Hydrogen energy group control and grid connection method and system

Abstract

The present invention relates to the field of power supply technology, and specifically to a hydrogen energy group control and grid connection method and system. The edge decision implementation module obtains the operation data and grid status data of the hydrogen fuel cell group, and after integrity diagnosis, evaluates the matching degree between the current computing resources and the data processing requirements, and obtains real-time data flow distribution information by combining the availability and computing power of the computing resources, as well as the data processing speed and network delay; by adjusting the output power of the hydrogen fuel cell and matching the corresponding grid load, using the obtained decision information, analyzing the behavior trend and performance fluctuation of the hydrogen fuel cell group, and adjusting and optimizing the grid connection control strategy; the edge decision implementation module improves the energy management and utilization efficiency of the hydrogen fuel cell group, and through real-time evaluation and dynamic adjustment of the collected data, it can flexibly respond and adjust under changing grid load conditions, thereby ensuring the stability of the grid and the continuity of power supply.

Description

Technical Field

[0001] The present invention relates to the technical field of power supply, and in particular to a hydrogen energy group control and grid connection method and system. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] The power system regulates and controls the generation, transmission, distribution and consumption of electricity to ensure the stability, reliability and efficiency of power supply, while optimizing the allocation and use of resources. The resources in the power grid include traditional thermal power generation, and new energy power generation such as wind power, solar power, tidal power and hydrogen fuel cells. Hydrogen fuel cells are power generation devices that directly convert the chemical energy of hydrogen and oxygen into electrical energy. Their basic principle is the reverse reaction of water electrolysis. When hydrogen fuel cells are used in power systems, similar to wind power generation, tidal power generation and other devices, there are instability problems. When the number of hydrogen fuel cell devices in a regional power grid is large enough, it is easy to cause grid fluctuations during grid connection, and the power system needs to be adjusted to cope with the fluctuations, thereby ensuring a stable supply of electricity.

[0004] In dealing with unstable energy sources, such as hydrogen energy, the power system still shows obvious deficiencies. It lacks sufficient flexibility and adaptability, and is difficult to cope with power fluctuations and instability from new energy sources such as hydrogen energy, which limits the wider application of new energy. For example, without the support of real-time data flow dynamic allocation and instant performance adjustment, the power grid cannot effectively optimize energy efficiency, resulting in resource waste and inconsistency in power supply. In addition, the power system lacks sufficient behavioral trend analysis and prediction capabilities, making it difficult for traditional power grids to predict and respond to changes in grid load, which may cause grid stability problems under high load conditions, affecting the economy and efficiency of the grid and bringing potential safety risks. Summary of the invention

[0005] In order to solve the technical problems existing in the above-mentioned background technology, the present invention provides a hydrogen energy group control and grid-connected method and system, which improves the energy management and utilization efficiency of the hydrogen fuel cell group through real-time optimization scheduling and dynamic allocation of data streams, and real-time evaluation and dynamic adjustment of the real-time operation data of hydrogen fuel cells and grid status information. It can flexibly respond and adjust under changing grid load conditions, thereby ensuring the stability of the grid.

[0006] In order to achieve the above object, the present invention adopts the following technical solution:

[0007] The first aspect of the present invention provides a hydrogen energy group control and grid connection system, comprising:

[0008] The data flow dynamic allocation module is configured to: obtain the operation data of the hydrogen fuel cell group and the power grid status data, adjust the flow of data between the cloud and the edge nodes according to the computing requirements and resource availability, and obtain real-time data flow allocation information;

[0009] The edge decision implementation module is configured to: use the data stream allocation information to adjust the output power of the hydrogen fuel cell and match the corresponding grid load to obtain real-time decision information;

[0010] The cloud analysis module is configured to: analyze the behavior trend and performance fluctuation of the hydrogen fuel cell group according to the decision information, adjust the grid-connected control strategy, and obtain the optimized control strategy;

[0011] Among them, the operating data of the hydrogen fuel cell group and the power grid status data are obtained, and after integrity diagnosis, the matching degree between the current computing resources and data processing requirements is evaluated. Combined with the availability and computing power of computing resources, as well as the data processing speed and network delay, real-time data flow distribution information is obtained.

[0012] Furthermore, it also has an event-triggered response module, which is configured to: implement grid connection using the optimized control strategy, monitor grid demand and real-time performance data of hydrogen fuel cells, trigger corresponding events through set monitoring thresholds, respond to grid changes by adjusting the output power and frequency of the hydrogen fuel cell, and obtain response adjustment results.

[0013] Furthermore, it also has an adaptive scheduling control module, which is configured to: evaluate the matching degree of the power grid demand according to the response adjustment result and the real-time demand of the power grid, adjust the performance output of the hydrogen fuel cell, and obtain matching scheduling decision information.

[0014] Furthermore, it also has a multi-objective optimization integration module, which is configured to: use the matching scheduling decision information to analyze the operating cost, efficiency and response time of the hydrogen fuel cell, and balance the operating goals of the hydrogen fuel cell by adjusting the operating strategy of the hydrogen fuel cell to obtain optimized operating information.

[0015] Furthermore, real-time data stream distribution information includes data quality assessment information after edge node processing, real-time power adjustment instructions and hydrogen fuel cell output parameters; optimized control strategy includes behavior pattern analysis results, predicted performance fluctuation data and optimized grid-connected control parameters; response adjustment results include event identification type, response action measures and emergency adjustment parameters of grid-connected operation; matching scheduling decision information includes grid demand matching degree, hydrogen fuel cell performance optimization indicators and adjusted energy output strategy; optimized operation information includes cost-efficiency balance analysis information and optimization indicators of energy efficiency and response time.

[0016] Further, the data flow dynamic allocation module includes a data evaluation submodule, a resource matching submodule and a data flow adjustment submodule;

[0017] The data evaluation submodule checks the information missing points, identifies the applicability of the data, evaluates the integrity and accuracy of the data, and obtains data integrity diagnostic information based on the real-time operating data of the hydrogen fuel cell group and the power grid status information;

[0018] The resource matching submodule evaluates the matching degree between the current computing resources and the data processing requirements based on the data integrity diagnostic information, adjusts the resource allocation based on the availability and computing power of the computing resources, matches the real-time data processing requirements, and obtains resource adaptation evaluation information;

[0019] The data flow adjustment submodule adjusts the flow of data between the cloud and edge nodes based on the resource adaptation evaluation information, changes the data distribution path and processing nodes in combination with the data processing speed and network delay, optimizes the data processing efficiency, and obtains real-time data flow distribution information.

