A wind turbine generator cooperative control optimization method and system

Abstract

The application discloses a kind of wind turbine cooperative control optimization method and system, it is related to cooperative control technical field;Method includes obtaining historical regulation response, real-time operation and dispatching instruction data, and calculates the regulation state data of wind turbine, according to this, evolution map is constructed, realize the structural expression of the dynamic evolution process of the regulation resource inside wind farm, and obtain target area by partition, so that the scheduling side can identify the regulation growth, stable and different resource states of attenuation, according to the hierarchical regulation structure data of target area, determine target regulation instruction according to dispatching instruction data, select regulation resource set according to regulation structure data, generate cooperative regulation instruction by regulation resource set determination, realize the change from static capacity scheduling to dynamic evolution resource scheduling, and send corresponding wind turbine execution control, and update corresponding regulation state data by operation feedback data;It improves the efficiency of wind farm regulation resource cooperative control.

Description

Technical Field

[0001] This invention belongs to the field of collaborative control technology, specifically relating to a collaborative control optimization method and system for wind turbine generators. Background Technology

[0002] Wind turbines are crucial power generation equipment for realizing the large-scale utilization of renewable energy. They convert wind energy into electricity, providing clean and low-carbon energy supply to the power grid. This is of great significance for reducing fossil fuel consumption, promoting energy structure transformation, and achieving dual-carbon goals. Existing wind turbine and grid coordinated control methods typically adjust the grid based on current grid frequency, voltage, power deficit, and the real-time operating status of the wind turbines. They generally assume that wind farms can continuously provide the same regulation capabilities according to dispatch requirements and treat wind turbines as standard regulation resources that can be called upon in real time.

[0003] However, in high-proportion renewable energy grids, wind turbines will participate in ancillary services such as frequency regulation, voltage regulation, and power point tracking for a long time. Due to differences in the number of historical responses, response amplitude, and response duration, the rotor kinetic energy reserves, accumulated mechanical load levels, and sustainable regulation capabilities of different wind turbines will gradually diverge. This causes the actual regulation resource structure within the wind farm to continuously evolve, resulting in a gradual deviation between the distribution of adjustable resources perceived by the dispatching side and the actual sustainable regulation resource distribution within the wind farm. If the grid continuously issues frequency regulation, voltage regulation, or power point tracking commands, this deviation will further accumulate, making it impossible for dispatching commands to accurately match the actual regulation capabilities of each wind turbine. This leads to a situation where some wind turbines are continuously over-utilized, while the regulation resources of other wind turbines remain idle for a long time. Consequently, the overall regulation resource utilization efficiency of the wind farm is greatly reduced, seriously affecting the continuity and effectiveness of subsequent coordinated control. Summary of the Invention

[0004] The purpose of this invention is to solve the problem that, during long-term participation in frequency regulation, voltage regulation, and power point tracking, different wind turbine units have different historical response behaviors, resulting in some wind turbine units being continuously over-utilized while the regulation resources of other wind turbine units remain idle for a long time, leading to a significant reduction in the overall regulation resource utilization efficiency of the wind farm. Therefore, this invention proposes a wind turbine unit collaborative control optimization method and system.

[0005] In a first aspect of this invention, a method for optimizing the coordinated control of wind turbine generator sets is first proposed, the method comprising:

[0006] Acquire historical regulation response data, real-time operation data, and grid dispatch command data for each wind turbine unit in the wind farm, and calculate the corresponding regulation status data for each wind turbine unit based on the historical regulation response data and real-time operation data;

[0007] Based on the regulation state data, the regulation state change amount and regulation state change rate of each wind turbine are calculated, and a wind farm regulation evolution map is generated based on the regulation state change amount and regulation state change rate.

[0008] The regulation evolution map is divided into regions to obtain target regions. Based on the target regions, each wind turbine is stratified by resource allocation to obtain regulation structure data. The target regions include regulation growth regions, regulation stability regions, and regulation decay regions. The regulation structure data represents the hierarchical distribution relationship of each wind turbine in the target regions and the corresponding resource hierarchical division results within the current control cycle.

[0009] The target regulation instruction is parsed based on the power grid dispatch instruction data. The regulation resource set is determined based on the regulation structure data and the target regulation instruction. The regulation task allocation result for each wind turbine is determined through the regulation resource set, and a coordinated regulation instruction is generated.

[0010] The coordinated adjustment command is sent to the corresponding wind turbine to perform adjustment control, and the operation feedback data after adjustment is collected in real time. The adjustment status data of each wind turbine is updated through the operation feedback data, and the updated adjustment status data is used to perform coordinated adjustment control in the next control cycle.

[0011] Optionally, the regulation status data corresponding to each wind turbine is calculated based on historical regulation response data and real-time operation data, including:

[0012] The historical regulation response data is processed by time slicing according to the control cycle to obtain the historical regulation record sequence corresponding to each wind turbine.

[0013] Construct a regulation effect correlation sequence for each wind turbine based on the time interval and response correlation between adjacent regulation records in each historical regulation record sequence;

[0014] Mapping the real-time operating data of each wind turbine to the corresponding regulation action correlation sequence determines the influence coefficient of each historical regulation record sequence on the current operating status.

[0015] The historical regulation impact of each wind turbine is obtained by summing the impact coefficients corresponding to each historical regulation record sequence.

[0016] The historical adjustment impact and real-time operation data are used to calculate the adjustment status data corresponding to each wind turbine.

[0017] By slicing historical regulation response data over time, a correlation sequence of regulation effects is constructed, linking historical regulation behavior with the current real-time operating status. This quantifies the continuous impact of historical regulation behavior on the current operating status, and then calculates regulation status data that reflects the actual regulation capability of the wind turbine. Compared with evaluation based solely on real-time operating status, this approach fully considers the capability evolution brought about by long-term regulation behavior, improving the authenticity and accuracy of regulation status assessment.

[0018] Optionally, the change in regulation state and the rate of change in regulation state for each wind turbine are calculated based on the regulation state data, including:

[0019] The corresponding regulation state sequence is constructed by arranging the regulation state data of each wind turbine in multiple consecutive control cycles according to time.

[0020] The adjustment state sequence is divided into a first preset number of state evolution units based on the changes in adjustment state data between adjacent control cycles; each state evolution unit includes a state start node, a state end node, and a state change process.

[0021] The change in the adjustment state of the corresponding state evolution unit is calculated based on the difference in adjustment state between the state start node and the state end node.

[0022] The rate of change of the regulation state is calculated based on the continuous control period and the change in regulation state corresponding to each state evolution unit.

[0023] By organizing the regulation state data over multiple consecutive control cycles in a time sequence, dividing it into state evolution units, and calculating the regulation state change amount and rate of change for each stage, the discrete regulation state is transformed into a continuous evolution process. This accurately reflects the degree and rate of change of the wind turbine's regulation capacity in different control cycles, improving the accuracy and continuity of dynamic analysis of regulation resources.

[0024] Optionally, a wind farm regulation evolution map is generated based on the amount and rate of change of the regulation state, including:

[0025] The regulation state change amount and regulation state change rate of each wind turbine are combined to obtain the regulation evolution state data of each wind turbine.

[0026] The wind turbine arrangement order is established based on the equipment number of each wind turbine in the wind farm, and the regulation evolution state data corresponding to each wind turbine are sequentially mapped according to the arrangement order to obtain the regulation evolution distribution sequence of the wind turbine.

