Optimized scheduling method and system for power distribution of electrolytic cell group under wind power fluctuation condition

Abstract

The invention provides an optimization scheduling method and system for power distribution of an electrolytic cell group under a wind power fluctuation condition, and relates to the technical field of wind power grid-connected power generation control, and the method comprises the steps: collecting wind power plant power data and electrolytic cell operation parameters, carrying out the adaptive segmentation processing of the power data, constructing a fluctuation feature space, predicting the fluctuation risk, and carrying out the optimization scheduling of the power distribution of the electrolytic cell group. And an electrolytic cell regulation capability evaluation system is established and dynamically grouped, and a power regulation matrix is constructed to calculate an optimal power distribution proportion, so that coordinated regulation of wind power fluctuation by the electrolytic cell group is realized, and the system operation stability and the energy utilization efficiency are improved.

Description

Technical Field

[0001] The present invention relates to a wind power grid-connected power generation control technology, and in particular to an optimized scheduling method and system for power distribution of an electrolyzer group under wind power fluctuation conditions. Background Art

[0002] As the scale of new energy integration continues to expand, the volatility of renewable energy sources such as wind power poses a serious challenge to the safe and stable operation of the power grid. Large-scale hydrogen production, as an important means of absorbing new energy, requires addressing the key issue of how electrolyzer clusters can adapt to wind power fluctuations.

[0003] Existing electrolyzer power allocation methods primarily rely on fixed grouping strategies, which are unable to optimize and adjust in real time based on wind power fluctuation characteristics and the dynamic response capabilities of the electrolyzers. Furthermore, traditional allocation algorithms fail to fully consider the coupling relationships within the electrolyzer cluster, making it difficult to accurately track wind power fluctuations, reducing system efficiency.

[0004] As a critical load for absorbing renewable energy, the power allocation method for electrolyzer clusters directly impacts wind power absorption. Existing methods cannot accurately predict wind power fluctuation trends, nor do they establish a mapping between the dynamic response characteristics of electrolyzers and control requirements. This makes it difficult to achieve coordinated control of wind power fluctuations by electrolyzer clusters. Therefore, a method for optimizing power allocation for electrolyzer clusters based on dynamic grouping is urgently needed. Summary of the Invention

[0005] The embodiments of the present invention provide a method and system for optimizing the power distribution of an electrolyzer group under wind power fluctuation conditions, which can solve the problems in the prior art.

[0006] A first aspect of an embodiment of the present invention provides a method for optimizing power allocation of an electrolyzer group under wind power fluctuation conditions, comprising:

[0007] Collect wind farm output power data and electrolyzer group operating parameters;

[0008] Adaptively segment the output power data, calculate the power fluctuation feature vector within each time period, construct a three-dimensional fluctuation feature space based on the power fluctuation feature vector, extract the fluctuation trend trajectory in the three-dimensional fluctuation feature space, predict future fluctuation risks, and generate time-based control instructions;

[0009] A multi-dimensional regulation capacity evaluation system is constructed based on the operating parameters of the electrolytic cells. A mapping relationship between dynamic response characteristics and time-segment regulation requirements is established. The mapping relationship is used to calculate the comprehensive regulation capacity index of each electrolytic cell. The electrolytic cells are graded and prioritized according to the comprehensive regulation capacity index to generate a dynamic grouping plan for the electrolytic cells.

[0010] A power regulation matrix is ​​constructed based on the dynamic grouping scheme of electrolytic cells. A recursive iterative method is used to calculate the optimal power allocation ratio of each electrolytic cell in the power regulation matrix, and a control instruction containing the real-time power setting value of each electrolytic cell is generated.

[0011] The real-time power setting value is transmitted to the control unit of each electrolyzer to perform power regulation, and the real-time response data of the electrolyzer is collected. The control instructions are optimized according to the real-time response data to achieve coordinated control of the electrolyzer group on wind power fluctuations.

[0012] In an optional embodiment,

[0013] The output power data is adaptively segmented and the power fluctuation feature vector in each time period is calculated. The three-dimensional fluctuation feature space is constructed based on the power fluctuation feature vector, including:

[0014] Calculating the power difference between adjacent sampling points in the wind power data to obtain a power change rate sequence, performing sliding window processing on the power change rate sequence, and calculating the mean and standard deviation of the power change rate in each window;

[0015] A first-order difference sequence is constructed based on the mean of the power change rate, and a fluctuation amplitude sequence is constructed based on the standard deviation of the power change rate. The first-order difference sequence and the fluctuation amplitude sequence are weightedly combined to obtain a segmentation criterion. An adaptive threshold value is calculated for the segmentation criterion. A reference threshold value is determined based on the statistical distribution characteristics of the power change rate sequence. The threshold coefficient is dynamically adjusted in combination with the cumulative distribution function of the fluctuation amplitude sequence to obtain a segmentation threshold value.

[0016] Sampling points greater than the segmentation threshold are marked as segmentation points, and the wind power data sequence is divided into multiple time periods according to the segmentation points. The power fluctuation characteristics of the wind power data sequence in each time period are extracted, including the average power value, the power change rate and the power fluctuation frequency. The power fluctuation characteristics are combined to construct a power fluctuation feature vector. The feature contribution of the power fluctuation feature vector is calculated using the principal component analysis method, and the three feature directions with the largest cumulative contribution are selected to construct a three-dimensional fluctuation feature space.

[0017] In an optional embodiment,

[0018] Extracting the fluctuation trend trajectory in the three-dimensional fluctuation feature space, predicting future fluctuation risks and generating time-based control instructions include:

[0019] Connecting the power fluctuation feature vectors in a three-dimensional fluctuation feature space in time sequence to form a fluctuation trend trajectory, calculating the distance and direction angle between adjacent trajectory points in the fluctuation trend trajectory, determining a set of neighboring points for each trajectory point, calculating the local evolution direction of each trajectory point based on the set of neighboring points, and taking the ratio of the displacement change between adjacent trajectory points to the time interval as the evolution rate;

[0020] The fluctuation trend trajectory is divided into zones and counted by evolution direction. The product of the proportion of trajectory points in each direction zone and the average evolution rate is calculated to determine the development probability of each evolution direction. The direction with the highest development probability is selected as the predicted trend. The power fluctuation risk value is obtained by combining the average evolution rate of this direction.

[0021] The electrolytic cell control response requirement is set according to the power fluctuation risk value, the power regulation rate and steady-state error of each electrolytic cell are calculated using the electrolytic cell operating parameters, the control response requirement is compared with the power regulation rate and steady-state error of the electrolytic cell, the response matching degree is calculated, the electrolytic cells are grouped and sorted based on the response matching degree, and the electrolytic cell combination with the highest matching degree is selected as the target electrolytic cell combination. For the target electrolytic cell combination, the maximum regulation power and response time constraint are calculated according to its operating parameters, and the target regulation power and execution timing of each time period are determined in combination with the power fluctuation risk value to generate a time period control instruction.

[0022] In an optional embodiment,

[0023] A multi-dimensional regulation capability evaluation system is constructed based on the electrolytic cell operating parameters. A mapping relationship between dynamic response characteristics and time-segment regulation requirements is established. The mapping relationship is used to calculate the comprehensive regulation capability index of each electrolytic cell. The electrolytic cells are graded and prioritized according to the comprehensive regulation capability index. The dynamic grouping scheme for electrolytic cells is generated, including:

[0024] Based on the acquired electrolytic cell operation data, a multi-dimensional evaluation index system including response time, adjustment accuracy and efficiency loss is established, and the response characteristic curve, accuracy index value and loss index value of the electrolytic cell are calculated based on the electrolytic cell operation data;

[0025] Obtaining system regulation demand data, performing a matching analysis on the regulation demand data with the response characteristic curve, accuracy index value, and loss index value of the electrolytic cell, obtaining an adaptability evaluation value of the electrolytic cell to the regulation demand, dynamically evaluating the electrolytic cell based on the adaptability evaluation value, and calculating a comprehensive regulation capability index value of the electrolytic cell based on the regulation importance weight of each regulation period;

[0026] Obtaining the cumulative number of adjustments and adjustment intensity data of the electrolytic cell and calculating a fatigue index value; and classifying the electrolytic cell into a fast response level, a conventional adjustment level, and a standby level according to the comprehensive adjustment capability index value;

[0027] In each level of electrolytic cells, the comprehensive adjustment capability index value and the fatigue index value are weightedly calculated to obtain a priority coefficient, and the electrolytic cells are sorted according to the priority coefficient; when the fatigue index value exceeds the preset fatigue threshold, the electrolytic cell is downgraded and the priority ranking is updated to generate a dynamic electrolytic cell grouping scheme containing grading information and priority information.

[0028] In an optional embodiment,

[0029] Based on the adaptability evaluation value, the electrolytic cell is dynamically evaluated. According to the weight of the importance of regulation in each regulation period, the comprehensive regulation capability index value of the electrolytic cell is calculated, including:

[0030] Collect wind power fluctuation data, obtain power fluctuation inflection points through extreme value detection, divide the evaluation period into multiple regulation periods according to the power fluctuation inflection points, and calculate the regulation difficulty coefficient based on the power change trend within each regulation period;

[0031] Obtaining the power fluctuation amplitude, fluctuation frequency and system stability margin of each regulation period, constructing a regulation period weight evaluation matrix, and calculating the regulation importance weight of each regulation period according to the weight evaluation matrix;

[0032] The operating data of the electrolytic cell in each adjustment period is collected, and the adaptability evaluation value of the electrolytic cell in each adjustment period is calculated based on the operating data and the control difficulty coefficient. The adaptability evaluation value is normalized, and the comprehensive adjustment capability index value of the electrolytic cell is obtained by combining the control importance weight.

