Simple and efficient wind power plant power distribution method and device and storage medium

Abstract

The invention discloses a simple and efficient wind power plant power distribution method and device and a storage medium, and the method comprises the steps: collecting the operation data of each unit in a wind power plant and the corresponding meteorological data, and determining the prediction power of each unit in a prediction time period based on the operation data and the meteorological data; obtaining a scheduling power instruction value of the wind power plant, if the predicted power is greater than the scheduling power instruction value, determining a first priority based on the obtained first current power value of the wind power plant and the scheduling power instruction value, and allocating the scheduling power instruction value to each cluster according to the first priority to obtain a first output power value corresponding to each cluster; and determining a second priority based on the obtained second current power value and the first output power value of each unit, and performing power distribution on each unit according to the second priority to obtain a second output power value. According to the method and the device, the power grid power dispatching instruction can be accurately, quickly and reasonably distributed to each unit.

Description

Technical Field

[0001] The present application relates to the field of wind farm power distribution, and particularly to a simple and efficient wind farm power distribution method, device and storage medium. Background Art

[0002] The active power control technology of wind farms is not only a core research direction in the field of wind power, but also a key force driving the development of the wind power industry. This technology has inestimable value for improving the efficiency of wind power grid connection, optimizing the dispatching strategy of the entire power system, and ensuring the safe and stable operation of the power grid in a complex and changing environment. Due to the randomness of wind speed and the different operating states of each unit in the wind farm, the combined effect of these two factors makes it a complex and difficult problem to accurately and reasonably distribute the power dispatching instructions of the power grid to each unit.

[0003] Traditional wind farm power distribution mostly adopts power average distribution or distribution according to wind speed ratio. Due to the failure to fully consider the randomness of wind speed and the differences in unit operating states, there are often large errors in the output power of the wind farm, which not only affects the stable operation of the power grid, but also increases the operating burden of the units, making the unit power regulation too frequent and the failure rate rise accordingly. To address these challenges, researchers have continuously explored new power control methods. Among them, the power control method based on the objective function has attracted much attention because it can be optimized and distributed according to specific objectives or requirements. However, when facing large-scale wind farms, the solution speed of this method often fails to meet the requirements of real-time dispatching. Therefore, how to accurately and quickly distribute the power dispatching instructions of the power grid reasonably to each unit has become an important topic in the current research on wind farm optimal control.

[0004] Application Content

[0005] The present application provides a simple and efficient wind farm power distribution method, device and storage medium to accurately and quickly distribute the power dispatching instructions of the power grid reasonably to each unit.

[0006] In a first aspect, the present application provides a simple and efficient wind farm power distribution method, including:

[0007] Collect the operation data of each unit in the wind farm and the corresponding meteorological data, and determine the predicted power of each unit in the prediction time period based on the operation data and the meteorological data;

[0008] Obtain the dispatching power command value of the wind farm. If the predicted power is greater than the dispatching power command value, determine the first priority based on the obtained first current power value of the wind farm and the dispatching power command value, and allocate the dispatching power command value to each cluster according to the first priority to obtain the first output power value corresponding to each cluster, where each cluster is determined by clustering analysis of the predicted power;

[0009] Determine the second priority based on the obtained second current power value of each unit and the first output power value, and perform power allocation for each unit according to the second priority to obtain the second output power value.

[0010] In the embodiment of the present application, by collecting the operation data of each unit in the wind farm and the corresponding meteorological data, it helps to accurately predict the predicted power of each unit in the wind farm in the next period of time, that is, the power generation potential; by determining the predicted power of each unit in the prediction time period, it can help to perform power dispatching based on the predicted power in the subsequent process, and avoid problems caused by insufficient or excessive power during the dispatching process; if the predicted power is greater than the dispatching power command value, it means that power dispatching is required to avoid problems caused by insufficient or excessive power; by determining the first priority based on the obtained first current power value of the wind farm and the dispatching power command value, the allocated first priority can be accurately determined, which is convenient for subsequent power allocation; by allocating the dispatching power command value to each cluster according to the first priority, the total output power of the wind farm can be quickly adjusted based on the dispatching command value according to the first priority; by performing power allocation for each unit according to the second priority, the power grid power dispatching command can be accurately and quickly allocated to each unit reasonably based on the second priority, avoiding uneven or deviated power allocation. Compared with the prior art, the present application can reasonably allocate the power grid power dispatching command to each unit accurately and quickly.

[0011] Further, each cluster is determined by clustering analysis of the predicted power, specifically:

[0012] Randomly determine several first clustering centers, and calculate the distances from each unit to the first clustering centers;

[0013] Based on the distances and a preset fuzzy index, determine the membership degrees of each unit belonging to each of the first clustering centers;

[0014] Iteratively update the second clustering centers based on the membership degrees until the objective function corresponding to the second clustering centers in the current iteration meets the first preset condition, and then determine the corresponding several clusters based on the second clustering centers.

[0015] In this way, by clustering each cluster, it is convenient to understand the performance status of the units in the wind farm, which is convenient for subsequent power dispatching.

[0016] Further, determining the first priority based on the obtained first current power value of the wind farm and the dispatching power instruction value is specifically as follows:

[0017] Obtain the first current power value of the wind farm, and determine the first power adjustment value between the dispatching power instruction value and the first current power value;

[0018] If the first power adjustment value meets the second preset condition, then determine the first adjustable amount of each unit group based on the first current power output value, and determine the first priority based on the first adjustable amount.

