Methods, devices, electronic equipment and storage media for predicting hill climb events

Abstract

This disclosure provides a method, apparatus, electronic device, and storage medium for predicting ramp events, relating to the field of computer technology, and particularly to the field of power detection. The specific implementation scheme is as follows: A time window is slid across the wind power sequence, and sequences within the time window are extracted to obtain multiple wind power sub-sequences; among the multiple wind power sub-sequences, multiple first sub-sequences belonging to ramp events are identified; based on the Euclidean distance between each first sub-sequence and other sub-sequences within the multiple first sub-sequences, neighboring sub-sequences of each first sub-sequence are determined; based on the sampling time of wind power in the neighboring sub-sequences of each first sub-sequence, the occurrence time interval of the ramp event is determined; based on the most recent occurrence time of the ramp event and the occurrence time interval, the next occurrence time of the ramp event is determined. Using the technical solution of this disclosure can improve the prediction accuracy of power ramp events.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and more particularly to the field of power detection. Specifically, this disclosure relates to a method, apparatus, electronic device, and storage medium for predicting ramp events. Background Technology

[0002] In response to the development strategy of effectively achieving carbon peaking and carbon neutrality, the development direction of "vigorously promoting the development of new energy and facilitating cleaner energy supply" has been proposed. Among these initiatives, the proportion of renewable energy generation capacity in total installed power generation capacity is increasing. However, due to the inherent randomness and volatility of clean energy, the integration of high-proportion renewable energy generation, such as wind power, places higher demands on the ancillary services of the power system. Statistics show that wind power curtailment is increasing. In particular, wind power ramp-up events have severely impacted the power system. Especially in micro-meteorological scenarios such as mountainous and coastal areas, wind power output can experience sharp rises and falls, creating high-risk ramp-up events that affect the supply-demand balance of the power system.

[0003] Ramp-up events can be categorized into two types: uphill and downhill. Ramp-up events possess three key attributes: ramp amplitude, ramp slope, and ramp duration, typically characterized by high amplitude and short duration. Therefore, traditional power generation forecasting techniques struggle to accurately predict the rapid changes in wind power ramp-up events, failing to guarantee timely grid connection and consumption of renewable energy. Establishing accurate statistical characteristics and predictive models for wind power ramp-up events to better support ancillary services for the power system is a crucial research topic.

[0004] Unlike the large-scale, long-term fluctuations in wind power caused by extreme weather, the need arises in micro-meteorological scenarios such as mountainous and coastal areas to identify short-term, small-scale uphill events. However, existing technologies struggle to address this challenge. Summary of the Invention

[0005] This disclosure provides a method, apparatus, electronic device, and storage medium for predicting hill-climbing events, which can solve the above-mentioned problems.

[0006] According to one aspect of this disclosure, a method for predicting hill climbing events is provided, comprising:

[0007] For a wind power sequence arranged in the order of sampling time, slide the time window one power at a time and extract the sequence in the time window to obtain multiple wind power sub-sequences;

[0008] Among the multiple wind power subsequences, identify multiple first subsequences that belong to the ramping event;

[0009] Based on the Euclidean distance between each of the first subsequences and other subsequences among the plurality of first subsequences, the neighboring subsequences of each of the first subsequences are determined respectively;

[0010] The time interval for the occurrence of the ramping event is determined based on the sampling time of the wind power in the neighboring subsequences corresponding to each of the first subsequences;

[0011] The next occurrence time of the climbing event is determined based on the most recent occurrence time of the climbing event and the occurrence time interval.

[0012] According to another aspect of this disclosure, a hill-climbing event prediction device is provided, comprising:

[0013] The subsequence truncation module is used to slide time windows one by one and truncate the sequence in the time window of the wind power sequence arranged in the order of sampling time to obtain multiple wind power subsequences;

[0014] A ramp event detection module is used to identify multiple first subsequences belonging to ramp events among the multiple wind power subsequences;

[0015] The subsequence filtering module is used to determine the neighboring subsequences of each first subsequence based on the Euclidean distance between each first subsequence and other subsequences in the plurality of first subsequences;

[0016] The time interval determination module is used to determine the time interval of the ramping event based on the sampling time of the wind power in the neighboring subsequences of each first subsequence;

[0017] The hill-climbing event prediction module is used to determine the next occurrence time of the hill-climbing event based on the most recent occurrence time of the hill-climbing event and the occurrence time interval.