[0033] In an optional embodiment,

[0034] Based on the dynamic grouping scheme of electrolytic cells, a power regulation matrix is ​​constructed. A recursive iterative method is used to calculate the optimal power allocation ratio of each electrolytic cell in the power regulation matrix. The control instructions containing the real-time power setting value of each electrolytic cell are generated, including:

[0035] Collect the operating power, power fluctuation and response time of the electrolytic cell group, and calculate the dynamic response characteristics of the electrolytic cell based on the operating power, power fluctuation and response time;

[0036] Constructing a power regulation matrix based on the dynamic grouping scheme of the electrolytic cells, calculating the inter-group power coupling coefficient based on the dynamic response characteristics of the electrolytic cells, and writing the inter-group power coupling coefficient into the corresponding position of the power regulation matrix to obtain an initial power regulation matrix;

[0037] Performing a difference operation on each element value of the initial power regulation matrix and the rated power value of the electrolytic cell to obtain a power regulation deviation matrix, calculating an inter-group adaptive weight based on the power regulation deviation matrix, and multiplying the inter-group adaptive weight by the initial power regulation matrix to obtain an optimized power regulation matrix;

[0038] Constructing a multidimensional optimization objective function based on the optimized power regulation matrix and the power regulation deviation matrix, setting the power regulation deviation, the inter-group power coupling coefficient and the dynamic response characteristic as optimization variables, and calculating the optimization variable weight coefficients according to the system operation requirements;

[0039] A recursive iterative method is used to calculate the power allocation ratio of each electrolytic cell in the power regulation matrix. The adaptive step size is calculated by multiplying the optimization variable weight coefficient with the gradient of the multidimensional optimization objective function. The dynamic compensation factor is calculated based on the historical iterative data to obtain the optimal power allocation ratio. The optimal power allocation ratio is multiplied by the rated power of the electrolytic cell to obtain the real-time power setting value of each electrolytic cell, and the control instruction is generated.

[0040] A second aspect of an embodiment of the present invention provides an optimized scheduling system for power distribution of an electrolyzer group under wind power fluctuation conditions, comprising:

[0041] The first unit is used to collect wind farm output power data and electrolyzer group operating parameters;

[0042] The second unit is used to perform adaptive segmentation processing on the output power data, calculate the power fluctuation feature vector in each time period, construct a three-dimensional fluctuation feature space based on the power fluctuation feature vector, extract the fluctuation trend trajectory in the three-dimensional fluctuation feature space, predict future fluctuation risks and generate time-based control instructions;

[0043] The third unit is used to build a multi-dimensional regulation capability evaluation system based on the operating parameters of the electrolytic cells, establish a mapping relationship between dynamic response characteristics and time-based regulation requirements, use the mapping relationship to calculate the comprehensive regulation capability index of each electrolytic cell, and perform hierarchical screening and priority sorting of the electrolytic cells based on the comprehensive regulation capability index to generate a dynamic grouping plan for the electrolytic cells;

[0044] The fourth unit is used to construct a power regulation matrix based on the dynamic grouping scheme of the electrolytic cells, calculate the optimal power allocation ratio of each electrolytic cell in the power regulation matrix using a recursive iterative method, and generate a control instruction containing the real-time power setting value of each electrolytic cell;

[0045] The fifth unit is used to transmit the real-time power setting value to the control unit of each electrolyzer to perform power regulation, and collect the real-time response data of the electrolyzer, optimize the control instructions according to the real-time response data, and realize the coordinated control of the electrolyzer group on wind power fluctuations.

[0046] According to a third aspect of an embodiment of the present invention, an electronic device is provided, including:

[0047] processor;

[0048] a memory for storing processor-executable instructions;

[0049] The processor is configured to call the instructions stored in the memory to execute the aforementioned method.

[0050] According to a fourth aspect of an embodiment of the present invention, a computer-readable storage medium is provided, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the method described above is implemented.

[0051] In this embodiment, by adaptively segmenting and processing wind power data and constructing a three-dimensional fluctuation feature space, accurate identification and prediction of wind power fluctuation trends are achieved, effectively reducing the blindness of electrolyzer group regulation and control, and improving the system's adaptability to different types of power fluctuations. A multi-dimensional regulation capability evaluation system and a dynamic grouping mechanism for electrolyzers are established, which realizes the reasonable classification and regulation priority ranking of electrolyzers with different response characteristics, fully utilizes the differentiated regulation potential of each electrolyzer, and significantly improves the overall coordination and flexibility of the electrolyzer group. A recursive iterative method is used to calculate the optimal power allocation ratio, and the control instructions are optimized by real-time response data, which realizes the accurate tracking and smooth control of wind power fluctuations by the electrolyzer group, improves hydrogen energy production efficiency, reduces electrolyzer equipment loss, and extends the system service life, providing technical support for the stable operation of the wind power-hydrogen energy system. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 Schematic diagram of a flow chart of a method for optimizing power allocation of an electrolyzer group under wind power fluctuation conditions according to an embodiment of the present invention;

[0053] Figure 2 This is a heat diagram showing the relationship between electrolytic cell adjustment accuracy and efficiency loss according to an embodiment of the present invention;

[0054] Figure 3 This is a bar chart comparing the adjustment capabilities of different electrolytic cell types according to an embodiment of the present invention. DETAILED DESCRIPTION

[0055] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings 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 making creative efforts shall fall within the scope of protection of the present invention.

[0056] The following specific embodiments are used to describe the technical solution of the present invention in detail. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0057] Figure 1 FIG. 1 is a flow chart of an optimized scheduling method for power distribution of an electrolyzer group under wind power fluctuation conditions according to an embodiment of the present invention. Figure 1 As shown, the method includes:

[0058] Collect wind farm output power data and electrolyzer group operating parameters;

[0059] Adaptively segment the output power data, calculate the power fluctuation feature vector within each time period, construct a three-dimensional fluctuation feature space based on the power fluctuation feature vector, extract the fluctuation trend trajectory in the three-dimensional fluctuation feature space, predict future fluctuation risks, and generate time-based control instructions;

[0060] A multi-dimensional regulation capacity evaluation system is constructed based on the operating parameters of the electrolytic cells. A mapping relationship between dynamic response characteristics and time-segment regulation requirements is established. The mapping relationship is used to calculate the comprehensive regulation capacity index of each electrolytic cell. The electrolytic cells are graded and prioritized according to the comprehensive regulation capacity index to generate a dynamic grouping plan for the electrolytic cells.

[0061] A power regulation matrix is ​​constructed based on the dynamic grouping scheme of electrolytic cells. A recursive iterative method is used to calculate the optimal power allocation ratio of each electrolytic cell in the power regulation matrix, and a control instruction containing the real-time power setting value of each electrolytic cell is generated.

[0062] The real-time power setting value is transmitted to the control unit of each electrolyzer to perform power regulation, and the real-time response data of the electrolyzer is collected. The control instructions are optimized according to the real-time response data to achieve coordinated control of the electrolyzer group on wind power fluctuations.

[0063] In an optional embodiment, adaptive segmentation processing is performed on the output power data, a power fluctuation feature vector in each time period is calculated, and a three-dimensional fluctuation feature space is constructed based on the power fluctuation feature vector, including:

[0064] Calculating the power difference between adjacent sampling points in the wind power data to obtain a power change rate sequence, performing sliding window processing on the power change rate sequence, and calculating the mean and standard deviation of the power change rate in each window;

[0065] A first-order difference sequence is constructed based on the mean of the power change rate, and a fluctuation amplitude sequence is constructed based on the standard deviation of the power change rate. The first-order difference sequence and the fluctuation amplitude sequence are weightedly combined to obtain a segmentation criterion. An adaptive threshold value is calculated for the segmentation criterion. A reference threshold value is determined based on the statistical distribution characteristics of the power change rate sequence. The threshold coefficient is dynamically adjusted in combination with the cumulative distribution function of the fluctuation amplitude sequence to obtain a segmentation threshold value.

[0066] Sampling points greater than the segmentation threshold are marked as segmentation points, and the wind power data sequence is divided into multiple time periods according to the segmentation points. The power fluctuation characteristics of the wind power data sequence in each time period are extracted, including the average power value, the power change rate and the power fluctuation frequency. The power fluctuation characteristics are combined to construct a power fluctuation feature vector. The feature contribution of the power fluctuation feature vector is calculated using the principal component analysis method, and the three feature directions with the largest cumulative contribution are selected to construct a three-dimensional fluctuation feature space.

[0067] For example, wind farm output power data is collected through a SCADA system with a sampling frequency of one minute. This data is collected for 24 hours, generating a time series of 1,440 sampling points. This data is then adaptively segmented to identify time periods with different fluctuation characteristics, providing a basis for subsequent power allocation to the electrolyzer cluster.

[0068] When processing wind power data, the power difference between adjacent sampling points is calculated to generate a power rate of change sequence. For example, consider a wind farm with a rated capacity of 100 MW. On a particular day, the power values ​​of two adjacent sampling points are 45.6 MW and 47.2 MW, respectively. This corresponds to a power rate of change of 1.6 MW / min. This operation is performed on the entire power data sequence, resulting in a power rate of change sequence with a length of 1439.

[0069] A sliding window process is performed on the power rate of change series, with a window size of 30 sampling points and a sliding step of 1 sampling point. Within each window, the mean and standard deviation of the power rate of change are calculated. For the wind farm described above, for a specific time window, the calculated mean power rate of change is 0.85 MW / min and the standard deviation is 1.24 MW / min. This sliding window process yields a series of mean and standard deviation values ​​for the power rate of change, both with a length of 1410.

[0070] Construct a first-order difference sequence based on the mean power rate sequence. Calculate the difference in the mean power rate between adjacent windows to obtain a first-order difference sequence. For example, if the mean power rate of change in two adjacent windows is 0.85 MW / min and 1.03 MW / min, the corresponding first-order difference is 0.18 MW / min. Perform this operation on the entire mean power rate sequence, resulting in a first-order difference sequence of length 1409.

[0071] Based on the standard deviation sequence of the power rate of change, a fluctuation amplitude sequence is constructed. The fluctuation amplitude sequence directly uses the standard deviation of the power rate of change. A weighted combination of the first-order difference sequence and the fluctuation amplitude sequence is performed to obtain the segmentation criterion. The weight coefficients are determined through historical data analysis, with the weight of the first-order difference sequence being 0.6 and the weight of the fluctuation amplitude sequence being 0.4. For example, at a certain moment, the first-order difference value is 0.18MW / min and the fluctuation amplitude value is 1.24MW / min. The segmentation criterion value is 0.6×0.18+0.4×1.24=0.604MW / min.

[0072] Adaptive threshold calculation is performed on the segmentation criterion. The benchmark threshold is determined based on the statistical distribution characteristics of the power change rate sequence, and twice the standard deviation of the power change rate sequence is used as the benchmark threshold. Taking the above-mentioned wind farm as an example, the standard deviation of the power change rate sequence is 1.5MW / min, so the benchmark threshold is 3.0MW / min. The threshold coefficient is dynamically adjusted in combination with the cumulative distribution function of the fluctuation amplitude sequence. The fluctuation amplitude of the cumulative distribution function value of the fluctuation amplitude sequence at the 0.9 quantile is 2.1MW / min, and the corresponding threshold coefficient is 0.7. The final segmentation threshold is the benchmark threshold multiplied by the threshold coefficient, that is, 3.0×0.7=2.1MW / min.

