A distributed hydrogen energy storage intelligent management system

Abstract

The present invention relates to the technical field of hydrogen energy storage management, specifically a distributed hydrogen energy storage intelligent management system, including a central control management system, the central control management system including: a data acquisition module, used to collect real-time operating data of each link in the system; an energy storage management module, including an energy scheduling optimization unit and a battery management unit, the energy scheduling optimization unit is used according to the operating status of the system, user needs and power grid conditions; an architecture optimization module, used to calculate system reliability, evaluate system scalability, and perform weighted calculations on the evaluation results, and optimize energy management according to the calculation results. When the present invention aims to maximize the utilization rate of hydrogen energy, the energy scheduling optimization unit will conduct all-round fine regulation of energy production, storage and release links. In the energy production stage, it is closely combined with the real-time data of hydrogen energy power generation to accurately adjust the scale of hydrogen energy storage.

Description

Technical Field

[0001] The present invention relates to the technical field of hydrogen energy storage management, and in particular to a distributed hydrogen energy storage intelligent management system. Background Art

[0002] With the continuous growth of global demand for clean energy and increasing attention to environmental protection, hydrogen energy, as a renewable clean energy, has been widely developed and utilized. In the process of development, hydrogen energy is characterized by intermittency and volatility. However, traditional energy storage technology is difficult to meet long-term, large-capacity energy storage needs when dealing with large-scale, distributed energy storage needs, and its service life is limited and the cost is high.

[0003] At the same time, distributed hydrogen energy storage systems can convert hydrogen energy into hydrogen for storage, and convert hydrogen into electrical energy when needed, realizing the time and space transfer of energy. However, in the management of hydrogen energy storage, it is difficult to accurately schedule the production, storage and release of hydrogen energy, which makes energy scheduling difficult, equipment maintenance costs high, and the entire energy storage management system has low intelligence, which cannot meet the current requirements for scheduling the production, storage and release of hydrogen energy. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides a distributed hydrogen energy storage intelligent management system to solve the problems raised in the above background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: a distributed hydrogen energy storage intelligent management system, including a central control management system, the central control management system includes:

[0006] The data acquisition module is used to collect the operating data of each link in the system in real time, including but not limited to the information data of hydrogen flow production, storage pressure, fuel cell output voltage and current, and equipment operation status, and add constraints to the acquired data;

[0007] The energy storage management module includes an energy scheduling optimization unit and a battery management unit. The energy scheduling optimization unit is used to optimize the production, storage and release of hydrogen energy according to the operating status of the system, user needs and power grid conditions. The battery management unit is used to manage the fuel cell and battery auxiliary system and monitor the voltage, current, temperature and charge state of the battery.

[0008] Intelligent control module, including a distributed control unit and an intelligent decision unit. The distributed control unit is used for distributed control of various subsystems and equipment. The intelligent decision unit is used for in-depth mining and analysis of collected data, predicting hydrogen energy power generation and equipment load status, and performing decision optimization calculations;

[0009] The current status assessment module is used to analyze the system architecture, evaluate system performance, and identify problems in the system architecture;

[0010] The architecture optimization module is used to calculate system reliability, evaluate system scalability, perform weighted calculations on the evaluation results, and perform energy management optimization based on the calculation results.

[0011] Preferably, the constraint conditions include power balance constraint and hydrogen energy storage system operation constraint, and the calculation formula of the power constraint is:

[0012]

[0013]

[0014] In the formula, , It is a collection of coal-fired units and wind turbines. , A combination of electrolyzer and fuel cell. A collection of hydrogen energy. is a collection of photovoltaic units, A collection of hydroelectric units. for The electrical load of the area at the time, , For coal-fired units and wind turbines The decision variables of the unit and equipment output at the moment, For fuel cells The decision variables of the unit and equipment output at the moment, For electrolytic cell The decision variable of power consumption at each moment, , for The decision variables of the short-term electrochemical energy storage discharge power at time, , for The decision variables of photovoltaic power output and hydropower output at the moment, for Decision variables of hydrogen energy equipment output at any moment.

[0015] Preferably, the constraint calculation formula for the hydrogen flow output is:

[0016]

[0017] In the formula, for The rate at which hydrogen is produced by electrolysis in time, for The power generated by the electrolysis system over time, is the Faraday efficiency, is the electrolyzer efficiency, and , is the Faraday constant, is the molar volume of the gas, and , is the number of electrolytic chambers, is the voltage of a single electrolysis cell, and .