[0019] In this way, determining the first priority based on the obtained first current power value of the wind farm and the dispatching power instruction value can accurately determine the allocated first priority, which is convenient for subsequent power distribution.

[0020] Further, allocating the dispatching power instruction value to each unit group according to the first priority to obtain the first output power value corresponding to each unit group is specifically as follows:

[0021] Stack the first adjustable amounts corresponding to each unit group in sequence according to the first priority until the first stacking result is greater than or equal to the first power adjustment value, and then determine the first output power value corresponding to each unit group based on the first current power value, the first power adjustment value, and the first adjustable amount.

[0022] In this way, by allocating the dispatching power instruction value to each unit group according to the first priority, the total output power of the wind farm can be quickly adjusted based on the dispatching instruction value according to the first priority.

[0023] Further, the calculation formula of the first output power value is specifically as follows:

[0024] When the first power adjustment value is greater than the first preset threshold, the calculation formula of the first output power value:

[0025]

[0026] When the first power adjustment value is less than the first preset threshold, the calculation formula of the first output power value:

[0027]

[0028] In the formula, P i ref is the first output power value of the i-th unit group; P i max is the maximum value of the predicted power of the i-th unit group; P imear is the first current power value of the i-th cluster; ΔP is the first power adjustment value of the i-th cluster; |ΔP| is the absolute value of the first power adjustment value of the i-th cluster; ΔP i add and ΔP i dec is the first adjustable amount that the i-th cluster can increase; n is the number of clusters in the wind farm; k is the number of cluster types that need to perform power adjustment, where k ≤ n; P i min is the minimum value of the predicted power of the i-th cluster.

[0029] In this way, by determining the corresponding first output power value in different situations, the first output power value corresponding to each cluster can be determined, which helps to quickly perform power distribution.

[0030] Further, determining the second priority based on the obtained second current power value of each unit and the first output power value is specifically as follows:

[0031] Obtain the second current power value of each cluster, and determine the second power adjustment value between the first output power value and the second current power value;

[0032] If the second power adjustment value meets the third preset condition, then determine the second adjustable amount of each unit based on the second current output value, and determine the second priority based on the second adjustable amount.

[0033] In this way, determining the second priority based on the obtained second current power value of each unit and the first output power value can accurately determine the second priority of the distribution, which is convenient for subsequent power distribution among each unit.

[0034] Further, the power distribution to each unit according to the second priority to obtain the second output power value is specifically as follows:

[0035] Superimpose the second adjustable amounts corresponding to each unit to obtain a second superimposed result;

[0036] Based on the second superimposed result and the second power adjustment value, determine the power scheduling strategy corresponding to different second priorities, and perform power distribution to each unit based on the power scheduling strategy to obtain the second output power value corresponding to each unit.

[0037] In this way, by performing power distribution to each unit according to the second priority, the output power of each unit can be quickly adjusted based on the first output power value according to the second priority.

[0038] Further, the power scheduling strategy includes a power-up scheduling strategy and a power-down scheduling strategy. The power-down scheduling strategy includes a non-shutdown scheduling strategy and a shutdown scheduling strategy. The calculation formula for obtaining the second output power value is specifically as follows:

[0039] In the power-up scheduling strategy, the calculation formula for the second output power value is;

[0040]

[0041] In the non-shutdown scheduling strategy, the calculation formula for the second output power value is;

[0042]

[0043] In the shutdown scheduling strategy, the calculation formula for the second output power value is;

[0044]

[0045] In the formula, is the second output power value; is the minimum power generation value for the normal operation of the i-th unit in the k-th fleet without shutdown; is the second current power value of the i-th unit in the k-th fleet; ΔP k is the second power adjustment value; is the second adjustable amount of the i-th unit in the k-th fleet; and are both the second superposition results, and n is the number of units in the wind farm.

[0046] In this way, by determining the corresponding second output power value in different situations, the second output power value corresponding to each unit can be determined, which helps to quickly perform power distribution.

[0047] In a second aspect, the present application provides a simple and efficient wind farm power distribution device, including: a collection module, a first distribution module, and a second distribution module;

[0048] The collection module is used to collect the operation data of each unit in the wind farm and the corresponding meteorological data, and determine the predicted power of each unit in the prediction time period based on the operation data and the meteorological data;

[0049] The first allocation module is configured to obtain the dispatching power command value of the wind farm. If the predicted power is greater than the dispatching power command value, it determines the first priority based on the obtained first current power value of the wind farm and the dispatching power command value, and allocates the dispatching power command value to each cluster according to the first priority to obtain the first output power value corresponding to each cluster, where each cluster is determined by clustering analysis of the predicted power;

[0050] The second allocation module is configured to determine the second priority based on the obtained second current power value of each unit and the first output power value, and perform power allocation on each unit according to the second priority to obtain the second output power value.

[0051] In the embodiment of the present application, by collecting the operation data of each unit in the wind farm and the corresponding meteorological data, it helps to accurately predict the predicted power of each unit in the wind farm in the next period of time, that is, the power generation potential; by determining the predicted power of each unit in the prediction time period, it can help to perform power dispatching based on the predicted power in the subsequent process, and avoid problems caused by insufficient or excessive power during the dispatching process; when the predicted power is greater than the dispatching power command value, it indicates that power dispatching is required to avoid problems caused by insufficient or excessive power; by determining the first priority based on the obtained first current power value of the wind farm and the dispatching power command value, the first priority of allocation can be accurately determined, which is convenient for subsequent power allocation; by allocating the dispatching power command value to each cluster according to the first priority, the total output power of the wind farm can be quickly adjusted based on the dispatching command value according to the first priority; by performing power allocation on each unit according to the second priority, the grid power dispatching command can be accurately and quickly allocated to each unit reasonably, avoiding uneven or deviated power allocation. Compared with the prior art, the present application can accurately and quickly allocate the grid power dispatching command to each unit reasonably.