[0073] Sampling points with a value greater than the segmentation threshold are marked as segmentation points. Sampling points with a segmentation criterion value greater than 2.1 MW / min are marked as segmentation points. In this example, a total of 8 segmentation points are identified, and the wind power data series is divided into 9 time periods, with the lengths of each time period being 126 minutes, 204 minutes, 153 minutes, 118 minutes, 217 minutes, 189 minutes, 152 minutes, 164 minutes, and 117 minutes, respectively.

[0074] Power fluctuation characteristics are extracted from the wind power data sequence within each time period. The average power value is calculated as the arithmetic mean of all power data within the time period. Taking the first time period as an example, the average power value is 36.4 MW. The power change rate is calculated as the mean of the power change rate sequence within the time period. Taking the first time period as an example, the power change rate is 0.42 MW / min. The power fluctuation frequency is calculated as the ratio of the number of power change direction changes within the time period to the length of the time period. Taking the first time period as an example, the number of power change direction changes within the time period is 47 times, and the time period length is 126 minutes. The power fluctuation frequency is 47 / 126 = 0.37 times / minute.

[0075] The extracted power fluctuation features are combined to construct a power fluctuation feature vector. For each time period, the power fluctuation feature vector consists of three components: the average power value, the power change rate, and the power fluctuation frequency. Taking the first time period as an example, the power fluctuation feature vector is [36.4, 0.42, 0.37].

[0076] Principal component analysis (PCA) was used to calculate the characteristic contribution of power fluctuation eigenvectors. PCA of the power fluctuation eigenvectors for nine time periods yielded eigenvalues ​​of 2.45, 0.38, and 0.17, corresponding to characteristic contributions of 81.7%, 12.7%, and 5.6%, respectively. The three characteristic directions with the largest cumulative contributions were selected to construct a three-dimensional fluctuation feature space, enabling a visual representation of wind power fluctuation characteristics and providing an intuitive basis for power allocation across electrolyzer clusters.

[0077] In this embodiment, by calculating the power change rate and performing sliding window processing, combined with the weighted combination of the first-order difference sequence and the fluctuation amplitude sequence, the segmentation threshold can be adaptively determined, thereby accurately capturing the key turning points of wind power fluctuations. Compared with the traditional segmentation method with a fixed threshold or a fixed time window, this method is more adaptable to the randomness and volatility characteristics of wind power. The constructed three-dimensional fluctuation feature space intuitively shows the power fluctuation characteristics of different time periods, providing a scientific basis for the subsequent power allocation of the electrolyzer group. By extracting features such as the average power value, power change rate, and power fluctuation frequency for each time period, the wind power fluctuation characteristics can be fully characterized, thereby realizing differentiated scheduling strategies for different fluctuation scenarios, improving the adaptability of the electrolyzer group to wind power fluctuations, reducing the adverse effects of power fluctuations on the stability of electrolyzer operation, and improving the wind power absorption efficiency and the overall economy of the system.

[0078] In an optional embodiment, extracting the fluctuation trend trajectory in the three-dimensional fluctuation feature space, predicting future fluctuation risks, and generating time-based control instructions includes:

[0079] Connecting the power fluctuation feature vectors in a three-dimensional fluctuation feature space in time sequence to form a fluctuation trend trajectory, calculating the distance and direction angle between adjacent trajectory points in the fluctuation trend trajectory, determining a set of neighboring points for each trajectory point, calculating the local evolution direction of each trajectory point based on the set of neighboring points, and taking the ratio of the displacement change between adjacent trajectory points to the time interval as the evolution rate;

[0080] The fluctuation trend trajectory is divided into zones and counted by evolution direction. The product of the proportion of trajectory points in each direction zone and the average evolution rate is calculated to determine the development probability of each evolution direction. The direction with the highest development probability is selected as the predicted trend. The power fluctuation risk value is obtained by combining the average evolution rate of this direction.

[0081] The electrolytic cell control response requirement is set according to the power fluctuation risk value, the power regulation rate and steady-state error of each electrolytic cell are calculated using the electrolytic cell operating parameters, the control response requirement is compared with the power regulation rate and steady-state error of the electrolytic cell, the response matching degree is calculated, the electrolytic cells are grouped and sorted based on the response matching degree, and the electrolytic cell combination with the highest matching degree is selected as the target electrolytic cell combination. For the target electrolytic cell combination, the maximum regulation power and response time constraint are calculated according to its operating parameters, and the target regulation power and execution timing of each time period are determined in combination with the power fluctuation risk value to generate a time period control instruction.

[0082] For example, based on the power fluctuation feature vectors obtained by the aforementioned adaptive segmentation processing, these vectors are first connected in time sequence in the three-dimensional fluctuation feature space to form a fluctuation trend trajectory. Taking the power fluctuation feature vectors of 9 time periods as an example, these 9 vectors are [36.4, 0.42, 0.37], [42.1, 0.56, 0.42], [38.7, 0.48, 0.39], [51.3, 0.71, 0.45], [47.2, 0.63, 0.41], [53.8, 0.78, 0.49], [49.5, 0.68, 0.43], [55.7, 0.82, 0.52], and [52.3, 0.75, 0.47]. These vectors are connected in three-dimensional space to obtain a fluctuation trend trajectory.

[0083] Calculate the distance and direction angle between adjacent points in the fluctuation trend trajectory. The distance between adjacent points is calculated using the Euclidean distance. For the first two points, the distance is 8.44. The direction angle is determined by calculating the angle between the line connecting the adjacent points and the coordinate axes. For the first two points, the angle with the x-axis is 41.6 degrees, the angle with the y-axis is 121.2 degrees, and the angle with the z-axis is 83.7 degrees.

[0084] Determine the set of neighboring points for each trajectory point. A neighboring point is defined as a trajectory point whose distance is less than a threshold. In this example, the distance threshold is set to 12.0. For the first trajectory point [36.4, 0.42, 0.37], its neighboring point set includes the second trajectory point [42.1, 0.56, 0.42] and the third trajectory point [38.7, 0.48, 0.39].

[0085] The local evolution direction of each trajectory point is calculated based on the set of neighboring points. The local evolution direction is determined by the vector average of the neighboring points and the current point. For the first trajectory point, its local evolution direction is [4.0, 0.1, 0.035]. The evolution rate is the ratio of the displacement change to the time interval between adjacent trajectory points. The time interval between adjacent trajectory points is the length of each time interval. Taking the first two trajectory points as an example, the displacement change is 8.44, the time interval is 126 + 204 = 330 minutes, and the evolution rate is 8.44 / 330 = 0.0256 / minute.

[0086] The fluctuation trend trajectory is divided into eight directional regions according to the evolution direction. The three-dimensional space is divided into eight directional regions, corresponding to the combination of increased or decreased power value, increased or decreased rate of change, and increased or decreased frequency of fluctuation. The proportion of the number of trajectory points in each directional region is counted. In this example, there are three trajectory points in the directional region where the power value increases, the rate of change increases, and the frequency of fluctuation increases, accounting for 3 / 8 = 0.375. The average evolution rate in this directional region is calculated to be 0.0283 / minute. The product of the proportion of the number of trajectory points in each directional region and the average evolution rate is calculated to obtain the development probability of each evolution direction. For the above directional region, the development probability is 0.375×0.0283=0.0106.

[0087] The direction with the highest probability of development is selected as the predicted trend. In this example, the direction with increasing power value, increasing rate of change, and increasing frequency of fluctuation has the highest probability of development, which is 0.0106. Combined with the average evolution rate of 0.0283 / minute in this direction, the power fluctuation risk value is predicted for the next 180 minutes. The power fluctuation risk value is defined as the displacement change within the prediction time period and is calculated as 0.0283 × 180 = 5.094.

[0088] The electrolyzer control response requirements are set based on the power fluctuation risk value. A power fluctuation risk value of 5.094 corresponds to the following control response requirements: a power regulation range of no less than 6 MW and a response time of no more than 5 minutes. There are 10 electrolyzers in the system, each with a rated power of 8 MW. The power regulation rate and steady-state error for each electrolyzer are calculated using the electrolyzer operating parameters. The power regulation rate for electrolyzer 1 is 1.2 MW / minute, with a steady-state error of 0.5%; the power regulation rate for electrolyzer 2 is 1.1 MW / minute, with a steady-state error of 0.6%; and so on.

[0089] The response matching degree is calculated by comparing the response requirement with the power regulation rate and the steady-state error of the electrolyzer. The response matching degree is determined by the ratio of the power regulation rate of the electrolyzer to the required response rate, and the ratio of the steady-state error to the allowed error. The response matching degree of electrolyzer 1 is 0.92, the response matching degree of electrolyzer 2 is 0.87, and so on. Based on the response matching degree, the electrolyzers are grouped and sorted, and the combination of electrolyzers with the highest matching degree is selected as the target electrolyzer combination. In this example, the combination of electrolyzer 1, electrolyzer 3 and electrolyzer 5 is selected, and the comprehensive matching degree is 0.89.

[0090] For the target electrolyzer combination, the maximum regulation power and response time constraint are calculated based on its operating parameters. The maximum regulation power of the target electrolyzer combination is 24 MW, and the response time constraint is 4.2 minutes. Combined with the power fluctuation risk value of 5.094, the target regulation power and execution timing of each time period are determined. The prediction period of 180 minutes is divided into 3 time periods, each of which is 60 minutes. The target regulation power of the first time period is 2 MW, the target regulation power of the second time period is 3 MW, and the target regulation power of the third time period is 1 MW. The execution timing is: the first time period starts from the prediction start time, the second time period starts from the 60th minute, and the third time period starts from the 120th minute. The generated time-periodic regulation instruction includes target electrolyzer combination information, target regulation power of each time period and execution time point.

[0091] Based on the above technical solutions, accurate prediction and optimal scheduling of electrolyzer group power distribution under wind power fluctuation conditions can be realized. By extracting the fluctuation trend trajectory in the three-dimensional fluctuation characteristic space, intuitive expression and quantitative analysis of wind power fluctuation characteristics are realized; the future fluctuation risk is predicted based on the evolution direction and rate of the trend trajectory, which improves the predictability of wind power fluctuation; the electrolyzer response matching degree is evaluated and grouped, which realizes the differentiated power distribution of the electrolyzer group and improves the adaptability of the system to the fluctuation; the generation of time-periodic regulation instruction enables the electrolyzer group to make power adjustment in advance, avoiding the impact of large-scale power fluctuation on the electrolyzer, and prolonging the service life of the equipment; the overall scheme improves the wind power consumption efficiency, enhances the economic efficiency and reliability of the system, and provides effective technical support for the coordinated operation of wind power and hydrogen energy system.