[0020] Furthermore, the edge decision implementation module includes a data cleaning submodule, a trend analysis submodule, and a decision adjustment submodule:

[0021] The data cleaning submodule performs data cleaning processing on the edge node based on the real-time data flow allocation information, removes outliers, fills missing data, and corrects erroneous data, unifies the data format and verifies the range, optimizes the data quality, and obtains a cleaned data set;

[0022] The trend analysis submodule performs data sorting, key performance indicator extraction and trend analysis based on the cleaned data set, extracts the core information and potential problems of the data through statistical analysis and data pattern recognition, and obtains trend analysis results;

[0023] The decision adjustment submodule adjusts the output power of the hydrogen fuel cell group based on the trend analysis results, distributes and adjusts the power according to the preset operating threshold, matches the current load demand and operating efficiency of the power grid, and obtains real-time decision information.

[0024] Furthermore, the cloud analysis module includes a data aggregation submodule, a pattern recognition submodule, and a strategy optimization submodule;

[0025] The data aggregation submodule organizes data based on the real-time decision information, unifies the format of data from multiple edge nodes and eliminates redundancy, optimizes data consistency and reliability, and integrates and checks the consistency of data to obtain unified data information;

[0026] The pattern recognition submodule, based on the unified data information, statistically analyzes the operation mode and performance fluctuation of the hydrogen fuel cell group, uses a cluster analysis algorithm to identify repeated patterns and abnormal fluctuations in the data, performs behavior trend analysis and performance fluctuation identification, and obtains behavior fluctuation information;

[0027] The strategy optimization submodule evaluates the effect of the current grid-connected control strategy based on the behavior fluctuation information, and adjusts the strategy according to the behavior trend and performance fluctuation, adjusts the grid-connected control parameters, optimizes energy efficiency and grid stability, and obtains the optimized control strategy.

[0028] Furthermore, the clustering analysis algorithm is shown in the following formula:

[0029] ;

[0030] in, Represents data points and The Euclidean distance between and is a vector and In the The performance indicator values ​​on the dimension, It is The standard deviation in dimension, It is The weight coefficient of the dimension, is the adjustment factor, It is a data point and The observation time difference is is the overall observation period length, Indicates the number of dimensions involved in the calculation.

[0031] Furthermore, the event trigger response module includes an event monitoring submodule, an event response submodule and a parameter adjustment submodule.

[0032] The event monitoring submodule performs real-time monitoring of grid demand and hydrogen fuel cell performance data based on the optimized control strategy, sets thresholds to detect key changes, including grid load mutations and hydrogen fuel performance degradation, and obtains monitoring event trigger records;

[0033] The event response submodule starts a preset emergency response strategy based on the monitoring event trigger record, adjusts the hydrogen fuel cell output, matches the immediate grid demand change, adjusts the output power and frequency of the hydrogen fuel cell, and obtains emergency adjustment information;

[0034] The parameter adjustment submodule adjusts the output parameters of the hydrogen fuel cell based on the emergency adjustment information, optimizes the compatibility between the hydrogen fuel cell equipment performance and the grid load, optimizes the operating efficiency and stability of the hydrogen fuel cell, and obtains a response adjustment result.

[0035] Furthermore, the adaptive scheduling control module includes a matching analysis submodule, a performance optimization submodule and a strategy updating submodule.

[0036] The matching analysis submodule collects and analyzes the real-time performance data of the hydrogen fuel cell and the power grid based on the response adjustment result, and uses the data to evaluate the matching degree between the power grid demand and the hydrogen fuel cell output to obtain a matching degree evaluation result;

[0037] The performance optimization submodule performs performance evaluation based on the matching evaluation result, including analyzing the efficiency, energy consumption and response time of the hydrogen fuel cell, performing performance optimization, adjusting the parameter settings of the hydrogen fuel cell, optimizing the efficiency and response capability of the hydrogen fuel cell, and obtaining performance tuning information;

[0038] Based on the performance tuning information, the strategy update submodule uses a dynamic optimization algorithm to adjust the operation mode of the hydrogen fuel cell, adapt to the real-time changes in the power grid load, optimize the stable operation of the power grid, and obtain matching scheduling decision information.

[0039] Further, the dynamic optimization algorithm is shown in the following formula:

[0040] ;

[0041] in, To match the scheduling decision information, that is, to minimize the total cost, It's in time The hydrogen fuel cell output, It's in time The grid demand, is the total time period, is the smoothing parameter.

[0042] Furthermore, the multi-objective optimization integration module includes a goal setting submodule, a decision search submodule, and an optimization execution submodule;

[0043] The target setting submodule evaluates the operating cost, efficiency and response time of the hydrogen fuel cell based on the matching scheduling decision information, sets multiple optimization targets, formulates optimization strategies and target priorities, and obtains an optimization target framework;

[0044] The decision search submodule formulates a variety of adjustment strategies based on the optimization target framework, identifies strategies that meet the set goals by analyzing the potential results of the various adjustment strategies, and obtains the target strategy identification results;

[0045] The optimization execution submodule adjusts the hydrogen fuel cell operating parameters based on the target strategy identification result, matches the grid demand and optimizes the hydrogen fuel cell efficiency, balances the operating objectives of the hydrogen fuel cell, and obtains optimized operating information.

[0046] A second aspect of the present invention provides a hydrogen energy group control and grid connection method, comprising the following steps:

[0047] Obtain the operating data of the hydrogen fuel cell group and the power grid status data, adjust the data flow between the cloud and edge nodes according to the computing requirements and resource availability, and obtain real-time data flow distribution information;

[0048] Use data stream allocation information to adjust the output power of hydrogen fuel cells and match the corresponding grid load to obtain real-time decision information;

[0049] According to the decision-making information, analyze the behavior trend and performance fluctuation of the hydrogen fuel cell group, adjust the grid-connected control strategy, and obtain the optimized control strategy;

[0050] The optimized control strategy is used to implement grid connection, monitor grid demand and real-time performance data of hydrogen fuel cells, trigger corresponding events through set monitoring thresholds, and respond to grid changes by adjusting the output power and frequency of hydrogen fuel cells to obtain response adjustment results;

[0051] According to the response adjustment results, combined with the real-time demand of the power grid, the grid demand matching degree is evaluated, the performance output of the hydrogen fuel cell is adjusted, and the matching scheduling decision information is obtained;

[0052] By using the matching scheduling decision information, the operating cost, efficiency and response time of the hydrogen fuel cell are analyzed. By adjusting the operating strategy of the hydrogen fuel cell and balancing the operating objectives of the hydrogen fuel cell, the optimized operating information is obtained.

