Power grid wind power generation system based on multi-mode energy storage cooperative regulation and control

Abstract

The invention relates to the technical field of power grid power generation regulation and control, in particular to a power grid wind power generation system based on multi-mode energy storage cooperative regulation and control. The real-time output power is combined with the output power of the historical adjacent time period, whether the output power fluctuates or not is analyzed, the predicted output power time sequence in the future time period is constructed when the output power fluctuates, the predicted output power time sequence is corrected according to the historical output power time sequence similar to the wind power change data, and the wind power change data is corrected. The output power at multiple initial time points in a future time period is verified, and when the output power is verified to be unqualified, the corrected output power time sequence is adjusted to output a final output power time sequence, so that the real-time adaptability of output power prediction is ensured; meanwhile, power fluctuation characteristics are determined according to the final output power time sequence, energy storage is carried out in a corresponding demand mode based on the power fluctuation characteristics, the characteristic advantages of energy storage in different modes are brought into full play, and the stability and reliability of power grid operation are improved.

Description

Technical Field

[0001] This invention relates to the field of power grid power generation control technology, and specifically to a power grid wind power generation system based on multi-mode energy storage coordinated control. Background Technology

[0002] The large-scale application of wind power technology has effectively alleviated the environmental pressure caused by traditional fossil fuels. However, wind energy has inherent instability, and random fluctuations in wind speed can cause significant fluctuations in the output power of wind power plants. These power fluctuations directly affect the frequency stability and power balance of the power grid, posing challenges to the safe and stable operation of the grid and limiting the grid-connected absorption capacity of wind power generation.

[0003] For example, Chinese Patent Publication No. CN119518986A discloses a wind-storage combined system and control method for coordinated control of hybrid energy storage devices. The system converts wind energy into electrical energy through wind turbine generators and outputs it to the power grid. The DC bus connects the wind turbine generators and two types of energy storage devices through the control system and exchanges energy with the power grid. The control system coordinates the control of the energy storage devices based on different power regulation needs, realizes power dispatch and frequency regulation control at different time scales, and thus improves the stability of the wind power generation system and the reliability of the power grid.

[0004] However, existing technologies have the following problems: 1. Existing technologies integrate two energy storage devices, batteries and supercapacitors, and coordinate control based on power regulation needs. However, they fail to accurately predict the output power of wind power generation and analyze fluctuation characteristics. They rely solely on the passive adjustment of energy storage devices, which leads to the energy storage devices having to respond frequently to power fluctuations. This makes it impossible to fully utilize the advantages of different energy storage devices, increases equipment losses, and makes it difficult to cope with power surges caused by complex and ever-changing wind speeds.

[0005] 2. Existing technologies do not have a power prediction verification and dynamic adjustment mechanism. They rely solely on preset control logic for regulation, which results in problems such as the inability to correct power prediction deviations in a timely manner and a lack of flexibility in the regulation strategy. This leads to lag in the regulation of energy storage devices, resulting in poor control of grid frequency fluctuations and affecting power supply reliability. Summary of the Invention

[0006] The purpose of this invention is to overcome the shortcomings of the prior art and provide a grid wind power generation system based on multi-mode energy storage coordinated regulation, so as to achieve accurate power prediction and dynamic regulation, improve the effect of energy storage coordinated regulation and grid operation stability.

[0007] The technical solution adopted by the present invention to solve its technical problem is: a grid wind power generation system based on multi-mode energy storage coordinated regulation, including a real-time power acquisition module, an output power prediction module, an output power correction module, a power prediction verification module, and a power fluctuation trend analysis module.

[0008] The connection relationships between the modules are as follows: the real-time power acquisition module is connected to the output power prediction module, the output power correction module is connected to both the output power prediction module and the power prediction verification module, and the power fluctuation trend analysis module is connected to the power prediction verification module.

[0009] The real-time power acquisition module collects the real-time output power of the wind power station in the power grid, and analyzes whether there are fluctuations in the output power by combining the output power of each historical time point in the nearby historical period.