[0052] In a third aspect, the present application also provides a computer-readable storage medium, on which a computer program is stored, characterized in that when the computer program is executed by a processor, it implements the simple and efficient wind farm power allocation method as described in the present application. Description of the Drawings

[0053] Figure 1 is a schematic flowchart of an embodiment of the simple and efficient wind farm power allocation method provided by the present application;

[0054] Figure 2 is a schematic flowchart of the clustering algorithm provided by the present application;

[0055] Figure 3 is a schematic diagram of the ascending power dispatching priority of each unit provided by the present application;

[0056] Figure 4 It is a schematic diagram of scheduling according to the shutdown priority when each unit provided by this application shuts down;

[0057] Figure 5 It is a schematic diagram of power distribution for each unit in the fleet provided by this application;

[0058] Figure 6 It is a schematic structural diagram of an embodiment of a simple and efficient wind farm power distribution device provided by this application. Specific Embodiments

[0059] Next, the technical solutions in the embodiments of this application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without making creative efforts shall fall within the protection scope of this application.

[0060] It should be understood that the step numbers used in the text are only for convenient description and do not limit the execution order of the steps.

[0061] It should be understood that the terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include the plural forms.

[0062] The terms "comprising" and "including" indicate the presence of the described features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or their combinations.

[0063] The term "and / or" refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0064] The active power control technology of wind farms is the core of the wind power field and the key to the industry's development. It is crucial for improving grid connection efficiency, optimizing dispatching strategies, and ensuring the safe and stable operation of the power grid. The randomness of wind speed and the differences in unit states make it a complex and difficult problem to accurately and reasonably distribute the power dispatching instructions of the power grid to each unit. Traditional methods such as average distribution or distribution according to wind speed ratio often cause large errors, affecting the stability of the power grid and increasing the burden on the units. Researchers are exploring new methods, among which the control method based on the objective function has received more attention. When facing large-scale wind farms, the solution speed of this method often fails to meet the requirements of real-time dispatching. Therefore, accurately and quickly distributing the power dispatching instructions of the power grid to each unit has become an important research topic at present.

[0065] Next, the terms involved in this application are analyzed:

[0066] Clustering algorithms are core technologies in data mining and pattern recognition. They group the objects in a dataset so that the objects within the same group have a high degree of similarity, while the objects between different groups have a low degree of similarity. These algorithms can be widely applied in fields such as image processing, market analysis, and bioinformatics. Through clustering, people can understand the structure and characteristics of the data, discover the patterns and rules hidden in the data, and thus conduct more effective data analysis and decision-making.

[0067] The fuzzy clustering algorithm applies the principles of fuzzy mathematics to clustering analysis and allows data objects to have a certain degree of membership among multiple clusters, that is, a data object can belong to multiple clusters simultaneously, but the degree of membership in each cluster is different.

[0068] Based on this, the embodiments of this application provide a simple and efficient wind farm power distribution method, device, and storage medium, which can accurately and quickly distribute the power dispatching instructions of the power grid reasonably to each unit.

[0069] A simple and efficient wind farm power distribution method, device, and storage medium provided by the embodiments of this application are specifically described through the following embodiments. First, the simple and efficient wind farm power distribution method in the embodiments of this application is described.

[0070] The simple and efficient wind farm power distribution method provided by the embodiments of the present application relates to the field of wind farm power distribution. The simple and efficient wind farm power distribution method provided by the embodiments of the present application can be applied to a terminal, or to a server side, or can be software running on a terminal or a server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server side can be configured as an independent physical server, or can be configured as a server cluster or a distributed system composed of multiple physical servers, or can be configured as a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application that implements a simple and efficient wind farm power distribution method, etc., but is not limited to the above forms.

[0071] The present application can also be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multi-processor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and so on. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in a distributed computing environment where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0072] Embodiment 1

[0073] Please refer to Figure 1 , Figure 1 which is a schematic flowchart of an embodiment of the simple and efficient wind farm power distribution method provided by the present application, including: step S101 to step S103;

[0074] Step S101, collect the operation data of each unit in the wind farm and the corresponding meteorological data, and determine the predicted power of each unit in the prediction time period based on the operation data and the meteorological data;

[0075] In some embodiments, the operation data and corresponding meteorological data of each unit in the wind farm are collected. Specifically: sensors are installed on each unit in the wind farm to measure the key operation data of the unit, such as wind speed, wind direction, power output, motor speed, temperature, etc.; and real-time meteorological data such as wind speed, wind direction, temperature, pressure, etc. are collected through meteorological sensors and observation stations around the wind farm.

[0076] In some embodiments, after obtaining the operation data and the meteorological data, it is necessary to remove invalid, incorrect or abnormal data points in these data, perform data calibration and perform data normalization for subsequent analysis.