[0053] Compared with the prior art, one or more of the above technical solutions have the following beneficial effects:

[0054] 1. Through the data flow dynamic allocation module, the collected operation data and grid status data of the hydrogen fuel cell group are adjusted, and the flow between the cloud and edge nodes is adjusted. By considering the data processing speed and network delay, the data distribution path and processing nodes are changed, and the data processing efficiency is optimized, thereby improving the energy management and utilization efficiency of the hydrogen fuel cell group. Through real-time evaluation and dynamic adjustment of the collected data, it can flexibly respond and adjust under changing grid load conditions, ensuring the stability of the grid and the continuity of power supply.

[0055] 2. Data cleaning and power adjustment are performed through edge nodes to match the current grid load demand, avoiding energy waste and potential grid safety issues caused by load mismatch. Through data aggregation and behavioral trend analysis, future changes can be predicted and the grid control strategy can be adjusted accordingly. The forward-looking management achieved improves the overall energy efficiency and operating cost-effectiveness of the power grid. The application of adaptive scheduling control and multi-objective optimization balances cost, efficiency and response time, optimizes the operating strategy, and enhances economy. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0057] Figure 1 is a flow chart of a hydrogen energy group control and grid connection system provided by one or more embodiments of the present invention;

[0058] Figure 2 is a structural schematic diagram of a hydrogen energy group control and grid connection system provided by one or more embodiments of the present invention;

[0059] Figure 3 is a flow chart of a data stream dynamic allocation module provided by one or more embodiments of the present invention;

[0060] Figure 4 is a flow chart of an edge decision implementation module provided by one or more embodiments of the present invention;

[0061] Figure 5 is a flow chart of a cloud analysis module provided by one or more embodiments of the present invention;

[0062] Figure 6 is a flow chart of an event trigger response module provided by one or more embodiments of the present invention;

[0063] Figure 7 is a flow chart of an adaptive scheduling control module provided by one or more embodiments of the present invention;

[0064] Figure 8 It is a flow chart of a multi-objective optimization integration module provided by one or more embodiments of the present invention. DETAILED DESCRIPTION

[0065] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0066] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0067] As introduced in the background technology, the power system still shows obvious deficiencies in handling unstable energy sources, such as hydrogen energy, and grid integration. The lack of sufficient flexibility and adaptability makes it difficult to cope with power fluctuations and instability from new energy sources such as hydrogen energy, limiting the wider application of new energy. For example, without the support of real-time data flow dynamic allocation and instant performance adjustment, the power grid cannot effectively optimize energy efficiency, resulting in waste of resources and inconsistency in power supply. In addition, the power system lacks sufficient behavioral trend analysis and prediction capabilities, making it difficult for traditional power grids to predict and respond to changes in grid load, which may cause grid stability problems under high load conditions, affecting the economy and efficiency of the grid and bringing potential safety risks.

[0068] Therefore, the following embodiments provide hydrogen energy group control and grid connection methods and systems, which improve the energy management and utilization efficiency of hydrogen fuel cell groups through real-time optimization scheduling and dynamic allocation of data streams, and real-time evaluation and dynamic adjustment of hydrogen fuel cell real-time operation data and grid status information, which can flexibly respond and adjust under changing grid load conditions, thereby ensuring the stability of the grid. Data cleaning and power adjustment are performed through edge nodes to match the current grid load demand, avoid energy waste and potential grid safety issues caused by load mismatch, and predict future changes through data aggregation and behavior trend analysis, and adjust the grid connection control strategy accordingly. This forward-looking management improves the overall energy efficiency and operating cost-effectiveness of the grid, and the application of adaptive scheduling control and multi-objective optimization balances cost, efficiency and response time, realizes the optimization of operation strategies, and enhances economy.

[0069] Embodiment 1:

[0070] like Figure 1 As shown, the hydrogen energy group control and grid-connected system includes:

[0071] The data flow dynamic allocation module evaluates the data in real time based on the real-time operation data of the hydrogen fuel cell group and the power grid status information, and dynamically adjusts the flow of data between the cloud and edge nodes according to computing requirements and resource availability to obtain real-time data flow allocation information;

[0072] The edge decision implementation module performs data cleaning processing on the edge node based on real-time data stream allocation information, including removing outliers and filling missing data, sorting and analyzing the data, and adjusting the output power of the hydrogen fuel cell according to the preset threshold to match the current grid load and obtain real-time decision information;

[0073] The cloud analysis module aggregates and analyzes data in the cloud based on real-time decision information. Through pattern recognition, it analyzes the behavior trend and performance fluctuation of the hydrogen fuel cell group, adjusts the grid-connected control strategy, optimizes energy efficiency and grid stability, and obtains the optimized control strategy.

[0074] The event-triggered response module implements grid-connected demonstration based on the optimized control strategy, monitors grid demand and real-time performance data of hydrogen fuel cells, sets monitoring thresholds to trigger corresponding events, including sudden increase in grid demand and decrease in hydrogen fuel efficiency, and automatically adjusts the output power and frequency of hydrogen fuel cells to respond to grid changes and obtain response adjustment results;

[0075] The adaptive dispatch control module evaluates the matching degree of the grid demand based on the response adjustment results and the real-time demand of the grid. Through real-time control, it dynamically adjusts the performance output of the hydrogen fuel cell to match the grid load and obtains matching dispatch decision information.

[0076] The multi-objective optimization integrated module analyzes the operating cost, efficiency and response time of the hydrogen fuel cell based on the matching scheduling decision information, and obtains optimized operating information by adjusting the operating strategy of the hydrogen fuel cell and balancing the operating objectives of the hydrogen fuel cell.

[0077] Real-time data stream allocation information includes data priority calibration, dynamic resource allocation indicators between cloud and edge nodes, and adjusted data processing paths. Real-time decision information includes data quality assessment after edge node processing, real-time power adjustment instructions, and hydrogen fuel cell output parameters. The optimized control strategy includes behavior pattern analysis results, predicted performance fluctuation data, and optimized grid-connected control parameters. The response adjustment results include event identification type, response action measures, and emergency adjustment parameters for grid-connected operations. Matching scheduling decision information includes grid demand matching degree, hydrogen fuel cell performance optimization indicators, and adjusted energy output strategies. Optimized operation information includes cost-efficiency balance analysis information and optimization indicators for energy efficiency and response time.