[0010] The output power prediction module, when there are fluctuations in output power, forms a predicted output power time series for future periods based on the constructed preliminary output power change curve.

[0011] The output power correction module, based on wind power variation data of the power grid wind power station, filters historical output power time series with similar data and corrects the predicted output power time series.

[0012] The power prediction verification module collects the output power at multiple starting time points in the future period in real time, verifies it with the corrected output power timing, and adjusts the corrected output power timing to output the final output power timing when the power verification fails.

[0013] The power fluctuation trend analysis module determines the power fluctuation characteristics based on the final output power time sequence and adapts the energy storage to the corresponding demand mode based on the power fluctuation characteristics.

[0014] Compared with the prior art, the present invention has the following beneficial effects: (1) Based on the wind power change data of the power grid wind power station, the present invention filters the historical output power time series with similar data, corrects the predicted output power time series, improves the accuracy of output power prediction, effectively reduces prediction error, makes the prediction results more in line with the actual operating conditions, and provides reliable data support for energy storage coordinated regulation.

[0015] (2) This invention collects the output power at multiple starting time points in the future period in real time, and verifies it with the corrected output power timing. When the power verification fails, the corrected output power timing is adjusted to output the final output power timing, ensuring the real-time adaptability of the output power prediction, improving the dynamic response capability of the power grid to power fluctuations, and avoiding the problem of energy storage regulation lag caused by prediction deviation.

[0016] (3) The present invention determines the power fluctuation characteristics based on the final output power timing, adapts the energy storage mode to the corresponding demand mode based on the power fluctuation characteristics, realizes the precise matching between the energy storage mode and the power fluctuation demand, gives full play to the characteristic advantages of different energy storage modes, avoids the phenomenon of blind scheduling and loss of energy storage equipment, and improves the stability and reliability of power grid operation. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a schematic diagram of the system module connections of the present invention.

[0019] Figure 2 This is a schematic diagram illustrating the steps of the output power correction module in this invention.

[0020] Figure 3 This is a schematic diagram illustrating the historical time period selection steps for wind force change data similar in this invention.

[0021] Figure 4 This is a schematic diagram of the point-by-point correction step for predicted output power in this invention. Detailed Implementation

[0022] Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps set forth in these embodiments do not limit the scope of the invention. Furthermore, it should be understood that, for ease of description, the dimensions of the various parts shown in the drawings are not drawn to actual scale.

[0023] The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit the invention or its application or use. Techniques, methods, and apparatus known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and apparatus should be considered part of the specification.

[0024] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limitations. Therefore, other examples of exemplary embodiments may have different values.

[0025] Please see Figure 1 As shown, the present invention provides a grid-based wind power generation system based on multi-mode energy storage coordinated regulation, including a real-time power acquisition module, an output power prediction module, an output power correction module, a power prediction verification module, and a power fluctuation trend analysis module.

[0026] The connection relationships between the modules are as follows: the real-time power acquisition module is connected to the output power prediction module, the output power correction module is connected to both the output power prediction module and the power prediction verification module, and the power fluctuation trend analysis module is connected to the power prediction verification module.

[0027] The real-time power acquisition module collects the real-time output power of the wind power station in the power grid, and analyzes whether there are fluctuations in the output power by combining the output power of each historical time point in the nearby historical period.

[0028] In one embodiment of the present invention, determining whether there is fluctuation in the output power of the grid wind power station is the core prerequisite for subsequent output power prediction and energy storage coordinated regulation. If the output power is stable, there is no need to trigger a complex regulation process, which can reduce the system's computing power consumption. If there is fluctuation in the output power, it is necessary to further analyze the fluctuation characteristics to provide a basis for energy storage device scheduling.

[0029] Considering that the power fluctuations of wind power generation are caused by random changes in wind force, relying solely on the real-time power at the current point in time cannot distinguish between occasional fluctuations and continuous fluctuations. Therefore, it is necessary to introduce power data from nearby historical periods.