[0077] In some embodiments, the predicted power of each unit in the prediction time period is determined based on the operation data and the meteorological data. Specifically: meteorological forecast data or meteorological models (such as numerical weather prediction models) are used to predict meteorological data in the future for a period of time, and the predicted meteorological data is substituted into physical models such as the wind power equation (such as the relationship equation between the power output of a wind turbine and the wind speed) to calculate the theoretical power generation in the future for a period of time; at the same time, the operation data and the meteorological data are input into a preset wind power prediction model to predict the predicted power generation of each unit in the prediction time period, and then the predicted power generation is fused with the theoretical power generation to determine the predicted power of each unit in the prediction time period.

[0078] It should be noted that the wind power prediction model is pre-trained in advance according to historical operation data and historical meteorological data.

[0079] Step S102, obtain the dispatching power command value of the wind farm. If the predicted power is greater than the dispatching power command value, determine the first priority based on the obtained first current power value of the wind farm and the dispatching power command value, and allocate the dispatching power command value to each cluster according to the first priority to obtain the corresponding first output power value of each cluster, where each cluster is determined by clustering analysis of the predicted power;

[0080] In some embodiments, obtaining the dispatching power command value of the wind farm specifically means obtaining the dispatching power command value P for the current time period or a future time period from the grid dispatching center or the management system of the wind farm ref , where this value is usually a determined target value, indicating the power that the wind farm needs to output during this time period, that is, the power of the wind farm needs to be adjusted to the dispatching power command value P ref .

[0081] In some embodiments, each cluster is determined according to the predicted power clustering analysis, including: randomly determining a number of first cluster centers, and calculating the distances from each unit to the first cluster centers; determining the membership degrees of each unit belonging to each of the first cluster centers based on the distances and a preset fuzzy index; iteratively updating the second cluster centers based on the membership degrees until the objective function corresponding to the second cluster centers in the current iteration satisfies a first preset condition, then determining a corresponding number of clusters based on the second cluster centers. Specifically, first, obtain the initial current power (P current_1 、P current_2 ,…,P current_n ) and the initial predicted power (P predict_1 、P predict_2 ,…,P predict_n ) of n wind turbines from the monitoring system of the wind farm, and determine an appropriate number of clusters c according to the current power, the predicted power, and the scheduling requirements, and randomly determine a number of first cluster centers within the data range, and at the same time set the fuzzy index m and the iteration stop threshold ∈, and calculate the distances d ij (i = 1..n, j = 1..c) from each unit to each of the first cluster centers; secondly, determine the membership degrees of each unit belonging to each of the first cluster centers based on the distances d ij and the preset fuzzy index m In the formula, u ij are the membership degrees, d ij and d ik are the distances from different units to the first cluster center, k = 1, 2…c; then, iteratively update the second cluster centers based on the membership degrees u ij and the original data, where the update calculation formula is, In the formula, C j is the second cluster center, P′ current_j is the current power corresponding to the second cluster center, P′ predict_j is the predicted power corresponding to the second cluster center, are the membership degrees, P current_i is the initial current power, P predict_i is the initial predicted power, and calculate the objective function based on the membership degrees u ij After determining the second cluster center, it is necessary to calculate the difference between the current objective function J current and the objective function J prev of the previous iteration. If the difference is less than the set threshold ∈, that is, |J current - J prev ​If <ε, the algorithm converges and the iteration stops. At this time, several clusters can be determined according to the second cluster center. Otherwise, continue to calculate the distances from each unit to the second cluster center and continue to iteratively update the third cluster center until the iteration termination condition is met, and divide each wind farm into several clusters. Among them, the algorithm used for clustering analysis is the fuzzy clustering algorithm. The flow schematic diagram of the clustering algorithm is as Figure 2 shown.

[0082] It should be noted that different cluster centers represent different fan performance states. If the current power and predicted power of the fans in a certain cluster center are relatively high, it means that the fans in this cluster center are operating at a high load, and the additional capacity that can be scheduled in the next cycle is also small; if the current power of the fans in a certain cluster center is low and the predicted power is high, it means that the fans in this cluster center are operating at a low load, and the additional capacity that can be scheduled in the next cycle is large, and priority scheduling can be carried out.

[0083] It should be noted that the original data for wind farm clustering is not limited to two-dimensional data, and the input data can be multi-dimensional vectors such as wind speed, power, and fan health.

[0084] In this way, by clustering each cluster, it is convenient to understand the performance status of the units in the wind farm and facilitate subsequent power scheduling.

[0085] In some embodiments, if the predicted power is greater than the scheduling power command value, specifically, compare the magnitude between the predicted power and the scheduling power command value to determine whether power allocation is required. When the predicted power is less than the scheduling power command value P ref at this time, it means that the scheduling command value P ref meets the operation requirements of the wind farm. At this time, the wind farm adopts an unlimited power operation mode to track the requirements of the scheduling power command value to the greatest extent; when the predicted power is greater than the scheduling power command value P ref at this time, it means that the scheduling command value P ref does not meet the operation requirements of the wind farm. At this time, it is necessary to limit the power of the wind farm.

[0086] In some embodiments, determining a first priority based on the obtained first current power value of the wind farm and the scheduling power command value includes: obtaining the first current power value of the wind farm and determining a first power adjustment value between the scheduling power command value and the first current power value; if the first power adjustment value meets the second preset condition, then determine the first adjustable amount of each cluster based on the first current power output value, and determine the first priority based on the first adjustable amount.