[0078] like Figure 2 As shown, the data flow dynamic allocation module includes a data evaluation submodule, a resource matching submodule, and a data flow adjustment submodule.

[0079] like Figure 3 As shown, the data evaluation submodule checks the information missing points, identifies the applicability of the data, evaluates the integrity and accuracy of the data, and obtains data integrity diagnostic information based on the real-time operating data of the hydrogen fuel cell group and the power grid status information.

[0080] The process of obtaining data integrity diagnostic information is as follows: In the data evaluation submodule, based on the real-time operation data of the hydrogen fuel cell group and the grid status information, the data is continuously collected from each monitoring point through the collector, and an integrity check is performed on each data point. The data integrity diagnostic formula is used to evaluate the consistency and accuracy of the data by calculating the deviation of each data point from the overall data average. The formula is: ,in, is the data integrity coefficient, which indicates the fluctuation and abnormality of the data. For the The actual observed value of the data points, is the average value of all data points, It is the total number of data points, helps identify outliers and missing points in the data set, and evaluates the availability and accuracy of the data to obtain data integrity diagnostic information.

[0081] like Figure 3 As shown, the resource matching submodule evaluates the matching degree between the current computing resources and the data processing requirements based on the data integrity diagnosis information, adjusts the resource allocation according to the availability and computing power of the computing resources, matches the real-time data processing requirements, and obtains the resource adaptation evaluation information.

[0082] The process of obtaining resource adaptation evaluation information is as follows: In the resource matching submodule, based on data integrity diagnosis information, by analyzing the current computing resource usage and task requirements, the resource adaptation evaluation formula is used to dynamically adjust resource allocation and optimize the utilization efficiency of computing resources. The formula is: ,in, is the resource adaptation coefficient, which measures the matching degree of resource allocation. is the current available computing resources, is the computing resource requirement of the current task, It is the priority weight of the task, reflecting the urgency of different tasks, ensuring that high-priority tasks obtain sufficient resources, thereby improving the processing capacity and response speed of the overall system and generating resource adaptation evaluation information.

[0083] like Figure 3 As shown, the data flow adjustment submodule adjusts the flow of data between the cloud and edge nodes based on the resource adaptation evaluation information, changes the data distribution path and processing nodes in combination with the data processing speed and network delay, optimizes the data processing efficiency, and obtains real-time data flow distribution information.

[0084] The process of obtaining real-time data flow allocation information is as follows: In the data flow adjustment submodule, based on the resource adaptation evaluation information, the data flow dynamic adjustment formula is implemented to optimize the data flow path and processing strategy according to the current network status and the performance of the processing node. The formula is: ,in, Adjust the index for data traffic to determine the distribution and flow of data. is the data processing speed, is the packet size, For network delay, The adjustment coefficient is used to adjust the data flow according to the real-time network status. The formula helps to dynamically adjust the flow of data between the cloud and edge nodes to adapt to the changing network conditions and processing requirements, optimize data processing efficiency, and obtain real-time data flow distribution information.

[0085] like Figure 2 As shown, the edge decision implementation module includes a data cleaning submodule, a trend analysis submodule and a decision adjustment submodule.

[0086] like Figure 4 As shown, the data cleaning submodule performs data cleaning processing on the edge node based on the real-time data stream allocation information, removes outliers, fills in missing data, corrects erroneous data, unifies the data format and verifies the range, optimizes the data quality, and obtains the cleaned data set.

[0087] The process of obtaining the cleaned data set is as follows: In the data cleaning submodule, data cleaning is performed on the edge node based on the real-time data stream distribution information. This process involves removing outliers, filling missing data, and correcting erroneous data from the received data. By introducing the data cleaning formula, the quality of the data set is systematically evaluated and optimized: ,in, represents the data quality score, represents the total number of data points processed, Indicates Is the data point valid (1 for valid, 0 for invalid), It represents the score of the standardized data point. The formula evaluates the overall data quality by calculating the weighted score of each data point, thereby ensuring the consistency and accuracy of the data. On this basis, the data format is unified and the range is checked to improve the availability and reliability of the data and obtain the cleaned data set.

[0088] like Figure 4 As shown, the trend analysis submodule performs data sorting, key performance indicator extraction and trend analysis based on the cleaned data set. Through statistical analysis and data pattern recognition, it extracts the core information and potential problems of the data to obtain the process of trend analysis results.

[0089] The process of obtaining trend analysis results is as follows: In the trend analysis submodule, based on the cleaned data set, perform data sorting and key performance indicator extraction. Use trend analysis formulas to extract core information and identify potential problems: ,in, Represents the trend analysis results, is the intercept term, each Corresponding performance indicators The influence coefficient of It is the total number of performance indicators analyzed. Through statistical analysis and data pattern recognition, the formula helps identify long-term change trends, provides a scientific basis for decision-making, and obtains trend analysis results.

[0090] like Figure 4 As shown, the decision adjustment submodule adjusts the output power of the hydrogen fuel cell group based on the trend analysis results, distributes and adjusts the power according to the preset operating threshold, matches the current load demand and operating efficiency of the power grid, and obtains the process of real-time decision information.

[0091] The process of obtaining real-time decision information is as follows: In the decision adjustment submodule, the output power of the hydrogen fuel cell group is adjusted based on the trend analysis results. The real-time decision adjustment formula is used to distribute and adjust power according to the current load demand and operating efficiency of the power grid: ,in, is the adjusted output power, is the maximum available output power, To adjust the parameters The weight of is the corresponding control parameter value, The total number of control parameters. The formula allows the output power to be adjusted dynamically according to the real-time trend analysis results, ensuring the optimization of the battery group output, meeting the preset threshold, achieving efficient power management, and obtaining real-time decision information.

[0092] like Figure 2 As shown, the cloud analysis module includes a data aggregation submodule, a pattern recognition submodule and a strategy optimization submodule.

[0093] like Figure 5 As shown, the data aggregation submodule organizes data based on real-time decision information, unifies the format of data from multiple edge nodes and eliminates redundancy, optimizes data consistency and reliability, and integrates and checks the consistency of data to obtain unified data information.

