An optimization scheduling method and system based on multi-source wind farms

Abstract

The application provides an optimization scheduling method and system based on a multi-source wind farm, and belongs to the field of load scheduling, and specifically comprises the following steps: firstly, determining scheduling processing priority values of different wind farms and predicted wind power resources of the different wind farms; then, predicting load demand of a joint grid connection point to obtain predicted load demand; and finally, determining a responding wind farm in the wind farm based on the predicted load demand, the scheduling processing priority values and the predicted wind power resources, determining deviations between wind turbines in the responding wind farm in similar date historical power generation data as a constraint condition of a preset adjustment capacity of the different responding wind farms, and determining responding wind turbines in the different responding wind farms in combination with historical output data of the wind turbines in the similar dates. The method can guarantee the operation reliability and economy of the wind farm.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of load scheduling, and particularly relates to an optimized scheduling method and system based on multi-source wind farms. BACKGROUND

[0002] Due to the variation of the output of thermal power units and the variation of the load power of the power grid side, the output demand of multiple wind farms connected to the same on-grid node is not constant, which leads to the technical problem of how to realize the load scheduling of the output of different wind farms to improve the economy and reliability of the output.

[0003] To solve the above technical problems, the existing technical solutions are often focused on generating a single wind farm scheduling strategy based on the prediction results of the load output of a single wind farm and the output results of the load scheduling demand. Specifically, the patent application CN202311300428.3 "Scheduling method and device based on wind power uncertainty, medium and electronic equipment" establishes a target function based on the target scenario, taking the start-stop state of the generator as the variable, establishes a constraint according to the power generation limit of the generator, solves the minimum value of the target function based on the constraint, and determines the target scheduling scheme according to the start-stop state corresponding to the minimum value; the patent application CN202210618069.5 "Offshore wind farm operation and maintenance scheduling method and system, computer equipment and storage medium" uses the technical solution of the optimal operation and maintenance scheduling scheme of the task point operation and maintenance plan and cost, the transportation tool operation and maintenance route and cost, the personnel scheduling and cost, the operation and maintenance resource cost and the operation and maintenance penalty cost.

[0004] However, the above technical solutions have the following problems:

[0005] In actual output scheduling, due to the differences in wind turbine parameters of multiple wind farms connected to the same on-grid node, there is a certain degree of difference in the operating efficiency of the wind turbines of different wind farms, which makes it a technical problem to be solved how to generate differentiated scheduling strategies for different wind turbines of multiple wind farms in combination with the operating efficiency of the wind turbines of different wind farms.

[0006] To solve the above technical problems, the present application provides an optimized scheduling method and system based on multi-source wind farms. SUMMARY

[0007] To solve the defects in the above background technology, the present application provides an optimized scheduling method based on multi-source wind farms. Wherein, the multi-source wind farm refers to multiple wind farms connected to the same on-grid node. For multiple wind farms connected to the same on-grid node, the method of the present application can generate differentiated scheduling strategies for different wind turbines of multiple wind farms in combination with the operating efficiency of the wind turbines of different wind farms.

[0008] The application adopts the following technical solutions to achieve the above technical effects.

[0009] An optimization scheduling method based on a multi-source wind farm, specifically comprising the following steps:

[0010] S1 obtains the constituent data and historical power generation data of the wind turbines of the wind farm, and determines the scheduling processing priority of different wind farms in combination with the wind turbine parameters and historical power generation data of different wind turbines;

[0011] S2 determines the similar dates and wind power distribution similarity based on the weather data of the current date, obtains the output data of the wind farm in different similar dates, and determines the predicted wind power resources of different wind farms in combination with the wind power distribution similarity of different similar dates;

[0012] S3 predicts the predicted load demand of the joint grid connection point, and determines the response wind farm in the wind farm based on the predicted load demand, the scheduling processing priority, and the predicted wind power resources;

[0013] S4 determines the deviation of the historical power generation data of the wind turbines in the response wind farm in the similar dates as the constraint condition of the preset regulation capacity of different response wind farms, and determines the response wind turbine in different response wind farms in combination with the historical output data of the wind turbines in the similar dates.

[0014] Further technical solutions are that the constituent data of the wind turbines of the wind farm is determined according to the wind turbine parameters of different wind turbines of the wind farm.