[0092] In an alternative embodiment, a multi-dimensional regulation capability evaluation system is constructed based on the operating parameters of the electrolyzers, a mapping relationship between dynamic response characteristics and time-periodic regulation requirements is established, the comprehensive regulation capability index of each electrolyzer is calculated using the mapping relationship, the electrolyzers are classified and prioritized according to the comprehensive regulation capability index, and a dynamic grouping scheme of the electrolyzers is generated, including:

[0093] Based on the acquired electrolytic cell operation data, a multi-dimensional evaluation index system including response time, adjustment accuracy and efficiency loss is established, and the response characteristic curve, accuracy index value and loss index value of the electrolytic cell are calculated based on the electrolytic cell operation data;

[0094] Obtaining system regulation demand data, performing a matching analysis on the regulation demand data with the response characteristic curve, accuracy index value, and loss index value of the electrolytic cell, obtaining an adaptability evaluation value of the electrolytic cell to the regulation demand, dynamically evaluating the electrolytic cell based on the adaptability evaluation value, and calculating a comprehensive regulation capability index value of the electrolytic cell based on the regulation importance weight of each regulation period;

[0095] Obtaining the cumulative number of adjustments and adjustment intensity data of the electrolytic cell and calculating a fatigue index value; and classifying the electrolytic cell into a fast response level, a conventional adjustment level, and a standby level according to the comprehensive adjustment capability index value;

[0096] In each level of electrolytic cells, the comprehensive adjustment capability index value and the fatigue index value are weightedly calculated to obtain a priority coefficient, and the electrolytic cells are sorted according to the priority coefficient; when the fatigue index value exceeds the preset fatigue threshold, the electrolytic cell is downgraded and the priority ranking is updated to generate a dynamic electrolytic cell grouping scheme containing grading information and priority information.

[0097] In this embodiment, a multi-dimensional evaluation index system, including response time, regulation accuracy, and efficiency loss, is first established based on the acquired electrolyzer operating data. The response time index describes the time required for the electrolyzer to reach the target power value after receiving the power adjustment command, expressed in seconds. The regulation accuracy index describes the deviation between the actual output power of the electrolyzer and the target power, expressed as a percentage. The efficiency loss index describes the degree of reduction in the energy conversion efficiency of the electrolyzer during the power adjustment process, expressed as a percentage. Taking 10 electrolytic cells in a system as an example, the response time of electrolytic cell 1 is 120 seconds, the adjustment accuracy is 0.5%, and the efficiency loss is 1.2%; the response time of electrolytic cell 2 is 135 seconds, the adjustment accuracy is 0.6%, and the efficiency loss is 1.0%; the response time of electrolytic cell 3 is 115 seconds, the adjustment accuracy is 0.4%, and the efficiency loss is 1.3%; the response time of electrolytic cell 4 is 150 seconds, the adjustment accuracy is 0.7%, and the efficiency loss is 0.9%; the response time of electrolytic cell 5 is 125 seconds, the adjustment accuracy is 0.5%, and the efficiency loss is The response time of electrolytic cell 6 is 140 seconds, the adjustment accuracy is 0.6%, and the efficiency loss is 1.0%; the response time of electrolytic cell 7 is 130 seconds, the adjustment accuracy is 0.5%, and the efficiency loss is 1.2%; the response time of electrolytic cell 8 is 145 seconds, the adjustment accuracy is 0.7%, and the efficiency loss is 0.9%; the response time of electrolytic cell 9 is 120 seconds, the adjustment accuracy is 0.5%, and the efficiency loss is 1.1%; the response time of electrolytic cell 10 is 155 seconds, the adjustment accuracy is 0.8%, and the efficiency loss is 0.8%.

[0098] The electrolyzer's response characteristic curve, accuracy index, and loss index were calculated based on the electrolyzer's operating data. The response characteristic curve describes how the electrolyzer's power changes over time and is obtained by fitting power variation data collected under different electrolyzer operating conditions. For electrolyzer 1, during the power adjustment from 6 MW to 7 MW, the collected power variation data points were: 6.00 MW at 0 seconds, 6.32 MW at 20 seconds, 6.58 MW at 40 seconds, 6.75 MW at 60 seconds, 6.88 MW at 80 seconds, 6.95 MW at 100 seconds, and 6.99 MW at 120 seconds. The fitted response characteristic curve is an exponential curve with a characteristic parameter of 85 seconds. The accuracy index was calculated by statistically analyzing the power deviation of the electrolyzer under stable operating conditions. For electrolyzer 1, when the target power was 7 MW, the actual power had an average value of 7.02 MW and a standard deviation of 0.035 MW, resulting in a calculated accuracy index of 0.5%. The loss index value was calculated by comparing the energy conversion efficiency of the electrolyzers before and after the adjustment. For electrolyzer 1, the energy conversion efficiency dropped from 68.5% to 67.3% during the power adjustment from 6 MW to 7 MW, resulting in a calculated loss index value of 1.2%.

[0099] Obtain system control demand data and analyze its compatibility with the electrolytic cell's response characteristic curve, accuracy index, and loss index to determine the electrolytic cell's adaptability to the control requirements. System control demand data includes control time requirements, accuracy requirements, and efficiency requirements. For example, for a specific time period, the control time requirement is 130 seconds, the accuracy requirement is 0.6%, and the efficiency requirement is 1.1%. Calculate the degree of compatibility between the electrolytic cell's response characteristics and the control time requirements. For electrolytic cell 1, the response time is 120 seconds, which is less than the control time requirement of 130 seconds. The compatibility is 130 / 120 = 1.08, with a value greater than 1 indicating that the requirements are met. Calculate the degree of compatibility between the electrolytic cell's accuracy index and the control accuracy requirements. For electrolytic cell 1, the accuracy index is 0.5%, which is less than the control accuracy requirement of 0.6%. The compatibility is 0.6 / 0.5 = 1.2, with a value greater than 1 indicating that the requirements are met. Calculate the degree of compatibility between the electrolytic cell's loss index and the control efficiency requirements. For electrolyzer 1, the loss index value is 1.2%, which exceeds the control efficiency requirement of 1.1%. The matching degree is 1.1 / 1.2 = 0.92, and less than 1 indicates that the requirement is not fully met. Combining the matching degrees of the three aspects, the adaptability evaluation value of electrolyzer 1 to this control requirement is calculated as 1.08 × 0.4 + 1.2 × 0.4 + 0.92 × 0.2 = 1.076, where 0.4, 0.4, and 0.2 are the weight coefficients of each indicator.

[0100] The electrolytic cell is dynamically evaluated based on its adaptability evaluation value. The comprehensive adjustability index of the electrolytic cell is calculated based on the control importance weights of each adjustment period. A day is divided into six adjustment periods, each lasting four hours. The control importance weights for each period are 0.15, 0.2, 0.25, 0.2, 0.15, and 0.05, respectively. The adaptability evaluation value of the electrolytic cell for each period is calculated, multiplied by the control importance weights, and the sum is calculated to obtain the comprehensive adjustability index of the electrolytic cell. For electrolytic cell 1, the adaptability evaluation values ​​for the six time periods were 1.076, 1.102, 1.054, 1.089, 1.065, and 1.033, respectively. The calculated comprehensive regulation capability index was 1.076 × 0.15 + 1.102 × 0.2 + 1.054 × 0.25 + 1.089 × 0.2 + 1.065 × 0.15 + 1.033 × 0.05 = 1.074. Similarly, the comprehensive regulation capability index values ​​for the other electrolytic cells were calculated as follows: 0.989 for electrolytic cell 2, 1.095 for electrolytic cell 3, 0.921 for electrolytic cell 4, 1.035 for electrolytic cell 5, 0.978 for electrolytic cell 6, 1.002 for electrolytic cell 7, 0.934 for electrolytic cell 8, 1.056 for electrolytic cell 9, and 0.912 for electrolytic cell 10.

[0101] Obtain the cumulative number of adjustments and adjustment intensity data for each electrolytic cell and calculate the fatigue index value. The cumulative number of adjustments refers to the total number of times the electrolytic cell has participated in power regulation. The adjustment intensity refers to the ratio of the power change amplitude during each adjustment to the rated power of the electrolytic cell. For electrolytic cell 1, the cumulative number of adjustments is 156, and the average adjustment intensity is 0.15. The calculated fatigue index value is 156 × 0.15 = 23.4. Similarly, the fatigue index values ​​of the other electrolytic cells are calculated: electrolytic cell 2 is 19.8, electrolytic cell 3 is 25.2, electrolytic cell 4 is 17.1, electrolytic cell 5 is 21.5, electrolytic cell 6 is 18.7, electrolytic cell 7 is 20.3, electrolytic cell 8 is 16.9, electrolytic cell 9 is 22.6, and electrolytic cell 10 is 15.8.

[0102] Based on their comprehensive regulation capability, electrolytic cells are classified into rapid response, conventional regulation, and backup levels. Rapid response requires a comprehensive regulation capability greater than 1.05, conventional regulation requires a value between 0.95 and 1.05, and backup requires a value less than 0.95. Based on this standard, electrolytic cells 1, 3, and 9 are classified as rapid response; electrolytic cells 2, 5, 6, and 7 are classified as conventional regulation; and electrolytic cells 4, 8, and 10 are classified as backup.

[0103] Within each electrolytic cell, the comprehensive regulation capability index and fatigue index are weighted to calculate the priority coefficient. The priority coefficient is calculated as follows: the comprehensive regulation capability index multiplied by 0.7 plus the normalized fatigue margin multiplied by 0.3. The fatigue margin is defined as the fatigue index value minus the preset fatigue threshold, which is set to 30. For electrolytic cell 1, the fatigue margin is 30-23.4=6.6, and the normalized fatigue margin is 6.6 / 30=0.22, resulting in a calculated priority coefficient of 1.074×0.7+0.22×0.3=0.818. Similarly, the priority coefficients of the other electrolytic cells are calculated and ranked within each level. The internal order of the quick response level is: electrolytic cell 3 (0.834), electrolytic cell 9 (0.815), electrolytic cell 1 (0.818); the internal order of the conventional regulation level is: electrolytic cell 5 (0.797), electrolytic cell 7 (0.760), electrolytic cell 2 (0.734), electrolytic cell 6 (0.721); the internal order of the standby level is: electrolytic cell 10 (0.684), electrolytic cell 8 (0.679), electrolytic cell 4 (0.670).