[0030] The historical proximity period is a continuous preset historical period before the current data collection time. Its preset duration needs to be adjusted according to the actual operation scenario of the power plant. For example, it can be set to 1 hour or 2 hours. Usually, a duration that can reflect the recent power change pattern is selected. If the duration is too short, it is easy to misjudge the fluctuation due to insufficient data. If the duration is too long, it is easy to introduce early irrelevant historical data and interfere with the current fluctuation analysis. Implementers can flexibly set it according to the power grid's requirements for power stability.

[0031] The output power is collected by a group of power sensors deployed on the output bus of the wind power station in the power grid, such as Hall effect power sensors. This sensor acquisition technology is an existing technology in the field of power system monitoring and will not be described in detail here.

[0032] In a specific embodiment of the present invention, the real-time power acquisition module is as follows: First, it retrieves the output power of all historical time points within the historical adjacent period in the historical database of the power station, and constructs an output power time series dataset with the real-time output power of the wind power station in the power grid.

[0033] Then, rate analysis is performed on the output power at adjacent time points in the output power time series dataset to obtain the output power change rate at all adjacent time points, and the average output power change rate is calculated.

[0034] If the rate of change of output power at multiple consecutive adjacent time points is different from the average rate of change of output power, then the output power fluctuates; otherwise, the output power does not fluctuate.

[0035] It should be noted that the rate of change of output power is the ratio of the difference in output power at adjacent time points in the output power time series dataset to the time interval.

[0036] The number of consecutive adjacent time points mentioned above needs to be combined with the power grid's power stability settings. For example, for urban core power grids, which have high power stability requirements, it can be set to 3 consecutive adjacent time points. For remote power grids, which have slightly lower power stability requirements, it can be set to 5 consecutive adjacent time points. Implementers can adjust it according to actual needs.

[0037] The output power prediction module, when there are fluctuations in output power, forms a predicted output power time series for future periods based on the constructed preliminary output power change curve.

[0038] Considering that the randomness of wind causes output power fluctuations to have no fixed period, but short-term power changes still exhibit traceable trends, for example, when wind force changes gradually, the power changes linearly; when wind force fluctuates slightly, the power changes smoothly and non-linearly. Therefore, this invention predicts the power change trend in the future based on the recent output power change patterns.

[0039] Based on this, in one embodiment of the present invention, the process of forming a predicted output power time series for a future period specifically includes: establishing a coordinate system with time points as independent variables and output power as dependent variables; plotting points on the established coordinate system based on the output power of each time point in the output power time series dataset; and using the least squares method to fit and obtain a preliminary output power change curve.

[0040] Extend the curve of the initial output power change to the future time period based on the slope of the curve, smooth the extended curve to obtain the predicted output power change curve for the future time period, and extract the predicted output power time series for the future time period.

[0041] It should be noted that the future time period needs to be set in conjunction with the response speed of the wind power station corresponding to the current mode of energy storage. For example, the response speed of energy-type energy storage is usually a long-term stable response at the minute level. The future time period can be set to 30 minutes, so power changes can be predicted 30 minutes in advance, allowing sufficient scheduling time for energy storage. The response speed of power-type energy storage is usually an instantaneous response at the millisecond or second level. The future time period can be set to 10 minutes. Implementers can set the future time period themselves.

[0042] As an example, the smoothing of the extended curve can be achieved using the moving average method, where the output power at each extended time point is the average of the output power at its adjacent extended time points, so that the extended curve closely matches the actual wind force fluctuation characteristics and reduces the deviation in predicted output power.

[0043] The output power correction module, based on wind power variation data of the power grid wind power station, filters historical output power time series with similar data and corrects the predicted output power time series.

[0044] Since the output power prediction module is based solely on curve fitting of historical and real-time power data and does not directly relate to the fundamental influence of wind force changes on output power, it is necessary to introduce wind force change data. By using the power patterns in scenarios corresponding to similar historical wind force change data, the predicted output power timing can be corrected to ensure that the prediction results are more in line with the actual logic that wind force determines output power.