[0015] Further technical solutions are that the weather data includes the wind speed and wind direction in different time periods, and the weather data is determined according to the prediction result of the weather data of the region where the wind farm is located on the current date.

[0016] Further technical solutions are that the determination method of the similar dates is:

[0017] The wind speed and wind direction in different time periods on the current date are determined according to the weather data of the current date, and the wind power condition similarity coefficient of the current date and different dates in different time periods is determined according to the wind speed and wind direction in different time periods;

[0018] The wind power distribution similarity of the current date and different dates is determined by using the average value of the wind power condition similarity coefficient of the current date and different dates in different time periods, and the similar dates are determined according to the wind power distribution similarity.

[0019] Further technical solutions are that the similar dates are determined according to the wind power distribution similarity, specifically comprising:

[0020] When the wind power distribution similarity of the date is greater than a preset similarity threshold, the date is determined as a similar date.

[0021] A further technical solution is to determine the predicted wind power resource of the wind farm according to the output data of different similar dates in the reference output date interval, specifically including:

[0022] Determine the predicted wind power resource of the wind farm according to the average value of the output data of different similar dates in the reference output date interval.

[0023] A further technical solution is that the predicted load demand of the joint grid point is determined according to the load of adjacent dates of the joint grid point in a preset time period.

[0024] In another aspect, the embodiment of the application provides an optimization scheduling system based on a multi-source wind farm, which adopts the optimization scheduling method based on a multi-source wind farm.

[0025] The output priority value determination module, the wind power resource prediction module, the response wind farm determination module, and the response wind turbine determination module.

[0026] The output priority value determination module is responsible for obtaining the constituent data of the wind turbines of the wind farm, and determining the scheduling processing priority values of different wind farms in combination with the wind turbine parameters and historical power generation data of different wind turbines.

[0027] The wind power resource prediction module is responsible for determining similar dates and wind power distribution similarities based on weather data of the current date, obtaining output data of the wind farm in different similar dates, and determining predicted wind power resources of different wind farms in combination with the wind power distribution similarities of different similar dates.

[0028] The response wind farm determination module is responsible for predicting the load demand of the joint grid point to obtain a predicted load demand, and taking the predicted load demand, the scheduling processing priority value, and the predicted wind power resource as basic data to determine the response wind farm in the wind farm.

[0029] The response wind turbine determination module is responsible for determining the deviation of historical power generation data of wind turbines in different response wind farms in similar dates as a constraint condition, and determining the response wind turbines in different response wind farms in combination with the historical output data of wind turbines in similar dates.

[0030] The application has the following beneficial effects:

[0031] 1. According to the predicted load demand, the scheduling processing priority value and the predicted wind power resource, the determination of the responding wind farm in the wind farm is carried out, so as to avoid the technical problem that the operation reliability of the power equipment of the wind farm does not meet the requirements due to the dispersion of the responding wind turbine in the wind farm. Through the determination of the responding wind farm by comprehensively considering various factors, the determination of the responding wind farm with higher priority is realized from multiple angles such as the richness of wind power resources and the reliability of power generation.

[0032] 2. The determination of the responding wind turbine in different responding wind farms is carried out by using the deviation of the wind turbine output data of different wind turbines in the responding wind farm in different similar dates and the historical power generation data of other wind turbines. Not only the fluctuation of the wind turbine output of the wind turbine in different similar dates and the size of the wind turbine output are considered, but also the difference of the power quality of the wind turbine caused by the difference of the output power waveform of the wind turbine is considered. The determination of the responding wind turbine is realized from multiple angles, and the reliability of the responding wind turbine output is ensured. BRIEF DESCRIPTION OF DRAWINGS

[0033] The above and other features and advantages of the present application will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings.

[0034] Figure 1 is a flow chart of an optimal scheduling method based on a multi-source wind farm according to embodiment 1.

[0035] Figure 2 is a flow chart of a method for determining the predicted wind power resource of the wind farm.

[0036] Figure 3 is a framework diagram of an optimal scheduling system based on a multi-source wind farm according to embodiment 2. DETAILED DESCRIPTION

[0037] Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments, however, can be implemented in many different ways and should not be construed as limited to the implementations set forth herein; rather, these implementations are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art. Like reference numerals refer to like elements throughout the drawings, and thus a detailed description of them will not be repeated.

