of the hydrogen storage tank equipment; determining the storage boundary violation penalty value of the multi-agent set based on the maximum and minimum hydrogen storage rates and the optimized operating parameters of the hydrogen storage tank equipment; obtaining the first actual operating parameters of the hydrogen gas turbine equipment at the time preceding the start time of the preset time period; and obtaining the start time of the electrolyzer equipment at the time preceding the start time of the preset time period. The system obtains the second actual operating parameters of the previous moment; determines the operating parameter fluctuation penalty value of the multi-agent set based on the first actual operating parameters, the second actual operating parameters, the optimized operating parameters of the hydrogen gas turbine equipment, and the optimized operating parameters of the electrolyzer equipment; obtains the standard operating parameters of the hydrogen gas turbine equipment issued by the scheduling center during the preset time period; determines the scheduling tracking reward value of the multi-agent set based on the standard operating parameters and the optimized operating parameters of the hydrogen gas turbine equipment; determines the comprehensive reward value of the multi-agent set based on the cost reward value, the storage out-of-bounds penalty value, the operating parameter fluctuation penalty value, and the scheduling tracking reward value; and jointly optimizes each agent in the multi-agent set based on the comprehensive reward value.

[0011] A second aspect of this disclosure discloses an optimization operation device for an electro-hydrogen coupling system based on a multi-agent system, comprising: an acquisition unit, configured to acquire a set of multi-agent systems of the electro-hydrogen coupling system to be optimized, wherein the set of multi-agent systems includes agents corresponding to each device in the electro-hydrogen coupling system to be optimized, and each agent in the set of multi-agent systems is obtained through joint training based on historical global information, wherein the historical global information includes historical state information of each device in the electro-hydrogen coupling system to be optimized; the acquisition unit is further configured to acquire local observation information required by each agent in the set of multi-agent systems at preset intervals, wherein the agent determines an adjustment action based on the local observation information. The preset period is less than or equal to one minute, and the local observation information is the state information of the local devices in each device of the electro-hydrogen coupling system to be optimized, which is required when the agent makes a decision-making and adjustment action. The acquisition unit is also used to acquire the preset constraint information and the corresponding preset action projection strategy for each agent. The determination unit is used to determine the optimized operating parameters of each device in the electro-hydrogen coupling system within a preset time period for each agent, based on the agent's adjustment action, the preset constraint information, and the preset action projection strategy. The preset time period is a time period that starts at the current time and ends at a time later than the current time and equal to the preset period duration.

[0012] This disclosure also provides an electronic device, comprising: a memory for storing at least one instruction; and a processor for invoking the instruction stored in the memory to execute the optimized operation method of the multi-agent-based electro-hydrogen coupling system in the first aspect and any embodiment thereof.

[0013] This disclosure also provides a computer-readable storage medium storing at least one executable instruction, which is loaded and executed by a processor to implement the optimized operation method of the multi-agent-based electro-hydrogen coupling system in the first aspect and any embodiment of the first aspect.

[0014] This disclosure also provides a computer program product, which includes: computer program code, which, when executed by a computer, causes the computer to perform the optimized operation method of the multi-agent-based electro-hydrogen coupling system in the first aspect and any embodiment of the first aspect.

[0015] Compared with the prior art, this disclosure has the following beneficial effects: This scheme achieves efficient, safe, and collaborative optimization of an electro-hydrogen coupling system on a minute-scale timescale by constructing a multi-agent ensemble based on joint training using historical global information and independent decision-making from local observations. Each agent can quickly generate adjustment actions relying solely on local observation information, and by combining preset constraint information and action projection strategies, ensures that the output optimized operating parameters always meet physical and safety limitations. This method effectively overcomes the bottlenecks of high computational complexity and slow response of traditional scheduling optimization methods in high-dimensional, nonlinear, and real-time scheduling scenarios. It significantly improves the system's real-time adaptability and optimization response capability to renewable energy fluctuations, increases optimization efficiency, and simultaneously ensures equipment safety and lifespan, demonstrating strong engineering practicality. Attached Figure Description

[0016] Figure 1 This is a flowchart illustrating an optimized operation method for a multi-agent-based electro-hydrogen coupling system according to an embodiment of this disclosure. Figure 2 This is a block diagram of an optimized operation device for a multi-agent-based electro-hydrogen coupling system provided according to an embodiment of the present disclosure. Detailed Implementation

[0017] The present disclosure will now be further described with reference to the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solutions of the present disclosure and should not be construed as limiting the scope of protection of the present disclosure. It should be noted that the following detailed descriptions are exemplary and intended to provide further explanation of this application.

[0018] The acquisition, transmission, storage, use, and processing of data in this disclosed technical solution comply with relevant national laws and regulations. In the embodiments of this disclosure, certain existing industry solutions such as software, components, and models may be mentioned. These should be considered exemplary, intended only to illustrate the feasibility of implementing the technical solution of this disclosure, and do not imply that the applicant has already used or necessarily used such solutions.

[0019] All terms used in this disclosure have the same meaning as understood by one of ordinary skill in the art to which this disclosure pertains, unless otherwise specifically defined. It should also be understood that terms defined in general dictionaries should be interpreted as having meanings consistent with their meanings in the context of the relevant art, and not as idealized or highly formalized, unless expressly defined herein.

[0020] Example 1; The optimized operation method of the multi-agent-based electro-hydrogen coupling system in this embodiment can be applied to electronic devices with communication, computing, and data storage capabilities. Its specific process can be as follows: Figure 1 As shown, it includes: Step 110: Obtain a multi-agent set of the electro-hydrogen coupling system to be optimized. The multi-agent set includes agents corresponding to each device in the electro-hydrogen coupling system to be optimized. Each agent in the multi-agent set is obtained through joint training based on historical global information. The historical global information includes the historical state information of each device in the electro-hydrogen coupling system to be optimized.

[0021] The term "electro-hydrogen coupling system to be optimized" refers to an electro-hydrogen coupling system that requires optimization or adjustment of its operating parameters. The multi-agent ensemble refers to a collection of multiple agents, each representing a device within the electro-hydrogen coupling system. Agents are autonomous decision-making units trained using deep reinforcement learning. Historical state information corresponds one-to-one with the devices in the electro-hydrogen coupling system to be optimized. Historical state information represents the operating state of the corresponding device over a past period, serving as key input information for the agent of that device to make decisions. Historical global information refers to the set of state data for all devices in the entire electro-hydrogen coupling system to be optimized over a past period, used for joint training of the multi-agent model. Joint training refers to the centralized collaborative training of all initial agents to be trained using the same historical global information during the training phase, resulting in a multi-agent ensemble. This allows each agent in the ensemble to implicitly or explicitly perceive and respond to the state evolution of other agents and the overall electro-hydrogen coupling system to be optimized while learning its own strategy.

[0022] Specifically, the electro-hydrogen coupling system to be optimized includes at least an electrolyzer, a hydrogen gas turbine, and a hydrogen storage tank. The method further includes: acquiring multiple historical global information sets, including first historical observation state information of the electrolyzer, second historical observation state information of the hydrogen gas turbine, and third historical observation state information of the hydrogen storage tank; and using deep reinforcement learning to jointly train each initial agent in the initial multi-agent set based on the multiple historical global information sets to obtain the multi-agent set, which includes at least an electrolyzer agent corresponding to the electrolyzer, a hydrogen gas turbine agent corresponding to the hydrogen gas turbine, and a hydrogen storage tank agent corresponding to the hydrogen storage tank.

[0023] Among them, an electrolyzer is a device that uses electrical energy to decompose water into hydrogen and oxygen, thereby converting electrical energy into hydrogen energy. A hydrogen gas turbine is a thermal power generation device that uses hydrogen as fuel to generate electricity, thereby converting hydrogen energy back into electrical energy. A hydrogen storage tank is a pressure vessel or storage and transportation unit used to safely store high-pressure or cryogenic liquid hydrogen. The first historical observation state information refers to the observation information required for the electrolyzer agent to make action decisions; the second historical observation state information refers to the observation information required for the hydrogen gas turbine agent to make action decisions; and the third historical observation state information refers to the observation information required for the hydrogen storage tank agent to make action decisions.