[0027] Based on the electrical connection relationship between each wind turbine, the wind turbines with electrical connection relationship in the regulation evolution distribution sequence are associated and connected to form a second preset number of regulation evolution association units;

[0028] By combining the various regulation evolution correlation units according to their corresponding electrical connection positions, the regulation evolution map of the wind farm is obtained.

[0029] By combining the change in regulation state with the rate of change in regulation state to form regulation evolution state data, and constructing a regulation evolution map based on the arrangement order and electrical connection relationship of wind turbine units, the independent evolution state of each wind turbine unit is transformed into an overall evolution distribution with topological correlation. This can intuitively reflect the spatial distribution and correlation evolution characteristics of regulation resources within the wind farm, providing a unified data carrier for subsequent regulation resource area division and dynamic resource stratification, and improving the accuracy of regulation resource identification and overall collaborative analysis capabilities.

[0030] Optionally, the regulation evolution map is divided into regions to obtain target regions, and each wind turbine is stratified according to the target regions to obtain regulation structure data, including:

[0031] Based on the regulatory evolution state data corresponding to each regulatory evolution correlation unit in the regulatory evolution map, preliminary regional division is carried out to obtain the regulatory growth region, the regulatory stability region, and the regulatory decay region;

[0032] A temporary buffer area is added, and the regulatory evolution correlation units in each area are traversed. The regulatory evolution correlation units that satisfy the first preset rule are temporarily stored in the temporary buffer area.

[0033] Continuously monitor the change in regulation state and the rate of change in regulation state corresponding to each regulation evolution correlation unit in the temporary buffer area, and reclassify the regulation evolution correlation units that meet the second preset rule to the corresponding target area;

[0034] Based on the final division of the regulation growth region, regulation stability region, and regulation decay region, resource stratification is performed on each wind turbine to generate regulation structure data.

[0035] By initially dividing the regulation evolution map into regions and adding a temporary buffer zone to continuously monitor the regulation evolution associated units with regional switching tendencies, and then reclassifying them to the corresponding target regions after their evolutionary state stabilizes, the system effectively avoids regional misjudgment caused by short-term operating condition fluctuations, improves the stability and accuracy of the division of regulation growth regions, regulation stability regions, and regulation decay regions, and thus enhances the reliability of resource stratification results.

[0036] Optionally, the target regulation instruction is parsed from the power grid dispatch instruction data, and the regulation resource set is determined based on the regulation structure data and the target regulation instruction, including:

[0037] Determine the target adjustment requirement corresponding to the target adjustment command; the target adjustment requirement includes adjustment type, adjustment direction, and adjustment intensity;

[0038] Based on the adjustment structure data, the adjustment evolution correlation units in the resource layer corresponding to the target adjustment requirements are obtained to construct a set of target adjustment candidate resources;

[0039] Traverse each regulation evolution correlation unit in the target regulation candidate resource set and determine whether each regulation evolution correlation unit meets the target regulation requirements:

[0040] If the conditions are met, the corresponding regulatory evolution correlation unit will be added to the target regulatory resource set;

[0041] If the conditions are not met, the adjustment evolution correlation unit corresponding to the next resource layer is added to the target adjustment candidate resource set, and the traversal judgment process is repeated until the target adjustment resource set meets the target adjustment requirements.

[0042] Based on the target regulation resource set, determine the wind turbine generation and the regulation resource set corresponding to the target regulation command contained in each regulation evolution association unit.

[0043] By analyzing grid dispatch instructions to determine target regulation needs, and combining regulation structure data to screen regulation evolution related units at each resource level, a set of regulation resources matching the target regulation instructions is formed. This avoids direct allocation of regulation resources across the entire wind farm, enabling regulation tasks to be prioritized for allocation to resource layers with stronger regulation capabilities. While meeting regulation needs, this reduces frequent calls to units with diminishing regulation capabilities, improves the accuracy of regulation resource matching and the balance of resource utilization, and enhances the sustainability and execution efficiency of wind farm coordinated regulation.

[0044] Optionally, the allocation of regulation tasks for each wind turbine is determined by adjusting the resource set, including:

[0045] Based on the set of regulatory resources, each regulatory evolution correlation unit is extracted, and a regulatory task allocation sequence is constructed according to the electrical connection relationship corresponding to each regulatory evolution correlation unit;

[0046] The tasks of each regulation evolution association unit are decomposed sequentially according to the regulation task allocation sequence to obtain the unit regulation tasks corresponding to each regulation evolution association unit.

[0047] The adjustment tasks of each unit are assigned to each wind turbine unit contained in the corresponding adjustment evolution association unit, so that each wind turbine unit can jointly complete the adjustment tasks of the corresponding unit.

[0048] The allocation results of the regulation tasks for each wind turbine are generated based on the unit regulation tasks corresponding to each regulation evolution correlation unit.

[0049] Based on the set of regulation resources, regulation evolution correlation units are extracted. Based on the electrical connection relationship between each correlation unit, a regulation task allocation sequence is constructed. The overall regulation task is decomposed into unit regulation tasks corresponding to each correlation unit and allocated to each wind turbine unit within the correlation unit for coordinated execution. This achieves hierarchical allocation of regulation tasks from the whole to the part, which can make full use of the coordinated regulation capabilities between electrically connected wind turbine units, avoid disordered or overly concentrated allocation of regulation tasks, and improve the coordination and execution efficiency of wind farm regulation task allocation.

[0050] Optionally, the adjustment status data corresponding to each wind turbine is updated through the operational feedback data, including:

[0051] Obtain the operation feedback data corresponding to each wind turbine, and convert the operation feedback data into corresponding adjustment feedback records according to the control cycle;

[0052] Each regulation feedback record is appended to the end of the historical regulation record sequence of the corresponding wind turbine, and the historical regulation record sequence of each wind turbine is updated.

[0053] Traverse the updated historical regulation record sequence, reconstruct the regulation effect correlation sequence corresponding to each wind turbine, and recalculate the influence coefficient of each historical regulation record on the current operating state.

[0054] The historical regulation impact of each wind turbine is updated based on the recalculated impact coefficient, and the regulation status data of each wind turbine is recalculated based on the real-time operating data of the current control cycle.

[0055] By converting operational feedback data into regulation feedback records according to the control cycle and appending them to the historical regulation record sequence, the latest regulation behavior is continuously integrated into the historical regulation process. This reconstructs the correlation sequence of regulation effects, calculates the historical regulation impact and regulation status data, and enables dynamic iterative updates of the wind turbine's regulation status. This allows for timely reflection of changes in the actual regulation capacity of wind turbines after long-term participation in ancillary services, avoids the disconnect between regulation status and actual operating status, improves the real-time performance and accuracy of subsequent regulation resource assessment and collaborative scheduling, and forms a continuously optimized closed-loop collaborative control mechanism.

[0056] In a second aspect of this invention, a wind turbine collaborative control optimization system is proposed, the system comprising:

[0057] The data acquisition module is used to acquire historical regulation response data, real-time operation data and grid dispatch command data of each wind turbine in the wind farm, and calculate the corresponding regulation status data of each wind turbine based on the historical regulation response data and real-time operation data.