[0018] Preferably, the energy scheduling optimization unit aims to maximize the utilization rate of hydrogen energy, and the calculation formula is:

[0019]

[0020]

[0021]

[0022]

[0023] In the formula, is the total cost, is the cost of purchasing electricity from the grid, The cost of hydrogen production, storage and conversion. is the system operation and maintenance cost, for The power purchased from the grid at all times, for The electricity price from the grid at all times, for The power of hydrogen energy used at all times, , , are the costs of hydrogen energy production, storage and conversion per unit power, is the operation and maintenance cost per unit power of the system, for The operating power of the system at all times, is the energy utilization rate, for The load power at the moment, is the time interval, The final moment for the production of hydrogen energy.

[0024] Preferably, the intelligent decision-making unit predicts energy demand and equipment operating status including the following steps:

[0025] S1. Evaluate the state of charge and health status of the energy storage system. The calculation formula for the state of charge evaluation is:

[0026]

[0027] In the formula, for The state of charge of the hydrogen energy storage system at all times. and They are The charging current and discharging current at the moment, is the rated capacity of the energy storage system, is the infinitesimal time interval considered in the integration process;

[0028] The calculation formula of the health status is:

[0029]

[0030] In the formula, is the actual capacity of the energy storage system at present, is the initial capacity of the energy storage system;

[0031] S2. According to the evaluation results, the hydrogen energy power generation and equipment load status are predicted. The calculation formula for the hydrogen energy power generation prediction is:

[0032]

[0033] In the formula, is the output of hydrogen produced by water electrolysis, For the efficiency of the fuel cell, is the heat of combustion of hydrogen;

[0034] The calculation formula for the equipment load state prediction is:

[0035]

[0036] In the formula, and are the autoregressive coefficient and the moving average coefficient, respectively. and are the autoregressive order and the moving average order, respectively. is a white noise sequence, is a white noise sequence in The value of for The maximum variance of is the lag in the time series The observed value of the period;

[0037] S3. According to the prediction results, the decision optimization calculation based on model predictive control and economic dispatch is performed. The decision optimization calculation formula based on model predictive control is:

[0038]

[0039]

[0040]

[0041]

[0042]

[0043] In the formula, is the performance indicator, is the system output, is the reference output, is the control input, To control the input weight coefficient, is the system status, and are the system state equation and output equation respectively, , , and are the upper and lower limits of the control input and system state, respectively. is the current discrete time step, For the prediction time domain;

[0044] The decision optimization calculation formula based on economic dispatch is:

[0045]

[0046] In the formula, for The cost of purchasing electricity from the grid at all times, for The production, storage and conversion costs of hydrogen energy at all times, for The operation and maintenance costs of the system at all times, for The power generated by the directional movement of charges at a moment, for The power consumed by the directional movement of charges at a given moment, for The interaction power between the power system and the grid at any moment, for The power of hydrogen energy used at all times, For the time range.

[0047] Preferably, the current status evaluation module evaluates the uniformity of power distribution between various energy storage nodes of the distributed energy storage system performance, and the calculation formula is:

[0048]

[0049] In the formula, For the The actual power of each energy storage node, is the average power of all energy storage nodes, is the number of energy storage nodes.

[0050] Preferably, the system reliability calculated by the architecture optimization module includes calculation of series system reliability and parallel reliability, and the calculation formula of the series system reliability is:

[0051]

[0052] In the formula, is the number of independent components connected in series to form a system, The reliability of each series component;

[0053] The calculation formula of the parallel reliability is:

[0054]

[0055] In the formula, is the number of independent components connected in parallel to form a system, The reliability of each parallel component.

[0056] Preferably, the architecture optimization module evaluates the system scalability according to the result of calculating the system reliability, and the system scalability evaluation includes node expansion factor evaluation and storage expansion ratio evaluation, and the calculation formula of the node expansion factor evaluation is:

[0057]

[0058] In the formula, is the coefficient related to node performance, is the performance index of the system before adding new nodes. To add Performance indicators after adding new nodes;

[0059] The calculation formula for the storage expansion ratio evaluation is:

[0060]

[0061] In the formula, is the system storage capacity before expansion. This is the system storage capacity after expansion.