[0087] In some embodiments, the first priority is determined based on the obtained first current power value of the wind farm and the dispatching power instruction value. Specifically: The first current power value P in the wind farm is obtained through the wind farm monitoring system. mear to determine the dispatching power instruction value P ref and the deviation of the first current power value P mear , that is, the first power adjustment value ΔP. Among them, the calculation formula of the first power adjustment value ΔP is ΔP = P ref -P mear , ΔP is the first power adjustment value, P ref is the dispatching power instruction value, P mear is the total output power of each fleet at the current moment, that is, the first current power value, P i mear is the first current power value of the i-th fleet, and n is the number of fleets in the wind farm; when the first power adjustment value ΔP meets the second preset condition, the second preset condition is the first preset threshold. When the first power adjustment value ΔP is greater than the first preset threshold, that is, ΔP>0, it indicates that the predicted power cannot reach the dispatching power instruction value P ref , so the wind farm needs to increase power and needs to perform up-power dispatching. At this time, according to the maximum value P i max of the predicted power of each fleet and the first current power value P i mear to determine the first adjustable amount ΔP i add of each fleet, where the calculation formula of the first adjustable amount ΔP i add is ΔP i add =P i max -P i mear , ΔP i add is the first adjustable amount, P i max is the maximum value of the predicted power of the i-th fleet, P i mear is the first current power value of the i-th fleet, and the first priority S1 of each fleet during power dispatching is determined according to the size of the first adjustable amount ΔP i add . Among them, the larger the first adjustable amount ΔP i add , the higher the fleet priority. The smaller the first adjustable amount ΔP i add , the higher the fleet priority.

[0088] In some embodiments, a first priority is determined based on the obtained first current power value of the wind farm and the dispatching power instruction value. Specifically, when the first power adjustment value ΔP is less than the first preset threshold, i.e., ΔP < 0, it indicates that the predicted power exceeds the dispatching power instruction value P ref , so the wind farm needs to reduce power and a down-power dispatching is required. At this time, according to the minimum value P i min of the predicted power of each fleet and the first current power value P i mear to determine the first adjustable amount ΔP i dec of each fleet. Among them, the calculation formula for the first adjustable amount ΔP i dec is ΔP i dec = P i mear - P i min . ΔP i dec is the first adjustable amount, P i min is the minimum value of the predicted power of the i-th fleet, and P i mear is the first current power value of the i-th fleet. And the first priority S1 during the power dispatching of each fleet is determined according to the size of the first adjustable amount ΔP i dec . Among them, the larger the first adjustable amount ΔP i dec , the higher the priority of the fleet; the smaller the first adjustable amount ΔP i dec , the higher the priority of the fleet.

[0089] It should be noted that the first power adjustment value ΔP is the power value that each fleet needs to increase or decrease, and the first adjustable amount ΔP i add or ΔP i dec is the power adjustment ability of the i-th fleet.

[0090] In this way, determining the first priority based on the obtained first current power value of the wind farm and the dispatching power instruction value can accurately determine the allocated first priority, which is convenient for subsequent power distribution.

[0091] In some embodiments, allocating the scheduling power instruction value to each cluster according to the first priority to obtain the first output power value corresponding to each cluster includes: sequentially superimposing the first adjustable amounts corresponding to each cluster according to the first priority until the first superimposed result is greater than or equal to the first power adjustment value, and then determining the first output power value corresponding to each cluster based on the first current power value, the first power adjustment value, and the first adjustable amount. Specifically, after determining the first priority S1 of each cluster's scheduling, assuming the adjustment order is 1, 2, …, n, it is necessary to start from the cluster 1 with the highest priority and superimpose the first adjustable amounts ΔP i add or ΔP i dec of each cluster in sequence until reaching the cluster k, obtaining the first superimposed result, until the first superimposed result is greater than or equal to the first power adjustment value ΔP, that is where k is the number of cluster types that need to adjust power, k ≤ n. At this time, based on the first current power value P i mear , the first power adjustment value ΔP, and the first adjustable amount ΔP i add or ΔP i dec , determine the first output power value P i ref corresponding to each cluster. Among them, the reference power of clusters 1 to k - 1 is the maximum value P i max / minimum value P i min of the predicted power of this cluster, and the kth cluster makes up the remaining power adjustment amount, while other clusters maintain the first current power value.

[0092] It should be noted that during power increase scheduling, the units in the first k - 1 clusters are all operating at the maximum power, and the kth cluster restricts the power to make up the remaining power increment; during power decrease scheduling, the units in the first k - 1 clusters are all operating at the minimum power, and the kth cluster restricts the power to make up the remaining power reduction.

[0093] It should be noted that when the cluster clustering is reasonable, the first to k - 1 clusters should not include the shutdown units in the previous cycle, and the kth cluster does not include or includes a reasonable number of shutdown units, and tries to minimize the start and stop of the units.

[0094] It should be noted that the first output power value and the second output power value do not indicate the order, and can be understood as nouns. Among them, the first output power value is the power that each fleet needs to adjust to meet the dispatching power instruction value, and the second output power value is the power that each unit needs to adjust to meet the dispatching power instruction value, and the second output power is adjusted from the first output power value of each fleet.

[0095] In this way, by allocating the dispatching power instruction value to each fleet according to the first priority, the total output power of the wind farm can be quickly adjusted based on the dispatching instruction value according to the first priority.