[0058] The map generation module is used to calculate the amount and rate of change of the regulation state for each wind turbine based on the regulation state data, and to generate a wind farm regulation evolution map based on the amount and rate of change of the regulation state.

[0059] The region division module is used to divide the regulation evolution map into target regions, and to perform resource stratification of each wind turbine according to the target regions to obtain regulation structure data. The target regions include regulation growth regions, regulation stability regions, and regulation decay regions. The regulation structure data represents the hierarchical distribution relationship of each wind turbine in the target regions and the corresponding resource stratification results within the current control cycle.

[0060] The instruction generation module is used to parse the target regulation instruction based on the power grid dispatch instruction data, determine the regulation resource set based on the regulation structure data and the target regulation instruction, determine the regulation task allocation result for each wind turbine through the regulation resource set, and generate the coordinated regulation instruction.

[0061] The data update module is used to send the coordinated adjustment command to the corresponding wind turbine to perform adjustment control, and to collect the operation feedback data after adjustment in real time. The module updates the adjustment status data of each wind turbine through the operation feedback data, and then executes the coordinated adjustment control of the next control cycle with the updated adjustment status data.

[0062] The beneficial effects of this invention are:

[0063] This invention corrects the current regulation status of wind turbines by introducing historical regulation response data and constructs a regulation evolution map reflecting the evolution of regulation capacity. Based on this, regional division and resource stratification are completed, enabling the actual regulation capacity distribution within the wind farm to be dynamically identified and continuously updated. Combined with the grid dispatch command requirements, regulation resources are selected from the corresponding resource layer and collaborative task allocation is implemented to achieve matching between dispatch commands and the actual regulation capacity of wind turbines. This avoids continuous over-utilization of some units and long-term idleness of some units, improves the overall regulation resource utilization efficiency of the wind farm, slows down the decay of regulation capacity, and enhances the continuity and effectiveness of subsequent collaborative control. Attached Figure Description

[0064] The invention will now be further described with reference to the accompanying drawings.

[0065] Figure 1 A flowchart of a wind turbine collaborative control optimization method provided in an embodiment of the present invention;

[0066] Figure 2 This is a framework diagram of a wind turbine collaborative control optimization system provided in an embodiment of the present invention. Detailed Implementation

[0067] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The term "and / or" in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and B can represent: A alone, A and B simultaneously, and B alone. Furthermore, descriptions involving "first," "second," etc., in this invention are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, features defined with "first" or "second" can explicitly or implicitly include at least one of those features. Additionally, the technical solutions of the various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed by the present invention.

[0068] Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0069] This invention provides a method for optimizing the coordinated control of wind turbine generators. See also... Figure 1 The method includes the following steps:

[0070] S1: Obtain historical regulation response data, real-time operation data and grid dispatch command data of each wind turbine in the wind farm, and calculate the regulation status data corresponding to each wind turbine based on the historical regulation response data and real-time operation data.

[0071] S2, calculate the change in regulation state and the rate of change in regulation state for each wind turbine based on the regulation state data, and generate a wind farm regulation evolution map based on the change in regulation state and the rate of change in regulation state.

[0072] S3, divide the regulation evolution map into regions to obtain the target region, and perform resource stratification of each wind turbine according to the target region to obtain regulation structure data;

[0073] S4. Parse the target regulation instruction based on the power grid dispatch instruction data, determine the regulation resource set based on the regulation structure data and the target regulation instruction, determine the regulation task allocation result for each wind turbine through the regulation resource set, and generate the coordinated regulation instruction.

[0074] S5 sends the coordinated adjustment command to the corresponding wind turbine to execute the adjustment control, and collects the operation feedback data after adjustment in real time. It updates the corresponding adjustment status data of each wind turbine through the operation feedback data, and executes the coordinated adjustment control of the next control cycle with the updated adjustment status data.

[0075] The target region includes a region of regulated growth, a region of regulated stability, and a region of regulated decline.

[0076] The adjustment structure data represents the hierarchical distribution relationship of each wind turbine unit in the target area and the corresponding resource level division results within the current control cycle.

[0077] In one implementation, the historical regulation response data includes the number of responses, the response amplitude, and the response duration, while the real-time operating data includes the current output power, rotor speed, pitch angle, and unit load data.

[0078] In one implementation, the coordinated regulation command is sent to the corresponding wind turbine to execute regulation control, the process being as follows:

[0079] The control center sends the coordinated adjustment command to the unit controller of the corresponding wind turbine. The unit controller first parses the adjustment type, adjustment direction and adjustment task in the coordinated adjustment command, and generates control parameters based on the real-time operating status of the corresponding wind turbine.

[0080] When the coordinated regulation command is an active power regulation command, the active power reference value of the converter and the pitch angle control strategy are adjusted to gradually increase or decrease the active power output of the wind turbine.

[0081] When the coordinated regulation command is a frequency regulation command, the unit can quickly respond to changes in grid frequency by releasing or absorbing rotor energy through adjusting the converter torque control command.

[0082] When the coordinated regulation command is a voltage regulation command, the reactive power output is controlled by adjusting the reactive current reference value of the converter to achieve voltage support;

[0083] During the adjustment process, the actual output power, speed, pitch angle and operating status information of the wind turbine are continuously collected as operating feedback data and uploaded to the control center for updating the adjustment status data in the next control cycle.

[0084] For example:

[0085] Suppose the power grid issues an instruction: the active power output of the wind farm is reduced by 30MW during the current control cycle;

[0086] The regulation workload of wind turbine units is as follows:

[0087] Wind Turbine A: Reduced by 10MW

[0088] Wind Turbine B: Reduced by 8MW

[0089] Wind Turbine C: Reduced by 12MW

[0090] Then, the corresponding coordinated adjustment instructions are generated:

[0091] A power regulation command to reduce the active power by 10MW is sent to wind turbine A. The controller of wind turbine A increases the pitch angle and adjusts the active power reference value of the converter, so that the output power is gradually reduced by 10MW.

[0092] Send a power regulation command to reduce the active power by 8MW to wind turbine B, and wind turbine B completes the power reduction control in the same way;

[0093] A power regulation command to reduce the active power by 12MW is sent to wind turbine C, and wind turbine C executes the control synchronously.

[0094] After the control is completed, each wind turbine will feed back the actual power change, rotor speed, pitch angle change, etc. to the control center. If wind turbine A actually only reduces by 9.5MW, the actual execution result will be used as operation feedback data to participate in the update of the adjustment status data in the next control cycle, so that the subsequent resource assessment can reflect the latest adjustment capacity changes.

[0095] In one embodiment, the regulation status data corresponding to each wind turbine is calculated based on historical regulation response data and real-time operation data, including:

[0096] The historical regulation response data is processed by time slicing according to the control cycle to obtain the historical regulation record sequence corresponding to each wind turbine.

[0097] Construct a regulation effect correlation sequence for each wind turbine based on the time interval and response correlation between adjacent regulation records in each historical regulation record sequence;

[0098] Mapping the real-time operating data of each wind turbine to the corresponding regulation action correlation sequence determines the influence coefficient of each historical regulation record sequence on the current operating status.

[0099] The historical regulation impact of each wind turbine is obtained by summing the impact coefficients corresponding to each historical regulation record sequence.

[0100] The regulation status data for each wind turbine is calculated by combining historical regulation impact data with real-time operation data.