[0024] It should be noted that the electro-hydrogen coupling system to be optimized includes at least one electrolyzer, at least one hydrogen gas turbine, and at least one hydrogen storage tank, with a corresponding intelligent agent for each device.

[0025] Furthermore, the agents in the multi-agent ensemble are trained using a centralized training method, and decision-making is performed using a distributed execution approach. Specifically, during the training phase, each agent in the multi-agent ensemble is jointly trained using minute-level historical global information combined with randomly added perturbation information. Once the multi-agent ensemble is acquired, each agent makes independent decisions based on its required local observation information, without the need for joint decision-making, which greatly improves decision-making efficiency and optimization efficiency.

[0026] Step 120: At preset intervals, for each agent in the multi-agent set, acquire the local observation information required by the agent. The agent determines the adjustment action based on the local observation information. The preset interval is less than or equal to one minute. The local observation information is the state information of the local devices in each device of the electro-hydrogen coupling system to be optimized, which is required when the agent makes the adjustment decision.

[0027] In this system, each agent is jointly trained based on the same historical global information. However, each agent makes decisions based on its corresponding local observation information. Therefore, this scheme employs a centralized training and distributed decision-making working mode for the agents. Adjustment actions refer to the adjustment information provided by the agent to the corresponding device.

[0028] For example, taking a preset cycle of one minute as an example, the local observation information required by each agent is acquired every minute, so that each agent can make a decision based on the local observation information it needs, thereby obtaining the adjustment action of the device corresponding to each agent.

[0029] Specifically, in step 120 above, obtaining the local observation information required by the intelligent agent includes: when the intelligent agent is the electrolyzer intelligent agent, obtaining first observation status information for the preset time period, the first observation status information including the preset output power of the renewable energy equipment supplying power to the electro-hydrogen coupling system during the preset time period, the preset power consumption of the load supplied by the electro-hydrogen coupling system during the preset time period, the expected hydrogen storage rate of the hydrogen storage tank equipment at the end of the preset time period, and the preset electricity price during the preset time period; when the intelligent agent is the hydrogen gas turbine intelligent agent, obtaining second observation status information for the preset time period, the second observation status information including the initial hydrogen production power of the electrolyzer equipment during the preset time period, the expected hydrogen consumption of the hydrogen gas turbine equipment during the preset time period, the preset power consumption, the expected hydrogen storage rate of the hydrogen storage tank equipment at the end of the preset time period, and the preset electricity price; when the intelligent agent is the hydrogen storage tank intelligent agent, obtaining third observation status information for the preset time period, the third observation status information including the initial hydrogen production power and the initial power generation power of the hydrogen gas turbine equipment during the preset time period.

[0030] Among them, renewable energy equipment refers to equipment that provides energy to the electro-hydrogen coupling system. Load refers to equipment that consumes energy from the electro-hydrogen coupling system. Preset output power refers to the power of energy generated by the renewable energy equipment within a preset time period. Preset power consumption refers to the power of energy consumed by the set load within a preset time period. Preset electricity price refers to the electricity price set within the preset time period. Initial hydrogen production power refers to the hydrogen production power of the electrolyzer equipment (without optimization by the electrolyzer intelligent agent) within a preset time period. Expected hydrogen consumption refers to the total amount of hydrogen expected to be consumed by the hydrogen gas turbine equipment within a preset time period. Expected hydrogen storage rate refers to the ratio of the amount of hydrogen stored in the hydrogen storage tank equipment to the maximum amount of hydrogen that the hydrogen storage tank equipment can store. Initial power generation power refers to the power of hydrogen consumption by the hydrogen gas turbine equipment (without optimization by the hydrogen gas turbine intelligent agent) within a preset time period.

[0031] Further, obtaining the expected hydrogen storage rate includes: calculating the expected hydrogen production based on the initial hydrogen production power of the electrolyzer equipment during the preset time period, the duration of the preset time period, and the hydrogen production efficiency; obtaining the historical actual hydrogen storage capacity of the hydrogen storage tank equipment at the moment before the start time of the preset time period; obtaining the expected hydrogen consumption of the hydrogen gas turbine equipment during the preset time period; obtaining the unit hydrogen loss and maximum hydrogen storage capacity of the hydrogen storage tank equipment; and determining the expected hydrogen storage rate based on the historical total hydrogen storage, the unit hydrogen loss, the expected hydrogen production, the expected hydrogen consumption, and the maximum hydrogen storage capacity.

[0032] For example, the expected hydrogen production is calculated based on the initial hydrogen production power of the electrolyzer equipment during the preset time period, the duration of the preset time period, and the hydrogen production efficiency, as shown in the following formula: ; in, This is for the projected hydrogen production. For hydrogen production efficiency. This represents the initial hydrogen production power. The duration of the preset time period.

[0033] For example, the expected hydrogen storage rate is determined based on the historical actual hydrogen storage capacity, the unit hydrogen loss, the expected hydrogen production, the expected hydrogen consumption, and the maximum hydrogen storage capacity, as shown in the following formula: ; ; in, This refers to the total amount of hydrogen stored in the hydrogen storage tank at the end of the preset time period. This represents the actual historical hydrogen storage capacity. This is for the projected hydrogen production. This represents the projected hydrogen consumption. This represents the amount of hydrogen lost per unit. This represents the initial hydrogen production power. The duration of the preset time period. To predict the hydrogen storage rate. This represents the maximum hydrogen storage capacity.

[0034] Furthermore, obtaining the expected hydrogen consumption includes: calculating the expected hydrogen consumption based on the initial power generation and power generation efficiency of the hydrogen gas turbine equipment during the preset time period.

[0035] For example, the expected hydrogen consumption is calculated based on the initial power generation and power generation efficiency of the hydrogen gas turbine equipment during the preset time period, as shown in the following formula: ; in, This represents the projected hydrogen consumption. This represents the initial power generation. For power generation efficiency.

[0036] Step 130: Obtain the preset constraint information and the corresponding preset action projection strategy for each agent.

[0037] Among them, the preset constraint information refers to the constraint information on the adjustment actions given by each agent, in order to avoid the risk of the corresponding device directly adjusting based on the adjustment actions given by the agent, resulting in the adjusted information exceeding the device's characteristics and thus causing damage to the device. The preset action projection strategy refers to using the preset constraint information to map the adjustment actions given by each agent to the adjustment information of the corresponding device, so as to obtain the optimized operating parameters of the device after adjustment that meet the preset constraint information.

[0038] Step 140: For each agent, based on the agent's adjustment action, the preset constraint information, and the preset action projection strategy, determine the optimized operating parameters of each device in the electro-hydrogen coupling system within a preset time period. The preset time period is a time period that starts at the current time and ends at a time later than the current time and equal to the preset period duration.

[0039] Specifically, in step 140 above, determining the optimized operating parameters of each device in the electro-hydrogen coupling system within a preset time period based on the agent's adjustment actions, the preset constraint information, and the preset action projection strategy includes: when the agent is the electrolyzer agent, the preset constraint information includes the first maximum ramp rate of the electrolyzer device, the maximum and minimum hydrogen production power thresholds of the electrolyzer device, the maximum hydrogen storage rate of the hydrogen storage tank device, and the maximum hydrogen storage capacity of the hydrogen storage tank device; obtaining the historical hydrogen storage rate of the hydrogen storage tank device at the time preceding the start time of the preset time period; obtaining the hydrogen production efficiency of the electrolyzer device; and using the preset action projection strategy corresponding to the electrolyzer agent, combined with the duration of the preset time period in the preset constraint information and the first maximum ramp rate, to optimize the operating parameters of each device in the electro-hydrogen coupling system within a preset time period. The adjustment actions of the electrolyzer are mapped to obtain the hydrogen production power adjustment amount; the historical hydrogen production power of the electrolyzer equipment in the previous preset cycle is obtained; based on the historical hydrogen production power and the hydrogen production power adjustment amount, the target hydrogen production power of the electrolyzer equipment in the preset time period is determined by the electrolyzer intelligence based on the first observation state information of the preset time period; the target hydrogen production power is constrained by the maximum hydrogen production power threshold, the minimum hydrogen production power threshold, the maximum hydrogen storage rate, the maximum hydrogen storage capacity, the historical hydrogen storage rate, the duration of the preset time period, and the hydrogen production efficiency to obtain the updated target hydrogen production power, which conforms to the preset constraint information; the updated target hydrogen production power is used as the optimized operating parameter of the electrolyzer equipment.