[0104] When the fatigue index exceeds the preset fatigue threshold, the electrolyzer is downgraded and the priority ranking is updated. The preset fatigue threshold is 30. If the fatigue index value of electrolyzer 3 increases to 32.1, exceeding the preset fatigue threshold of 30, electrolyzer 3 is downgraded from the rapid response level to the conventional regulation level, and the priority coefficient and ranking are recalculated within the conventional regulation level. A dynamic electrolyzer grouping scheme containing hierarchical and priority information is generated: the rapid response level includes electrolyzer 9 and electrolyzer 1; the conventional regulation level includes electrolyzer 3, electrolyzer 5, electrolyzer 7, electrolyzer 2, and electrolyzer 6; and the standby level includes electrolyzer 10, electrolyzer 8, and electrolyzer 4.

[0105] Based on the above technical solution, it is possible to achieve efficient and optimized scheduling of the power distribution of the electrolytic cell group under the condition of wind power fluctuation. In the existing technology, the evaluation of the regulation ability of the electrolytic cell often only considers a single indicator such as response speed or power capacity, which cannot fully reflect the comprehensive performance of the electrolytic cell in the dynamic regulation process; and the scheduling strategy usually adopts a fixed grouping method, which is difficult to adapt to the changes in the operating state of the electrolytic cell and the fluctuation characteristics of wind power. The present application constructs a multi-dimensional evaluation system including response time, regulation accuracy and efficiency loss, and realizes a comprehensive evaluation of the regulation ability of the electrolytic cell; by establishing a mapping relationship between the response characteristics of the electrolytic cell and the regulation demand, it realizes the precise matching of the electrolytic cell with the regulation demand; introduces fatigue indicators and sets a dynamic degradation mechanism to effectively balance the service life of the electrolytic cell and the system regulation performance. Through dynamic classification and priority sorting, the adaptability of the electrolytic cell group to wind power fluctuations is enhanced, the wind power absorption efficiency is improved, and the stability and economy of the system operation are guaranteed.

[0106] Figure 2 This is a heat diagram showing the relationship between the electrolytic cell adjustment accuracy and efficiency loss according to an embodiment of the present invention. Figure 2 As shown in the figure, this heat map shows the relationship between the electrolytic cell regulation accuracy and the load regulation rate and its impact on efficiency loss. The figure intuitively presents the degree of loss through different shades of color, from the light-colored low-loss area (0-2%) to the dark-colored high-loss area (>6%). The heat map clearly shows that with the increase of load regulation rate and the improvement of regulation accuracy requirements, the efficiency loss shows a nonlinear growth trend. The optimal operating area is located in the dotted box area in the lower left corner, which represents the ideal operating state. This technical solution can achieve low efficiency loss while maintaining high accuracy by virtue of the multi-dimensional evaluation index system; traditional methods such as the PID feedback algorithm based on voltage control can meet basic regulation requirements, but the efficiency loss is high. The partition analysis of the heat map provides an intuitive basis for the formulation of the electrolytic cell operation strategy, which helps to select the most appropriate operating point according to the accuracy requirements and load conditions in actual applications, thereby balancing the regulation performance and energy efficiency.

[0107] In an optional embodiment, the electrolytic cell is dynamically evaluated based on the adaptability evaluation value, and the comprehensive regulation capability index value of the electrolytic cell is calculated according to the regulation importance weight of each regulation period, including:

[0108] Collect wind power fluctuation data, obtain power fluctuation inflection points through extreme value detection, divide the evaluation period into multiple regulation periods according to the power fluctuation inflection points, and calculate the regulation difficulty coefficient based on the power change trend within each regulation period;

[0109] Obtaining the power fluctuation amplitude, fluctuation frequency and system stability margin of each regulation period, constructing a regulation period weight evaluation matrix, and calculating the regulation importance weight of each regulation period according to the weight evaluation matrix;

[0110] The operating data of the electrolytic cell in each adjustment period is collected, and the adaptability evaluation value of the electrolytic cell in each adjustment period is calculated based on the operating data and the control difficulty coefficient. The adaptability evaluation value is normalized, and the comprehensive adjustment capability index value of the electrolytic cell is obtained by combining the control importance weight.

[0111] In this implementation, wind power fluctuation data is first collected. Extreme value detection is used to identify power fluctuation inflection points. The evaluation period is then divided into multiple adjustment periods based on these inflection points. Wind power fluctuation data is collected via the wind farm SCADA system, with a sampling frequency of 1 minute and a 24-hour collection period. This yields a power data sequence of 1,440 sampling points. For a particular wind farm, the collected power data are: 42.3MW, 43.5MW, 45.1MW, 46.8MW, 47.2MW, 46.9MW, 45.8MW, 44.2MW, 42.9MW, and 41.5MW. Power fluctuation inflection points are identified through extreme value detection, which uses a sliding window method with a window size of five sampling points. If the power value of a sampling point is greater than that of other sampling points within the window, it is marked as a maximum point; if the power value of a sampling point is less than that of other sampling points within the window, it is marked as a minimum point. Maximum and minimum points are collectively referred to as power fluctuation inflection points. The above data was tested for extreme values, and the maximum value point identified was 47.2MW at the 5th sampling point, and the minimum value point was 41.5MW at the 10th sampling point. Extreme value detection was performed on the power data throughout the day, and a total of 18 maximum points and 17 minimum points were identified, for a total of 35 power fluctuation inflection points. Based on these inflection points, the 24-hour evaluation period was divided into 36 adjustment periods, and the duration of each period was the time interval between two consecutive inflection points. Taking the first two inflection points as an example, the first inflection point occurred at the 82nd minute and the second inflection point occurred at the 127th minute, so the duration of the first adjustment period was 45 minutes.

[0112] The control difficulty coefficient is calculated based on the power change trend within each regulation period. The power change trend is characterized by the slope and fluctuation amplitude of the power data within the period. The slope is calculated as the ratio of the power change within the period to the period duration. The fluctuation amplitude is calculated as the difference between the maximum and minimum power values ​​within the period. The control difficulty coefficient is determined based on the absolute value of the slope and the fluctuation amplitude. The calculation formula is the absolute value of the slope multiplied by 0.6 plus the ratio of the fluctuation amplitude to the rated power multiplied by 0.4. Taking the first regulation period as an example, the starting power is 35.6MW, the ending power is 47.2MW, the period duration is 45 minutes, the slope is (47.2-35.6) / 45=0.26MW / minute, and the absolute value of the slope is 0.26MW / minute. The maximum power within the period is 47.2MW, the minimum is 35.6MW, the fluctuation amplitude is 47.2-35.6=11.6MW, the rated power of the wind farm is 100MW, and the ratio of the fluctuation amplitude to the rated power is 11.6 / 100=0.116. The calculated regulation difficulty coefficient is 0.26×0.6+0.116×0.4=0.2024. Similarly, the regulation difficulty coefficients for the other regulation periods are calculated. The regulation difficulty coefficient for the second regulation period is 0.1853, the regulation difficulty coefficient for the third regulation period is 0.2145, and so on.

[0113] The power fluctuation amplitude, fluctuation frequency, and system stability margin of each regulation period are obtained to construct a weight evaluation matrix for the regulation period. The power fluctuation amplitude is defined as the ratio of the power change within the period to the rated power. The fluctuation frequency is defined as the number of times the power change direction changes per unit time. The system stability margin is defined as the ratio of the grid frequency deviation to the allowable deviation, which represents the stability of the system. Taking the first regulation period as an example, the power fluctuation amplitude is (47.2-35.6) / 100=0.116, the fluctuation frequency is 3 times / 45 minutes=0.067 times / minute, and the system stability margin is 0.8. The three indicators are weighted according to their importance, with the power fluctuation amplitude weighted as 0.5, the fluctuation frequency weighted as 0.3, and the system stability margin weighted as 0.2. The three indicators are normalized so that their value range is between 0 and 1. Taking the power fluctuation amplitude as an example, the maximum power fluctuation amplitude among the 36 time periods is 0.215, and the minimum is 0.042. The normalized power fluctuation amplitude for the first time period is (0.116 - 0.042) / (0.215 - 0.042) = 0.427. Similarly, the normalized fluctuation frequency is calculated to be 0.568, and the normalized system stability margin is 0.625. A weighted evaluation matrix for the regulation period is constructed, with the rows representing each regulation period and the columns representing the three evaluation indicators. The row vectors of the weighted evaluation matrix for the first time period are [0.427, 0.568, 0.625].

[0114] Calculate the importance weight of each regulation period based on the weight evaluation matrix. Multiply each indicator value in the weight evaluation matrix by its corresponding weight and sum the results to obtain the importance score for each regulation period. The importance score for the first period is 0.427 × 0.5 + 0.568 × 0.3 + 0.625 × 0.2 = 0.5126. Similarly, calculate the importance scores for the other periods. Normalize the importance scores for each period so that the sum of the importance weights for all periods is 1. The importance weight for the first period is 0.5126 / 18.4536 = 0.0278, where 18.4536 is the sum of the importance scores for all periods. Similarly, calculate the importance weights for the other periods. The importance weight for the second period is 0.0246, the third period is 0.0312, and so on.

[0115] The electrolytic cell's operating data for each adjustment period is collected, and the cell's adaptability evaluation value for each adjustment period is calculated based on the operating data and the control difficulty coefficient. The electrolytic cell operating data includes response time, control accuracy, and efficiency loss. Taking electrolytic cell 1 in a system as an example, during the first adjustment period, the response time was 125 seconds, the control accuracy was 0.5%, and the efficiency loss was 1.2%. The electrolytic cell operating data is combined with the period control difficulty coefficient to calculate the adaptability evaluation value. The adaptability evaluation value is calculated as the response time adaptability multiplied by 0.4 plus the control accuracy adaptability multiplied by 0.4 plus the efficiency loss adaptability multiplied by 0.2. The response time adaptability is calculated as the baseline response time divided by the actual response time, with the baseline response time set to 120 seconds. The control accuracy adaptability is calculated as the baseline accuracy divided by the actual accuracy, with the baseline accuracy set to 0.6%. The efficiency loss adaptability is calculated as the baseline loss divided by the actual loss, with the baseline loss set to 1.0%. Taking electrolyzer 1 in the first regulation period as an example, the response time adaptability is 120 / 125 = 0.96, the regulation accuracy adaptability is 0.6 / 0.5 = 1.2, and the efficiency loss adaptability is 1.0 / 1.2 = 0.833. The calculated adaptability evaluation value is 0.96 × 0.4 + 1.2 × 0.4 + 0.833 × 0.2 = 1.007. The adaptability evaluation value is multiplied by the adjustment factor for the control difficulty coefficient, calculated as 1 plus the control difficulty coefficient. The control difficulty coefficient for the first period is 0.2024, and the adjustment factor is 1 + 0.2024 = 1.2024. The adjusted adaptability evaluation value is 1.007 × 1.2024 = 1.211. Similarly, the adaptability evaluation values ​​of electrolyzer 1 in the other regulation periods are calculated. In the second regulation period, the adaptability evaluation value is 1.15; in the third regulation period, the adaptability evaluation value is 1.23; and so on.