[0096] In some embodiments, the calculation formula of the first output power value is specifically:

[0097] When the first power adjustment value is greater than the first preset threshold, that is, ΔP>0, the first output power value P i ref Calculation formula:

[0098]

[0099] When the first power adjustment value is less than the first preset threshold, that is, ΔP<0, the first output power value P i ref Calculation formula:

[0100]

[0101] In the formula, P i ref Is the first output power value of the i-th fleet; P i max Is the maximum value of the predicted power of the i-th fleet; P i mear Is the first current power value of the i-th fleet; ΔP is the first power adjustment value of the i-th fleet; |ΔP| is the absolute value of the first power adjustment value of the i-th fleet; ΔP i add And ΔP i dec Is the first adjustable amount that can be increased by the i-th fleet; n is the number of fleets in the wind farm; k is the number of fleet types that need to adjust power, where k≤n; P i min Is the minimum value of the predicted power of the i-th fleet.

[0102] In this way, by determining the corresponding first output power value in different situations, the first output power value corresponding to each fleet can be determined, which helps to quickly perform power distribution.

[0103] Step S103: Determine the second priority based on the obtained second current power values of each unit and the first output power value, and allocate power to each unit according to the second priority to obtain the second output power value.

[0104] In some embodiments, determining the second priority based on the obtained second current power values of each unit and the first output power value includes: obtaining the second current power values of each unit group, and determining the second power adjustment value between the first output power value and the second current power value; if the second power adjustment value meets the third preset condition, then determine the second adjustable amount of each unit based on the second current power output value, and determine the second priority based on the second adjustable amount.

[0105] In some embodiments, specifically, to determine the second priority based on the obtained second current power values of each unit and the first output power value, obtain the second current power values of each unit group in the wind farm through the wind farm monitoring system and determine the first output power value P i ref and the deviation of the second current power value which is the second power adjustment value ΔP k . If the second power adjustment value ΔP k meets the third preset condition, and the third preset condition is the second preset threshold. When the second power adjustment value ΔP k is greater than the second preset threshold, that is, ΔP>0, it indicates that the second current power value of this unit cannot reach the first output power value P i ref . Therefore, it is necessary to perform a power increase scheduling for each unit in the unit group. At this time, based on the second current power output value determine the second adjustable amount of each unit where the second adjustable amount is calculated by the formula: In the formula, is the second adjustable amount of the i-th unit in the k-th unit group, is the maximum power generation power value of the normal operation of the i-th unit in the k-th unit group, is the second current power value of the i-th unit in the k-th unit group, is the maximum power increase value of the k-th unit group; when the second adjustable amount is determined, determine the second priority S2 during the power scheduling of each unit according to the size of the second adjustable amount . Among them, the larger the second adjustable amount , the less power the unit can adjust, and the higher the unit priority. The second adjustable amount The smaller it is, the less adjustable power the unit has and the lower the unit priority. Among them, the schematic diagram of the power increase scheduling priority of each unit is as Figure 3 shown.

[0106] In some embodiments, the second priority is determined based on the obtained second current power value of each unit and the first output power value. Specifically: when the second power adjustment value ΔP k is less than the second preset threshold, that is, ΔP < 0, it indicates that the second current power value of this unit exceeds the first output power value P i ref . Therefore, it is necessary to perform a power reduction scheduling on each unit in the fleet. At this time, based on the second current power output value determine the second adjustable amount of each unit Among them, the calculation formula of the second adjustable amount is: In the formula, is the second adjustable amount of the i-th unit of the fleet k, is the second current power value of the i-th unit of the fleet k, is the minimum power generation value for the i-th fan unit of the fleet k to operate normally without shutdown, is the maximum power reduction value of the fleet k; after determining the second adjustable amount , determine the second priority S2 during the power scheduling of each unit according to the size of the second adjustable amount . Among them, the larger the second adjustable amount , the less adjustable power the unit has and the higher the unit priority. The smaller the second adjustable amount , the less adjustable power the unit has and the lower the unit priority.

[0107] In some embodiments, the power reduction scheduling of each unit in the fleet includes non-shutdown scheduling and shutdown scheduling. When the maximum power reduction value of the fleet k that is , the maximum power reduction value of the fleet k is greater than the power value ΔP that the unit needs to adjust k . At this time, the non-shutdown mode is adopted to limit the output of some units. When the maximum power reduction value of the fleet k that is , the maximum power reduction value of the fleet k is less than the power value ΔP that the unit needs to adjust k . At this time, the shutdown mode is adopted and it is ensured that the shutdown meets the adjustment amount.

[0108] In some embodiments, when the unit adopts the shutdown mode, it is necessary to ensure that the first s units with large predicted power values in the next control cycle are shut down, and the remaining units are all in the minimum power operation state, so as to obtain the shutdown priority sequence S3. Among them, when each unit is shut down, the scheduling schematic diagram according to the shutdown priority is as follows Figure 4 as shown.

[0109] It should be noted that the second power adjustment value ΔP k is the power value that each unit needs to increase or decrease, and the second adjustable amount is the power adjustment ability of the i-th unit.