[0101] In one implementation, the regulation status data represents the current occupancy level of the wind turbine's regulation resources and the remaining sustainable regulation capacity, while the cumulative amount of historical regulation effects is used to reflect the continuous impact of historical regulation behavior on the current regulation capacity.

[0102] In one implementation, a regulation action correlation sequence corresponding to each wind turbine is constructed, including:

[0103] Historical regulation response data of each wind turbine within a preset time window are arranged chronologically to form a corresponding historical regulation record sequence (each historical regulation record includes at least the regulation start time, regulation end time, regulation amplitude, and regulation duration). Adjacent regulation records in the historical regulation record sequence are analyzed traversally, and the time difference between the end time of the previous regulation record and the start time of the next regulation record is calculated. This time difference is determined as the time interval between the corresponding adjacent regulation records. Simultaneously, the regulation direction, regulation amplitude, and regulation duration of adjacent regulation records are compared to determine the response similarity between the two regulation actions. The degree of response similarity is used as the response correlation. Regulation continuation identifiers are constructed based on the time interval and response correlation. When the time interval is less than a preset interval threshold and the response correlation meets the preset correlation conditions, it is determined that the previous regulation record has a continuation effect on the next regulation record, and a correlation node is established between the two regulation records. When the time interval is greater than the preset interval threshold, it is determined that the regulation effect of the previous regulation record has been largely released, and no correlation node is established. The correlation nodes are connected according to the chronological order of the historical regulation records, and the corresponding regulation effect continuation intensity is recorded to obtain the regulation effect correlation sequence for each wind turbine.

[0104] It should be noted that the adjustment direction refers to the power adjustment direction executed by the wind turbine when responding to the dispatch command, including the power increase adjustment direction and the power decrease adjustment direction (the direction is determined by the positive and negative signs).

[0105] The adjustment range refers to the difference between the actual power change during the adjustment process of the wind turbine and the power value before adjustment.

[0106] The preset association condition refers to the fact that adjacent adjustment records have the same adjustment direction and the difference in adjustment amplitude and the difference in adjustment duration are both less than the corresponding preset threshold.

[0107] In one implementation, the real-time operating data of each wind turbine is matched with the corresponding regulation action association sequence to determine the target association node corresponding to the current operating state. Starting from the historical regulation record corresponding to the target association node, the association nodes are traced step by step along the regulation action association sequence to obtain the regulation action continuation intensity corresponding to each historical regulation record. At the same time, the state offset between the current operating state and the operating state at the end of each historical regulation record is calculated. The corresponding action retention degree is determined according to the state offset corresponding to each historical regulation record. The influence coefficient of each historical regulation record on the current operating state is calculated based on the action retention degree and regulation action continuation intensity corresponding to each historical regulation record.

[0108] In one implementation, the modulation amplitude, modulation duration, and time interval between adjacent modulation records in the modulation effect correlation sequence are determined by formula... The duration of the regulatory effect corresponding to each historical regulation record was calculated; This represents the adjustment range corresponding to the i-th historical adjustment record. This represents the duration of adjustment corresponding to the i-th historical adjustment record. This represents the time interval between the end time of the i-th historical adjustment record and the start time of the (i+1)-th historical adjustment record. This indicates the duration of the regulatory effect corresponding to the i-th historical regulation record;

[0109] Acquire the operating status data corresponding to the end of each historical regulation record, compare it with the current real-time operating data, and obtain the corresponding state offset based on the power deviation, speed deviation and pitch angle deviation between the two using the Euclidean distance calculation formula;

[0110] Based on the state offset corresponding to each historical adjustment record The corresponding retention rate was calculated. This indicates the degree of retention of the effect corresponding to the i-th historical adjustment record. This represents the state offset corresponding to the end of the i-th historical adjustment record;

[0111] The influence coefficient of each historical adjustment record on the current operating status is calculated by multiplying the retention degree of the adjustment effect and the duration of the adjustment effect corresponding to each historical adjustment record.

[0112] In one implementation, feature extraction is performed on real-time operating data to obtain operating status feature data. Based on historical regulation impact, a corresponding impact correction factor is calculated. The operating status feature data is then corrected using the impact correction factor to obtain regulation status data for each wind turbine. The regulation status data is used to comprehensively reflect the current regulation resource occupancy status and remaining sustainable regulation capacity of each wind turbine, serving as the basis for subsequent calculations of regulation status change, regulation status change rate, and generation of regulation evolution map.

[0113] In one implementation, historical regulation response data is constructed into a historical regulation record sequence, and a regulation effect correlation sequence is established. This allows for the linking of previously independent regulation behaviors, enabling the analysis of the continuous impact of historical regulation behaviors on the current operating state. By combining real-time operating data, the influence coefficient of each historical regulation record on the current operating state is determined, and these are accumulated to form a historical regulation influence quantity. This not only reflects the current operating condition of the wind turbine but also the consumption of regulation resources caused by long-term participation in ancillary services such as frequency regulation and voltage regulation. The historical regulation influence quantity and real-time operating data are then used together to generate regulation state data, achieving an accurate characterization of the wind turbine's true and sustainable regulation capability. This provides a reliable basis for subsequent regulation capability evolution analysis and regulation task allocation, avoiding scheduling resource misallocation problems.

[0114] In one embodiment, the calculation of the regulation state change and regulation state change rate for each wind turbine based on regulation state data includes:

[0115] The corresponding regulation state sequence is constructed by arranging the regulation state data of each wind turbine in multiple consecutive control cycles according to time.

[0116] The regulation state sequence is divided into a first preset number of state evolution units based on the changes in regulation state data between adjacent control cycles; each state evolution unit includes a state start node, a state end node, and a state change process.

[0117] The change in the adjustment state of the corresponding state evolution unit is calculated based on the difference in adjustment state between the state start node and the state end node.

[0118] The rate of change of the regulation state is calculated based on the continuous control period and the change in regulation state corresponding to each state evolution unit.

[0119] In one implementation, a state evolution unit refers to a range of state changes corresponding to multiple consecutive control cycles in a control state sequence, and each state evolution unit includes control state data corresponding to the initial control cycle, control state data corresponding to the end control cycle, and control state data corresponding to consecutive control cycles within the range.

[0120] In one implementation, the regulation state sequence is divided into a first preset number of state evolution units, so that each state evolution unit corresponds to a complete regulation state evolution process of the wind turbine in a continuous control cycle. This decomposes the long-term continuous change into multiple local continuous evolution processes for analysis, avoiding the averaging or masking of local regulation state change characteristics caused by overall calculation. This effectively improves the accuracy of the calculation of regulation state change amount and regulation state change rate, so that the subsequently generated regulation evolution map can more realistically reflect the stage evolution characteristics of the wind turbine's regulation capability.

[0121] In one implementation, the state start node, state end node, and intermediate state node corresponding to each state evolution unit are obtained. The adjustment state data corresponding to the state start node is used as the reference state data. The state offset between each intermediate state node and the reference state data is calculated, and the final state offset between the state end node and the reference state data is calculated. The state offsets are accumulated step by step according to the time sequence of each state node in the state evolution unit to obtain the cumulative state offset value of the corresponding state evolution unit. The cumulative state offset value is used to determine the adjustment state change of the corresponding state evolution unit.