[0094] The process of obtaining unified data information is as follows: In the data aggregation submodule, data from multiple edge nodes is processed based on real-time decision information. The data format is unified and redundant data is eliminated to ensure the consistency and reliability of the overall data. The data aggregation process uses a specific formula to calculate and optimize the consistency of data integration: ,in, Represents the consistency index of the unified data, Indicates The formatted data after processing by each node, Represents the total number of nodes participating in the aggregation. The formula calculates the weighted average of all node data to ensure the integration and consistency of information, thereby improving data processing efficiency and accuracy. The aggregated data will be used for analysis and decision-making to obtain unified data information.

[0095] like Figure 5 As shown, the pattern recognition submodule is based on unified data information, statistically analyzes the operation mode and performance fluctuation of the hydrogen fuel cell group, uses a cluster analysis algorithm to identify repeated patterns and abnormal fluctuations in the data, performs behavioral trend analysis and performance fluctuation identification, and obtains behavioral fluctuation information.

[0096] The specific process of obtaining behavior fluctuation information is as follows: In the pattern recognition submodule, based on the unified data information, statistical analysis of the operation mode and performance fluctuation of the hydrogen fuel cell group is performed. Through the cluster analysis formula, repeated patterns and abnormal fluctuations in the data can be identified, and behavior trend analysis and performance fluctuation identification can be performed to provide a basis for strategy adjustment and obtain behavior fluctuation information.

[0097] The clustering analysis algorithm is shown in the following formula:

[0098] ;

[0099] The above formula is used to calculate the Euclidean distance between data points to identify stable operating modes and abnormal performance fluctuations, where: Represents data points and The Euclidean distance between and is a vector and In the The performance indicator values ​​on the dimension, It is The standard deviation in dimension, It is The weight coefficient of the dimension, is the adjustment factor, It is a data point and The observation time difference is is the overall observation period length, Indicates the number of dimensions involved in the calculation, covering all indicators that affect the performance of hydrogen fuel cells.

[0100] The specific execution process of the formula is as follows: Calculate the and performance differences, and according to the variability of each dimension Adjust the influence of these differences by dividing the difference in each dimension by its standard deviation And multiply by the corresponding weight , adjust the influence of each dimension. In addition, in order to consider the impact of time factors on clustering results, the time difference Total observation time The ratio multiplied by the adjustment factor , so that the temporal proximity of data points is taken into account in the distance calculation. This approach can more accurately reflect the operating mode and performance fluctuations of hydrogen fuel cells at different times and under different environmental conditions, determine which cells are similar to each other in performance, and identify stable operating modes and abnormal performance fluctuations.

[0101] like Figure 5 As shown, the strategy optimization submodule evaluates the effect of the current grid-connected control strategy based on the behavior fluctuation information, and adjusts the strategy according to the behavior trend and performance fluctuation, adjusts the grid-connected control parameters, optimizes energy efficiency and grid stability, and obtains the optimized control strategy.

[0102] The process of obtaining the optimized control strategy is as follows: In the strategy optimization submodule, the grid-connected control strategy is evaluated and optimized based on the behavior fluctuation information. The strategy optimization formula is used to adjust the grid-connected control parameters according to the behavior trend and performance fluctuation to optimize energy efficiency and grid stability: ,in, For the optimized control strategy, For initial policy settings, is the strategy adjustment factor, For the The weight of the control parameters, is the corresponding performance fluctuation value, To control the total number of parameters, strategy optimization not only reflects the changes in real-time data, but also takes into account the needs of long-term efficiency and stability, ensuring the optimal state of power grid operation and obtaining the optimized control strategy.

[0103] like Figure 2 As shown, the event trigger response module includes an event monitoring submodule, an event response submodule and a parameter adjustment submodule.

[0104] like Figure 6 As shown, the event monitoring submodule performs real-time monitoring of grid demand and hydrogen fuel cell performance data based on the optimized control strategy, sets thresholds to detect key changes, including sudden changes in grid load and degradation of hydrogen fuel performance, and obtains monitoring event trigger records.

[0105] The specific process of obtaining monitoring event trigger records is as follows: In the event monitoring submodule, based on the optimized control strategy, real-time monitoring of grid demand and hydrogen fuel cell performance data is performed. By setting sensitive thresholds, the monitoring module can detect key changes, including sudden changes in grid load and degradation of hydrogen fuel performance. The event trigger monitoring formula is used: ,in, To monitor event trigger indicators, is the grid load at the current time point, is the grid load at the previous time point, By comparing the load changes at consecutive time points with the preset threshold, the sudden change in demand or the decline in performance can be effectively identified, and the monitoring event record can be triggered to obtain the monitoring event trigger record.

[0106] like Figure 6 As shown, the event response submodule starts the preset emergency response strategy based on the monitoring event trigger record, adjusts the hydrogen fuel cell output, matches the immediate grid demand changes, adjusts the output power and frequency of the hydrogen fuel cell, and obtains emergency adjustment information.

[0107] The specific process of obtaining emergency adjustment information is as follows: In the event response submodule, based on the monitoring event trigger record, the preset emergency response strategy is initiated. The output of the hydrogen fuel cell is adjusted through the emergency response formula to match the immediate grid demand changes: ,in, is the adjusted output power, is the original output power, To adjust the amplitude, To meet the new grid demand, For the original grid demand, the formula dynamically adjusts the output power and frequency of the hydrogen fuel cell according to the changes in grid demand to ensure the response speed and efficiency and obtain emergency adjustment information.

[0108] like Figure 6 As shown, the parameter adjustment submodule adjusts the output parameters of the hydrogen fuel cell based on the emergency adjustment information, optimizes the compatibility between the hydrogen fuel cell equipment performance and the grid load, optimizes the operating efficiency and stability of the hydrogen fuel cell, and obtains a response adjustment result.

[0109] The specific process of obtaining the response adjustment result is as follows: In the parameter adjustment submodule, the output parameters of the hydrogen fuel cell are adjusted based on the emergency adjustment information. The parameter optimization formula is used to optimize the compatibility between the performance of the hydrogen fuel cell equipment and the grid load: ,in, is the adjusted hydrogen fuel cell output parameter, is the current parameter setting, is the adjustment factor, is the current grid load, In order to optimize the previous grid load, the formula adjusts the output parameters according to the real-time changes in the grid load, improves the operating efficiency and stability of the hydrogen fuel cell, and obtains responsive adjustment results.

[0110] like Figure 2 As shown, the adaptive scheduling control module includes a matching analysis submodule, a performance optimization submodule, and a strategy update submodule.

[0111] like Figure 7 As shown, the matching analysis submodule collects and analyzes the real-time performance data of the hydrogen fuel cell and the power grid based on the response adjustment result, and uses the data to evaluate the matching degree between the power grid demand and the hydrogen fuel cell output to obtain the matching evaluation result.