[0038] The terms "one", "a", "an", "the", and "said" are used to indicate the existence of one or more than one element / portion / etc.; the terms "include" and "have" are used to indicate an open-ended inclusion in such a way that additional elements / portions / etc. can be present in addition to the listed elements / portions / etc.

[0039] Embodiment 1

[0040] To solve the above problems, according to one aspect of the present application, as shown in Figure 1 An optimization scheduling method based on a multi-source wind farm is provided, specifically comprising:

[0041] S1 obtains the constituent data of the wind turbines of the wind farm, and determines the scheduling processing priority of different wind farms in combination with the wind turbine parameters and historical power generation data of different wind turbines;

[0042] Further, the constituent data of the wind turbines of the wind farm is determined according to the wind turbine parameters of different wind turbines of the wind farm.

[0043] Specifically, the method for determining the scheduling processing priority of the wind farm is:

[0044] According to the historical power generation data, the historical power generation of the wind farm under different wind conditions is determined, and the power output scheduling priority of the wind farm is determined by using the historical power generation;

[0045] The power generation efficiency of different wind turbines is determined by the wind turbine parameters of different wind turbines of the wind farm, and the power generation efficiency priority of the wind farm is determined according to the power generation efficiency of different wind turbines;

[0046] The failure occurrence frequency of different wind turbines is determined by using the historical power generation data of different wind turbines of the wind farm, and the power generation stability of the wind farm is determined by the failure occurrence frequency of different wind turbines;

[0047] The scheduling processing priority of the wind farm is determined based on the power generation stability, power generation efficiency priority and power output scheduling priority of the wind farm.

[0048] In one embodiment, the scheduling processing priority of the wind farm is determined according to the average value of the power generation stability, power generation efficiency priority and power output scheduling priority.

[0049] It can be understood that the value range of the scheduling processing priority of the wind farm is between 0 and 1, wherein the higher the scheduling processing priority of the wind farm, the higher the priority level of the wind farm in scheduling processing.

[0050] It should be noted that the weather data includes wind speed and wind direction at different time periods, and is specifically determined according to the prediction result of the weather data of the region where the wind farm is located on the current date.

[0051] S2 determines the similar dates and wind power distribution similarity based on the weather data of the current date, obtains the power output data of the wind farm on different similar dates, and determines the predicted wind power resources of different wind farms in combination with the wind power distribution similarity of different similar dates;

[0052] Specifically, the method for determining the similar date comprises:

[0053] determining wind speed and wind direction of the current date in different time periods according to weather data of the current date, and determining a wind condition similarity coefficient of the current date and different dates in different time periods according to the wind speed and the wind direction in different time periods;

[0054] determining a wind power distribution similarity of the current date and different dates by using the wind condition similarity coefficient of the current date and different dates in different time periods, and determining the similar date according to the wind power distribution similarity.

[0055] Further, the method for determining the similar date according to the wind power distribution similarity comprises:

[0056] when the wind power distribution similarity of the date is greater than a preset similarity threshold, the date is determined as the similar date.

[0057] In another possible embodiment, the method for determining the similar date comprises:

[0058] determining wind speed of the current date in different time periods according to weather data of the current date, and determining a wind speed deviation time period of different dates by using the wind speed, when the date has the wind speed deviation time period:

[0059] when the number of the wind speed deviation time period of the date does not meet a requirement, the date is determined as not belonging to the similar date;

[0060] when the number of the wind speed deviation time period of the date meets the requirement, determining a wind speed deviation amount of the date according to a wind speed deviation condition of the wind speed deviation time period of the date, when the wind speed deviation amount of the date does not meet the requirement, the date is determined as not belonging to the similar date;

[0061] when the wind speed deviation amount of the date meets the requirement or there is no risk deviation time period:

[0062] determining a wind condition similarity coefficient of the current date and different dates in different time periods according to the wind speed and the wind direction in different time periods, and determining a wind condition deviation time period by using the wind condition similarity coefficient, when the number of the wind condition deviation time period does not meet the requirement, the date is determined as not belonging to the similar date;

[0063] when the number of the wind condition deviation time period meets the requirement:

[0064] The time period is divided into different time interval, and the interval similarity coefficient of different time interval is determined according to the number of wind condition deviation time period in different time interval and the wind condition similarity coefficient, when there is a time interval whose interval similarity coefficient does not meet the requirement, it is determined that the date does not belong to the similar date;

[0065] When all interval similarity coefficients meet the requirement:

[0066] The wind power distribution similarity between the current date and different dates is determined by using the average value of wind condition similarity coefficient of different time period of the current date and different dates, and the similar date is determined according to the wind power distribution similarity.