[0062] Preferably, the architecture optimization module performs weighted calculation on the evaluation results according to the system scalability evaluation results, and the weighted calculation formula is:

[0063]

[0064] In the formula, Score the current status of the system. As the evaluation index, is the corresponding weight, is the number of dimensions to evaluate.

[0065] Preferably, the architecture optimization module performs energy management optimization including energy production scheduling optimization, energy storage management optimization and energy distribution optimization according to system reliability, system scalability evaluation and weighted calculation results of the evaluation results. The energy production scheduling optimization is used to formulate a reasonable hydrogen energy production plan based on energy demand forecasts and the characteristics of power generation equipment. The energy storage management optimization is used to optimize the charging and discharging strategy of the energy storage system to improve the service life of the energy storage equipment and the system stability. The energy distribution optimization is used to distribute energy to different users or regions to ensure efficient use of energy.

[0066] The present invention provides a distributed hydrogen energy storage intelligent management system. It has the following beneficial effects:

[0067] 1. The present invention realizes the refined management of hydrogen energy production, storage and release by accurately grasping the system operation status, user needs and power grid conditions through the energy scheduling optimization unit, and can timely detect abnormal conditions of the battery, effectively extending the service life of the battery. Even when there are large fluctuations in hydrogen energy power generation or sudden power grid failures, the normal operation of the system can be maintained by reasonably allocating hydrogen energy storage and power generation.

[0068] 2. When the present invention aims to maximize the utilization rate of hydrogen energy, the energy scheduling optimization unit will conduct all-round fine regulation of energy production, storage and release. In the energy production stage, it will closely combine the real-time data of hydrogen energy power generation, accurately adjust the scale of hydrogen energy storage, and flexibly adjust the storage and release of hydrogen energy to effectively balance energy supply and demand.

[0069] 3. The present invention provides forward-looking guidance for the entire energy scheduling system through the intelligent decision-making unit with accurate prediction of energy demand. By real-time monitoring and in-depth analysis of the operating data of key equipment such as fuel cells and electrolyzers, potential fault hazards can be discovered in advance. By evaluating and analyzing the energy scheduling effects under different operating scenarios, the intelligent decision-making unit can automatically adjust the energy production, storage and release strategies.

[0070] 4. The present invention can significantly improve the overall performance of the system by optimizing the architecture of the distributed hydrogen energy storage intelligent management system. During the energy scheduling process, the real-time status and energy demand information of the energy storage equipment can be obtained more quickly, so as to make decisions more quickly and improve the efficiency of energy scheduling. At the same time, the architecture optimization module focuses on the scalability design of the system, so that the system can easily cope with future developments and changes. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] Figure 1 It is a schematic diagram of the system flow of the present invention. DETAILED DESCRIPTION

[0072] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0073] Example:

[0074] like Figure 1 As shown, an embodiment of the present invention provides a distributed hydrogen energy storage intelligent management system, including a central control management system, which includes:

[0075] The data acquisition module is used to collect the operating data of each link in the system in real time, including but not limited to the information data of hydrogen flow production, storage pressure, fuel cell output voltage and current, and equipment operation status, and add constraints to the acquired data;

[0076] Energy storage management module, including energy scheduling optimization unit and battery management unit. The energy scheduling optimization unit is used to optimize the production, storage and release of hydrogen energy according to the system's operating status, user needs and power grid conditions. The battery management unit is used to manage fuel cells and battery auxiliary systems, and monitor the battery's voltage, current, temperature and charge state data;

[0077] Intelligent control module, including distributed control unit and intelligent decision unit. The distributed control unit is used for distributed control of various subsystems and equipment. The intelligent decision unit is used to conduct in-depth mining and analysis of the collected data, predict hydrogen energy power generation and equipment load status, and perform decision optimization calculations;

[0078] The current status assessment module is used to analyze the system architecture, evaluate system performance, and identify problems in the system architecture;

[0079] The architecture optimization module is used to calculate system reliability, evaluate system scalability, perform weighted calculations on the evaluation results, and perform energy management optimization based on the calculation results.