[0112] The specific process of obtaining the matching evaluation result is as follows: In the matching analysis submodule, based on the response adjustment result, the real-time performance data of the hydrogen fuel cell and the power grid are collected and analyzed. By obtaining the power grid demand and the actual output data of the hydrogen fuel cell at each time point, the matching degree between the two is calculated using the matching evaluation formula. The formula is: ,in, For the matching degree, For the The grid demand at a point in time, For the The hydrogen fuel cell output at a time point, is the total number of time points. The formula accurately evaluates the matching degree between the output of the hydrogen fuel cell and the grid demand by calculating the mean of the sum of squares of the relative deviations between demand and output at each time point, and obtains the matching evaluation result.

[0113] like Figure 7 As shown, the performance optimization submodule performs performance evaluation based on the matching evaluation results, including analyzing the efficiency, energy consumption and response time of the hydrogen fuel cell, performing performance optimization, adjusting the parameter settings of the hydrogen fuel cell, optimizing the efficiency and response capability of the hydrogen fuel cell, and obtaining performance tuning information.

[0114] The specific process of obtaining performance tuning information is as follows: In the performance optimization submodule, based on the matching evaluation results, a detailed performance evaluation is performed, including the efficiency, energy consumption and response time of the hydrogen fuel cell. The performance optimization formula is used to optimize the parameter settings by analyzing the input and output energy and their response time. The formula is: ,in, To optimize the results for performance, is the efficiency coefficient of hydrogen fuel cell, is the input energy, is the output energy, is the response time, is the maximum allowable response time. Through this formula, the energy efficiency and response capability of the hydrogen fuel cell can be comprehensively considered, the performance bottlenecks and optimization points can be identified, and the parameter settings can be adjusted to improve the operating efficiency and response capability of the hydrogen fuel cell and obtain performance tuning information.

[0115] like Figure 7 As shown, the strategy update submodule uses a dynamic optimization algorithm based on performance tuning information to adjust the operation mode of the hydrogen fuel cell, adapt to the real-time changes in the grid load, optimize the stable operation of the grid, and obtain matching scheduling decision information.

[0116] The specific process of obtaining matching scheduling decision information is as follows: in the strategy update submodule, based on the performance tuning information, the operation mode of the hydrogen fuel cell is adjusted, and a dynamic optimization formula is used to dynamically adjust the strategy according to the real-time grid load changes and performance tuning information. By adjusting the strategy settings in real time, it adapts to the real-time changes in the grid load, optimizes the output of the hydrogen fuel cell and the stability of the grid, ensures efficient and stable operation under different load conditions, and obtains matching scheduling decision information.

[0117] The dynamic optimization algorithm is shown in the following formula:

[0118] ;

[0119] By calculating the scheduling cost, the matching scheduling decision information is obtained, where: is the optimization objective, i.e. minimizing the total cost, It's in time The hydrogen fuel cell output, It's in time The grid demand, is the total time period, is a smoothing parameter that controls the penalty for output changes between adjacent time steps.

[0120] The specific execution process of the formula is as follows: For each time step Calculating the output of a hydrogen fuel cell and grid demand The deviation between the two time steps is calculated, and the sum of the squares of these deviations is calculated. This part aims to evaluate the matching degree between the output of the hydrogen fuel cell and the grid demand to ensure the consistency between energy supply and demand. By adding the output changes of adjacent time steps , taking into account the stationarity of the output. By applying a smoothing parameter to the sum of the changes , the fluctuation of output can be controlled to reduce the cost and potential risk caused by drastic changes. The optimal solution is found by adjusting the value of , which ensures the grid demand response while making the operation of the hydrogen fuel cell as smooth as possible.

[0121] like Figure 2 As shown, the multi-objective optimization integration module includes a goal setting submodule, a decision search submodule, and an optimization execution submodule.

[0122] like Figure 8 As shown, the target setting submodule evaluates the operating cost, efficiency and response time of the hydrogen fuel cell based on the matching scheduling decision information, sets multiple optimization goals, formulates optimization strategies and target priorities, and obtains the optimization target framework.

[0123] The specific process of obtaining the optimization target framework is as follows: In the target setting submodule, based on the matching scheduling decision information, the operating cost, efficiency and response time of the hydrogen fuel cell are evaluated in detail, various cost data generated during the operation are collected, including fuel cost, maintenance cost and operating cost, and the efficiency of the battery is calculated, and a comprehensive evaluation is performed through energy conversion efficiency and response time. The following formula is used to set the optimization target framework: ,in, represents the optimization target framework, is the running cost, including fuel, maintenance and operation cost, is the efficiency coefficient of hydrogen fuel cells, reflecting the energy conversion efficiency. is the target weight coefficient, which is used to balance the importance of different optimization objectives. For response time, the formula helps to set multiple optimization goals by combining cost, efficiency and response time, and sets priorities for each goal to form a comprehensive optimization goal framework, ensure the coordination and consistency of various optimization goals, and obtain the optimization goal framework.

[0124] like Figure 8 As shown, the decision search submodule formulates multiple adjustment strategies based on the optimization target framework, analyzes the potential results of multiple adjustment strategies, identifies strategies that meet the set goals, and obtains the target strategy identification results.

[0125] The specific process of obtaining the target strategy identification result is as follows: In the decision search submodule, based on the optimization target framework, a variety of adjustment strategies are formulated, the implementation effects of different strategies are simulated, the potential results of each strategy under different conditions are analyzed, and the decision search formula is used for identification and screening: ,in, Identify results for the target strategy, For the The weight of an adjustment strategy reflects the importance of the strategy. For the The result value of each strategy is used to measure the effectiveness of the strategy implementation. is the total number of strategies. This formula calculates the weighted sum of all strategies to identify the optimal strategy that meets the set goal and obtains the target strategy identification result.

[0126] like Figure 8 As shown, the optimization execution submodule adjusts the operating parameters of the hydrogen fuel cell based on the target strategy identification result, matches the grid demand and optimizes the efficiency of the hydrogen fuel cell, balances the operating goals of the hydrogen fuel cell, and obtains optimized operating information.