[0067] It should be noted that, as shown in Figure 2 The method for determining the predicted wind power resource of the wind farm is:

[0068] The wind farm output of different similar dates is determined based on the output data of the wind farm of different similar dates, and the similar date is divided into different similar output date intervals by using the wind farm output;

[0069] The output similarity coefficient of different similar output date intervals is determined by the number of similar dates in different similar output date intervals and the deviation of output data between different similar dates;

[0070] The wind similarity coefficient of different similar date intervals is determined based on the number of similar dates in different similar date intervals and the wind power distribution similarity of different similar dates;

[0071] The deviation of processing data of similar dates between the similar date intervals is obtained, and the reference coefficient of different similar output date intervals is determined in combination with the output similarity coefficient and the wind similarity coefficient of different similar output date intervals;

[0072] In one possible embodiment, the deviation of processing data of similar dates between the similar date intervals, the output similarity coefficient and the wind similarity coefficient of the similar output date interval are used as the input quantity of the prediction model of the improved sparrow search algorithm (ISSA) optimized BP neural network (ISSA-BP), and the output quantity of the prediction model of the improved sparrow search algorithm (ISSA) optimized BP neural network (ISSA-BP) is used as the reference coefficient of the similar output date interval.

[0073] The reference output date interval is determined by using the reference coefficient, and the predicted wind power resource of the wind farm is determined according to the output data of different similar dates in the reference output date interval.

[0074] Further, the determination of the predicted wind power resource of the wind farm according to the output data of different similar dates of the reference output date interval specifically comprises:

[0075] The determination of the predicted wind power resource of the wind farm according to the average value of the output data of different similar dates of the reference output date interval.

[0076] In another possible embodiment, the method for determining the predicted wind power resource of the wind farm comprises:

[0077] The determination of the output of the wind farm of different similar dates based on the output data of the wind farm of different similar dates, and the division of the similar dates into different similar output date intervals by using the output of the wind farm, when the number of similar dates of the similar output date interval is less than a preset date number, it is determined that the similar output date interval does not belong to the reference output date interval;

[0078] When the number of similar dates of the similar output date interval is not less than the preset date number:

[0079] The determination of the output similarity coefficient of different similar output date intervals by the number of similar dates of different similar output date intervals and the deviation of the output data between different similar dates, when the output similarity coefficient of the similar output date interval does not meet the requirement, it is determined that the similar output date interval does not belong to the reference output date interval;

[0080] When the output similarity coefficient of the similar output date interval meets the requirement:

[0081] The determination of the wind similarity coefficient of different similar date intervals based on the number of similar dates of different similar date intervals and the wind distribution similarity of different similar dates, when the wind similarity coefficient of the similar output date interval does not meet the requirement, it is determined that the similar output date interval does not belong to the reference output date interval;

[0082] When the wind similarity coefficient of the similar output date interval meets the requirement:

[0083] The deviation of the processing data of the similar dates between the similar date intervals is obtained, and the reference coefficient of different similar output date intervals is determined in combination with the output similarity coefficient and the wind similarity coefficient of different similar output date intervals;

[0084] The determination of the reference output date interval by using the reference coefficient, and the determination of the predicted wind power resource of the wind farm according to the output data of different similar dates of the reference output date interval.

[0085] S3 predicts the load demand of the joint grid connection point to obtain a predicted load demand, and determines the responding wind farm in the wind farm based on the predicted load demand, a dispatching processing priority value, and a predicted wind resource;

[0086] Further, the predicted load demand of the joint grid connection point is determined according to the load of the joint grid connection point in the adjacent date within a preset time period.

[0087] It can be understood that the method for determining the responding wind farm in the wind farm is:

[0088] The responding wind farm in the wind farm is determined based on the predicted load demand;

[0089] The responding priority value of different wind farms is determined according to different dispatching processing priority values and weights of the predicted wind resource;

[0090] The responding wind farm in the wind farm is determined based on the responding priority value of different wind farms and the number of the responding wind farm in the wind farm.