[0018] According to another aspect of this disclosure, an electronic device is provided, comprising:

[0019] At least one processor; and

[0020] The memory is communicatively connected to the at least one processor; wherein,

[0021] The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform any of the hill-climbing event detection methods in the embodiments of this disclosure.

[0022] According to another aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are used to cause the computer to perform any of the hill-climbing event detection methods in the embodiments of this disclosure.

[0023] According to the technology disclosed herein, for a wind power sequence arranged in chronological order of sampling time, a time window is slid across each power and the sequence within the time window is extracted to obtain multiple wind power sub-sequences. This allows for the identification of multiple first sub-sequences that belong to a ramping event and have the same duration among these multiple wind power sub-sequences. Then, using the Euclidean distance between each first sub-sequence and other sub-sequences belonging to the ramping event, the neighboring sub-sequences of each first sub-sequence that experienced the ramping event can be accurately determined. Furthermore, by utilizing the sampling time of wind power in each neighboring sub-sequence, the time interval between ramping events can be accurately determined, and consequently, the next occurrence time of the ramping event can be accurately predicted.

[0024] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0025] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0026] Figure 1 This is a flowchart of a hill-climbing event prediction method according to an embodiment of the present disclosure;

[0027] Figure 2 This is a schematic diagram of a hill-climbing event according to an embodiment of the present disclosure;

[0028] Figure 3 This is a schematic diagram of the distance calculation process between two window subsequences according to an embodiment of the present disclosure;

[0029] Figure 4 This is a structural block diagram of a hill-climbing event prediction device according to an embodiment of the present disclosure;

[0030] Figure 5 This is a block diagram of an electronic device used to implement the hill-climbing event prediction method of the embodiments of this disclosure. Detailed Implementation

[0031] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0032] Figure 1 This is a flowchart of a hill-climbing event prediction method according to an embodiment of the present disclosure.

[0033] like Figure 1 As shown, this hill-climbing event prediction method may include:

[0034] S110, For the wind power sequence arranged in the order of sampling time, slide the time window one by one and extract the sequence in the time window to obtain multiple wind power sub-sequences;

[0035] S120, in multiple wind power subsequences, identify multiple first subsequences belonging to the ramping event;

[0036] S130, Based on the Euclidean distance between each first subsequence and other subsequences in the multiple first subsequences, determine the neighboring subsequences of each first subsequence respectively;

[0037] S140, Based on the sampling time of wind power in the neighboring subsequences of each first subsequence, determine the time interval for the occurrence of the ramping event;

[0038] S150, based on the most recent occurrence time of the climbing event and the time interval between occurrences, determine the next occurrence time of the climbing event.

[0039] For example, a wind power sequence includes multiple wind power units, which are generally wind power output or wind power generation. The individual wind power units in the sequence are arranged in chronological order of sampling time. For instance, a wind power sequence can be denoted as: P = [p1, ..., p...]. t ,…,p T ], where t∈{1,2,…,T}, and T is the total number of sampling points.

[0040] Figure 2 This is a schematic diagram of a hill-climbing event according to an embodiment of the present disclosure.

[0041] For example, such as Figure 2 As shown, a climbing event can be defined as:

[0042] If, within the time period Δt, the difference between the maximum and minimum wind power is greater than a pre-set power threshold θ, then the following condition is met: (max i∈{t,...,t+Δt} P(i)-min i∈{t,...,t+Δt} If P(i))>θ, then a wind power ramp-up event is considered to have occurred during that period.

[0043] Where, max i∈{t,...,t+Δt} P(i)-min i∈{t,...,t+Δt} P(i) represents the slope amplitude; Δt represents the slope duration.

[0044] Typically, depending on the hill-climbing detection cycle, Δt can be preset to 15 minutes, 30 minutes, or 60 minutes, etc., without any specific limitation here.

[0045] Furthermore, if max i∈{t,...,t+Δt} P(i)>min i∈{t,...,t+Δt} When P(i), the event is an uphill event; if max i∈{t,...,t+Δt} P(i) <min i∈{t,...,t+Δt} When P(i), the event is a downhill climbing event.