[0127] The specific process of obtaining optimized operation information is as follows: In the optimization execution submodule, based on the target strategy identification results, the operation parameters of the hydrogen fuel cell are adjusted, the grid demand and the actual operation status of the hydrogen fuel cell are analyzed, and the operation parameters are dynamically adjusted through the optimization execution formula to achieve the best performance: ,in, Indicates optimized operation information, reflecting the adjusted system status. is the adjustment coefficient used to adjust the output power of the hydrogen fuel cell. The adjusted operating parameters include power output, frequency, etc. is the grid demand coefficient, reflecting the current load demand of the grid. For the grid load, the formula comprehensively adjusts the operating parameters of the hydrogen fuel cell and the grid demand to ensure that the hydrogen fuel cell can achieve efficient and stable operation while meeting the grid demand and obtain optimized operation information.

[0128] The above system improves the energy management and utilization efficiency of the hydrogen fuel cell group through real-time optimization scheduling and dynamic allocation of data streams. The real-time evaluation and dynamic adjustment of the real-time operation data of hydrogen fuel cells and the grid status information can flexibly respond and adjust under changing grid load conditions, ensuring the stability of the grid. Data cleaning and power adjustment are carried out through edge nodes to match the current grid load demand, avoid energy waste and potential grid safety issues caused by load mismatch, and through data aggregation and behavior trend analysis, predict future changes and adjust the grid control strategy accordingly. This forward-looking management improves the overall energy efficiency and operating cost-effectiveness of the grid. The application of adaptive scheduling control and multi-objective optimization balances cost, efficiency and response time, optimizes the operation strategy, and enhances economy.

[0129] Embodiment 2:

[0130] The hydrogen energy group control and grid connection method comprises the following steps:

[0131] Obtain the operating data of the hydrogen fuel cell group and the power grid status data, adjust the data flow between the cloud and edge nodes according to the computing requirements and resource availability, and obtain real-time data flow distribution information;

[0132] Use data stream allocation information to adjust the output power of hydrogen fuel cells and match the corresponding grid load to obtain real-time decision information;

[0133] According to the decision-making information, analyze the behavior trend and performance fluctuation of the hydrogen fuel cell group, adjust the grid-connected control strategy, and obtain the optimized control strategy;

[0134] The optimized control strategy is used to implement grid connection, monitor grid demand and real-time performance data of hydrogen fuel cells, trigger corresponding events through set monitoring thresholds, and respond to grid changes by adjusting the output power and frequency of hydrogen fuel cells to obtain response adjustment results;

[0135] According to the response adjustment results, combined with the real-time demand of the power grid, the grid demand matching degree is evaluated, the performance output of the hydrogen fuel cell is adjusted, and the matching scheduling decision information is obtained;

[0136] By using the matching scheduling decision information, the operating cost, efficiency and response time of the hydrogen fuel cell are analyzed. By adjusting the operating strategy of the hydrogen fuel cell and balancing the operating objectives of the hydrogen fuel cell, the optimized operating information is obtained.

[0137] Through real-time optimization scheduling and dynamic allocation of data streams, the energy management and utilization efficiency of the hydrogen fuel cell group is improved. The real-time evaluation and dynamic adjustment of the real-time operation data of hydrogen fuel cells and the grid status information can flexibly respond and adjust under changing grid load conditions, ensuring the stability of the grid. Data cleaning and power adjustment are performed through edge nodes to match the current grid load demand, avoiding energy waste and potential grid safety issues caused by load mismatch. Through data aggregation and behavioral trend analysis, future changes can be predicted and the grid control strategy can be adjusted accordingly. This forward-looking management improves the overall energy efficiency and operating cost-effectiveness of the grid. The application of adaptive scheduling control and multi-objective optimization balances cost, efficiency and response time, optimizes the operation strategy, and enhances economy.

[0138] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. Hydrogen energy group control and grid connection system, characterized in that: include: The data flow dynamic allocation module is configured to: obtain the operation data of the hydrogen fuel cell group and the power grid status data, adjust the flow of data between the cloud and the edge nodes according to the computing requirements and resource availability, and obtain real-time data flow allocation information; The edge decision implementation module is configured to: use the data stream allocation information to adjust the output power of the hydrogen fuel cell and match the corresponding grid load to obtain real-time decision information; The cloud analysis module is configured to: analyze the behavior trend and performance fluctuation of the hydrogen fuel cell group according to the decision information, adjust the grid-connected control strategy, and obtain the optimized control strategy; The operation data of the hydrogen fuel cell group and the power grid status data are obtained, and after integrity diagnosis, the matching degree between the current computing resources and the data processing requirements is evaluated. The real-time data flow distribution information is obtained by combining the availability and computing power of computing resources, as well as the data processing speed and network delay. It also has an event-triggered response module, an adaptive scheduling control module, and a multi-objective optimization integration module; The event trigger response module is configured to: implement grid connection using the optimized control strategy, monitor the grid demand and the real-time performance data of the hydrogen fuel cell, trigger the corresponding event through the set monitoring threshold, and respond to the grid change by adjusting the output power and frequency of the hydrogen fuel cell to obtain the response adjustment result; The adaptive dispatch control module is configured to: evaluate the matching degree of the grid demand according to the response adjustment result and the real-time demand of the grid, adjust the performance output of the hydrogen fuel cell, and obtain matching dispatch decision information; The multi-objective optimization integrated module is configured to: utilize the matching scheduling decision information to analyze the operating cost, efficiency and response time of the hydrogen fuel cell, and obtain optimized operating information by adjusting the operating strategy of the hydrogen fuel cell and balancing the operating objectives of the hydrogen fuel cell.

2. The hydrogen energy group control and grid connection system according to claim 1, characterized in that: Real-time data stream distribution information includes data quality assessment after edge node processing, real-time power adjustment instructions and hydrogen fuel cell output parameters; optimized control strategy includes behavior pattern analysis results, predicted performance fluctuation data and optimized grid-connected control parameters; response adjustment results include event identification type, response action measures and emergency adjustment parameters of grid-connected operation; matching scheduling decision information includes grid demand matching degree, hydrogen fuel cell performance optimization indicators and adjusted energy output strategy; optimized operation information includes cost-efficiency balance analysis information and optimization indicators of energy efficiency and response time.