[0091] Further, the preset adjustment capacity of the responding wind farm is determined according to the installed capacity of the wind farm, wherein the more the installed capacity of the wind farm is, the greater the preset adjustment capacity of the responding wind farm is.

[0092] S4 determines the deviation of the historical power generation data of the wind turbines in the responding wind farm in similar dates as a constraint condition, and determines the responding wind turbine in different responding wind farms in combination with the historical output data of the wind turbines in similar dates.

[0093] Specifically, it needs to be explained that the method for determining the responding wind turbine in the responding wind farm is:

[0094] The wind turbine output of the wind turbine in different similar dates is determined by using the wind turbine output data of the wind turbine in the responding wind farm in different similar dates, and the output reliability coefficient of the wind turbine is determined by using the fluctuation of the wind turbine output of the wind turbine in different similar dates and the average value of the wind turbine output;

[0095] In one possible embodiment, the similar date in which the deviation between the wind turbine output in different similar dates and the average value of the wind turbine output in similar dates is greater than 1 MW is used as a fluctuation date, and the product of the proportion of the fluctuation date in similar dates and the ratio of the average value of the wind turbine output to 10 MW is used as the processing reliability coefficient of the wind turbine;

[0096] determine the power generation voltage waveform and the power generation current waveform in the wind turbine output interval based on the deviation of the historical power generation data of any wind turbine in the response wind farm from other wind turbines, and determine the waveform consistency of the wind turbine in different wind turbine output intervals by using the waveform deviation amount of the power generation voltage waveform and the power generation current waveform of the wind turbine from other wind turbines;

[0097] obtain the historical running time length of the wind turbine in different wind turbine processing intervals, and determine the power output reliability of the wind turbine in combination with the waveform consistency of the wind turbine in different wind turbine output intervals;

[0098] In one possible embodiment, the historical running time length of the wind turbine in different wind turbine processing intervals and the waveform consistency of the wind turbine in different wind turbine output intervals are used as input quantities of an improved sparrow search algorithm (ISSA) optimized BP neural network (ISSA-BP) prediction model, and the output quantity of the improved sparrow search algorithm (ISSA) optimized BP neural network (ISSA-BP) prediction model is used as the power output reliability of the wind turbine.

[0099] determine the comprehensive reliability of the wind turbine by using the power output reliability and the output reliability coefficient of the wind turbine, and determine the response wind turbine in the response wind farm by using the comprehensive reliability.

[0100] In one possible embodiment, the comprehensive reliability of the wind turbine is the average value of the power output reliability and the output reliability coefficient of the wind turbine.

[0101] In one possible embodiment, the determination of the comprehensive reliability of the wind turbine is performed by using an improved sparrow search algorithm (ISSA) optimized BP neural network (ISSA-BP) prediction model, and the prediction process of the prediction model is as follows:

[0102] Step one: respectively select the power output reliability and the output reliability coefficient of the wind turbine as the input of the BP neural network.

[0103] Step two: initialize the BP neural network, and perform multiple training of the BP neural network to determine the structure of the BP neural network, which includes an input layer, a hidden layer and an output layer. Finally, initialize the weight and threshold of the hidden layer and input them to the sparrow search algorithm.

[0104] Step three: initialize the sparrow population according to the characteristics of the Tent chaotic mapping, and complete the initialization of the ISSA parameters.

[0105] Step four: calculate the fitness value of the sparrow individual and sort them by size.

[0106] Step five: update the positions of the predator, the joiner and the guard in turn according to the position update rule.

[0107] Step six: calculate the updated population individual fitness value, and disturb the global optimal individual using the firefly disturbance strategy to generate a new solution.

[0108] Step seven: calculate whether the population fitness value meets the termination condition, if yes, end, obtain the optimal combination of the weight value and the threshold value, otherwise jump to step four to continue optimization.

[0109] Step eight: input the obtained optimal weight value and threshold value solution into the BP neural network structure for network training until the number of iterations or the pre-set error precision is reached.

[0110] Step nine: use the improved sparrow algorithm to optimize the BP neural network model to determine the comprehensive reliability of the fan.