[0045] Based on this, such as Figure 2 As shown, the output power correction module operates as follows: S1, acquire wind speed change data of the grid wind power station in the near historical period, including wind speed range, duration of each wind speed and wind direction angle range.

[0046] S2. Filter historical periods similar to wind force change data, and retrieve the historical output power time series of all similar historical periods followed by consecutive future periods.

[0047] In a specific embodiment of the present invention, such as Figure 3 As shown, the filtering of historical time periods similar to wind force change data specifically includes: S21, filtering all historical time periods that are the same as the historical time periods corresponding to the current time, and retrieving historical wind force change data for all historical time periods from the historical database.

[0048] S22. Compare the wind speed change data of the nearby historical period with the historical wind speed change data of all historical periods to obtain the wind speed interval overlap length, the duration of the same wind speed, and the overlapping wind direction angle.

[0049] S23. Combining wind force change data from nearby historical periods, determine wind speed interval similarity score, duration similarity score, and wind direction angle similarity score, and calculate the average to obtain the similarity score between the wind force change data from nearby historical periods and each historical period.

[0050] S24. Select historical periods with similarity scores to wind force change data that are greater than the set similarity score, and use them as historical periods similar to wind force change data.

[0051] As an example, the wind speed range in the near historical period is... Its wind speed range length is 3, and the wind speed range for a certain historical period is... If the wind speed interval overlap length is 1, then the wind speed interval overlap length is longer, and the wind speed characteristics are more similar. Therefore, the wind speed interval similarity score is determined by obtaining the ratio of the wind speed interval overlap length to the wind speed interval length of the historical adjacent period, and multiplying it by the total similarity score as the wind speed interval similarity score.

[0052] For example, during a certain historical period The sum of the durations of all wind speeds within the interval is 27 minutes, meaning the duration of the same wind speed is 27 minutes. Historically, the nearest time period is... If the interval lasts for 30 minutes, the longer duration is used as the denominator and the shorter duration as the numerator. The product of the ratio and the total similarity score is used as the duration similarity score. The closer the ratio is to 1, the more similar the duration features are.

[0053] For example, the wind direction angle range in the near historical period is The wind direction angle range for a certain historical period is Then the overlapping wind direction angle is The larger the overlapping wind direction angle, the more similar the wind direction characteristics. Therefore, the wind direction angle similarity score is determined by obtaining the ratio of the overlapping wind direction angle to the interval difference of the wind direction angle in the historical adjacent period, and multiplying it by the total similarity score as the wind direction angle similarity score.

[0054] S3. Calculate the cosine similarity between the predicted output power time series and each historical output power time series. If the similarity between the predicted output power time series and any historical output power time series is greater than the set similarity threshold, then there is no need to correct the output power time series in the future period.

[0055] As an example, considering the range of similarity results is... The closer the similarity is to 1, the more consistent the trends of the two time series are. Therefore, the similarity threshold can be set as follows: If the similarity is greater than the set similarity threshold, it means that the current predicted time series is highly matched with the output power pattern of the historical time series, and no correction is needed; otherwise, point-by-point correction needs to be initiated to avoid prediction deviations exceeding a reasonable range.

[0056] In other examples, implementers can also adjust the similarity threshold themselves, but it cannot exceed 1.

[0057] S4. Conversely, obtain the mode of output power at each time point in the historical output power time series, and correct the predicted output power at each time point in the predicted output power time series point by point based on the mode of output power.

[0058] As an example, the mode, compared to the mean, avoids interference from outliers in historical time series and better reflects the actual power output pattern at that point in time.

[0059] In a specific embodiment of the present invention, such as Figure 4 As shown, the step of correcting the predicted output power at each time point in the predicted output power time series includes: S41, performing deviation analysis between the predicted output power at each time point in the predicted output power time series and the mode of the output power at the corresponding time point to obtain the output power deviation value.