[0122] In one implementation, the continuous control period and the adjustment state change amount corresponding to each state evolution unit are obtained, and each state evolution unit is divided into a preset number of evolution stages according to the continuous control period; wherein, each evolution stage corresponds to a number of consecutive control periods.

[0123] Calculate the changes in regulation state corresponding to adjacent control cycles within each evolution stage, generate corresponding change sequences by time, and determine the continuity of regulation state changes within each evolution stage based on the change sequences:

[0124] When the change in the adjustment state between adjacent control cycles is greater than the first change threshold, it is determined to be a positive change; when the change in the adjustment state between adjacent control cycles is less than the second change threshold, it is determined to be a negative change; when the change in the adjustment state is not less than the second change threshold and not greater than the first change threshold, it is determined to be an invalid fluctuation and does not participate in the direction determination; the first change threshold is greater than the second change threshold.

[0125] The stage change rate corresponding to each evolution stage is calculated based on the cumulative change in regulation state and the continuous control period. The stage change rates are then connected in chronological order to generate the regulation state change rate corresponding to each state evolution unit.

[0126] In one implementation, the regulation state data within multiple consecutive control cycles is processed as a time sequence and divided into state evolution units, transforming the originally discrete state data into a stage-continuous evolution process. This avoids the problem that the difference at a single time point cannot reflect the fluctuations in regulation behavior. The change in regulation state is then calculated using the state difference between the start and end nodes, and the rate of change in regulation state is calculated by combining the continuous control cycle corresponding to the state evolution unit. This allows for accurate analysis of the cumulative change intensity and rate of change of the wind turbine's regulation capability in the time dimension, thereby achieving a segmented quantitative expression of the dynamic evolution process of regulation resources.

[0127] In one embodiment, generating a wind farm regulation evolution map based on the amount of regulation state change and the rate of regulation state change includes:

[0128] The regulation state change amount and regulation state change rate of each wind turbine are combined to obtain the regulation evolution state data of each wind turbine.

[0129] The wind turbine arrangement order is established based on the equipment number of each wind turbine in the wind farm, and the regulation evolution state data corresponding to each wind turbine are sequentially mapped according to the arrangement order to obtain the regulation evolution distribution sequence of the wind turbine.

[0130] Based on the electrical connection relationship between each wind turbine, wind turbines with electrical connection relationships in the regulation evolution distribution sequence are associated and connected to form a second preset number of regulation evolution association units;

[0131] By combining the various regulation evolution correlation units according to their corresponding electrical connection positions, the regulation evolution map of the wind farm is obtained.

[0132] In one implementation, the regulation state change amount and regulation state change rate of each wind turbine are correlated one-to-one according to the order of the wind turbine number, and the correlation result is used as the regulation evolution state data of the corresponding wind turbine.

[0133] In one implementation, a unique correspondence is established based on the equipment number of each wind turbine in the wind farm. The regulation evolution status data corresponding to each wind turbine is written to the corresponding position in ascending order of equipment number. When the same equipment number corresponds to new regulation evolution status data, the data in the original position is overwritten and updated, so that each wind turbine maintains a fixed data mapping position in different control cycles, forming a regulation evolution distribution sequence of wind turbines.

[0134] In one implementation, the electrical connection relationship between wind turbines is established based on the connection relationship of the collection lines corresponding to each wind turbine in the wind farm. Based on the regulation evolution distribution sequence corresponding to each wind turbine, the electrical connection relationship corresponding to each wind turbine is traversed sequentially. When the regulation evolution state corresponding to an adjacent electrically connected wind turbine meets the preset conditions, the corresponding wind turbine is associated and connected, and the connection continues to extend to the next electrically connected wind turbine until there is no wind turbine that meets the preset conditions in the current electrical connection path. The wind turbines associated and connected in the same extension process are determined as a regulation evolution association unit. The above process is repeated until the association connection of all wind turbines is completed, forming a second preset number of regulation evolution association units.

[0135] It should be noted that: electrical connection relationship refers to the electrical topology relationship formed when wind turbine units are connected to the power grid through the same collector line, the same feeder, or the same collection node;

[0136] Preset conditions: The preset conditions refer to the absolute difference in the change of regulation state of adjacent electrically connected wind turbine units not being greater than the first change threshold, and the absolute difference in the rate of change of regulation state not being greater than the second rate of change threshold.

[0137] In one implementation, the electrical connection positions corresponding to each regulation evolution association unit are obtained, and the units are arranged according to their connection order in the wind farm's collector lines. Using the collection nodes corresponding to the collector lines as connection base points, regulation evolution association units with the same collection nodes are combined, and the connection relationships between each regulation evolution association unit are established. Then, based on the connection relationships between the collection nodes, the combined regulation evolution association units are connected sequentially to obtain a wind farm regulation evolution map. The regulation evolution map is used to characterize the dynamic evolution distribution of the regulation capabilities of each wind turbine unit in the wind farm, providing a basis for subsequent hierarchical allocation of regulation resources and coordinated regulation tasks.

[0138] In one implementation, regulation evolution state data is formed by combining the regulation state change quantity and the regulation state change rate. Regulation evolution association units are constructed according to the arrangement order and electrical connection relationship of wind turbine units. This allows the discrete regulation state changes of each wind turbine unit to be associated and organized according to the actual electrical connection structure of the wind farm. Then, a wind farm regulation evolution map is generated according to the electrical connection position corresponding to each association unit. This achieves an integrated and structured expression of the wind farm regulation capability evolution process, which can intuitively reflect the spatial distribution and evolution characteristics of regulation capability within the wind farm.

[0139] In one embodiment, the regulation evolution map is divided into regions to obtain target regions, and the regulation structure data is obtained by resource stratification of each wind turbine based on the target regions, including:

[0140] Based on the regulatory evolution state data corresponding to each regulatory evolution correlation unit in the regulatory evolution map, preliminary regional division is carried out to obtain the regulatory growth region, the regulatory stability region, and the regulatory decay region;

[0141] A temporary buffer area is added, and the regulatory evolution correlation units in each area are traversed. The regulatory evolution correlation units that satisfy the first preset rule are temporarily stored in the temporary buffer area.

[0142] Continuously monitor the change in regulation state and the rate of change in regulation state corresponding to each regulation evolution correlation unit in the temporary buffer area, and reclassify the regulation evolution correlation units that meet the second preset rule to the corresponding target area;

[0143] Based on the final division of the regulation growth region, regulation stability region, and regulation decay region, resource stratification is performed on each wind turbine to generate regulation structure data.

[0144] In one implementation, the preliminary regional division process for the regulation evolution state data corresponding to each regulation evolution correlation unit is as follows: obtain the regulation evolution state data corresponding to each regulation evolution correlation unit; calculate the average value of the regulation state change amount and the regulation state change rate based on the regulation evolution state data corresponding to all regulation evolution correlation units; construct growth benchmark, stability benchmark, and decay benchmark with the average value of regulation state change amount and the average value of regulation state change rate as the center; calculate the state difference between the regulation evolution state data corresponding to each regulation evolution correlation unit and each regional benchmark; and confirm the regional benchmark with the smallest state difference as the preliminary assigned region of the corresponding regulation evolution correlation unit, thereby obtaining the regulation growth region, regulation stability region, and regulation decay region.

[0145] In one implementation, the corresponding state fluctuation value is calculated based on the rate of change of the regulation state of each regulation evolution correlation unit within the continuous control cycle.