[0080] In this embodiment, the constraints include power balance constraints and hydrogen energy storage system operation constraints. The calculation formula for the power constraint is:

[0081]

[0082]

[0083] In the formula, , It is a collection of coal-fired units and wind turbines. , A combination of electrolyzer and fuel cell. A collection of hydrogen energy. is a collection of photovoltaic units, A collection of hydroelectric units. for The electrical load of the area at the time, , For coal-fired units and wind turbines The decision variables of the unit and equipment output at the moment, For fuel cells The decision variables of the unit and equipment output at the moment, For electrolytic cell The decision variable of power consumption at each moment, , for The decision variables of the short-term electrochemical energy storage discharge power at time, , for The decision variables of photovoltaic power output and hydropower output at the moment, for Decision variables of hydrogen energy equipment output at any moment.

[0084] In this embodiment, the constraint calculation formula for hydrogen flow production is:

[0085]

[0086] In the formula, for The rate at which hydrogen is produced by electrolysis in time, for The power generated by the electrolysis system over time, is the Faraday efficiency, is the electrolyzer efficiency, and , is the Faraday constant, is the molar volume of the gas, and , is the number of electrolytic chambers, is the voltage of a single electrolysis cell, and .

[0087] Specifically, the energy scheduling and optimization unit has achieved refined management of hydrogen energy production, storage and release by relying on its accurate grasp of the system operating status, user needs and power grid conditions. It can flexibly adjust the scale of hydrogen energy storage according to the real-time status of hydrogen energy power generation to ensure efficient conversion and storage of energy. It can also promptly detect abnormal conditions of the battery and effectively extend the battery life. Even when there are large fluctuations in hydrogen energy power generation or sudden power grid failures, it can maintain the normal operation of the system by reasonably allocating hydrogen energy storage and power generation. This intelligent management model not only improves the efficiency and accuracy of energy storage management, but also promotes the development of the entire system in a smarter and more efficient direction, providing users with better-quality and more convenient energy management services.

[0088] In this embodiment, the energy scheduling optimization unit aims to maximize the utilization rate of hydrogen energy, and the calculation formula is:

[0089]

[0090]

[0091]

[0092]

[0093] In the formula, is the total cost, is the cost of purchasing electricity from the grid, The cost of hydrogen energy production, storage and conversion is is the system operation and maintenance cost, for The power purchased from the grid at all times, for The electricity price from the grid at all times, for The power of hydrogen energy used at all times, , , are the costs of hydrogen energy production, storage and conversion per unit power, is the operation and maintenance cost per unit power of the system, for The operating power of the system at all times, is the energy utilization rate, for The load power at the moment, is the time interval, The final moment for the production of hydrogen energy.

[0094] Specifically, when the goal is to maximize the utilization rate of hydrogen energy, the energy scheduling optimization unit will conduct comprehensive and fine-tuned regulation of energy production, storage and release. In the energy production stage, it will closely combine the real-time data of hydrogen energy power generation to accurately adjust the scale of hydrogen energy storage. On the one hand, it will reduce the frequency of purchasing electricity from the power grid at high prices and reduce the cost of purchasing electricity. On the other hand, due to the efficient use of hydrogen energy, the consumption of hydrogen production raw materials is more reasonable, avoiding unnecessary waste and reducing the cost of hydrogen production. When hydrogen energy power generation fluctuates, the storage and release of hydrogen energy can be flexibly adjusted to effectively balance energy supply and demand.

[0095] In this embodiment, the intelligent decision-making unit predicts energy demand and equipment operation status including the following steps:

[0096] S1. Evaluate the state of charge and health status of the energy storage system. The calculation formula for the state of charge evaluation is:

[0097]

[0098] In the formula, for The state of charge of the hydrogen energy storage system at all times. and They are The charging current and discharging current at the moment, is the rated capacity of the energy storage system, is the infinitesimal time interval considered in the integration process;

[0099] The formula for calculating health status is:

[0100]

[0101] In the formula, is the actual capacity of the energy storage system at present, is the initial capacity of the energy storage system;

[0102] S2. Based on the evaluation results, the hydrogen energy power generation and equipment load status are predicted. The calculation formula for hydrogen energy power generation prediction is:

[0103]

[0104] In the formula, is the output of hydrogen produced by water electrolysis, For the efficiency of the fuel cell, is the heat of combustion of hydrogen;