[0060] S42. Based on the output power at each time point in the historical output power time series, filter the maximum and minimum output power at each time point, and calculate the extreme difference of output power at each time point.

[0061] S43. If the output power deviation at a certain time point in the predicted output power timing is greater than the extreme difference of the output power at the corresponding time point, then the predicted output power at that time point is corrected to the mode of the output power at the corresponding time point.

[0062] S44. Conversely, there is no need to correct the predicted output power at that time point.

[0063] This invention is based on wind power variation data of wind power stations in the power grid. It filters historical output power time series with similar data and corrects the predicted output power time series with them, thereby improving the accuracy of output power prediction, effectively reducing prediction errors, and making the prediction results more in line with actual operating conditions, thus providing reliable data support for energy storage coordinated regulation.

[0064] The power prediction verification module collects the output power at multiple starting time points in the future period in real time, verifies it with the corrected output power timing, and adjusts the corrected output power timing to output the final output power timing when the power verification fails.

[0065] Considering that the correction based on historical similar wind force change data is still a static correction, and the randomness of wind force will cause the output power of the starting time point of future periods to deviate from the corrected time series, it is necessary to dynamically verify by collecting the output power at the starting time point in real time to ensure that the final output power time series can accurately reflect the current actual power change trend, so as to provide data support that best fits the field conditions in the later stage.

[0066] In a specific embodiment of the present invention, the verification method in the power prediction verification module is as follows: First, the output power at each starting time point in the future time period is compared with the output power at the corresponding time point in the corrected output power time series to obtain the output power difference at each starting time point in the future time period.

[0067] Secondly, based on the output power at each time point in the corrected output power time series, the mean and standard deviation of the output power corresponding to the corrected output power time series are calculated, and the standard deviation analysis of the mean output power and the output power at each starting time point in the future period is performed to obtain the standard deviation of the output power at the starting time.

[0068] Finally, the power verification is deemed unqualified if any of the following conditions are met: a) The difference in output power between multiple consecutive starting time points is greater than the set output power error value. The number of consecutive starting time points matches the total number of starting time points, typically a preset ratio of the total number of starting time points. The implementer can also adjust the preset ratio themselves.

[0069] b. The standard deviation of the output power at the initial time is greater than the standard deviation of the output power in the corrected output power time series. This indicates that the fluctuation range of the output power at the initial time exceeds the expected fluctuation range of the output power in the corrected output power time series. Even if the difference between multiple consecutive initial time points meets the qualification condition, there may still be a risk of drastic power fluctuations in the future, and the verification should be judged as unqualified.

[0070] In a specific embodiment of the present invention, the output final output power timing is as follows: First, determine the output power change trend based on the output power at each starting time point in the future period.

[0071] It should be noted that the method for judging the output power change trend is as follows: if the output power does not change at the beginning of each time point in the future period, then the output power change trend is judged to be a stable trend.

[0072] If the output power at each starting point in the future period is monotonically increasing or monotonically decreasing, then the output power change trend is determined to be a monotonically changing trend.

[0073] Conversely, the output power change trend is determined to be a fluctuating trend.

[0074] The second step is to analyze the rate of change of the output power based on the output power at each initial time point, and then adjust the output power at the remaining time points in the corrected output power time series accordingly.

[0075] As an example, the output power to be adjusted at the earliest remaining time point is the sum of the output power at the latest time point and the rate of change of the output power among the initial time points, and so on for the other remaining time points.

[0076] The third step is to determine whether the output power is a periodic fluctuation trend based on the output power at each initial time point.

[0077] As an example, if the output power at each initial time point shows peaks or valleys with the same interval, then the output power exhibits a periodic fluctuation trend.

[0078] Step 4: When the output power shows a periodic fluctuation trend, the output power at the remaining time points in the corrected output power time series is adjusted for periodic fluctuation.

[0079] Fifth step: Conversely, based on the output power at each initial time point, construct the correlation equation for the change of output power over time, and combine it with the remaining time points in the corrected output power time series to determine the output power adjustment value for the remaining time points.