[0111] In one possible embodiment, in the discoverer update formula of the SSA, when R2< ST, the search range is reduced in the iteration process, which is easy to fall into local, and the solution generated is a local optimal solution. In order to avoid this problem as much as possible, the sparrow search algorithm is improved by adding a nonlinear decreasing factor to obtain the improved sparrow search algorithm (ISSA), and the discoverer update formula in the improved algorithm is as follows:

[0112] ω = ω min -(ω max -ω min )·sin(tπ / T max )

[0113]

[0114] Wherein, ω min is 0.1, ω max is 1; t is the iteration number; T max is the maximum iteration number; is the position of the i-th sparrow in the j-th dimension of the t-th generation; X best is the overall optimal position; r1 is a random number in [0, 2π], r2 is a random number in [0, 2], R2 ∈ [0, 1] is a warning value, ST ∈ [0.5, 1] is a safety value, and R2 < ST indicates safety.

[0115] In another possible embodiment, the method for determining the response fan in the response wind farm is:

[0116] The wind turbine output data of the wind turbine in different similar dates are used to determine the wind turbine output of the wind turbine in different similar dates, and when the wind turbine output of the wind turbine in different similar dates is less than a preset output threshold, it is determined that the wind turbine does not belong to the responding wind turbine in the responding wind farm.

[0117] When the wind turbine output of the wind turbine in different similar dates is less than a preset output threshold:

[0118] The fluctuation of the wind turbine output of the wind turbine in different similar dates is used to determine the deviation of the wind turbine output from the average value of the output of the wind turbine in different similar dates, and the fluctuation date is determined by using the deviation, and when the number of fluctuation dates of the wind turbine in different similar dates does not meet the requirement, it is determined that the wind turbine does not belong to the responding wind turbine in the responding wind farm.

[0119] When the number of fluctuation dates of the wind turbine in different similar dates meets the requirement:

[0120] The number of fluctuation dates of the wind turbine in different similar dates and the average value of the wind turbine output are used to determine the output reliability coefficient of the wind turbine.

[0121] The power generation voltage waveform and the power generation current waveform in the wind turbine output interval are determined based on the deviation of the historical power generation data of any wind turbine in the responding wind farm from other wind turbines, and the waveform consistency of the wind turbine in different wind turbine output intervals is determined by using the waveform deviation of the power generation voltage waveform and the power generation current waveform of the wind turbine from other wind turbines, and when there is a wind turbine processing interval with inconsistent waveform that does not meet the requirement, it is determined that the wind turbine does not belong to the responding wind turbine in the responding wind farm.

[0122] When there is no wind turbine processing interval with inconsistent waveform that does not meet the requirement, the historical running time of the wind turbine in different wind turbine processing intervals is obtained, and the electrical energy output reliability of the wind turbine is determined in combination with the waveform consistency of the wind turbine in different wind turbine output intervals.

[0123] The comprehensive reliability of the wind turbine is determined by the electrical energy output reliability and the output reliability coefficient of the wind turbine, and the responding wind turbine in the responding wind farm is determined by using the comprehensive reliability.

[0124] Embodiment 2

[0125] On the other hand, as Figure 3 shown, the application embodiment provides a kind of optimization scheduling system based on multi-source wind farm, executes the optimization scheduling method based on multi-source wind farm described above, specifically includes:

[0126] An output priority value determination module, a wind power resource prediction module, a responsive wind farm determination module, and a responsive wind turbine determination module;

[0127] The output priority value determination module is responsible for obtaining the configuration data and historical power generation data of wind turbines in a wind farm, and determining the scheduling processing priority of different wind farms in combination with the wind turbine parameters and historical power generation data of different wind turbines.

[0128] The wind power resource prediction module is responsible for determining the similar dates and wind power distribution similarity based on the weather data of the current date, obtaining the output data of the wind farm in different similar dates, and determining the predicted wind power resources of different wind farms in combination with the wind power distribution similarity of different similar dates.

[0129] The responsive wind farm determination module is responsible for predicting the predicted load demand of the joint grid-connected point, and determining the responsive wind farm in the wind farm based on the predicted load demand, the scheduling processing priority, and the predicted wind power resource.

[0130] The responsive wind turbine determination module is responsible for determining the deviation of the historical power generation data of wind turbines in different responsive wind farms in similar dates as the constraint condition of the preset adjustment capacity of the different responsive wind farms, and determining the responsive wind turbine in different responsive wind farms in combination with the historical output data of the wind turbines in similar dates.