[0105] The calculation formula for equipment load status prediction is:

[0106]

[0107] In the formula, and are the autoregressive coefficient and the moving average coefficient, respectively. and are the autoregressive order and the moving average order, respectively. is a white noise sequence, is a white noise sequence in The value of for The maximum variance of is the lag in the time series The observed value of the period;

[0108] S3. According to the prediction results, the decision optimization calculation based on model predictive control and economic dispatch is carried out. The decision optimization calculation formula based on model predictive control is:

[0109]

[0110]

[0111]

[0112]

[0113]

[0114] In the formula, is the performance indicator, is the system output, is the reference output, is the control input, To control the input weight coefficient, is the system status, and are the system state equation and output equation respectively, , , and are the upper and lower limits of the control input and system state, respectively. is the current discrete time step, For the prediction time domain;

[0115] The decision optimization calculation formula based on economic dispatch is:

[0116]

[0117] In the formula, for The cost of purchasing electricity from the grid at all times, for The production, storage and conversion costs of hydrogen energy at all times, for The operation and maintenance costs of the system at all times, for The power generated by the directional movement of charges at a moment, for The power consumed by the directional movement of charges at a given moment, for The interaction power between the power system and the grid at any moment, for The power of hydrogen energy used at all times, For the time range.

[0118] In this embodiment, the status evaluation module evaluates the uniformity of power distribution between various energy storage nodes of the distributed energy storage system performance, and the calculation formula is:

[0119]

[0120] In the formula, For the The actual power of each energy storage node, is the average power of all energy storage nodes, is the number of energy storage nodes.

[0121] Specifically, the intelligent decision-making unit provides forward-looking guidance for the entire energy dispatching system by accurately predicting energy demand. By real-time monitoring and in-depth analysis of the operating data of key equipment such as fuel cells and electrolyzers, it can discover potential fault hazards in advance. By evaluating and analyzing the energy dispatching effects under different operating scenarios, the intelligent decision-making unit can automatically adjust the energy production, storage and release strategies. Whether it is the intermittent fluctuations of hydrogen energy power generation or the sudden changes in user electricity demand, the intelligent decision-making unit can adjust the energy dispatching and equipment operation strategies in time through real-time monitoring and data analysis to ensure the system Stable operation. Through the analysis and prediction of factors such as energy market price fluctuations and changes in policies and regulations, the intelligent decision-making unit can formulate a more reasonable market participation strategy. For example, in areas with large differences in peak and valley electricity prices, the intelligent decision-making unit can guide the system to produce hydrogen and store energy during valley electricity price periods, and release hydrogen to generate electricity and sell electricity to the grid during peak electricity price periods, thereby maximizing economic benefits. The intelligent decision-making unit can also participate in the auxiliary service market of the power grid according to market demand and the system's own capabilities, such as providing frequency regulation, peak regulation and other services, which not only contributes to the stable operation of the power grid, but also brings additional sources of income to the system operator.

[0122] In this embodiment, the system reliability calculated by the architecture optimization module includes the calculation of the series system reliability and the parallel reliability. The calculation formula of the series system reliability is:

[0123]

[0124] In the formula, is the number of independent components connected in series to form a system, The reliability of each series component;

[0125] The calculation formula for parallel reliability is:

[0126]

[0127] In the formula, is the number of independent components connected in parallel to form a system, The reliability of each parallel component.

[0128] In this embodiment, the architecture optimization module evaluates the system scalability based on the result of calculating the system reliability. The system scalability evaluation includes node expansion factor evaluation and storage expansion ratio evaluation. The calculation formula for node expansion factor evaluation is:

[0129]

[0130] In the formula, is the coefficient related to node performance, is the performance index of the system before adding new nodes. To add Performance indicators after adding new nodes;

[0131] The calculation formula for storage expansion ratio evaluation is:

[0132]

[0133] In the formula, is the system storage capacity before expansion. This is the system storage capacity after expansion.

[0134] In this embodiment, the architecture optimization module performs weighted calculation on the evaluation results according to the system scalability evaluation results, and the weighted calculation formula is:

[0135]

[0136] In the formula, Score the current status of the system. As the evaluation index, is the corresponding weight, is the number of dimensions to evaluate.