[0116] The adaptability evaluation value is normalized and combined with the control importance weight to calculate the comprehensive adjustment capability index value of the electrolytic cell. The adaptability evaluation value of the electrolytic cell in each adjustment period is normalized so that its value range is between 0 and 1. Taking electrolytic cell 1 as an example, in the 36 adjustment periods, the maximum adaptability evaluation value is 1.45 and the minimum is 0.92. The normalized adaptability evaluation value of the first period is (1.211-0.92) / (1.45-0.92)=0.547. Similarly, the normalized adaptability evaluation value of electrolytic cell 1 in the second period is 0.434, the normalized adaptability evaluation value in the third period is 0.585, and so on. The normalized adaptability evaluation value is multiplied by the control importance weight of the corresponding adjustment period, and the sum is taken for all periods to obtain the comprehensive adjustment capability index value of the electrolytic cell. The comprehensive regulation capability index value of electrolytic cell 1 is 0.547 × 0.0278 + 0.434 × 0.0246 + 0.585 × 0.0312 + ... = 0.526. Similarly, the comprehensive regulation capability index values ​​of the other electrolytic cells in the system are calculated. The comprehensive regulation capability index value of electrolytic cell 2 is 0.489, the comprehensive regulation capability index value of electrolytic cell 3 is 0.542, and so on.

[0117] Based on the above technical solution, it is possible to achieve accurate evaluation and optimized scheduling of the power distribution of the electrolyzer group under wind power fluctuation conditions. In the existing technology, the evaluation of the electrolyzer regulation capacity usually adopts a fixed time period division method, which cannot reflect the actual fluctuation characteristics of wind power; and the evaluation index system is single, and it is difficult to fully characterize the adaptability of the electrolyzer under different fluctuation conditions; at the same time, the weight distribution of each time period lacks a scientific basis, resulting in the evaluation results being out of touch with actual needs. The present application uses extreme value detection technology to identify the inflection point of power fluctuations, realizes the adaptive division of the evaluation cycle, and closely combines the time period division with the actual fluctuation characteristics of wind power; constructs a multi-dimensional weight evaluation matrix including power fluctuation amplitude, fluctuation frequency and system stability margin, and scientifically quantifies the importance of each regulation period; introduces a control difficulty coefficient, and dynamically adjusts the electrolyzer adaptability evaluation value to make the evaluation results more objective and accurate. Through the above improvements, this solution realizes the accurate evaluation of the electrolyzer regulation capacity, enhances the adaptability of the electrolyzer group to wind power fluctuations, improves the stability and economy of system operation, and provides a more scientific scheduling basis for wind power consumption and hydrogen energy production.

[0118] Figure 3 This is a bar chart comparing the adjustment capabilities of different electrolytic cell types according to an embodiment of the present invention. Figure 3As shown, this bar chart compares in detail the comprehensive regulation capability indicators of three types of electrolytic cells (alkaline electrolytic cell, PEM electrolytic cell, solid oxide electrolytic cell) under three different evaluation methods. The gray solid columns in the figure represent the evaluation results of this technical solution, the light gray border columns represent the results of the uniform time period method, and the white dotted border columns represent the results of the empirical threshold method. Judging from the data, under all evaluation methods, the regulation capability of the PEM electrolytic cell is the best, followed by the alkaline electrolytic cell, and the solid oxide electrolytic cell performs the weakest. Specifically, under the evaluation of this technical solution, the comprehensive regulation capability index of the PEM electrolytic cell reached 0.79, which is significantly higher than the 0.59 of the alkaline electrolytic cell and the 0.43 of the solid oxide electrolytic cell; under the traditional uniform time period method, the indicators of the three electrolytic cells are 0.65, 0.49 and 0.31 respectively; under the empirical threshold method, the indicators of the three electrolytic cells are even lower, at 0.61, 0.45 and 0.24 respectively. This solution more accurately reflects the actual differences in the regulation capabilities of various electrolyzer types, particularly their adaptability under extreme operating conditions. Compared to traditional methods that simply use uniform time periods or fixed empirical thresholds, this technical solution precisely divides the regulation period based on the inflection points of power fluctuations and constructs a multi-dimensional weighted evaluation matrix, enabling a more comprehensive assessment of the electrolyzer's adaptability to wind power fluctuations.

[0119] In an optional embodiment, a power regulation matrix is ​​constructed based on the dynamic grouping scheme of electrolytic cells, and a recursive iterative method is used to calculate the optimal power allocation ratio of each electrolytic cell in the power regulation matrix. The generation of a control instruction containing the real-time power setting value of each electrolytic cell includes:

[0120] Collect the operating power, power fluctuation and response time of the electrolytic cell group, and calculate the dynamic response characteristics of the electrolytic cell based on the operating power, power fluctuation and response time;

[0121] Constructing a power regulation matrix based on the dynamic grouping scheme of the electrolytic cells, calculating the inter-group power coupling coefficient based on the dynamic response characteristics of the electrolytic cells, and writing the inter-group power coupling coefficient into the corresponding position of the power regulation matrix to obtain an initial power regulation matrix;

[0122] Performing a difference operation on each element value of the initial power regulation matrix and the rated power value of the electrolytic cell to obtain a power regulation deviation matrix, calculating an inter-group adaptive weight based on the power regulation deviation matrix, and multiplying the inter-group adaptive weight by the initial power regulation matrix to obtain an optimized power regulation matrix;

[0123] Constructing a multidimensional optimization objective function based on the optimized power regulation matrix and the power regulation deviation matrix, setting the power regulation deviation, the inter-group power coupling coefficient and the dynamic response characteristic as optimization variables, and calculating the optimization variable weight coefficients according to the system operation requirements;

[0124] A recursive iterative method is used to calculate the power allocation ratio of each electrolytic cell in the power regulation matrix. The adaptive step size is calculated by multiplying the optimization variable weight coefficient with the gradient of the multidimensional optimization objective function. The dynamic compensation factor is calculated based on the historical iterative data to obtain the optimal power allocation ratio. The optimal power allocation ratio is multiplied by the rated power of the electrolytic cell to obtain the real-time power setting value of each electrolytic cell, and the control instruction is generated.

[0125] The operating power, power fluctuation, and response time of the electrolyzer group are collected. Based on these data, the dynamic response characteristics of the electrolyzers are calculated. For example, in a system with 10 electrolyzers, each rated at 8 MW. The electrolyzer control system collects the current operating power of each electrolyzer: electrolyzer 1 is currently operating at 6.5 MW, electrolyzer 2 at 7.2 MW, electrolyzer 3 at 5.8 MW, electrolyzer 4 at 6.8 MW, electrolyzer 5 at 7.5 MW, electrolyzer 6 at 6.2 MW, electrolyzer 7 at 7.0 MW, electrolyzer 8 at 5.6 MW, electrolyzer 9 at 6.4 MW, and electrolyzer 10 at 6.0 MW. Power fluctuation refers to the magnitude of power changes during the electrolyzer regulation process and is determined through statistical analysis of historical operating data. The power fluctuation for electrolyzer 1 is 0.8 MW, for electrolyzer 2 is 0.6 MW, for electrolyzer 3 is 0.9 MW, for electrolyzer 4 is 0.5 MW, for electrolyzer 5 is 0.7 MW, for electrolyzer 6 is 0.6 MW, for electrolyzer 7 is 0.8 MW, for electrolyzer 8 is 0.5 MW, for electrolyzer 9 is 0.7 MW, and for electrolyzer 10 is 0.4 MW. Response time refers to the time it takes for an electrolyzer to reach the target power value after receiving a power adjustment command. The response time for electrolyzer 1 is 125 seconds, for electrolyzer 2 is 135 seconds, for electrolyzer 3 is 115 seconds, for electrolyzer 4 is 150 seconds, for electrolyzer 5 is 125 seconds, for electrolyzer 6 is 140 seconds, for electrolyzer 7 is 130 seconds, for electrolyzer 8 is 145 seconds, for electrolyzer 9 is 120 seconds, and for electrolyzer 10 is 155 seconds.

[0126] The dynamic response characteristics of the electrolyzer are calculated based on the collected data. Dynamic response characteristics include power regulation rate, steady-state error, and response sensitivity. Power regulation rate is calculated as the ratio of power fluctuation to response time, with units of MW / second. The power regulation rate of electrolyzer 1 is 0.8 / 125=0.0064MW / second, that of electrolyzer 2 is 0.6 / 135=0.0044MW / second, that of electrolyzer 3 is 0.9 / 115=0.0078MW / second, that of electrolyzer 4 is 0.5 / 150=0.0033MW / second, that of electrolyzer 5 is 0.7 / 125=0.0056MW / second, that of electrolyzer 6 is 0.6 / 140=0.0043MW / second, that of electrolyzer 7 is 0.8 / 130=0.0062MW / second, that of electrolyzer 8 is 0.5 / 145=0.0034MW / second, that of electrolyzer 9 is 0.7 / 120=0.0058MW / second, and that of electrolyzer 10 is 0.4 / 155=0.0026MW / second. Steady-state error refers to the deviation between the actual power and the target power of an electrolyzer after power adjustment, and is calculated based on historical operating data. The steady-state error for electrolyzer 1 is 0.5%, for electrolyzer 2 0.6%, for electrolyzer 3 0.4%, for electrolyzer 4 0.7%, for electrolyzer 5 0.5%, for electrolyzer 6 0.6%, for electrolyzer 7 0.5%, for electrolyzer 8 0.7%, for electrolyzer 9 0.5%, and for electrolyzer 10 0.8%. Response sensitivity refers to the electrolyzer's sensitivity to power adjustment commands and is calculated as the ratio of power fluctuation to rated power. The response sensitivity of electrolytic cell 1 is 0.8 / 8=0.1, that of electrolytic cell 2 is 0.6 / 8=0.075, that of electrolytic cell 3 is 0.9 / 8=0.1125, that of electrolytic cell 4 is 0.5 / 8=0.0625, that of electrolytic cell 5 is 0.7 / 8=0.0875, that of electrolytic cell 6 is 0.6 / 8=0.075, that of electrolytic cell 7 is 0.8 / 8=0.1, that of electrolytic cell 8 is 0.5 / 8=0.0625, that of electrolytic cell 9 is 0.7 / 8=0.0875, and that of electrolytic cell 10 is 0.4 / 8=0.05.