[0040] The adjustment action of the electrolyzer's intelligent agent refers to the power adjustment of the electrolyzer equipment. The hydrogen production power adjustment is the power adjustment of the electrolyzer equipment after being adjusted according to preset constraint information. The maximum hydrogen storage rate refers to the ratio of the hydrogen storage tank's storage capacity to its maximum hydrogen storage capacity. The maximum hydrogen storage capacity refers to the maximum capacity of hydrogen that the hydrogen storage tank can store in its brand-new, unused state. The updated target hydrogen production power refers to the hydrogen production power of the electrolyzer equipment at each moment within a preset time period, optimized based on the electrolyzer's intelligent agent and constrained by the physical limits of the equipment in the electro-hydrogen coupling system.

[0041] Furthermore, by combining the maximum hydrogen production power threshold, the minimum hydrogen production power threshold, the maximum hydrogen storage rate, the maximum hydrogen storage capacity, the historical hydrogen storage rate, the duration of the preset time period, and the hydrogen production efficiency to constrain the target hydrogen production power and obtain an updated target hydrogen production power, the following steps are taken: constraining the target hydrogen production power by combining the maximum hydrogen production power threshold and the minimum hydrogen production power threshold to obtain a constrained hydrogen production power; and then using the maximum hydrogen storage rate, the maximum hydrogen storage capacity, the historical hydrogen storage rate, the duration of the preset time period, and the hydrogen production efficiency to perform a secondary constraint process on the constrained hydrogen production power to obtain the updated target hydrogen production power.

[0042] For example, by using a preset action projection strategy corresponding to the electrolyzer agent, and combining the duration of the preset time period in the preset constraint information and the first maximum ramp rate, the adjustment action of the electrolyzer agent is processed by action mapping to obtain the hydrogen production power adjustment amount, as shown in the following formula: ; ; in, The first maximum climbing speed, The duration of the preset time period. This is the amount of hydrogen production power adjustment. The action is adjusted; t refers to the preset time period or the preset cycle.

[0043] For example, based on the historical hydrogen production power and the hydrogen production power adjustment amount, the target hydrogen production power determined by the electrolyzer agent for the electrolyzer equipment during the preset time period based on the first observation state information of the preset time period can be seen from the following formula: ; in, The target hydrogen production capacity. Historical hydrogen production capacity, The hydrogen production power adjustment amount is t-1, which refers to the previous preset time period or the previous cycle of the current preset cycle. The historical hydrogen production power is the same at each moment in the preset time period.

[0044] For example, by combining the maximum hydrogen production power threshold and the minimum hydrogen production power threshold, the target hydrogen production power is constrained to obtain the constrained hydrogen production power, as shown in the following formula: ; in, ). To constrain hydrogen production power. To achieve the target hydrogen production capacity, The minimum hydrogen production power threshold is t, which refers to a preset time period or the current preset cycle. This is the maximum hydrogen production power threshold.

[0045] For example, the target hydrogen production power is subjected to a secondary constraint process using the maximum hydrogen storage rate, the maximum hydrogen storage capacity, the historical hydrogen storage rate, the duration of the preset time period, and the hydrogen production efficiency to obtain the updated target hydrogen production power, as shown in the following formula: ; in, The updated target hydrogen production capacity. To constrain hydrogen production capacity, The maximum hydrogen storage rate is given by t, which refers to a preset time period or the current preset cycle. For hydrogen production efficiency. The duration of the preset time period. This represents the maximum hydrogen storage capacity. The historical hydrogen storage rate is the time preceding the start time Q of the preset time period.

[0046] Specifically, in step 140 above, determining the optimized operating parameters of each device in the electro-hydrogen coupling system within a preset time period based on the agent's adjustment actions, the preset constraint information, and the preset action projection strategy includes: when the agent is the hydrogen gas turbine agent, the preset constraint information includes the second maximum ramp rate of the hydrogen gas turbine device, the maximum and minimum power generation thresholds of the hydrogen gas turbine device, the minimum hydrogen storage rate of the hydrogen storage tank device, and the maximum hydrogen storage capacity of the hydrogen storage tank device; obtaining the historical hydrogen storage rate of the hydrogen storage tank device at the time preceding the start time of the preset time period; obtaining the hydrogen consumption efficiency of the hydrogen gas turbine device; and using the preset action projection strategy corresponding to the hydrogen gas turbine agent, combined with the second maximum ramp rate in the preset constraint information and the duration of the preset time period, to optimize the operating parameters of each device in the electro-hydrogen coupling system within a preset time period. The adjustment actions of the turbine intelligent agent are processed through action mapping to obtain the power adjustment amount of the hydrogen gas turbine; the historical power generation of the hydrogen gas turbine equipment in the previous preset cycle is obtained; based on the historical power generation and the power adjustment amount of the hydrogen gas turbine, the target power generation of the hydrogen gas turbine equipment in the preset time period is determined by the hydrogen gas turbine intelligent agent based on the second observation state information of the preset time period; the target power generation is constrained by the maximum power generation threshold, the minimum power generation threshold, the minimum hydrogen storage rate, the maximum hydrogen storage capacity, the historical hydrogen storage rate, the duration of the preset time period, and the hydrogen consumption efficiency to obtain an updated target power generation, which conforms to the preset constraint information; the updated target power generation is used as the optimized operating parameter of the hydrogen gas turbine equipment.

[0047] The adjustment actions of the hydrogen gas turbine intelligent agent are defined as the power regulation of the hydrogen gas turbine equipment. The power regulation of the hydrogen gas turbine is the power regulation of the hydrogen gas turbine equipment adjusted after pre-defined constraint information. The minimum hydrogen storage rate refers to the ratio of the minimum hydrogen storage capacity of the hydrogen storage tank equipment to its maximum hydrogen storage capacity. The updated target power generation refers to the power generation of the hydrogen gas turbine equipment at each moment within a preset time period, optimized based on the hydrogen gas turbine intelligent agent and constrained by the physical limits of the equipment in the electro-hydrogen coupling system.

[0048] Furthermore, the target power generation is constrained by combining the maximum power generation threshold, the minimum power generation threshold, the minimum hydrogen storage rate, the maximum hydrogen storage capacity, the historical hydrogen storage rate, the duration of the preset time period, and the hydrogen consumption efficiency to obtain an updated target power generation. The updated target power generation conforms to the preset constraint information, including: constraining the target power generation by combining the maximum power generation threshold and the minimum power generation threshold to obtain a constrained power generation; and performing a secondary constraint on the constrained power generation using the minimum hydrogen storage rate, the maximum hydrogen storage capacity, the historical hydrogen storage rate, the duration of the preset time period, and the hydrogen consumption efficiency to obtain the updated target power generation.

[0049] For example, by utilizing a preset action projection strategy corresponding to the hydrogen gas turbine agent, and combining the second maximum ramp rate in the preset constraint information and the duration of the preset time period, the adjustment actions of the hydrogen gas turbine agent are processed by action mapping to obtain the hydrogen gas turbine power adjustment amount, as shown in the following formula: ; in, , The second maximum climbing speed. The duration of the preset time period. This refers to the power regulation of the hydrogen gas turbine. The action is adjusted; t refers to the preset time period or the preset cycle.