[0080] Step 6: If the output power trend is stable, obtain the average output power at each initial time point, and adjust the output power at the remaining time points in the corrected output power time series to match its average. This ensures that the output power at the remaining time points is consistent with the stable trend at the initial time point.

[0081] This invention collects the output power at multiple starting points in a future period in real time, verifies it with the corrected output power timing sequence, and adjusts the corrected output power timing sequence to output the final output power timing sequence when the power verification fails. This ensures the real-time adaptability of the output power prediction, improves the grid's dynamic response to power fluctuations, and avoids the problem of energy storage regulation lag caused by prediction deviation.

[0082] The power fluctuation trend analysis module determines the power fluctuation characteristics based on the final output power time sequence and adapts the energy storage to the corresponding demand mode based on the power fluctuation characteristics.

[0083] In a specific embodiment of the present invention, the method of adapting energy storage to corresponding demand patterns based on power fluctuation characteristics is as follows: First, the output power at each predicted time point in the final output power time series is extracted to establish the final output power curve.

[0084] Secondly, capture the inflection points of the final output power curve, count the number of inflection points on the curve, as well as the interval between adjacent inflection points and the fluctuation amplitude, and use these as the power fluctuation characteristics corresponding to the curve.

[0085] Finally, based on the pre-stored compatibility between various energy storage modes and power fluctuation characteristic ranges, the demand mode energy storage of wind power stations in the power grid is determined.

[0086] It should be noted that the inflection point is the point where the slope of the final output power curve changes from positive to negative, directly reflecting the point of change in power fluctuation. The more inflection points there are, the more frequent the changes in output power in the future, and the more drastic the power fluctuations.

[0087] The interval between adjacent inflection points reflects the time period of power fluctuations. The shorter the interval, the shorter the period of power fluctuations, and the higher the requirement for the response speed of energy storage devices.

[0088] The fluctuation amplitude reflects the intensity of power fluctuations. The larger the fluctuation amplitude, the stronger the intensity of a single power change, and the higher the capacity requirement for energy storage equipment.

[0089] As an example, the specific method for obtaining the pre-stored adaptation relationship between various energy storage modes and power fluctuation characteristic ranges is as follows: filter the energy storage switching records from the historical database of wind power stations in the power grid, retrieve the output power curve after switching in each energy storage switching record, and identify the power fluctuation characteristics in the output power curve.

[0090] Statistically analyze the power fluctuation characteristics of each energy storage mode corresponding to each energy storage switch, and analyze the standard deviation of the power fluctuation characteristics corresponding to each energy storage mode. ,use Outliers are eliminated in principle, and the power fluctuation characteristic range corresponding to each energy storage mode is constructed based on the remaining power fluctuation characteristics to obtain the adaptation relationship between each energy storage mode and the power fluctuation characteristic range.

[0091] This invention determines the power fluctuation characteristics based on the final output power timing, and adapts the energy storage mode to the corresponding demand based on the power fluctuation characteristics. This achieves a precise match between the energy storage mode and the power fluctuation demand, fully leverages the advantages of different energy storage modes, avoids blind scheduling and losses of energy storage devices, and improves the stability and reliability of power grid operation.

[0092] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, in the form of a computer program product.

[0093] Those skilled in the art will recognize that the modules and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0094] In addition, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0095] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0096] Finally, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A power grid wind power system based on multi-mode energy storage collaborative regulation, characterized in that, The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station.

2. The multi-mode energy storage coordinated regulating based power grid wind power system according to claim 1, characterized in that: The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station.

3. The multi-mode energy storage coordinated regulating based power grid wind power system according to claim 1, characterized in that: The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station.

4. The multi-mode energy storage coordinated regulating based power grid wind power system according to claim 1, characterized in that: The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station.