[0146] The first preset rule is:

[0147] Regulation evolution correlation units whose state fluctuation values ​​exceed the preset fluctuation threshold and whose rate of change of regulation state changes changes in direction within consecutive control cycles are assigned to the virtual transition region, while the remaining regulation evolution correlation units are stored normally in the corresponding target region; a change in the rate of change of regulation state changes in direction means that the sign of the rate of change of regulation state changes changes in two consecutive adjacent control cycles.

[0148] The second preset rule is:

[0149] The rate of change of regulation state corresponding to each regulation evolution associated unit in the virtual transition area is continuously monitored. When the rate of change of regulation state remains in the same direction within a continuous control cycle and the state fluctuation value is less than the preset fluctuation threshold, the regulation evolution associated unit is reassigned to the corresponding target area based on the corresponding regulation evolution state data.

[0150] In one implementation, after dividing the regulation growth region, regulation stability region, and regulation decay region, the regulation evolution correlation units in each region are taken as the processing objects. A comprehensive index is calculated by weighting the change in regulation state and the rate of change in regulation state. A numerical ranking sequence is formed in the same region based on the comprehensive index. According to the ranking sequence, the first 1 / 3 of the regulation evolution correlation units are classified as high adjustable resource level, the middle 1 / 3 are classified as medium adjustable resource level, and the bottom 1 / 3 are classified as low adjustable resource level. In this way, without changing the regional affiliation, fine-grained differentiation of the regulation capacity within the region is achieved, providing a hierarchical basis for subsequent on-demand calling and priority scheduling.

[0151] In one implementation, relying solely on the three regions of growth, stability, and decay can only reflect the directional changes in the state of the wind turbine's regulation capability. However, it cannot distinguish the differences in response intensity, rate of change, and sustainability among units within the same state region. This can lead to units within the same region being used equally during scheduling, resulting in some units being continuously prioritized and experiencing accelerated capacity decay, while other units are not fully utilized, leading to uneven resource allocation.

[0152] After further resource stratification, the units in the same area are divided into different regulation capacity levels, enabling the dispatch system to perform orderly calling and differentiated allocation from high to low based on the stratification results. This not only meets the target regulation needs but also avoids excessive dependence on a single unit or the same type of unit, making the call for regulation resources within the wind farm more balanced and reducing the cumulative capacity attenuation caused by frequent regulation of local units, thereby improving the sustainability and stability of the overall regulation capacity.

[0153] In one implementation, since the regulation capacity of wind turbine units is in a continuous evolution process, some regulation evolution related units may frequently switch regions due to short-term operating condition fluctuations. If the region division is completed directly, it is easy to cause instability in the resource stratification results, thereby affecting the accuracy of subsequent regulation resource allocation. Therefore, on the basis of initially dividing the regulation growth region, regulation stability region, and regulation decay region, a temporary buffer region is added. Regulation evolution related units with a tendency to switch regions are continuously monitored, and after the evolution state stabilizes, they are reclassified to the corresponding target region, thereby improving the stability of region division and the accuracy of dynamic resource stratification.

[0154] In one embodiment, the target regulation instruction is parsed from the power grid dispatch instruction data, and the set of regulation resources is determined based on the regulation structure data and the target regulation instruction, including:

[0155] Determine the target adjustment requirements corresponding to the target adjustment command; the target adjustment requirements include adjustment type, adjustment direction, and adjustment intensity;

[0156] Based on the adjustment structure data, the adjustment evolution correlation units in the resource layer corresponding to the target adjustment requirements are obtained to construct a set of target adjustment candidate resources;

[0157] Traverse each regulation evolution correlation unit in the target regulation candidate resource set and determine whether each regulation evolution correlation unit meets the target regulation requirements:

[0158] If the conditions are met, the corresponding regulatory evolution correlation unit will be added to the target regulatory resource set;

[0159] If the conditions are not met, the adjustment evolution correlation unit corresponding to the next resource layer is added to the target adjustment candidate resource set, and the traversal judgment process is repeated until the target adjustment resource set meets the target adjustment requirements.

[0160] Based on the target regulation resource set, determine the wind turbine generation and the regulation resource set corresponding to the target regulation command contained in each regulation evolution association unit.

[0161] In one implementation, the regulation type identifier (including frequency regulation command, voltage regulation command, and active power regulation command), regulation direction information, and regulation amplitude information are extracted. The regulation category to which the target regulation command belongs is determined based on the regulation type identifier, and the regulation direction information is converted into the corresponding regulation execution direction. Then, the regulation amplitude information is converted into the target regulation intensity. A target regulation demand vector (used to represent the grid's regulation capacity demand for the wind farm in the current control cycle) is constructed based on the regulation category, regulation execution direction, and target regulation intensity. The target regulation demand vector is output as the target regulation demand corresponding to the target regulation command.

[0162] In one implementation, the target regulation demand refers to the explicit requirement of the power grid to regulate the output changes of the wind farm in the current control cycle, including at least the type, direction, and intensity of regulation.

[0163] For example:

[0164] Active power regulation requirements:

[0165] Power grid dispatch instruction: Requires the wind farm to reduce its active power output by 50MW in the current cycle;

[0166] Analysis reveals the following: Adjustment type: active power adjustment; adjustment direction: decrease; adjustment intensity: 50MW.

[0167] The target regulation requirement is: within the current control cycle, the regulation capacity requirement is to reduce the active power output of the wind farm by 50MW.

[0168] Frequency support requirements:

[0169] Power grid dispatch instruction: The system frequency is too low, and support capabilities need to be improved rapidly;

[0170] After analysis, the following results are obtained: Adjustment type: frequency adjustment, adjustment direction: boost (support), adjustment intensity: fast response (can correspond to high priority or high intensity level).

[0171] The target adjustment requirement is: the adjustment requirement to provide support for frequency increase in a short period of time.

[0172] In one implementation, since the regulation demand corresponding to the grid dispatch command has dynamic change characteristics, and the sustainable regulation capacity of the regulation resources corresponding to different resource layers in the wind farm is different, if the regulation task is directly allocated throughout the entire field, it is easy to cause some wind turbines to continuously bear the regulation task, resulting in uneven utilization of regulation resources.

[0173] Therefore, firstly, a set of candidate resources for target regulation is constructed from the regulation structure data based on the target regulation requirements. Then, a layer-by-layer expansion method is used to screen the regulation evolution correlation units that meet the regulation requirements until a set of target regulation resources is formed. This enables the orderly use of regulation resources layer by layer, significantly improves the matching accuracy between regulation tasks and actual regulation resources, avoids excessive use of local resources, and enhances the sustainability and resource utilization efficiency of wind farm coordinated regulation.

[0174] In one embodiment, determining the allocation of regulation tasks for each wind turbine unit by adjusting the resource set includes:

[0175] Based on the set of regulatory resources, each regulatory evolution correlation unit is extracted, and a regulatory task allocation sequence is constructed according to the electrical connection relationship corresponding to each regulatory evolution correlation unit;

[0176] The tasks of each regulation evolution association unit are decomposed sequentially according to the regulation task allocation sequence to obtain the unit regulation tasks corresponding to each regulation evolution association unit.

[0177] The adjustment tasks of each unit are assigned to each wind turbine unit contained in the corresponding adjustment evolution association unit, so that each wind turbine unit can jointly complete the adjustment tasks of the corresponding unit.