[0127] A power regulation matrix is ​​constructed based on the dynamic grouping scheme for electrolyzers. The inter-group power coupling coefficient is calculated based on the dynamic response characteristics of the electrolyzers. The inter-group power coupling coefficient is then written into the corresponding position in the power regulation matrix to obtain the initial power regulation matrix. Based on the dynamic grouping scheme, the electrolyzers are divided into three groups: the fast-response group includes electrolyzers 1, 3, and 9; the conventional-regulation group includes electrolyzers 2, 5, 6, and 7; and the standby group includes electrolyzers 4, 8, and 10. The power regulation matrix is ​​a 10×10 matrix, with rows and columns corresponding to the 10 electrolyzers, respectively. The elements in the matrix represent the power coupling relationship between the electrolyzers. The inter-group power coupling coefficient is calculated as the weighted average of the ratio of the power regulation rate to the response sensitivity of the two electrolyzers. The weighting coefficient is 0.6 for the power regulation rate and 0.4 for the response sensitivity. Taking the inter-group power coupling coefficient of electrolytic cells 1 and 2 as an example, the power regulation rate ratio is 0.0064 / 0.0044 = 1.455, the response sensitivity ratio is 0.1 / 0.075 = 1.333, and the inter-group power coupling coefficient is 1.455 × 0.6 + 1.333 × 0.4 = 1.407. Similarly, the inter-group power coupling coefficients of other electrolytic cell pairs are calculated and filled into the corresponding positions of the power regulation matrix to obtain the initial power regulation matrix.

[0128] The power regulation deviation matrix is ​​obtained by subtracting the values ​​of each element in the initial power regulation matrix from the rated power of the electrolyzer. Inter-group adaptive weights are calculated based on the power regulation deviation matrix, and the optimized power regulation matrix is ​​obtained by multiplying the inter-group adaptive weights by the initial power regulation matrix. The power regulation deviation matrix is ​​calculated by subtracting each element of the initial power regulation matrix from the rated power of the electrolyzer in the corresponding row. For example, the element in row 1, column 2 of the power regulation matrix has a value of 1.407. The rated power of electrolyzer 1 is 8 MW, and the power regulation deviation is 1.407 - 8 = -6.593 MW. Similarly, the other elements of the power regulation deviation matrix are calculated. The inter-group adaptive weights are calculated by normalizing the mean deviations between each group in the power regulation deviation matrix. The mean deviation between the rapid response stage and the conventional stage is -6.285 MW, the mean deviation between the rapid response stage and the backup stage is -6.748 MW, and the mean deviation between the conventional stage and the backup stage is -6.532 MW. After normalization, the adaptive weight between the rapid response level and the conventional regulation level is 0.322, the adaptive weight between the rapid response level and the backup level is 0.346, and the adaptive weight between the conventional regulation level and the backup level is 0.332. Multiplying the inter-group adaptive weights by the initial power regulation matrix yields the optimized power regulation matrix. For example, the element in row 1, column 2 of the optimized power regulation matrix has a value of 1.407 × 0.322 = 0.453.

[0129] A multidimensional optimization objective function is constructed based on the optimized power regulation matrix and the power regulation deviation matrix. The power regulation deviation, inter-group power coupling coefficient, and dynamic response characteristics are set as optimization variables. The weight coefficients of the optimization variables are calculated based on the system's operating requirements. The multidimensional optimization objective function contains three sub-objective functions: a power balance objective function, a response characteristic objective function, and a coupling optimization objective function. The power balance objective function is used to ensure system power balance and is defined as the sum of the squares of the elements in the power regulation deviation matrix. The response characteristic objective function is used to optimize the dynamic response characteristics of the electrolyzers and is defined as the sum of the squares of the differences between the power regulation rate of each electrolyzer and the target rate. The coupling optimization objective function is used to optimize the power coupling relationship between electrolyzers and is defined as the sum of the squares of the elements in the optimized power regulation matrix. The weight coefficients of the optimization variables are determined based on the system's operating requirements: the weight coefficient of the power balance objective function is 0.5, the weight coefficient of the response characteristic objective function is 0.3, and the weight coefficient of the coupling optimization objective function is 0.2.

[0130] A recursive iterative method is used to calculate the power allocation ratio for each electrolyzer in the power regulation matrix. The adaptive step size is calculated by multiplying the optimization variable weight coefficients with the gradient of the multidimensional optimization objective function. A dynamic compensation factor is calculated based on historical iteration data to obtain the optimal power allocation ratio. This optimal power allocation ratio is multiplied by the rated power of each electrolyzer to obtain the real-time power setpoint for each electrolyzer, which is then used to generate the control instructions. During the recursive iteration process, the initial power allocation ratio is set to the ratio of the current operating power to the rated power of each electrolyzer. The initial power allocation ratio for electrolyzer 1 is 6.5 / 8 = 0.8125, for electrolyzer 2 it is 7.2 / 8 = 0.9, for electrolyzer 3 it is 5.8 / 8 = 0.725, and so on. The gradient of the multidimensional optimization objective function is calculated by taking the partial derivatives of the objective function with respect to each optimization variable. The optimization variable weight coefficients are multiplied by the gradient to obtain the weighted gradient. The adaptive step size is calculated by multiplying the modulus of the weighted gradient by a preset step size coefficient. The preset step size coefficient is 0.05. The dynamic compensation factor is calculated by adaptively adjusting it based on the convergence trend of historical iterative data. The initial dynamic compensation factor is set to 1.0 and adjusted based on the changing trend of the objective function value over three consecutive iterations. If the objective function value continues to decrease, the compensation factor is increased; if the objective function value fluctuates, the compensation factor is decreased. After 20 iterative calculations, the optimal power allocation ratio is obtained. The optimal power allocation ratio for electrolyzer 1 is 0.85, for electrolyzer 2 is 0.82, for electrolyzer 3 is 0.88, for electrolyzer 4 is 0.75, for electrolyzer 5 is 0.84, for electrolyzer 6 is 0.78, for electrolyzer 7 is 0.81, for electrolyzer 8 is 0.72, for electrolyzer 9 is 0.86, and for electrolyzer 10 is 0.70. The optimal power allocation ratio is multiplied by the rated power of the electrolyzer to obtain the real-time power setpoint for each electrolyzer. The real-time power setting values ​​for electrolyzer 1 are 0.85×8=6.8MW, electrolyzer 2 is 0.82×8=6.56MW, electrolyzer 3 is 0.88×8=7.04MW, electrolyzer 4 is 0.75×8=6MW, electrolyzer 5 is 0.84×8=6.72MW, electrolyzer 6 is 0.78×8=6.24MW, electrolyzer 7 is 0.81×8=6.48MW, electrolyzer 8 is 0.72×8=5.76MW, electrolyzer 9 is 0.86×8=6.88MW, and electrolyzer 10 is 0.70×8=5.6MW. A control instruction containing the real-time power setting values ​​is generated, which includes information such as the electrolyzer identification, power setting value, and execution timestamp.

[0131] Based on the above technical solution, it is possible to achieve precise optimization and efficient scheduling of the power distribution of the electrolyzer group under wind power fluctuation conditions. The electrolyzer power distribution method in the existing technology usually adopts an equal distribution strategy or a simple proportional distribution, which cannot take into account the dynamic response differences and power coupling relationships between electrolyzers, resulting in low overall system response efficiency; and the optimization algorithm mostly adopts a fixed step size iterative method, which has a slow convergence speed and is prone to falling into local optimality. This application constructs a power regulation matrix based on the dynamic response characteristics of the electrolyzer, realizes the accurate characterization of the power coupling relationship between electrolyzers; introduces an inter-group adaptive weight mechanism to effectively balance the regulation load of electrolyzers with different response levels; designs a multidimensional objective function including power balance, response characteristics and coupling optimization, and comprehensively considers various constraints of system operation; adopts a recursive iterative method with adaptive step size and dynamic compensation factor, which significantly improves the convergence speed and optimization accuracy of the algorithm. Through the synergistic effect of the above technical means, this solution realizes the precise distribution and dynamic regulation of the power of the electrolyzer group, improves the system's adaptability to wind power fluctuations, reduces the impact of power fluctuations on electrolyzers, enhances wind power absorption capacity, and ensures the stability and economy of hydrogen energy production.

[0132] A second aspect of an embodiment of the present invention provides an optimized scheduling system for power distribution of an electrolyzer group under wind power fluctuation conditions, the system comprising:

[0133] The first unit is used to collect wind farm output power data and electrolyzer group operating parameters;

[0134] The second unit is used to perform adaptive segmentation processing on the output power data, calculate the power fluctuation feature vector in each time period, construct a three-dimensional fluctuation feature space based on the power fluctuation feature vector, extract the fluctuation trend trajectory in the three-dimensional fluctuation feature space, predict future fluctuation risks and generate time-based control instructions;

[0135] The third unit is used to build a multi-dimensional regulation capability evaluation system based on the operating parameters of the electrolytic cells, establish a mapping relationship between dynamic response characteristics and time-based regulation requirements, use the mapping relationship to calculate the comprehensive regulation capability index of each electrolytic cell, and perform hierarchical screening and priority sorting of the electrolytic cells based on the comprehensive regulation capability index to generate a dynamic grouping plan for the electrolytic cells;

[0136] The fourth unit is used to construct a power regulation matrix based on the dynamic grouping scheme of the electrolytic cells, calculate the optimal power allocation ratio of each electrolytic cell in the power regulation matrix using a recursive iterative method, and generate a control instruction containing the real-time power setting value of each electrolytic cell;

[0137] The fifth unit is used to transmit the real-time power setting value to the control unit of each electrolyzer to perform power regulation, and collect the real-time response data of the electrolyzer, optimize the control instructions according to the real-time response data, and realize the coordinated control of the electrolyzer group on wind power fluctuations.

[0138] According to a third aspect of an embodiment of the present invention, an electronic device is provided, including:

[0139] processor;

[0140] a memory for storing processor-executable instructions;

[0141] The processor is configured to call the instructions stored in the memory to execute the aforementioned method.

[0142] According to a fourth aspect of an embodiment of the present invention, a computer-readable storage medium is provided, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the method described above is implemented.