[0050] For example, based on the historical power generation and the power adjustment of the hydrogen gas turbine, the target power generation of the hydrogen gas turbine device determined by the hydrogen gas turbine agent for the preset time period based on the second observation state information of the preset time period can be seen from the following formula: ; in, The historical power generation is represented by t-1, which is either the previous time period of the preset time period or the previous preset cycle of the current preset cycle. The historical power generation at each moment in the previous time period of the preset time period is the same. This refers to the power regulation of the hydrogen gas turbine. The target power generation capacity.

[0051] For example, by combining the maximum power generation threshold and the minimum power generation threshold to constrain the target power generation, the constrained power generation is obtained, as shown in the following formula: ; in, To constrain power generation. The target power generation capacity. This is the minimum power generation threshold. This is the maximum power generation threshold. ).

[0052] For example, the minimum hydrogen storage rate, the maximum hydrogen storage capacity, the historical hydrogen storage rate, the duration of the preset time period, and the hydrogen consumption efficiency are used to perform a secondary constraint process on the constrained power generation to obtain the updated target power generation, as shown in the following formula: ; in, To constrain power generation. This represents the minimum hydrogen storage rate. This represents the maximum hydrogen storage capacity. This is the updated target power generation capacity. This refers to hydrogen consumption efficiency. The historical hydrogen storage rate is the time preceding the start time Q of the preset time period. The duration of the preset time period.

[0053] Specifically, in step 140 above, determining the optimized operating parameters of each device in the electro-hydrogen coupling system within a preset time period based on the agent's adjustment actions, the preset constraint information, and the preset action projection strategy includes: when the agent is the hydrogen storage tank agent, the preset constraint information includes the minimum unit hydrogen storage capacity, maximum unit hydrogen storage capacity, maximum hydrogen storage rate, and minimum hydrogen storage rate of the hydrogen storage tank device within the preset time period; using the preset action projection strategy corresponding to the hydrogen storage tank agent, combined with the minimum unit hydrogen storage capacity and maximum unit hydrogen storage capacity in the preset constraint information, to optimize the operating parameters of each device in the electro-hydrogen coupling system within the preset time period. The adjustment actions of the hydrogen storage tank's intelligent agent are processed through action mapping to obtain the optimized unit hydrogen storage capacity and optimized unit hydrogen release capacity of the hydrogen storage tank equipment; the maximum hydrogen storage capacity of the electrolyzer equipment and the historical hydrogen storage rate at the previous moment before the start time of the preset time period are obtained; based on the historical hydrogen storage rate, the maximum hydrogen storage capacity, the optimized unit hydrogen storage capacity, and the optimized unit hydrogen release capacity, combined with the maximum hydrogen storage rate and the minimum hydrogen storage rate in the preset constraint information, the target hydrogen storage rate of the hydrogen storage tank equipment at the end time of the preset time period is calculated; the target hydrogen storage rate is used as the optimized operating parameter of the hydrogen storage tank equipment.

[0054] The minimum unit hydrogen storage capacity refers to the minimum amount of hydrogen that the hydrogen storage tank equipment can store within a preset time period. The maximum unit hydrogen storage capacity refers to the maximum amount of hydrogen that the hydrogen storage tank equipment can store within a preset time period. The optimized unit hydrogen storage amount refers to the amount of hydrogen that the hydrogen storage tank equipment should store within a preset time period; the optimized unit hydrogen release amount refers to the amount of hydrogen that the hydrogen storage tank equipment should release within a preset time period.

[0055] Furthermore, the adjustment actions include hydrogen storage adjustment actions and hydrogen release adjustment actions. Using a preset action projection strategy corresponding to the hydrogen storage tank agent, and combining the minimum and maximum unit hydrogen storage capacities in the preset constraint information, the adjustment actions of the hydrogen storage tank agent are processed by action mapping to obtain the optimized unit hydrogen storage capacity and optimized unit hydrogen release capacity of the hydrogen storage tank equipment. This includes: using a preset action projection strategy corresponding to the hydrogen storage tank agent, and combining the minimum and maximum unit hydrogen storage capacities in the preset constraint information, the hydrogen storage adjustment actions of the hydrogen storage tank agent are processed by action mapping to obtain the optimized unit hydrogen storage capacity of the hydrogen storage tank equipment; using a preset action projection strategy corresponding to the hydrogen storage tank agent, and combining the minimum and maximum unit hydrogen storage capacities in the preset constraint information, the optimized unit hydrogen release capacity of the hydrogen storage tank agent is processed by action mapping to obtain the optimized unit hydrogen release capacity of the hydrogen storage tank equipment.

[0056] For example, by utilizing the preset action projection strategy corresponding to the hydrogen storage tank agent, and combining the minimum and maximum unit hydrogen storage capacities in the preset constraint information, the hydrogen storage adjustment actions of the hydrogen storage tank agent are processed through action mapping to obtain the optimized unit hydrogen storage capacity of the hydrogen storage tank equipment, as shown in the following formula: ; in, To optimize the unit hydrogen storage capacity. The duration of the preset time period. This is for hydrogen storage regulation. This represents the minimum unit hydrogen storage capacity. This represents the maximum unit hydrogen storage capacity.

[0057] For example, by utilizing the preset action projection strategy corresponding to the hydrogen storage tank agent, and combining the minimum unit hydrogen storage capacity and the maximum unit hydrogen storage capacity in the preset constraint information, the optimized unit hydrogen release amount of the hydrogen storage tank agent is processed by action mapping to obtain the optimized unit hydrogen release amount of the hydrogen storage tank equipment, as shown in the following formula: ; in, To optimize the amount of hydrogen released per unit. The duration of the preset time period. This is a hydrogen release regulation action. This represents the minimum unit hydrogen storage capacity. This represents the maximum unit hydrogen storage capacity.

[0058] For example, based on the historical hydrogen storage rate, the maximum hydrogen storage capacity, the optimized unit hydrogen storage amount, and the optimized unit hydrogen release amount, combined with the maximum hydrogen storage rate and the minimum hydrogen storage rate in the preset constraint information, the target hydrogen storage rate of the hydrogen storage tank equipment at the end of the preset time period can be calculated, as shown in the following formula: ; ; in, The target hydrogen storage rate is defined as the end time k of the preset time period t. The historical hydrogen storage rate is the time preceding the start time Q of the preset time period. To optimize the unit hydrogen storage capacity; Optimize the amount of hydrogen released per unit. This represents the maximum hydrogen storage capacity. This represents the self-loss coefficient of the hydrogen storage tank equipment. To improve the hydrogen filling efficiency of hydrogen storage tank equipment. The hydrogen release efficiency of the hydrogen storage tank equipment. This represents the maximum hydrogen storage rate. This represents the minimum hydrogen storage rate.

[0059] In some examples, the method further includes: determining the cost reward value of the multi-agent ensemble based on the preset output power, the preset power consumption, the preset electricity price, the optimized operating parameters of the hydrogen gas turbine equipment in the electro-hydrogen coupling system, the duration of the preset time period, and the optimized operating parameters of the electrolyzer equipment; obtaining the maximum and minimum hydrogen storage rates of the hydrogen storage tank equipment; determining the storage out-of-bounds penalty value of the multi-agent ensemble based on the maximum and minimum hydrogen storage rates and the optimized operating parameters of the hydrogen storage tank equipment; obtaining the first actual operating parameters of the hydrogen gas turbine equipment at the time preceding the start time of the preset time period; and obtaining the first actual operating parameters of the electrolyzer equipment at the time preceding the start time of the preset time period. The system calculates the second actual operating parameters at a given moment; determines the operating parameter fluctuation penalty value of the multi-agent set based on the first actual operating parameters, the second actual operating parameters, the optimized operating parameters of the hydrogen gas turbine equipment, and the optimized operating parameters of the electrolyzer equipment; obtains the standard operating parameters of the hydrogen gas turbine equipment issued by the scheduling center during the preset time period; determines the scheduling tracking reward value of the multi-agent set based on the standard operating parameters and the optimized operating parameters of the hydrogen gas turbine equipment; determines the comprehensive reward value of the multi-agent set based on the cost reward value, the storage out-of-bounds penalty value, the operating parameter fluctuation penalty value, and the scheduling tracking reward value; and jointly optimizes each agent in the multi-agent set based on the comprehensive reward value.