3. The hydrogen energy group control and grid connection system according to claim 1, characterized in that: The data flow dynamic allocation module includes a data evaluation submodule, a resource matching submodule and a data flow adjustment submodule; The data evaluation submodule checks the information missing points, identifies the applicability of the data, evaluates the integrity and accuracy of the data, and obtains data integrity diagnostic information based on the real-time operating data of the hydrogen fuel cell group and the power grid status information; The resource matching submodule evaluates the matching degree between the current computing resources and the data processing requirements based on the data integrity diagnostic information, adjusts the resource allocation based on the availability and computing power of the computing resources, matches the real-time data processing requirements, and obtains resource adaptation evaluation information; The data flow adjustment submodule adjusts the flow of data between the cloud and edge nodes based on the resource adaptation evaluation information, changes the data distribution path and processing nodes in combination with the data processing speed and network delay, optimizes the data processing efficiency, and obtains real-time data flow distribution information.

4. The hydrogen energy group control and grid connection system according to claim 3, characterized in that: The edge decision implementation module includes a data cleaning submodule, a trend analysis submodule, and a decision adjustment submodule; The data cleaning submodule performs data cleaning processing on the edge node based on the real-time data flow allocation information, removes outliers, fills missing data, and corrects erroneous data, unifies the data format and verifies the range, optimizes the data quality, and obtains a cleaned data set; The trend analysis submodule performs data sorting, key performance indicator extraction and trend analysis based on the cleaned data set, extracts the core information and potential problems of the data through statistical analysis and data pattern recognition, and obtains trend analysis results; The decision adjustment submodule adjusts the output power of the hydrogen fuel cell group based on the trend analysis results, distributes and adjusts the power according to the preset operating threshold, matches the current load demand and operating efficiency of the power grid, and obtains real-time decision information.

5. The hydrogen energy group control and grid connection system according to claim 4, characterized in that: The cloud analysis module includes a data aggregation submodule, a pattern recognition submodule, and a strategy optimization submodule; The data aggregation submodule organizes data based on the real-time decision information, unifies the format of data from multiple edge nodes and eliminates redundancy, optimizes data consistency and reliability, and integrates and checks the consistency of data to obtain unified data information; The pattern recognition submodule, based on the unified data information, statistically analyzes the operation mode and performance fluctuation of the hydrogen fuel cell group, uses a cluster analysis algorithm to identify repeated patterns and abnormal fluctuations in the data, performs behavior trend analysis and performance fluctuation identification, and obtains behavior fluctuation information; The strategy optimization submodule evaluates the effect of the current grid-connected control strategy based on the behavior fluctuation information, and adjusts the strategy according to the behavior trend and performance fluctuation, adjusts the grid-connected control parameters, optimizes energy efficiency and grid stability, and obtains the optimized control strategy.

6. The hydrogen energy group control and grid connection system according to claim 1, characterized in that: The event trigger response module includes an event monitoring submodule, an event response submodule and a parameter adjustment submodule; The event monitoring submodule performs real-time monitoring of grid demand and hydrogen fuel cell performance data based on the optimized control strategy, sets thresholds to detect key changes, including grid load mutations and hydrogen fuel performance degradation, and obtains monitoring event trigger records; The event response submodule starts a preset emergency response strategy based on the monitoring event trigger record, adjusts the hydrogen fuel cell output, matches the immediate grid demand change, adjusts the output power and frequency of the hydrogen fuel cell, and obtains emergency adjustment information; The parameter adjustment submodule adjusts the output parameters of the hydrogen fuel cell based on the emergency adjustment information, optimizes the compatibility between the hydrogen fuel cell equipment performance and the grid load, optimizes the operating efficiency and stability of the hydrogen fuel cell, and obtains a response adjustment result.

7. The hydrogen energy group control and grid connection system according to claim 1, characterized in that: The adaptive scheduling control module includes a matching analysis submodule, a performance optimization submodule and a strategy update submodule; The matching analysis submodule collects and analyzes the real-time performance data of the hydrogen fuel cell and the power grid based on the response adjustment result, and uses the data to evaluate the matching degree between the power grid demand and the hydrogen fuel cell output to obtain a matching degree evaluation result; The performance optimization submodule performs performance evaluation based on the matching evaluation result, including analyzing the efficiency, energy consumption and response time of the hydrogen fuel cell, performing performance optimization, adjusting the parameter settings of the hydrogen fuel cell, optimizing the efficiency and response capability of the hydrogen fuel cell, and obtaining performance tuning information; Based on the performance tuning information, the strategy update submodule uses a dynamic optimization algorithm to adjust the operation mode of the hydrogen fuel cell, adapt to the real-time changes in the power grid load, optimize the stable operation of the power grid, and obtain matching scheduling decision information.

8. The hydrogen energy group control and grid connection system according to claim 1, characterized in that: The multi-objective optimization integrated module includes a target setting submodule, a decision search submodule, and an optimization execution submodule; The target setting submodule evaluates the operating cost, efficiency and response time of the hydrogen fuel cell based on the matching scheduling decision information, sets multiple optimization targets, formulates optimization strategies and target priorities, and obtains an optimization target framework; The decision search submodule formulates a variety of adjustment strategies based on the optimization target framework, identifies strategies that meet the set goals by analyzing the potential results of the various adjustment strategies, and obtains the target strategy identification results; The optimization execution submodule adjusts the hydrogen fuel cell operating parameters based on the target strategy identification result, matches the grid demand and optimizes the hydrogen fuel cell efficiency, balances the operating objectives of the hydrogen fuel cell, and obtains optimized operating information.

9. A method for realizing hydrogen energy group control and grid connection based on the system according to any one of claims 1 to 8, characterized in that: The following steps are involved: Obtain the operating data of the hydrogen fuel cell group and the power grid status data, adjust the data flow between the cloud and edge nodes according to the computing requirements and resource availability, and obtain real-time data flow distribution information; Use data stream allocation information to adjust the output power of hydrogen fuel cells and match the corresponding grid load to obtain real-time decision information; According to the decision-making information, analyze the behavior trend and performance fluctuation of the hydrogen fuel cell group, adjust the grid-connected control strategy, and obtain the optimized control strategy; The optimized control strategy is used to implement grid connection, monitor grid demand and real-time performance data of hydrogen fuel cells, trigger corresponding events through set monitoring thresholds, and respond to grid changes by adjusting the output power and frequency of hydrogen fuel cells to obtain response adjustment results; According to the response adjustment results, combined with the real-time demand of the power grid, the grid demand matching degree is evaluated, the performance output of the hydrogen fuel cell is adjusted, and the matching scheduling decision information is obtained; By using the matching scheduling decision information, the operating cost, efficiency and response time of the hydrogen fuel cell are analyzed. By adjusting the operating strategy of the hydrogen fuel cell and balancing the operating objectives of the hydrogen fuel cell, the optimized operating information is obtained.

Images