[0110] In some embodiments, the power of each unit is allocated according to the second priority to obtain the second output power value. Specifically: the second adjustable amounts corresponding to each unit are superimposed to obtain a second superimposed result; based on the second superimposed result and the second power adjustment value, a power scheduling strategy corresponding to different second priorities is determined, and based on the power scheduling strategy, the power of each unit is allocated to obtain the second output power value corresponding to each unit. Among them, the schematic diagram of power allocation for each unit in the fleet is as follows Figure 5 as shown. The power scheduling strategy includes a power increase scheduling strategy and a power decrease scheduling strategy. The power decrease scheduling strategy includes a non-shutdown scheduling strategy and a shutdown scheduling strategy. Specifically, when the power increase scheduling is adopted, the second adjustable amounts corresponding to each unit are superimposed to obtain a second superimposed result Among them, the second superimposed result The calculation formula is: If Then the first j units in the second priority S2 of the i-th fleet participate in the adjustment, the (j + 1)-th unit compensates for the error, and the remaining units remain unchanged. Among them, the second output power value The calculation formula is: i = j + 1, where is the second output power value; is the second adjustable amount of the i-th unit of the k-th fleet; is the second current power value of the i-th unit of the k-th fleet; ΔP k is the second power adjustment value; is the second superimposed result, and n is the number of units in the wind farm; when the non-shutdown scheduling strategy is adopted, the second adjustable amounts corresponding to each unit are superimposed to obtain a second superimposed result Among them, the second superimposed result The calculation formula is: If Then, among the first j units in the second priority S2 of the i-th cluster, they participate in the regulation, the (j + 1)-th unit compensates for the error, and the remaining units remain unchanged. Among them, the second output power value is calculated by the formula: In the formula, is the second output power value; is the minimum power generation value for the normal operation without shutdown of the i-th unit in the k-th cluster; is the second current power value of the i-th unit in the k-th cluster; ΔP k is the second power regulation value; is the second superposition result, and n is the number of units in the wind farm. When adopting the shutdown scheduling strategy, since the start-stop process of wind turbines involves the off-grid and on-grid of the units, which is not conducive to the stable and economic operation of the wind power system, the number of shutdown wind turbines should be minimized. At this time, it is necessary to ensure that all units are in the minimum power operation state. Therefore, the first s units with large predicted power values in the next cycle are preferentially shut down, and the last unit compensates for the error. Among them, the second output power value is calculated by the formula: In the formula, is the second output power value; is the minimum power generation value for the normal operation without shutdown of the i-th unit in the k-th cluster; is the second current power value of the i-th unit in the k-th cluster; ΔP k is the second power regulation value; is the second superposition result, and n is the number of units in the wind farm.

[0111] It should be noted that the power increase scheduling strategy is maximum power tracking operation; the non-shutdown scheduling strategy is non-shutdown operation with the output of some units restricted; the shutdown scheduling strategy is shutdown mode operation with the shutdown meeting the adjustment amount.

[0112] In this way, by allocating power to each unit according to the second priority, the output power of each unit can be quickly adjusted based on the first output power value according to the second priority.

[0113] In the embodiments of the present application, by collecting the operation data of each unit in the wind farm and the corresponding meteorological data, it helps to accurately predict the predicted power of each unit in the wind farm in a future period, that is, the power generation potential; by determining the predicted power of each unit in the prediction period, it can help to perform power scheduling based on the predicted power in the subsequent process, and avoid problems caused by insufficient or excessive power during the scheduling process; if the predicted power is greater than the scheduling power command value, it indicates that power scheduling is required to avoid problems caused by insufficient or excessive power; by determining the first priority based on the obtained first current power value of the wind farm and the scheduling power command value, the assigned first priority can be accurately determined, which is convenient for subsequent power distribution; by distributing the scheduling power command value to each cluster according to the first priority, the total output power of the wind farm can be quickly adjusted based on the scheduling command value according to the first priority; by performing power distribution on each unit according to the second priority, the power grid power scheduling command can be accurately and quickly distributed to each unit reasonably based on the second priority, avoiding uneven or deviated power distribution. Compared with the prior art, the present application can accurately and quickly distribute the power grid power scheduling command to each unit reasonably.

[0114] Embodiment 2

[0115] Please refer to Figure 6 , Figure 6 FIG. is a schematic flowchart of an embodiment of a simple and efficient wind farm power distribution device provided by the present application, including: a collection module 100, a first distribution module 200, and a second distribution module 300;

[0116] The collection module 100 is configured to collect the operation data of each unit in the wind farm and the corresponding meteorological data, and determine the predicted power of each unit in the prediction period based on the operation data and the meteorological data;

[0117] The first distribution module 200 is configured to obtain the scheduling power command value of the wind farm. If the predicted power is greater than the scheduling power command value, it determines the first priority based on the obtained first current power value of the wind farm and the scheduling power command value, and distributes the scheduling power command value to each cluster according to the first priority to obtain the first output power value corresponding to each cluster, where each cluster is determined by clustering analysis based on the predicted power;

[0118] The second distribution module 300 is configured to determine the second priority based on the obtained second current power value of each unit and the first output power value, and perform power distribution on each unit according to the second priority to obtain the second output power value.

[0119] The information interaction, execution process, etc. among the modules in the above simple and efficient wind farm power distribution device are based on the same concept as the embodiment of the simple and efficient wind farm power distribution method in the first aspect of the present invention, and the achieved technical effects are basically the same. For specific content, refer to the description in Embodiment 1 of the method of the present invention, and details will not be repeated here.

[0120] The device embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separated, that is, they may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the method in this embodiment.

[0121] The present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the simple and efficient wind farm power distribution method as described in Embodiment 1 above.

[0122] Those of ordinary skill in the art can understand that all or part of the processes in the above method embodiments can be completed by instructing relevant hardware through a computer program. The program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above method embodiments. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM), etc.

[0123] The above specific embodiments have further detailed the purpose, technical solution, and beneficial effects of the present application. It should be understood that the above are only specific embodiments of the present application and are not used to limit the protection scope of the present application.