[0060] The cost reward value refers to the cost of purchasing electricity within a preset time period. The storage over-limit penalty value refers to the penalty value when the hydrogen stored in the hydrogen tank exceeds the hydrogen storage threshold at the end of the preset time period. The operating parameter fluctuation penalty value refers to the penalty value for power fluctuations between the power of the hydrogen gas turbine equipment and the electrolyzer equipment in the preset time period and the power in the previous preset time period. The standard operating parameters refer to the power generation of the hydrogen gas turbine equipment within the preset time period issued by the dispatch center. The dispatch tracking reward value refers to the reward value when the target power generation, after optimization and adjustment by the hydrogen gas turbine intelligent agent and preset constraint information, matches the standard operating parameters. The dispatch tracking reward value is maximized when the target power generation and the standard operating parameters are the same.

[0061] For example, based on the preset power output, the preset power consumption, the preset electricity price, the optimized operating parameters of the hydrogen gas turbine equipment in the electro-hydrogen coupling system, the duration of the preset time period, and the optimized operating parameters of the electrolyzer equipment, the cost reward value of the multi-agent set is determined, as shown in the following formula: ; in, Preset power consumption; This is the preset output power. The optimized operating parameters for the hydrogen gas turbine equipment, i.e., the updated target power generation. The optimized operating parameters for the electrolyzer equipment, i.e., the updated target hydrogen production power. When A value greater than 0 indicates purchasing electricity from the grid. A value less than 0 indicates that electricity is sold to the grid.

[0062]

[0063] in, ; = ; The duration of the preset time period. This is the preset cost coefficient. This is the cost incentive value.

[0064] For example, the storage out-of-bounds penalty value of the multi-agent set is determined based on the maximum hydrogen storage rate, the minimum hydrogen storage rate, and the optimized operating parameters of the hydrogen storage tank equipment, as shown in the following formula: ; in, To store out-of-bounds penalty values. The optimized operating parameters for hydrogen storage tank equipment, i.e., the target hydrogen storage rate. This represents the maximum hydrogen storage rate. This represents the minimum hydrogen storage rate.

[0065] For example, the operating parameter fluctuation penalty value of the multi-agent set is determined based on the first actual operating parameters, the second actual operating parameters, the optimized operating parameters of the hydrogen gas turbine equipment, and the optimized operating parameters of the electrolyzer equipment, as shown in the following formula: ; in, The optimized operating parameters for the hydrogen gas turbine equipment, i.e., the updated target power generation. The optimized operating parameters for the electrolyzer equipment are the updated target hydrogen production power. This is a penalty value for fluctuations in operating parameters. This is the first actual operating parameter. This is the second actual operating parameter.

[0066] For example, the scheduling and tracking reward value of the multi-agent set is determined based on the standard operating parameters and the optimized operating parameters of the hydrogen gas turbine equipment, as shown in the following formula: ; in, The optimized operating parameters for the hydrogen gas turbine equipment, i.e., the updated target power generation. These are the standard operating parameters. To schedule and track reward values.

[0067] For example, the comprehensive reward value of the multi-agent set is determined based on the cost reward value, the storage out-of-bounds penalty value, the operating parameter fluctuation penalty value, and the scheduling tracking reward value, as shown in the following formula: ; in, The total reward value; Cost incentive value; To store out-of-bounds penalty values. This is a penalty value for fluctuations in operating parameters. To schedule and track reward values. This is used to store the weight coefficients for out-of-bounds penalties. The weighting coefficient for penalizing fluctuations in operating parameters; This is the weighting coefficient for scheduling tracking rewards. , , These are all preset values, which can be set according to actual needs.

[0068] Therefore, by constructing a multi-objective comprehensive reward mechanism that includes cost rewards, storage out-of-bounds penalties, operating parameter fluctuation penalties, and scheduling tracking rewards, multiple agents are effectively guided to collaboratively optimize the operation of the electro-hydrogen coupling system within a minute-level scheduling cycle. Specifically, the cost reward accurately reflects electricity purchase expenditure, incentivizing the system to prioritize the use of low-cost electricity or renewable energy for hydrogen production; the storage out-of-bounds penalty ensures that the hydrogen storage tank always operates within a safe capacity range, avoiding the risks of overpressure or empty tanks; the operating parameter fluctuation penalty suppresses frequent and drastic changes in the power of the electrolyzer and hydrogen gas turbine, extending equipment lifespan; and the scheduling tracking reward enhances the responsiveness to dispatch center instructions, ensuring the system's reliability as a flexible adjustment resource. Based on this comprehensive reward value, joint optimization training of multiple agents not only significantly improves the economy, safety, and stability of scheduling but also achieves high-precision tracking of superior dispatch instructions. This overcomes the shortcomings of traditional methods in real-time performance, multi-objective coordination, and engineering constraint integration, providing an efficient, robust, and schedulable intelligent operation optimization scheme for the electro-hydrogen coupling system.

[0069] In summary, a multi-agent set of the electro-hydrogen coupling system to be optimized is obtained. This set includes agents corresponding to each device in the system, and each agent is jointly trained based on historical global information, which includes the historical state information of each device in the system. At preset intervals, for each agent in the multi-agent set, the required local observation information is obtained. Based on this local observation information, the agent determines an adjustment action. The preset interval is less than or equal to one minute, and the local observation information is the state information of the local devices in the electro-hydrogen coupling system required by the agent when making the adjustment decision. Preset constraint information and a corresponding preset action projection strategy are obtained for each agent. For each agent, based on the agent's adjustment action, the preset constraint information, and the preset action projection strategy, optimized operating parameters for each device in the electro-hydrogen coupling system are determined within a preset time period. This preset time period starts at the current time and ends at a time later than the current time but equal to the preset interval. By constructing a multi-agent ensemble based on joint training using historical global information and independent decision-making from local observations, efficient, safe, and collaborative optimization of the electro-hydrogen coupling system was achieved on a minute-level timescale. Each agent can quickly generate adjustment actions relying solely on local observation information, and by combining preset constraint information and action projection strategies, the output optimized operating parameters are ensured to always meet physical and safety limitations. This method effectively overcomes the bottlenecks of traditional scheduling optimization methods, such as high computational complexity and slow response in high-dimensional, nonlinear, and real-time scheduling scenarios. It significantly improves the system's real-time adaptability and response capability to renewable energy fluctuations, increases optimization accuracy and efficiency, while ensuring equipment safety and lifespan, demonstrating strong engineering practicality.

[0070] Specifically, by modeling the electrolyzer, hydrogen storage tank, and hydrogen gas turbine as independent intelligent agents, autonomous decision-making and collaborative operation of each device are achieved. Compared to single-agent or centralized control methods, this centralized training and distributed decision-making approach improves the robustness of system decision-making and fully leverages the complementary characteristics of each device to optimize overall performance. It also enhances the timeliness and flexibility of decision-making in the electro-hydrogen coupling system, enabling minute-level decision-making by utilizing independent agents, significantly improving the system's response efficiency. Furthermore, each agent can directly learn the optimal scheduling strategy from historical global information, exhibiting adaptability to uncertainties in power output and fluctuations in electricity prices, avoiding the difficulties or deviations in results encountered by traditional scheduling optimization methods in complex nonlinear environments.

[0071] Example 2: Another embodiment of this application relates to an optimized operation device for a multi-agent-based electro-hydrogen coupling system. The implementation details of this embodiment's optimized operation device for an electro-hydrogen coupling system are described below. The following details are provided for ease of understanding and are not essential for implementing this solution. A schematic diagram of the optimized operation device 20 for the multi-agent-based electro-hydrogen coupling system in this embodiment can be seen as follows: Figure 2 As shown, it includes an acquisition unit 200 and a determination unit 210.