[0131] In the embodiments of the present application, the term "a plurality of" refers to two or more, unless otherwise explicitly limited. The terms "mounting", "connecting", "fixing", and the like should be understood in a broad sense, for example, "connecting" can be fixed connection, can also be detachable connection, or integral connection. For those skilled in the art, the specific meaning of the above terms in the embodiments of the present application can be understood according to the specific circumstances.

[0132] In the description of the embodiments of the present application, it should be understood that the positions or position relationships indicated by the terms "upper", "lower", and the like are based on the positions or position relationships shown in the drawings, and are only for the convenience of describing the embodiments of the present application and simplifying the description, and do not indicate or imply that the devices or units referred to must have a particular direction, be constructed and operated in a particular position, therefore, it cannot be understood as a limitation on the embodiments of the present application.

[0133] In the description of the specification, the description of the terms "one embodiment", "one preferred embodiment", and the like means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are contained in at least one embodiment or example of the embodiments of the present application. In the specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0134] The above merely describes the preferred embodiments of the embodiments of the present application and is not intended to limit the embodiments of the present application. The embodiments of the present application can have various modifications and changes for those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the embodiments of the present application shall be included in the protection scope of the embodiments of the present application.

Claims

1. A method for optimal scheduling based on multi-source wind farms, characterized in that, Specifically comprising: Obtaining the constituent data and historical power generation data of the wind turbines of the wind farm, and determining the scheduling processing priority of different wind farms in combination with the wind turbine parameters and historical power generation data of different wind turbines; Determining the similar dates and wind power distribution similarity based on the weather data of the current date, obtaining the output data of the wind farm in different similar dates, and determining the predicted wind power resources of different wind farms in combination with the wind power distribution similarity of different similar dates; Predicting the predicted load demand of the joint grid connection point, and determining the response wind farm in the wind farm based on the predicted load demand, the scheduling processing priority, and the predicted wind power resources; Determining the deviation of the historical power generation data of the wind turbines in the response wind farm in the similar dates as the constraint condition of the preset adjustment capacity of the different response wind farms, and determining the response wind turbine in the different response wind farms in combination with the historical output data of the wind turbines in the similar dates. 2.The method of claim 1, wherein, The constituent data of the wind turbines of the wind farm is determined according to the wind turbine parameters of different wind turbines of the wind farm. 3.The method of claim 1, wherein, The method for determining the scheduling processing priority of the wind farm is: Determining the historical power generation amount of the wind farm under different wind conditions according to the historical power generation data, and determining the output scheduling priority of the wind farm by using the historical power generation amount; Determining the power generation efficiency of different wind turbines by using the wind turbine parameters of different wind turbines of the wind farm, and determining the power generation efficiency priority of the wind farm according to the power generation efficiency of different wind turbines; Determining the fault occurrence frequency of different wind turbines by using the historical power generation data of different wind turbines of the wind farm, and determining the power generation stability of the wind farm by using the fault occurrence frequency of different wind turbines; Determining the scheduling processing priority of the wind farm based on the power generation stability, the power generation efficiency priority, and the output scheduling priority of the wind farm. 4.The method of claim 3, wherein, The value range of the scheduling processing priority of the wind farm is between 0 and 1, wherein the higher the scheduling processing priority of the wind farm, the higher the priority level of the wind farm when performing scheduling processing. 5.The method of claim 1, wherein, The weather data includes wind speed and wind direction at different time periods, and is determined according to the prediction result of the weather data of the region where the wind farm is located on the current date. 6.The method of claim 1, wherein, The method for determining the similar dates is: Determining the wind speed and wind direction at different time periods on the current date based on the weather data of the current date, and determining the wind condition similarity coefficient of the current date and different dates at different time periods based on the wind speed and wind direction at different time periods; Determining the wind power distribution similarity of the current date and different dates by using the average value of the wind condition similarity coefficient of the current date and different dates at different time periods, and determining the similar dates based on the wind power distribution similarity. 