[0178] The allocation results of the regulation tasks for each wind turbine are generated based on the unit regulation tasks corresponding to each regulation evolution correlation unit.

[0179] In one implementation, the total target regulation task corresponding to the target regulation command is obtained. Each regulation evolution association unit is traversed sequentially according to the regulation task allocation sequence. The total target regulation task is preferentially allocated to the regulation evolution association unit corresponding to the first resource layer. If there are still remaining regulation tasks after all the regulation evolution association units corresponding to the first resource layer have completed task allocation, the remaining regulation tasks are then allocated to the regulation evolution association units corresponding to the second resource layer. If there are still remaining regulation tasks after the second resource layer has completed task allocation, the remaining regulation tasks are then allocated to the regulation evolution association units corresponding to the third resource layer. Within the same resource layer, the regulation tasks allocated to that resource layer are divided according to the proportion of the number of wind turbine units contained in each regulation evolution association unit to the total number of wind turbine units in that resource layer, thus obtaining the unit regulation tasks corresponding to each regulation evolution association unit.

[0180] In one implementation, the adjustment task allocation result is used to record the specific adjustment tasks that each wind turbine should perform in the current control cycle, and should include at least the following:

[0181] Wind turbine identification: Used to identify which wind turbine is performing the regulation;

[0182] Adjustment task type: such as frequency regulation, power regulation, voltage regulation;

[0183] Regulation task: This refers to the specific regulation task undertaken by the wind turbine, such as undertaking 5 MW of active power regulation.

[0184] Execution priority: When multiple wind turbines need to be coordinated, the order of execution is determined.

[0185] In one implementation, the target regulation resource set typically includes multiple interconnected regulation evolution linkage units. If regulation tasks are directly assigned to each wind turbine, it can easily lead to dispersed regulation tasks and insufficient coordination among the linked wind turbines, affecting the overall regulation effect. Therefore, a regulation task allocation sequence is first constructed based on the electrical connection relationship of the regulation evolution linkage units. Then, the target regulation task is decomposed into unit regulation tasks corresponding to each linkage unit, and further allocated to each wind turbine within the linkage unit for joint execution. This establishes a hierarchical task allocation mechanism composed of linkage units and wind turbines, enabling the orderly transmission and coordinated execution of regulation tasks, and improving the overall regulation coordination, resource utilization balance, and scheduling efficiency of the wind farm.

[0186] In one embodiment, updating the regulation status data corresponding to each wind turbine unit through operational feedback data includes:

[0187] Obtain the operation feedback data corresponding to each wind turbine, and convert the operation feedback data into the corresponding adjustment feedback record according to the control cycle;

[0188] Each regulation feedback record is appended to the end of the historical regulation record sequence of the corresponding wind turbine, and the historical regulation record sequence of each wind turbine is updated.

[0189] Traverse the updated historical regulation record sequence, reconstruct the regulation effect correlation sequence corresponding to each wind turbine, and recalculate the influence coefficient of each historical regulation record on the current operating state.

[0190] The historical regulation impact of each wind turbine is updated based on the recalculated impact coefficient, and the regulation status data of each wind turbine is recalculated based on the real-time operating data of the current control cycle.

[0191] In one implementation, since the actual regulation capacity of wind turbines changes continuously with the latest regulation process after long-term participation in coordinated regulation, subsequent scheduling based on historical states can easily lead to a lag in the understanding of regulation resources and reduce the accuracy of resource matching. Therefore, the operation feedback data is supplemented to the historical regulation record sequence according to the control cycle, and the regulation effect correlation sequence is reconstructed, the historical regulation impact and regulation status data are calculated, so that the latest regulation results are continuously integrated into the subsequent status assessment, realizing the dynamic iterative update of the wind turbine regulation status, ensuring that the regulation status data can reflect the evolution of actual regulation capacity in real time, providing an accurate data foundation for resource stratification and coordinated scheduling in the next control cycle, and forming a coordinated control closed loop.

[0192] Based on the same inventive concept, this invention also provides a wind turbine collaborative control optimization system. See [link to related document]. Figure 2 ,include:

[0193] The data acquisition module 101 is used to acquire historical regulation response data, real-time operation data and grid dispatch command data of each wind turbine in the wind farm, and calculate the regulation status data corresponding to each wind turbine based on the historical regulation response data and real-time operation data.

[0194] The map generation module 102 is used to calculate the amount of change in regulation state and the rate of change in regulation state corresponding to each wind turbine based on the regulation state data, and to generate a wind farm regulation evolution map based on the amount of change in regulation state and the rate of change in regulation state.

[0195] The region division module 103 is used to divide the regulation evolution map into regions to obtain the target region, and to perform resource stratification of each wind turbine according to the target region to obtain regulation structure data; the target region includes regulation growth region, regulation stability region and regulation decay region; the regulation structure data represents the hierarchical distribution relationship of each wind turbine in the target region and the corresponding resource stratification results within the current control cycle;

[0196] The instruction generation module 104 is used to parse the target regulation instruction based on the power grid dispatch instruction data, determine the regulation resource set based on the regulation structure data and the target regulation instruction, determine the regulation task allocation result for each wind turbine through the regulation resource set, and generate the coordinated regulation instruction.

[0197] The data update module 105 is used to send the coordinated adjustment command to the corresponding wind turbine to execute the adjustment control, and to collect the operation feedback data after adjustment in real time. The operation feedback data is used to update the corresponding adjustment status data of each wind turbine, and the updated adjustment status data is used to execute the coordinated adjustment control of the next control cycle.

[0198] The foregoing has described one embodiment of the present invention in detail, but this content is merely a preferred embodiment and should not be considered as limiting the scope of the present invention. All equivalent variations and modifications made within the scope of the claims of this invention should still fall within the scope of the claims of this invention.

Claims

1. A method for optimizing the coordinated control of wind turbine generators, characterized in that, The method includes: Acquire historical regulation response data, real-time operation data, and grid dispatch command data for each wind turbine unit in the wind farm, and calculate the corresponding regulation status data for each wind turbine unit based on the historical regulation response data and real-time operation data; Based on the regulation state data, the regulation state change amount and regulation state change rate of each wind turbine are calculated, and a wind farm regulation evolution map is generated based on the regulation state change amount and regulation state change rate. The regulation evolution map is divided into regions to obtain target regions. Based on the target regions, each wind turbine is stratified by resource allocation to obtain regulation structure data. The target regions include regulation growth regions, regulation stability regions, and regulation decay regions. The regulation structure data represents the hierarchical distribution relationship of each wind turbine in the target regions and the corresponding resource hierarchical division results within the current control cycle. The target regulation instruction is parsed based on the power grid dispatch instruction data. The regulation resource set is determined based on the regulation structure data and the target regulation instruction. The regulation task allocation result for each wind turbine is determined through the regulation resource set, and a coordinated regulation instruction is generated. The coordinated adjustment command is sent to the corresponding wind turbine to perform adjustment control, and the operation feedback data after adjustment is collected in real time. The adjustment status data of each wind turbine is updated through the operation feedback data, and the updated adjustment status data is used to perform coordinated adjustment control in the next control cycle.