[0072] The acquisition unit 200 is used to acquire a set of multiple agents for the electro-hydrogen coupling system to be optimized. The set of multiple agents includes agents corresponding to each device in the electro-hydrogen coupling system to be optimized. Each agent in the set of multiple agents is obtained by joint training based on historical global information. The historical global information includes the historical state information of each device in the electro-hydrogen coupling system to be optimized.

[0073] The acquisition unit 200 is further configured to acquire local observation information required by each agent in the multi-agent set at preset intervals, and the agent determines an adjustment action based on the local observation information. The preset interval is less than or equal to one minute, and the local observation information is the state information of local devices in each device of the electro-hydrogen coupling system to be optimized required when the agent makes the adjustment decision.

[0074] The acquisition unit 200 is also used to acquire the preset constraint information and the corresponding preset action projection strategy for each intelligent agent.

[0075] The determining unit 210 is used to determine, for each agent, the optimized operating parameters of each device in the electro-hydrogen coupling system within a preset time period based on the agent's adjustment action, the preset constraint information, and the preset action projection strategy. The preset time period is a time period that starts at the current time and ends at a time later than the current time and equal to the preset period duration.

[0076] In some examples, the electro-hydrogen coupling system to be optimized includes at least an electrolyzer, a hydrogen gas turbine, and a hydrogen storage tank. The device further includes: acquiring multiple historical global information sets, including first historical observation state information of the electrolyzer, second historical observation state information of the hydrogen gas turbine, and third historical observation state information of the hydrogen storage tank; and using deep reinforcement learning to jointly train each initial agent in the initial multi-agent set based on the multiple historical global information sets to obtain the multi-agent set, which includes at least an electrolyzer agent corresponding to the electrolyzer, a hydrogen gas turbine agent corresponding to the hydrogen gas turbine, and a hydrogen storage tank agent corresponding to the hydrogen storage tank.

[0077] In some examples, when the device is used to acquire the local observation information required by the intelligent agent, it is specifically used to: when the intelligent agent is the electrolyzer intelligent agent, acquire first observation state information for the preset time period, the first observation state information including the preset output power of the renewable energy equipment supplying power to the electro-hydrogen coupling system during the preset time period, the preset power consumption of the load supplied by the electro-hydrogen coupling system during the preset time period, the expected hydrogen storage rate of the hydrogen storage tank equipment at the end of the preset time period, and the preset electricity price during the preset time period; when the intelligent agent is the hydrogen gas turbine intelligent agent, acquire second observation state information for the preset time period, the second observation state information including the initial hydrogen production power of the electrolyzer equipment during the preset time period, the expected hydrogen consumption of the hydrogen gas turbine equipment during the preset time period, the preset power consumption, the expected hydrogen storage rate of the hydrogen storage tank equipment at the end of the preset time period, and the preset electricity price; when the intelligent agent is the hydrogen storage tank intelligent agent, acquire third observation state information for the preset time period, the third observation state information including the initial hydrogen production power and the initial power generation power of the hydrogen gas turbine equipment during the preset time period.

[0078] In some examples, when the device is used to determine the optimized operating parameters of each device in the electro-hydrogen coupling system within a preset time period based on the agent's adjustment actions, the preset constraint information, and the preset action projection strategy, it is specifically used for: when the agent is the electrolyzer agent, the preset constraint information includes the first maximum ramp rate of the electrolyzer device, the maximum hydrogen production power threshold and the minimum hydrogen production power threshold of the electrolyzer device, the maximum hydrogen storage rate of the hydrogen storage tank device, and the maximum hydrogen storage capacity of the hydrogen storage tank device; obtaining the historical hydrogen storage rate of the hydrogen storage tank device at the time before the start time of the preset time period; obtaining the hydrogen production efficiency of the electrolyzer device; and using the preset action projection strategy corresponding to the electrolyzer agent, combined with the duration of the preset time period in the preset constraint information and the first maximum ramp rate, to optimize the operating parameters of each device in the electrolyzer device. The adjustment actions of the electrolyzer's intelligent agent are processed through action mapping to obtain the hydrogen production power adjustment amount; the historical hydrogen production power of the electrolyzer equipment in the previous preset cycle is obtained; based on the historical hydrogen production power and the hydrogen production power adjustment amount, the target hydrogen production power determined by the electrolyzer's intelligent agent for the electrolyzer equipment in the preset time period is determined based on the first observation state information of the preset time period; the target hydrogen production power is constrained by the maximum hydrogen production power threshold, the minimum hydrogen production power threshold, the maximum hydrogen storage rate, the maximum hydrogen storage capacity, the historical hydrogen storage rate, the duration of the preset time period, and the hydrogen production efficiency to obtain an updated target hydrogen production power, which conforms to the preset constraint information; the updated target hydrogen production power is used as the optimized operating parameter of the electrolyzer equipment.

[0079] In some examples, when the device is used to determine the optimized operating parameters of each device in the electro-hydrogen coupling system within a preset time period based on the agent's adjustment actions, the preset constraint information, and the preset action projection strategy, it is specifically used for: when the agent is the hydrogen gas turbine agent, the preset constraint information includes the second maximum ramp rate of the hydrogen gas turbine device, the maximum power generation threshold and the minimum power generation threshold of the hydrogen gas turbine device, the minimum hydrogen storage rate of the hydrogen storage tank device, and the maximum hydrogen storage capacity of the hydrogen storage tank device; obtaining the historical hydrogen storage rate of the hydrogen storage tank device at the time preceding the start time of the preset time period; obtaining the hydrogen consumption efficiency of the hydrogen gas turbine device; and using the preset action projection strategy corresponding to the hydrogen gas turbine agent, combined with the second maximum ramp rate in the preset constraint information and the duration of the preset time period, to optimize the operating parameters of the hydrogen gas turbine device. The adjustment actions of the gas turbine intelligent agent are processed through action mapping to obtain the power adjustment amount of the hydrogen gas turbine; the historical power generation of the hydrogen gas turbine equipment in the previous preset cycle is obtained; based on the historical power generation and the power adjustment amount of the hydrogen gas turbine, the target power generation of the hydrogen gas turbine equipment in the preset time period is determined by the hydrogen gas turbine intelligent agent based on the second observation state information of the preset time period; the target power generation is constrained by the maximum power generation threshold, the minimum power generation threshold, the minimum hydrogen storage rate, the maximum hydrogen storage capacity, the historical hydrogen storage rate, the duration of the preset time period, and the hydrogen consumption efficiency to obtain an updated target power generation, which conforms to the preset constraint information; the updated target power generation is used as the optimized operating parameter of the hydrogen gas turbine equipment.

[0080] In some examples, when the device is used to determine the optimized operating parameters of each device in the electro-hydrogen coupling system within a preset time period based on the agent's adjustment actions, the preset constraint information, and the preset action projection strategy, it is specifically used as follows: when the agent is the hydrogen storage tank agent, the preset constraint information includes the minimum unit hydrogen storage capacity, maximum unit hydrogen storage capacity, maximum hydrogen storage rate, and minimum hydrogen storage rate of the hydrogen storage tank device within the preset time period; using the preset action projection strategy corresponding to the hydrogen storage tank agent, combined with the minimum unit hydrogen storage capacity and maximum unit hydrogen storage capacity in the preset constraint information, to optimize the operating parameters of each device in the electro-hydrogen coupling system within the preset time period. The adjustment actions of the hydrogen storage tank's intelligent agent are processed through action mapping to obtain the optimized unit hydrogen storage capacity and optimized unit hydrogen release capacity of the hydrogen storage tank equipment; the maximum hydrogen storage capacity of the electrolyzer equipment and the historical hydrogen storage rate at the previous moment before the start time of the preset time period are obtained; based on the historical hydrogen storage rate, the maximum hydrogen storage capacity, the optimized unit hydrogen storage capacity, and the optimized unit hydrogen release capacity, combined with the maximum hydrogen storage rate and the minimum hydrogen storage rate in the preset constraint information, the target hydrogen storage rate of the hydrogen storage tank equipment at the end time of the preset time period is calculated; the target hydrogen storage rate is used as the optimized operating parameter of the hydrogen storage tank equipment.