[0124] It is particularly pointed out that for those skilled in the art, any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A simple and efficient wind farm power allocation method, characterized in that: include: Collecting operation data and corresponding meteorological data of each unit in the wind farm, and determining the predicted power of each unit in a predicted time period based on the operation data and the meteorological data; Obtaining a dispatching power command value of the wind farm, and if the predicted power is greater than the dispatching power command value, determining a first priority based on the first current power value of the wind farm and the dispatching power command value, and allocating the dispatching power command value to each cluster according to the first priority, to obtain a first output power value corresponding to each cluster, wherein each cluster is determined according to the predicted power cluster analysis; A second priority is determined based on the acquired second current power value of each unit and the first output power value, and power is allocated to each unit according to the second priority to obtain a second output power value.

2. The simple and efficient wind farm power allocation method according to claim 1, characterized in that: The clusters are determined according to the predicted power cluster analysis, specifically: Randomly determine a number of first cluster centers, and calculate the distance between each unit and the first cluster center; Determining the membership degree of each unit belonging to each first cluster center based on the distance and a preset fuzzy index; The second cluster center is iteratively updated based on each of the membership degrees until the objective function corresponding to the second cluster center of the current iteration meets the first preset condition, and then a number of corresponding machine clusters are determined based on the second cluster center.

3. The simple and efficient wind farm power allocation method according to claim 1, characterized in that: The determining of the first priority based on the acquired first current power value of the wind farm and the dispatching power command value is specifically: Acquire a first current power value of the wind farm, and determine a first power adjustment value between the dispatching power command value and the first current power value; If the first power adjustment value satisfies the second preset condition, a first adjustable amount of each machine group is determined based on the first current power output value, and a first priority is determined based on the first adjustable amount.

4. The simple and efficient wind farm power allocation method according to claim 3, characterized in that: The dispatching power command value is distributed to each cluster according to the first priority to obtain a first output power value corresponding to each cluster, specifically: The first adjustable quantities corresponding to each machine group are superimposed in sequence according to the first priority until the first superposition result is greater than or equal to the first power adjustment value, and then the first output power value corresponding to each machine group is determined based on the first current power value, the first power adjustment value and the first adjustable quantity.

5. The simple and efficient wind farm power allocation method according to claim 4, characterized in that: The calculation formula of the first output power value is specifically: When the first power adjustment value is greater than the first preset threshold, the calculation formula of the first output power value is: When the first power adjustment value is less than the first preset threshold, the calculation formula of the first output power value is: Where P i ref is the first output power value of the i-th cluster; P i max The maximum power predicted for the i-th cluster; P i mear is the first current power value of the i-th cluster; ΔP is the first power adjustment value of the i-th cluster; |ΔP| is the absolute value of the first power adjustment value of the i-th cluster; ΔP i add and ΔP i dec is the first adjustable amount that can be increased by the i-th group; n is the number of groups in the wind farm; k is the number of groups that need to be adjusted in power, where k≤n; P i min is the minimum predicted power of the i-th group, and n is the number of units in the wind farm.

6. The simple and efficient wind farm power allocation method according to claim 1, characterized in that: The determining of the second priority based on the acquired second current power value of each unit and the first output power value is specifically: Acquire a second current power value of each cluster, and determine a second power adjustment value between the first output power value and the second current power value; If the second power adjustment value satisfies the third preset condition, the second adjustable amount of each unit is determined based on the second current power output value, and the second priority is determined based on the second adjustable amount.

7. The simple and efficient wind farm power allocation method according to claim 6, characterized in that: The power of each unit is allocated according to the second priority to obtain a second output power value, specifically: Superimposing the second adjustable quantities corresponding to each unit to obtain a second superposition result; Based on the second superposition result and the second power adjustment value, power scheduling strategies corresponding to different second priorities are determined, and power is allocated to each unit based on the power scheduling strategy to obtain a second output power value corresponding to each unit.

8. The simple and efficient wind farm power allocation method according to claim 7, characterized in that: The power scheduling strategy includes a power increase scheduling strategy and a power reduction scheduling strategy, the power reduction scheduling strategy includes a non-stop scheduling strategy and a shutdown scheduling strategy, and the calculation formula for obtaining the second output power value is specifically: In the power increase scheduling strategy, the calculation formula of the second output power value is: In the non-stop scheduling strategy, the calculation formula of the second output power value is: In the shutdown scheduling strategy, the calculation formula of the second output power value is: In the formula, is the second output power value; is the minimum power value of the i-th unit in the cluster k for normal operation without stopping; is the second current power value of the i-th unit in cluster k; ΔP k is the second power adjustment value; is the second adjustable variable of the i-th unit in the cluster k; and Both are the second superposition results.

9. A simple and efficient wind farm power distribution device, characterized in that: include: A collection module, a first allocation module and a second allocation module; The acquisition module is used to collect the operating data of each unit in the wind farm and the corresponding meteorological data, and determine the predicted power of each unit in the predicted time period based on the operating data and the meteorological data; The first allocation module is used to obtain the dispatching power command value of the wind farm, and if the predicted power is greater than the dispatching power command value, determine a first priority based on the first current power value of the wind farm and the dispatching power command value, and allocate the dispatching power command value to each cluster according to the first priority to obtain a first output power value corresponding to each cluster, wherein each cluster is determined according to the predicted power cluster analysis; The second allocation module is used to determine a second priority based on the acquired second current power value of each unit and the first output power value, and allocate power to each unit according to the second priority to obtain a second output power value.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the simple and efficient wind farm power allocation method according to any one of claims 1 to 8 is implemented.

Images