[0143] The present invention may be a method, an apparatus, a system and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for executing various aspects of the present invention.

[0144] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. An optimal scheduling method for power distribution of electrolyzer groups under wind power fluctuation conditions, characterized in that: include: Collect wind farm output power data and electrolyzer group operating parameters; Adaptively segment the output power data, calculate the power fluctuation feature vector within each time period, construct a three-dimensional fluctuation feature space based on the power fluctuation feature vector, extract the fluctuation trend trajectory in the three-dimensional fluctuation feature space, predict future fluctuation risks, and generate time-based control instructions; A multi-dimensional regulation capacity evaluation system is constructed based on the operating parameters of the electrolytic cells. A mapping relationship between dynamic response characteristics and time-segment regulation requirements is established. The mapping relationship is used to calculate the comprehensive regulation capacity index of each electrolytic cell. The electrolytic cells are graded and prioritized according to the comprehensive regulation capacity index to generate a dynamic grouping plan for the electrolytic cells. A power regulation matrix is ​​constructed based on the dynamic grouping scheme of electrolytic cells. A recursive iterative method is used to calculate the optimal power allocation ratio of each electrolytic cell in the power regulation matrix, and a control instruction containing the real-time power setting value of each electrolytic cell is generated. The real-time power setting value is transmitted to the control unit of each electrolyzer to perform power regulation, and the real-time response data of the electrolyzer is collected. The control instructions are optimized according to the real-time response data to achieve coordinated control of the electrolyzer group on wind power fluctuations.

2. The method according to claim 1, characterized in that The output power data is adaptively segmented and the power fluctuation feature vector in each time period is calculated. The three-dimensional fluctuation feature space is constructed based on the power fluctuation feature vector, including: Calculating the power difference between adjacent sampling points in the wind power data to obtain a power change rate sequence, performing sliding window processing on the power change rate sequence, and calculating the mean and standard deviation of the power change rate in each window; A first-order difference sequence is constructed based on the mean of the power change rate, and a fluctuation amplitude sequence is constructed based on the standard deviation of the power change rate. The first-order difference sequence and the fluctuation amplitude sequence are weightedly combined to obtain a segmentation criterion. An adaptive threshold value is calculated for the segmentation criterion. A reference threshold value is determined based on the statistical distribution characteristics of the power change rate sequence. The threshold coefficient is dynamically adjusted in combination with the cumulative distribution function of the fluctuation amplitude sequence to obtain a segmentation threshold value. Sampling points greater than the segmentation threshold are marked as segmentation points, and the wind power data sequence is divided into multiple time periods according to the segmentation points. The power fluctuation characteristics of the wind power data sequence in each time period are extracted, including the average power value, the power change rate and the power fluctuation frequency. The power fluctuation characteristics are combined to construct a power fluctuation feature vector. The feature contribution of the power fluctuation feature vector is calculated using the principal component analysis method, and the three feature directions with the largest cumulative contribution are selected to construct a three-dimensional fluctuation feature space.

3. The method according to claim 1, characterized in that Extracting the fluctuation trend trajectory in the three-dimensional fluctuation feature space, predicting future fluctuation risks and generating time-based control instructions include: Connecting the power fluctuation feature vectors in a three-dimensional fluctuation feature space in time sequence to form a fluctuation trend trajectory, calculating the distance and direction angle between adjacent trajectory points in the fluctuation trend trajectory, determining a set of neighboring points for each trajectory point, calculating the local evolution direction of each trajectory point based on the set of neighboring points, and taking the ratio of the displacement change between adjacent trajectory points to the time interval as the evolution rate; The fluctuation trend trajectory is divided into zones and counted by evolution direction. The product of the proportion of trajectory points in each direction zone and the average evolution rate is calculated to determine the development probability of each evolution direction. The direction with the highest development probability is selected as the predicted trend. The power fluctuation risk value is obtained by combining the average evolution rate of this direction. The electrolytic cell control response requirement is set according to the power fluctuation risk value, the power regulation rate and steady-state error of each electrolytic cell are calculated using the electrolytic cell operating parameters, the control response requirement is compared with the power regulation rate and steady-state error of the electrolytic cell, the response matching degree is calculated, the electrolytic cells are grouped and sorted based on the response matching degree, and the electrolytic cell combination with the highest matching degree is selected as the target electrolytic cell combination. For the target electrolytic cell combination, the maximum regulation power and response time constraint are calculated according to its operating parameters, and the target regulation power and execution timing of each time period are determined in combination with the power fluctuation risk value to generate a time period control instruction.

4. The method according to claim 1, wherein A multi-dimensional regulation capability evaluation system is constructed based on the electrolytic cell operating parameters. A mapping relationship between dynamic response characteristics and time-segment regulation requirements is established. The mapping relationship is used to calculate the comprehensive regulation capability index of each electrolytic cell. The electrolytic cells are graded and prioritized according to the comprehensive regulation capability index. The dynamic grouping scheme for electrolytic cells is generated, including: Based on the acquired electrolytic cell operation data, a multi-dimensional evaluation index system including response time, adjustment accuracy and efficiency loss is established, and the response characteristic curve, accuracy index value and loss index value of the electrolytic cell are calculated based on the electrolytic cell operation data; Obtaining system regulation demand data, performing a matching analysis on the regulation demand data with the response characteristic curve, accuracy index value, and loss index value of the electrolytic cell, obtaining an adaptability evaluation value of the electrolytic cell to the regulation demand, dynamically evaluating the electrolytic cell based on the adaptability evaluation value, and calculating a comprehensive regulation capability index value of the electrolytic cell based on the regulation importance weight of each regulation period; Obtaining the cumulative number of adjustments and adjustment intensity data of the electrolytic cell and calculating a fatigue index value; and classifying the electrolytic cell into a fast response level, a conventional adjustment level, and a standby level according to the comprehensive adjustment capability index value; In each level of electrolytic cells, the comprehensive adjustment capability index value and the fatigue index value are weightedly calculated to obtain a priority coefficient, and the electrolytic cells are sorted according to the priority coefficient; when the fatigue index value exceeds the preset fatigue threshold, the electrolytic cell is downgraded and the priority ranking is updated to generate a dynamic electrolytic cell grouping scheme containing grading information and priority information.

5. The method according to claim 4, characterized in that Based on the adaptability evaluation value, the electrolytic cell is dynamically evaluated. According to the weight of the importance of regulation in each regulation period, the comprehensive regulation capability index value of the electrolytic cell is calculated, including: Collect wind power fluctuation data, obtain power fluctuation inflection points through extreme value detection, divide the evaluation period into multiple regulation periods according to the power fluctuation inflection points, and calculate the regulation difficulty coefficient based on the power change trend within each regulation period; Obtaining the power fluctuation amplitude, fluctuation frequency and system stability margin of each regulation period, constructing a regulation period weight evaluation matrix, and calculating the regulation importance weight of each regulation period according to the weight evaluation matrix; The operating data of the electrolytic cell in each adjustment period is collected, and the adaptability evaluation value of the electrolytic cell in each adjustment period is calculated based on the operating data and the control difficulty coefficient. The adaptability evaluation value is normalized, and the comprehensive adjustment capability index value of the electrolytic cell is obtained by combining the control importance weight.

6. The method according to claim 1, characterized in that Based on the dynamic grouping scheme of electrolytic cells, a power regulation matrix is ​​constructed. A recursive iterative method is used to calculate the optimal power allocation ratio of each electrolytic cell in the power regulation matrix. The control instructions containing the real-time power setting value of each electrolytic cell are generated, including: Collect the operating power, power fluctuation and response time of the electrolytic cell group, and calculate the dynamic response characteristics of the electrolytic cell based on the operating power, power fluctuation and response time; Constructing a power regulation matrix based on the dynamic grouping scheme of the electrolytic cells, calculating the inter-group power coupling coefficient based on the dynamic response characteristics of the electrolytic cells, and writing the inter-group power coupling coefficient into the corresponding position of the power regulation matrix to obtain an initial power regulation matrix; Performing a difference operation on each element value of the initial power regulation matrix and the rated power value of the electrolytic cell to obtain a power regulation deviation matrix, calculating an inter-group adaptive weight based on the power regulation deviation matrix, and multiplying the inter-group adaptive weight by the initial power regulation matrix to obtain an optimized power regulation matrix; Constructing a multidimensional optimization objective function based on the optimized power regulation matrix and the power regulation deviation matrix, setting the power regulation deviation, the inter-group power coupling coefficient and the dynamic response characteristic as optimization variables, and calculating the optimization variable weight coefficients according to the system operation requirements; A recursive iterative method is used to calculate the power allocation ratio of each electrolytic cell in the power regulation matrix. The adaptive step size is calculated by multiplying the optimization variable weight coefficient with the gradient of the multidimensional optimization objective function. The dynamic compensation factor is calculated based on the historical iterative data to obtain the optimal power allocation ratio. The optimal power allocation ratio is multiplied by the rated power of the electrolytic cell to obtain the real-time power setting value of each electrolytic cell, and the control instruction is generated.

7. An optimized scheduling system for power distribution of electrolyzer groups under wind power fluctuation conditions, used to implement the method according to any one of claims 1 to 6, characterized in that: include: The first unit is used to collect wind farm output power data and electrolyzer group operating parameters; The second unit is used to perform adaptive segmentation processing on the output power data, calculate the power fluctuation feature vector in each time period, construct a three-dimensional fluctuation feature space based on the power fluctuation feature vector, extract the fluctuation trend trajectory in the three-dimensional fluctuation feature space, predict future fluctuation risks and generate time-based control instructions; The third unit is used to build a multi-dimensional regulation capability evaluation system based on the operating parameters of the electrolytic cells, establish a mapping relationship between dynamic response characteristics and time-based regulation requirements, use the mapping relationship to calculate the comprehensive regulation capability index of each electrolytic cell, and perform hierarchical screening and priority sorting of the electrolytic cells based on the comprehensive regulation capability index to generate a dynamic grouping plan for the electrolytic cells; The fourth unit is used to construct a power regulation matrix based on the dynamic grouping scheme of the electrolytic cells, calculate the optimal power allocation ratio of each electrolytic cell in the power regulation matrix using a recursive iterative method, and generate a control instruction containing the real-time power setting value of each electrolytic cell; The fifth unit is used to transmit the real-time power setting value to the control unit of each electrolyzer to perform power regulation, and collect the real-time response data of the electrolyzer, optimize the control instructions according to the real-time response data, and realize the coordinated control of the electrolyzer group on wind power fluctuations.

8. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor is configured to call the instructions stored in the memory to execute the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images