[0137] In this embodiment, the architecture optimization module performs energy management optimization including energy production scheduling optimization, energy storage management optimization and energy distribution optimization based on system reliability, system scalability evaluation and weighted calculation results of the evaluation results. Energy production scheduling optimization is used to formulate a reasonable hydrogen energy production plan based on energy demand forecasts and the characteristics of power generation equipment. Energy storage management optimization is used to optimize the charging and discharging strategy of the energy storage system to improve the service life of the energy storage equipment and system stability. Energy distribution optimization is used to distribute energy to different users or regions to ensure efficient use of energy.

[0138] Specifically, by optimizing the architecture of the distributed hydrogen energy storage intelligent management system, the overall performance of the system can be significantly improved. During the energy scheduling process, the real-time status and energy demand information of the energy storage equipment can be obtained more quickly, so that decisions can be made more quickly and the efficiency of energy scheduling can be improved. At the same time, the architecture optimization module focuses on the scalability design of the system, so that the system can easily cope with future developments and changes. When new energy storage nodes, power generation equipment or user access need to be added, the optimized architecture can be easily expanded without the need for large-scale modifications to the entire system. On the one hand, the clear architecture design and modular layout make equipment troubleshooting and maintenance easier. On the other hand, the system performance improvement and reliability enhancement achieved through architecture optimization also reduce the failure rate and maintenance frequency of equipment, thereby reducing maintenance costs.

[0139] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A distributed hydrogen energy storage intelligent management system, including a central control management system, characterized in that: The central control management system comprises: The data acquisition module is used to collect the operating data of each link in the system in real time, including but not limited to the information data of hydrogen flow production, storage pressure, fuel cell output voltage and current, and equipment operation status, and add constraints to the acquired data; The energy storage management module includes an energy scheduling optimization unit and a battery management unit. The energy scheduling optimization unit is used to optimize the production, storage and release of hydrogen energy according to the operating status of the system, user needs and power grid conditions. The battery management unit is used to manage the fuel cell and battery auxiliary system and monitor the voltage, current, temperature and charge state of the battery. Intelligent control module, including a distributed control unit and an intelligent decision unit. The distributed control unit is used for distributed control of various subsystems and equipment. The intelligent decision unit is used for in-depth mining and analysis of collected data, predicting hydrogen energy power generation and equipment load status, and performing decision optimization calculations; The current status assessment module is used to analyze the system architecture, evaluate system performance, and identify problems in the system architecture; The architecture optimization module is used to calculate system reliability, evaluate system scalability, perform weighted calculations on the evaluation results, and perform energy management optimization based on the calculation results; The constraints include power balance constraints and hydrogen energy storage system operation constraints. The calculation formula of the power constraint is: In the formula, , It is a collection of coal-fired units and wind turbines. , A combination of electrolyzer and fuel cell. A collection of hydrogen energy. is a collection of photovoltaic units, A collection of hydroelectric units. for The electrical load of the area at the time, , For coal-fired units and wind turbines The decision variables of the unit and equipment output at the moment, For fuel cells The decision variables of the unit and equipment output at the moment, For electrolytic cell The decision variable of power consumption at each moment, , for The decision variables of the short-term electrochemical energy storage discharge power at time, , for The decision variables of photovoltaic power output and hydropower output at the moment, for The decision variables of hydrogen energy equipment output at any moment; The constraint calculation formula for the hydrogen flow production is: In the formula, for The rate at which hydrogen is produced by electrolysis in time, for The power generated by the electrolysis system over time, is the Faraday efficiency, is the electrolyzer efficiency, and , is the Faraday constant, is the molar volume of the gas, and , is the number of electrolytic chambers, is the voltage of a single electrolysis cell, and .

2. A distributed hydrogen energy storage intelligent management system according to claim 1, characterized in that: The energy scheduling optimization unit aims to maximize the utilization rate of hydrogen energy, and the calculation formula is: In the formula, is the total cost, is the cost of purchasing electricity from the grid, The cost of hydrogen production, storage and conversion. is the system operation and maintenance cost, for The power purchased from the grid at all times, for The power of hydrogen energy used at all times, , , are the costs of hydrogen energy production, storage and conversion per unit power, is the operation and maintenance cost per unit power of the system, for The operating power of the system at all times, is the energy utilization rate, for The load power at the moment, is the time interval, The final moment for the production of hydrogen energy.