[0046] The power threshold θ can be set to 20% of the rated installed capacity of the wind turbine.

[0047] For example, the size of the time window can be the same as the duration of the time period Δt in the climbing event.

[0048] In this embodiment of the disclosure, the occurrence time interval of the ramping event is predicted by utilizing the neighboring subsequences of the wind power subsequence that also belong to the ramping event. Since the Euclidean distance between subsequences is used in the process of determining the neighboring subsequences, the first subsequence belonging to the ramping event is pre-selected from multiple wind power subsequences, and then the corresponding neighboring subsequences are determined by using the Euclidean distance between the first subsequence and other subsequences. This reduces the amount of computation required for subsequent Euclidean distance calculations.

[0049] For example, the k-th wind power subsequence can be represented as {p k ,…,p k+Δt In the wind power subsequence, there are T subsequences belonging to the ramping event. The i-th first subsequence can be represented as p. i ,…,p i+Δt , i∈T.

[0050] Traverse j∈{1,2,…,T} and calculate the Euclidean distance between the i-th first subsequence and the j-th first subsequence among the T subsequences, as follows:

[0051]

[0052] For example, for the i-th first subsequence, the j-th first subsequence with the smallest Euclidean distance to the i-th first subsequence can be selected as the neighbor subsequence of the i-th first subsequence. That is, when the i-th first subsequence is a climbing event, the next climbing event or the previous climbing event is its neighbor subsequence. The climbing event can be an uphill climbing event or a downhill climbing event.

[0053] like Figure 3 The diagram illustrates the calculation of the Euclidean distance between the i-th and j-th window subsequences. The window subsequence can be either the first subsequence or a wind power subsequence.

[0054] For example, the time interval for the occurrence of the ramping event is based on the sampling time of the first wind power in the neighboring subsequences of each first subsequence. Alternatively, the time interval for the occurrence of the ramping event is based on the average sampling time of the wind power in the neighboring subsequences of each first subsequence.

[0055] For example, the time of the most recent occurrence of the hill climb event is added to the time interval between occurrences to obtain the time of the next occurrence of the hill climb event.

[0056] According to the above implementation method, for a wind power sequence arranged in order of sampling time, a time window is slid across each power and the sequence within the time window is extracted to obtain multiple wind power sub-sequences. This allows for the identification of multiple first sub-sequences that belong to a ramping event and have the same duration among these multiple wind power sub-sequences. Then, using the Euclidean distance between each first sub-sequence and other sub-sequences belonging to the ramping event, the neighboring sub-sequences of each first sub-sequence that experienced the ramping event can be accurately determined. Furthermore, by utilizing the sampling time of wind power in each neighboring sub-sequence, the time interval between ramping events can be accurately determined, and consequently, the next occurrence time of the ramping event can be accurately predicted.

[0057] In one implementation, determining the neighboring subsequences of each first subsequence based on the Euclidean distance between each first subsequence and other subsequences among the plurality of first subsequences includes:

[0058] For any first subsequence, determine multiple second subsequences that do not overlap with the first subsequences from among the multiple first subsequences;

[0059] Based on the Euclidean distance between the first subsequence and each second subsequence, the second subsequence with the smallest Euclidean distance to the first subsequence is selected from among the multiple second subsequences and used as the neighbor subsequence of the first subsequence.

[0060] Understandably, the first subsequence can have one or more neighboring subsequences. If it has multiple neighboring subsequences, then the Euclidean distance between these multiple neighboring subsequences and the first subsequence is the same.

[0061] In this example, for other first subsequences that overlap with the first subsequence, the Euclidean distance between them and the first subsequence can be omitted, reducing the workload of subsequent filtering of neighboring subsequences of the first subsequence.

[0062] In one implementation, determining the time interval for the occurrence of the ramping event based on the sampling time of wind power in the neighboring subsequences corresponding to each first subsequence may include:

[0063] Based on the sampling time of wind power in the neighboring subsequences of each first subsequence, the neighbor sampling time of each first subsequence is determined respectively.

[0064] The time interval for the occurrence of the climbing event is determined based on the neighbor sampling time of each first subsequence.