2. The wind turbine collaborative control optimization method according to claim 1, characterized in that, The regulation status data for each wind turbine is calculated based on historical regulation response data and real-time operation data, including: The historical regulation response data is processed by time slicing according to the control cycle to obtain the historical regulation record sequence corresponding to each wind turbine. Construct a regulation effect correlation sequence for each wind turbine based on the time interval and response correlation between adjacent regulation records in each historical regulation record sequence; Mapping the real-time operating data of each wind turbine to the corresponding regulation action correlation sequence determines the influence coefficient of each historical regulation record sequence on the current operating status. The historical regulation impact of each wind turbine is obtained by summing the impact coefficients corresponding to each historical regulation record sequence. The historical adjustment impact and real-time operation data are used to calculate the adjustment status data corresponding to each wind turbine.

3. The wind turbine collaborative control optimization method according to claim 1, characterized in that, The regulation state change and regulation state change rate for each wind turbine were calculated based on the regulation state data, including: The corresponding regulation state sequence is constructed by arranging the regulation state data of each wind turbine in multiple consecutive control cycles according to time. The adjustment state sequence is divided into a first preset number of state evolution units based on the changes in adjustment state data between adjacent control cycles; each state evolution unit includes a state start node, a state end node, and a state change process. The change in the adjustment state of the corresponding state evolution unit is calculated based on the difference in adjustment state between the state start node and the state end node. The rate of change of the regulation state is calculated based on the continuous control period and the change in regulation state corresponding to each state evolution unit.

4. The wind turbine collaborative control optimization method according to claim 1, characterized in that, A wind farm regulation evolution map is generated based on the amount and rate of change of regulation state, including: The regulation state change amount and regulation state change rate of each wind turbine are combined to obtain the regulation evolution state data of each wind turbine. The wind turbine arrangement order is established based on the equipment number of each wind turbine in the wind farm, and the regulation evolution state data corresponding to each wind turbine are sequentially mapped according to the arrangement order to obtain the regulation evolution distribution sequence of the wind turbine. Based on the electrical connection relationship between each wind turbine, the wind turbines with electrical connection relationship in the regulation evolution distribution sequence are associated and connected to form a second preset number of regulation evolution association units; By combining the various regulation evolution correlation units according to their corresponding electrical connection positions, the regulation evolution map of the wind farm is obtained.

5. The wind turbine collaborative control optimization method according to claim 4, characterized in that, The regulation evolution map is divided into regions to obtain target regions. Based on the target regions, resource stratification is performed on each wind turbine to obtain regulation structure data, including: Based on the regulatory evolution state data corresponding to each regulatory evolution correlation unit in the regulatory evolution map, preliminary regional division is carried out to obtain the regulatory growth region, the regulatory stability region, and the regulatory decay region; A temporary buffer area is added, and the regulatory evolution correlation units in each area are traversed. The regulatory evolution correlation units that satisfy the first preset rule are temporarily stored in the temporary buffer area. Continuously monitor the change in regulation state and the rate of change in regulation state corresponding to each regulation evolution correlation unit in the temporary buffer area, and reclassify the regulation evolution correlation units that meet the second preset rule to the corresponding target area; Based on the final division of the regulation growth region, regulation stability region, and regulation decay region, resource stratification is performed on each wind turbine to generate regulation structure data.

6. The wind turbine collaborative control optimization method according to claim 5, characterized in that, Based on the parsing of the power grid dispatch instruction data, the target regulation instruction is determined, and based on the regulation structure data and the target regulation instruction, the set of regulation resources is determined, including: Determine the target adjustment requirement corresponding to the target adjustment command; the target adjustment requirement includes adjustment type, adjustment direction, and adjustment intensity; Based on the adjustment structure data, the adjustment evolution correlation units in the resource layer corresponding to the target adjustment requirements are obtained to construct a set of target adjustment candidate resources; Traverse each regulation evolution correlation unit in the target regulation candidate resource set and determine whether each regulation evolution correlation unit meets the target regulation requirements: If the conditions are met, the corresponding regulatory evolution correlation unit will be added to the target regulatory resource set; If the conditions are not met, the adjustment evolution correlation unit corresponding to the next resource layer is added to the target adjustment candidate resource set, and the traversal judgment process is repeated until the target adjustment resource set meets the target adjustment requirements. Based on the target regulation resource set, determine the wind turbine generation and the regulation resource set corresponding to the target regulation command contained in each regulation evolution association unit.

7. The wind turbine collaborative control optimization method according to claim 1, characterized in that, The allocation of regulation tasks for each wind turbine is determined by adjusting the resource set, including: Based on the set of regulatory resources, each regulatory evolution correlation unit is extracted, and a regulatory task allocation sequence is constructed according to the electrical connection relationship corresponding to each regulatory evolution correlation unit; The tasks of each regulation evolution association unit are decomposed sequentially according to the regulation task allocation sequence to obtain the unit regulation tasks corresponding to each regulation evolution association unit. The regulation tasks of each unit are assigned to each wind turbine unit contained in the corresponding regulation evolution association unit, so that each wind turbine unit can jointly complete the regulation tasks of the corresponding unit. The allocation results of the regulation tasks for each wind turbine are generated based on the unit regulation tasks corresponding to each regulation evolution correlation unit.

8. The wind turbine collaborative control optimization system according to claim 1, characterized in that, The adjustment status data of each wind turbine is updated through the operational feedback data, including: Obtain the operation feedback data corresponding to each wind turbine, and convert the operation feedback data into corresponding adjustment feedback records according to the control cycle; Each regulation feedback record is appended to the end of the historical regulation record sequence of the corresponding wind turbine, and the historical regulation record sequence of each wind turbine is updated. Traverse the updated historical regulation record sequence, reconstruct the regulation effect correlation sequence corresponding to each wind turbine, and recalculate the influence coefficient of each historical regulation record on the current operating state. The historical regulation impact of each wind turbine is updated based on the recalculated impact coefficient, and the regulation status data of each wind turbine is recalculated based on the real-time operating data of the current control cycle.

9. A wind turbine collaborative control optimization system, characterized in that, The module includes The data acquisition module is used to acquire historical regulation response data, real-time operation data and grid dispatch command data of each wind turbine in the wind farm, and calculate the corresponding regulation status data of each wind turbine based on the historical regulation response data and real-time operation data. The map generation module is used to calculate the amount and rate of change of the regulation state for each wind turbine based on the regulation state data, and to generate a wind farm regulation evolution map based on the amount and rate of change of the regulation state. The region division module is used to divide the regulation evolution map into target regions, and to perform resource stratification of each wind turbine according to the target regions to obtain regulation structure data; the target regions include regulation growth regions, regulation stability regions, and regulation decay regions. The adjustment structure data represents the hierarchical distribution relationship of each wind turbine in the target area and the corresponding resource level division results within the current control cycle; The instruction generation module is used to parse the target regulation instruction based on the power grid dispatch instruction data, determine the regulation resource set based on the regulation structure data and the target regulation instruction, determine the regulation task allocation result for each wind turbine through the regulation resource set, and generate the coordinated regulation instruction. The data update module is used to send the coordinated adjustment command to the corresponding wind turbine to perform adjustment control, and to collect the operation feedback data after adjustment in real time. The module updates the adjustment status data of each wind turbine through the operation feedback data, and then executes the coordinated adjustment control of the next control cycle with the updated adjustment status data.

Images