[0081] In some examples, the device is also used to: determine the cost reward value of the multi-agent ensemble based on the preset output power, the preset power consumption, the preset electricity price, the optimized operating parameters of the hydrogen gas turbine equipment in the electro-hydrogen coupling system, the duration of the preset time period, and the optimized operating parameters of the electrolyzer equipment; obtain the maximum and minimum hydrogen storage rates of the hydrogen storage tank equipment; determine the storage out-of-bounds penalty value of the multi-agent ensemble based on the maximum and minimum hydrogen storage rates and the optimized operating parameters of the hydrogen storage tank equipment; obtain the first actual operating parameters of the hydrogen gas turbine equipment at the time preceding the start time of the preset time period; and obtain the first actual operating parameters of the electrolyzer equipment at the time preceding the start time of the preset time period. The system calculates the second actual operating parameters at a given moment; determines the operating parameter fluctuation penalty value of the multi-agent set based on the first actual operating parameters, the second actual operating parameters, the optimized operating parameters of the hydrogen gas turbine equipment, and the optimized operating parameters of the electrolyzer equipment; obtains the standard operating parameters of the hydrogen gas turbine equipment issued by the scheduling center during the preset time period; determines the scheduling tracking reward value of the multi-agent set based on the standard operating parameters and the optimized operating parameters of the hydrogen gas turbine equipment; determines the comprehensive reward value of the multi-agent set based on the cost reward value, the storage out-of-bounds penalty value, the operating parameter fluctuation penalty value, and the scheduling tracking reward value; and jointly optimizes each agent in the multi-agent set based on the comprehensive reward value.

[0082] It is worth mentioning that all units involved in this embodiment are logical units. In practical applications, a logical unit can be a physical unit, a part of a physical unit, or a combination of multiple physical units. Furthermore, to highlight the innovative aspects of this application, this embodiment does not introduce units that are not closely related to solving the technical problems proposed in this application; however, this does not mean that other units are absent in this embodiment.

[0083] Example 3: This disclosure also provides an electronic device, comprising: a memory for storing at least one instruction; and a processor for calling the instruction stored in the memory to execute the optimized operation method of the multi-agent-based electro-hydrogen coupling system in any of the above embodiments.

[0084] Example 4: This disclosure also provides a computer-readable storage medium storing at least one executable instruction, which is loaded and executed by a processor to implement the optimized operation method of the multi-agent-based electro-hydrogen coupling system in any of the above embodiments.

[0085] Example 5: This disclosure also provides a computer program product, which includes computer program code. When the computer program code is run by a computer, it causes the computer to execute the optimized operation method of the multi-agent-based electro-hydrogen coupling system in any of the above embodiments.

[0086] Those skilled in the art will understand that embodiments of this disclosure can be provided as methods, systems, or computer program products. Therefore, this disclosure can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this disclosure can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0087] This disclosure is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations 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, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1A device that provides the functions specified in one or more boxes.

[0088] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0089] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0090] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0091] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0092] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, 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 technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0093] It should be noted that the terms "first," "second," and similar terms used in this disclosure do not indicate any order, quantity, or importance, but are merely used to distinguish different parts. Terms such as "including" or "contains" mean that the element preceding the word covers the element listed after the word, and do not exclude the possibility of covering other elements as well.

[0094] Although operations are described in a specific order in the accompanying drawings in this disclosure, it should not be construed as requiring these operations to be performed in the specific order or serial order shown, or requiring all of the shown operations to obtain the desired result. In certain environments, multitasking and parallel processing may be advantageous.

[0095] Finally, it should be noted that the above content is only used to illustrate the technical solution of this disclosure, and is not intended to limit the scope of protection of this disclosure. Simple modifications or equivalent substitutions made by those skilled in the art to the technical solution of this disclosure do not depart from the substance and scope of the technical solution of this disclosure.

Claims

1. An optimized operation method for a multi-agent-based electro-hydrogen coupling system, characterized in that, include: Obtain a multi-agent set of the electro-hydrogen coupling system to be optimized. The multi-agent set includes agents corresponding to each device in the electro-hydrogen coupling system to be optimized. Each agent in the multi-agent set is obtained through joint training based on historical global information. The historical global information includes the historical state information of each device in the electro-hydrogen coupling system to be optimized. Every preset period, for each agent in the multi-agent set, the local observation information required by the agent is obtained, and the agent determines the adjustment action based on the local observation information. The duration of the preset period is less than or equal to one minute, and the local observation information is the state information of the local devices in each device of the electro-hydrogen coupling system to be optimized required when the agent makes the decision on the adjustment action. Obtain the preset constraint information and the corresponding preset action projection strategy for each intelligent agent; For each agent, the optimized operating parameters of each device in the electro-hydrogen coupling system are determined based on the agent's adjustment actions, the preset constraint information, and the preset action projection strategy within a preset time period. The preset time period is a time period that starts at the current time and ends at a time later than the current time and equal to the preset period duration.

2. The optimized operation method for a multi-agent-based electro-hydrogen coupling system according to claim 1, characterized in that, The electro-hydrogen coupling system to be optimized includes at least an electrolyzer, a hydrogen gas turbine, and a hydrogen storage tank. The method further includes: Acquire multiple pieces of historical global information, including first historical observation status information of the electrolyzer equipment, second historical observation status information of the hydrogen gas turbine equipment, and third historical observation status information of the hydrogen storage tank equipment; By utilizing deep reinforcement learning and jointly training each initial agent in the initial multi-agent set based on multiple historical global information, the multi-agent set is obtained. The multi-agent set includes at least an electrolyzer agent corresponding to the electrolyzer equipment, a hydrogen gas turbine agent corresponding to the hydrogen gas turbine equipment, and a hydrogen storage tank agent corresponding to the hydrogen storage tank equipment.

3. The optimized operation method for a multi-agent-based electro-hydrogen coupling system according to claim 2, characterized in that, The acquisition of the local observation information required by the agent includes: When the intelligent agent is the electrolyzer intelligent agent, the first observation status information of the preset time period is obtained. The first observation status information includes the preset output power of the renewable energy equipment that supplies power to the electro-hydrogen coupling system in the preset time period, the preset power consumption of the load supplied by the electro-hydrogen coupling system in the preset time period, the expected hydrogen storage rate of the hydrogen storage tank equipment at the end time of the preset time period, and the preset electricity price of the preset time period. When the intelligent agent is the hydrogen gas turbine intelligent agent, the second observation status information of the preset time period is obtained. The second observation status information includes the initial hydrogen production power of the electrolyzer equipment in the preset time period, the expected hydrogen consumption of the hydrogen gas turbine equipment in the preset time period, the preset power consumption, the expected hydrogen storage rate of the hydrogen storage tank equipment at the end time of the preset time period, and the preset electricity price. When the intelligent agent is the hydrogen storage tank intelligent agent, the third observation status information of the preset time period is obtained. The third observation status information includes the initial hydrogen production power and the initial power generation power of the hydrogen gas turbine equipment during the preset time period.