7.The method of claim 1, wherein, The method for determining the similar dates is: Determining the wind speed at different time periods on the current date based on the weather data of the current date, and determining the wind speed deviation period of different dates by using the wind speed, when the dates have wind speed deviation periods: When the number of wind speed deviation periods of the date does not meet the requirement, it is determined that the date does not belong to the similar date; When the number of wind speed deviation periods of the date meets the requirement, the determination of the wind speed deviation amount of the date is performed according to the wind speed deviation condition of the wind speed deviation period of the date, and when the wind speed deviation amount of the date does not meet the requirement, it is determined that the date does not belong to the similar date; When the wind speed deviation amount of the date meets the requirement or there is no risk deviation period: The determination of the wind force condition similarity coefficient of the current date and different dates in different periods is performed according to the wind speed and wind direction in different periods, and the determination of the wind force condition deviation period is performed by using the wind force condition similarity coefficient; when the number of wind force condition deviation periods does not meet the requirement, it is determined that the date does not belong to the similar date; When the number of wind force deviation periods meets the requirement: The period is divided into different period intervals, and the interval similarity coefficient of different period intervals is determined according to the number of wind force condition deviation periods and the wind force condition similarity coefficient in different period intervals; when there is a period interval whose interval similarity coefficient does not meet the requirement, it is determined that the date does not belong to the similar date; When all interval similarity coefficients meet the requirement: The wind force distribution similarity of the current date and different dates is determined by using the average value of the wind force condition similarity coefficient of the current date and different dates in different periods, and the determination of the similar date is performed according to the wind force distribution similarity. 8.The method of claim 1, wherein, The determination method of the predicted wind power resource of the wind farm is: The determination of the wind farm output of different similar dates is performed based on the output data of the wind farm of different similar dates, and the similar date is divided into different similar output date intervals by using the wind farm output; The determination of the output similarity coefficient of different similar output date intervals is performed by using the number of similar dates in different similar output date intervals and the deviation condition of the output data between different similar dates; The determination of the wind force similarity coefficient of different similar date intervals is performed based on the number of similar dates in different similar date intervals and the wind force distribution similarity of different similar dates; The deviation condition of the processing data of the similar dates between the similar date intervals is obtained, and the reference coefficient of different similar output date intervals is determined in combination with the output similarity coefficient and the wind force similarity coefficient of different similar output date intervals; The determination of the reference output date interval is performed by using the reference coefficient, and the determination of the predicted wind power resource of the wind farm is performed according to the output data of different similar dates in the reference output date interval. 9.The method of claim 1, wherein, The determination method of the determined response wind turbine in the response wind farm is: The determination of the wind turbine output of the wind turbine in different similar dates is performed by using the wind turbine output data of the wind turbine in different similar dates in the response wind farm, and the determination of the output reliability coefficient of the wind turbine is performed by using the fluctuation condition and the average value of the wind turbine output of the wind turbine in different similar dates. Determine the power generation voltage waveform and power generation current waveform in the wind turbine output interval based on the deviation of the historical power generation data of any wind turbine in the response wind farm from other wind turbines, and determine the waveform consistency of the wind turbine in different wind turbine output intervals using the waveform deviation amount of the power generation voltage waveform and power generation current waveform of the wind turbine and other wind turbines; Obtain the historical running time of the wind turbine in different wind turbine processing intervals, and determine the power output reliability of the wind turbine in combination with the waveform consistency of the wind turbine in different wind turbine output intervals; Determine the comprehensive reliability of the wind turbine by the power output reliability and output reliability coefficient of the wind turbine, and determine the response wind turbine in the response wind farm using the comprehensive reliability.

10. An optimal scheduling system based on multi-source wind farm, used for performing the optimal scheduling method based on multi-source wind farm in any one of claims 1-9. Specifically includes: Output priority value determination module, wind power resource prediction module, response wind farm determination module, response wind turbine determination module; The output priority value determination module is responsible for obtaining the composition data and historical power generation data of the wind turbines of the wind farm, and determining the scheduling processing priority of different wind farms in combination with the wind turbine parameters and historical power generation data of different wind turbines; The wind power resource prediction module is responsible for determining the similar date and wind power distribution similarity based on the weather data of the current date, obtaining the output data of the wind farm in different similar dates, and determining the predicted wind power resource of different wind farms in combination with the wind power distribution similarity of different similar dates; The response wind farm determination module is responsible for predicting the predicted load demand of the joint grid connection point, and determines the response wind farm in the wind farm based on the predicted load demand, scheduling processing priority and predicted wind power resource; The response wind turbine determination module is responsible for determining the deviation of the historical power generation data of the wind turbines in the response wind farm in different similar dates as a constraint condition, and determining the response wind turbine in different response wind farms in combination with the historical output data of the wind turbines in similar dates.

Images