3. A distributed hydrogen energy storage intelligent management system according to claim 2, characterized in that: The intelligent decision-making unit predicts energy demand and equipment operation status including the following steps: S1. Evaluate the state of charge and health status of the energy storage system. The calculation formula for the state of charge evaluation is: In the formula, for The state of charge of the hydrogen energy storage system at all times. and They are The charging current and discharging current at the moment, is the rated capacity of the energy storage system, is the infinitesimal time interval considered in the integration process; The calculation formula of the health status is: In the formula, is the actual capacity of the energy storage system at present, is the initial capacity of the energy storage system; S2. Based on the evaluation results, the hydrogen energy power generation and equipment load status are predicted. The calculation formula for hydrogen energy power generation prediction is: In the formula, is the output of hydrogen produced by water electrolysis, For the efficiency of the fuel cell, is the heat of combustion of hydrogen; The calculation formula for equipment load status prediction is: In the formula, and are the autoregressive coefficient and the moving average coefficient, respectively. and are the autoregressive order and the moving average order, respectively. is a white noise sequence, is a white noise sequence in The value of for The maximum variance of ; S3. According to the prediction results, the decision optimization calculation based on model predictive control and economic dispatch is carried out. The decision optimization calculation formula based on model predictive control is: In the formula, is the performance indicator, is the system output, is the reference output, is the control input, To control the input weight coefficient, is the system status, and are the system state equation and output equation respectively, , , and are the upper and lower limits of the control input and system state, respectively. is the current discrete time step, For the prediction time domain; The decision optimization calculation formula based on economic dispatch is: In the formula, for The cost of purchasing electricity from the grid at all times, for The production, storage and conversion costs of hydrogen energy at all times, for The operation and maintenance costs of the system at all times, for The power generated by the directional movement of charges at a moment, for The power consumed by the directional movement of charges at a given moment, for The interaction power between the power system and the grid at any moment, for The power of hydrogen energy used at all times, For the time range.

4. A distributed hydrogen energy storage intelligent management system according to claim 2, characterized in that: The status evaluation module evaluates the uniformity of power distribution between various energy storage nodes of the distributed energy storage system. The calculation formula is: In the formula, For the The actual power of each energy storage node, is the average power of all energy storage nodes, is the number of energy storage nodes.

5. A distributed hydrogen energy storage intelligent management system according to claim 4, characterized in that: The system reliability calculated by the architecture optimization module includes calculation of the series system reliability and the parallel reliability. The calculation formula of the series system reliability is: In the formula, is the number of independent components connected in series to form a system, The reliability of each series component; The calculation formula of the parallel reliability is: In the formula, is the number of independent components connected in parallel to form a system, The reliability of each parallel component.

6. A distributed hydrogen energy storage intelligent management system according to claim 5, characterized in that: The architecture optimization module evaluates the system scalability according to the result of calculating the system reliability. The system scalability evaluation includes node expansion factor evaluation and storage expansion ratio evaluation. The calculation formula of the node expansion factor evaluation is: In the formula, is the coefficient related to node performance, is the performance index of the system before adding new nodes. To add Performance indicators after adding new nodes; The calculation formula for the storage expansion ratio evaluation is: In the formula, is the system storage capacity before expansion. This is the system storage capacity after expansion.

7. A distributed hydrogen energy storage intelligent management system according to claim 6, characterized in that: The architecture optimization module performs weighted calculation on the evaluation results according to the system scalability evaluation results, and the weighted calculation formula is: In the formula, Score the current status of the system. As the evaluation index, is the corresponding weight, is the number of dimensions to evaluate.

8. The distributed hydrogen energy storage intelligent management system according to claim 1 is characterized in that: The architecture optimization module performs energy management optimization including energy production scheduling optimization, energy storage management optimization and energy distribution optimization according to system reliability, system scalability evaluation and weighted calculation results of the evaluation results. The energy production scheduling optimization is used to formulate a reasonable hydrogen energy production plan based on energy demand forecasts and the characteristics of power generation equipment. The energy storage management optimization is used to optimize the charging and discharging strategy of the energy storage system to improve the service life of the energy storage equipment and the system stability. The energy distribution optimization is used to distribute energy to different users or regions to ensure efficient use of energy.

Images