5. The multi-mode energy storage coordinated regulating based power grid wind power system according to claim 4, characterized in that: The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method and device for a power grid wind power station. The application relates to a power fluctuation trend analysis method The wind speed interval overlap length, the same wind speed duration and the overlap wind direction angle are obtained by comparing the wind change data of the historical adjacent time period with the historical wind change data of all historical time periods; The wind speed interval similarity score, the duration similarity score and the wind direction angle similarity score are determined in combination with the wind change data of the historical adjacent time period, and the average value is calculated to obtain the wind change data similarity score of the historical adjacent time period and each historical time period; The historical time period with the wind change data similarity score greater than the set similarity score is selected as the historical time period similar to the wind change data.

6. The multi-mode energy storage coordinated regulating based power grid wind power system according to claim 4, characterized in that: The predicted output power at each time point in the predicted output power time sequence is corrected point by point, and the content includes: The predicted output power at each time point in the predicted output power time sequence is compared with the output power mode at the corresponding time point to obtain the output power deviation value; According to the output power at each time point in each historical output power time sequence, the maximum and minimum values of the output power at each time point are selected, and the output power extreme value difference at each time point is counted; If the output power deviation value at a certain time point in the predicted output power time sequence is greater than the output power extreme value difference at the corresponding time point, the predicted output power at the time point is corrected to the output power mode at the corresponding time point; Otherwise, the predicted output power at the time point does not need to be corrected.

7. The multi-mode energy storage coordinated regulating based power grid wind power system according to claim 1, characterized in that: The verification mode in the power prediction verification module is: The output power at the starting time point in the future time period is compared with the output power at the corresponding time point in the corrected output power time sequence to obtain the output power difference value at the starting time point in the future time period; According to the output power at each time point in the corrected output power time sequence, the output power mean value and the standard deviation of the corrected output power time sequence are calculated, and the output power mean value is analyzed with the standard deviation of the output power at the starting time point in the future time period to obtain the starting time output power standard deviation; When any of the following conditions is met, the power verification is determined to be unqualified: a. The output power difference value of the continuous multiple starting time points is greater than the set output power error value; b. The starting time output power standard deviation is greater than the output power standard deviation of the corrected output power time sequence.

8. The multi-mode energy storage coordinated grid-connected wind power system of claim 7, wherein: The final output power time sequence is output, specifically: According to the output power at the starting time point in the future time period, the output power change trend is determined; If the output power change trend is a monotonic change trend, the output power change rate is analyzed according to the output power at the starting time point, and the output power at the remaining time point in the corrected output power time sequence is adjusted; If the output power change trend is a fluctuation change trend, it is determined whether the output power is a periodic fluctuation change trend according to the output power at the starting time point; When the output power is a periodic fluctuation change trend, the output power at the remaining time point in the corrected output power time sequence is adjusted periodically; Otherwise, the correlation equation of the output power change with time is constructed according to the output power at the starting time point, and the output power adjustment value of the remaining time point is determined in combination with the remaining time point in the corrected output power time sequence. If the output power change trend is a stable trend, the average of the output power at the starting time points is obtained, and the output power at the remaining time points in the modified output power time sequence is adjusted to the average.

9. The multi-mode energy storage coordinated grid-connected wind power system of claim 8, wherein: The output power change trend judgment method is: If the output power at the starting time points in the future period is not changed, it is determined that the output power change trend is a stable trend; If the output power at the starting time points in the future period is monotonically increasing or monotonically decreasing, it is determined that the output power change trend is a monotonic change trend; Otherwise, it is determined that the output power change trend is a fluctuation change trend.

10. The multi-mode energy storage coordinated regulating based power grid wind power system according to claim 1, characterized in that: The content of the power fluctuation feature based demand mode energy storage adaptation is as follows: The output power at each prediction time point in the final output power time sequence is extracted, and a final output power curve is established; The inflection points of the curve are captured on the final output power curve, and the number of inflection points, the interval time length between adjacent inflection points and the fluctuation amplitude are counted as the power fluctuation characteristics corresponding to the curve; Based on the pre-stored adaptation relationship between each mode energy storage and the power fluctuation characteristic range, the demand mode energy storage of the power grid wind power station is judged.

Images