4. The optimized operation method for a multi-agent-based electro-hydrogen coupling system according to claim 2, characterized in that, The optimal operating parameters of each device in the electro-hydrogen coupling system during a preset time period are determined based on the agent's adjustment actions, the preset constraint information, and the preset action projection strategy, including: When the intelligent agent is the electrolyzer intelligent agent, the preset constraint information includes the first maximum ramp rate of the electrolyzer equipment, the maximum hydrogen production power threshold and the minimum hydrogen production power threshold of the electrolyzer equipment, the maximum hydrogen storage rate of the hydrogen storage tank equipment, and the maximum hydrogen storage capacity of the hydrogen storage tank equipment. Obtain the historical hydrogen storage rate of the hydrogen storage tank equipment at the time preceding the start time of the preset time period; Obtain the hydrogen production efficiency of the electrolyzer equipment; Using the preset action projection strategy corresponding to the electrolyzer agent, and combining the duration of the preset time period in the preset constraint information and the first maximum ramp rate, the adjustment action of the electrolyzer agent is processed by action mapping to obtain the hydrogen production power adjustment amount. Obtain the historical hydrogen production power of the electrolyzer equipment in the previous preset cycle of the current preset cycle; Based on the historical hydrogen production power and the hydrogen production power adjustment amount, the electrolyzer agent determines the target hydrogen production power of the electrolyzer equipment for the preset time period based on the first observation state information of the preset time period. The target hydrogen production power is constrained by combining the maximum hydrogen production power threshold, the minimum hydrogen production power threshold, the maximum hydrogen storage rate, the maximum hydrogen storage capacity, the historical hydrogen storage rate, the duration of the preset time period, and the hydrogen production efficiency to obtain an updated target hydrogen production power. The updated target hydrogen production power conforms to the preset constraint information. The updated target hydrogen production power is used as the optimized operating parameter for the electrolyzer equipment.

5. The optimized operation method for a multi-agent-based electro-hydrogen coupling system according to claim 2, characterized in that, The optimal operating parameters of each device in the electro-hydrogen coupling system during a preset time period are determined based on the agent's adjustment actions, the preset constraint information, and the preset action projection strategy, including: When the intelligent agent is the hydrogen gas turbine intelligent agent, the preset constraint information includes the second maximum ramp rate of the hydrogen gas turbine equipment, the maximum power generation threshold and the minimum power generation threshold of the hydrogen gas turbine equipment, the minimum hydrogen storage rate of the hydrogen storage tank equipment, and the maximum hydrogen storage capacity of the hydrogen storage tank equipment. Obtain the historical hydrogen storage rate of the hydrogen storage tank equipment at the time preceding the start time of the preset time period; Obtain the hydrogen consumption efficiency of the hydrogen gas turbine equipment; Using the preset action projection strategy corresponding to the hydrogen gas turbine intelligent agent, and combining the second maximum ramp rate in the preset constraint information and the duration of the preset time period, the adjustment action of the hydrogen gas turbine intelligent agent is processed by action mapping to obtain the hydrogen gas turbine power adjustment amount. Obtain the historical power generation of the hydrogen gas turbine equipment in the previous preset cycle of the current preset cycle; Based on the historical power generation and the power adjustment of the hydrogen gas turbine, the hydrogen gas turbine agent determines the target power generation of the hydrogen gas turbine equipment within the preset time period based on the second observation status information of the preset time period. The target power generation is constrained by combining the maximum power generation threshold, the minimum power generation threshold, the minimum hydrogen storage rate, the maximum hydrogen storage capacity, the historical hydrogen storage rate, the duration of the preset time period, and the hydrogen consumption efficiency to obtain an updated target power generation, which conforms to the preset constraint information. The updated target power generation is used as the optimized operating parameter for the hydrogen gas turbine equipment.

6. The optimized operation method for a multi-agent-based electro-hydrogen coupling system according to claim 2, characterized in that, The optimal operating parameters of each device in the electro-hydrogen coupling system during a preset time period are determined based on the agent's adjustment actions, the preset constraint information, and the preset action projection strategy, including: When the intelligent agent is the intelligent agent of the hydrogen storage tank, the preset constraint information includes the minimum unit hydrogen storage capacity, maximum unit hydrogen storage capacity, maximum hydrogen storage rate and minimum hydrogen storage rate of the hydrogen storage tank equipment within a preset time period. By using the preset action projection strategy corresponding to the hydrogen storage tank agent, and combining the minimum unit hydrogen storage capacity and the maximum unit hydrogen storage capacity in the preset constraint information, the adjustment action of the hydrogen storage tank agent is processed by action mapping to obtain the optimized unit hydrogen storage capacity and optimized unit hydrogen release capacity of the hydrogen storage tank equipment. Obtain the maximum hydrogen storage capacity of the electrolyzer and the historical hydrogen storage rate at the time preceding the start time of the preset time period; Based on the historical hydrogen storage rate, the maximum hydrogen storage capacity, the optimized unit hydrogen storage amount, and the optimized unit hydrogen release amount, combined with the maximum hydrogen storage rate and the minimum hydrogen storage rate in the preset constraint information, the target hydrogen storage rate of the hydrogen storage tank equipment at the end of the preset time period is calculated. The target hydrogen storage rate is used as the optimized operating parameter for the hydrogen storage tank equipment.

7. The optimized operation method for a multi-agent-based electro-hydrogen coupling system according to claim 3, characterized in that, The method further includes: Based on the preset power output, the preset power consumption, the preset electricity price, the optimized operating parameters of the hydrogen gas turbine equipment in the electro-hydrogen coupling system, the duration of the preset time period, and the optimized operating parameters of the electrolyzer equipment, the cost reward value of the multi-agent set is determined. Obtain the maximum and minimum hydrogen storage rates of the hydrogen storage tank equipment; The storage out-of-bounds penalty value of the multi-agent set is determined based on the maximum hydrogen storage rate, the minimum hydrogen storage rate, and the optimized operating parameters of the hydrogen storage tank equipment. Obtain the first actual operating parameters of the hydrogen gas turbine equipment at the time preceding the start time of the preset time period; Obtain the second actual operating parameters of the electrolytic cell equipment at the time preceding the start time of the preset time period; The operating parameter fluctuation penalty value of the multi-agent set is determined based on the first actual operating parameters, the second actual operating parameters, the optimized operating parameters of the hydrogen gas turbine equipment, and the optimized operating parameters of the electrolyzer equipment. Obtain the standard operating parameters of the hydrogen gas turbine equipment issued by the dispatch center during the preset time period; The scheduling and tracking reward value of the multi-agent set is determined based on the standard operating parameters and the optimized operating parameters of the hydrogen gas turbine equipment. The comprehensive reward value of the multi-agent set is determined based on the cost reward value, the storage out-of-bounds penalty value, the operating parameter fluctuation penalty value, and the scheduling tracking reward value. Based on the comprehensive reward value, the agents in the multi-agent set are jointly optimized.

8. An optimized operation device for a multi-agent-based electro-hydrogen coupling system, characterized in that, include: The acquisition unit is used to acquire a set of multiple agents of the electro-hydrogen coupling system to be optimized. The set of multiple agents includes agents corresponding to each device in the electro-hydrogen coupling system to be optimized. Each agent in the set of multiple agents is obtained by joint training based on historical global information. The historical global information includes the historical state information of each device in the electro-hydrogen coupling system to be optimized. The acquisition unit is also used to acquire local observation information required by each agent in the multi-agent set at preset intervals. The agent determines the adjustment action based on the local observation information. The duration of the preset interval is less than or equal to one minute. The local observation information is the state information of local devices in each device of the electro-hydrogen coupling system to be optimized required when the agent makes the decision on the adjustment action. The acquisition unit is also used to acquire the preset constraint information and the corresponding preset action projection strategy for each intelligent agent. The determining unit is used to determine, for each agent, the optimized operating parameters of each device in the electro-hydrogen coupling system within a preset time period based on the agent's adjustment actions, the preset constraint information, and the preset action projection strategy. The preset time period is a time period that starts at the current time and ends at a time later than the current time and equal to the preset period duration.

9. An electronic device, characterized in that, include: Memory, used to store at least one instruction; as well as A processor is configured to invoke instructions stored in the memory to execute the optimized operation method of the multi-agent-based electro-hydrogen coupling system as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one executable instruction, which is loaded and executed by a processor to implement the optimized operation method of the multi-agent-based electro-hydrogen coupling system as described in any one of claims 1-7.

Images