[0065] Understandably, the sampling time of any wind power in a neighboring subsequence of the first subsequence can be used as the neighbor sampling time of the first subsequence. Alternatively, the sampling time of the first wind power in a neighboring subsequence of the first subsequence can be used as the neighbor sampling time of the first subsequence. Alternatively, the average sampling time of wind power in a neighboring subsequence of the first subsequence can be used as the neighbor sampling time of the first subsequence.

[0066] In one example, since the first subsequence can have one or more neighboring subsequences, the above-mentioned determination of the neighbor sampling time of each first subsequence based on the sampling time of wind power in the neighboring subsequences corresponding to each first subsequence can include one of the following:

[0067] For any first subsequence, if the first subsequence corresponds to a neighboring subsequence, the sampling time of the first wind power in the neighboring subsequence is used as the neighbor sampling time of the first subsequence.

[0068] For any first subsequence, in the case of multiple neighboring subsequences corresponding to the first subsequence, the sampling time of the first wind power in each neighboring subsequence is obtained to obtain multiple sampling times. Among the multiple sampling times, the sampling time with the smallest time interval between it and the sampling time of the first wind power in the first subsequence is selected as the neighbor sampling time of the first subsequence.

[0069] Understandably, the time interval for the occurrence of the climbing event is determined based on the adjacent time intervals of the neighbor sampling times of each first subsequence. For example, the average or median of adjacent time intervals can be used as the time interval for the occurrence of the climbing event. Alternatively, a second-order or third-order polynomial curve formula can be used to fit the above adjacent time intervals to obtain a target curve formula, and then the time interval for the occurrence of the climbing event can be obtained by solving the target curve formula.

[0070] In one example, using a third-order polynomial, the determination of the time interval for the hill-climbing event based on the neighbor sampling time of each first subsequence can include:

[0071] Arrange the neighbor sampling times of each first subsequence in chronological order to obtain the neighbor sampling time sequence;

[0072] Starting with an initial value of 1 for s, the s-th time interval between the (s+1)-th neighbor sampling time and the s-th neighbor sampling time is obtained one by one to obtain the time interval sequence, where s is a positive integer;

[0073] Using any time interval in the time interval sequence as the independent and dependent variables of a third-order polynomial, the third-order polynomial is fitted to obtain the coefficients of each term in the third-order polynomial.

[0074] By using the coefficients of each term in the third-order polynomial to solve the third-order polynomial, the time interval between the occurrences of the hill-climbing events can be obtained.

[0075] For example, the neighbor sampling times of all window subsequences that match the climbing event, i.e., the first subsequence, are reconstructed in chronological order to obtain a new neighbor sampling time sequence: {t1,…,t s ,…,t S},S <T。

[0076] Then, construct the difference sequence, i.e., the time interval sequence mentioned above, represented as: {Δt1,…,Δt} s ,…,Δt S-1}, where Δt s =t s+1 -t s .

[0077] Next, a third-order polynomial is used to fit the above time interval sequence to estimate the following equation: Δt s+1 =a3(Δt) s+1 ) 3 +a2(Δt s+1 ) 2 +a1Δt s+1 By adding the coefficients of each term in a0, we obtain the values ​​of a0, a1, a2, and a3. Then, by filling these coefficients into a third-order polynomial and solving the polynomial with the coefficients, we obtain the time interval between the occurrences of the hill-climbing events.

[0078] Finally, using this third-order polynomial formula, the time t of the most recent occurrence of the climbing event can be determined. S and the time interval Δt between the occurrence of the climbing event S-1 Predict the next occurrence time t of the climbing event. S+1 .

[0079] According to the above implementation method, by fitting the difference sequence of neighbor sampling times belonging to the climbing event using a third-order polynomial, and then solving the fitted third-order polynomial, the time interval of the climbing event can be accurately obtained.

[0080] In some embodiments, the above method may further include:

[0081] Based on the Euclidean distance between each first subsequence and other subsequences in the multiple first subsequences, the distance profile of each first subsequence is determined respectively;

[0082] Among multiple first subsequences, the first subsequence with the smallest distance from the image is selected as the main pattern of the climbing event;

[0083] Based on the main patterns of climbing events, the evaluation criteria for climbing events are adjusted.

[0084] For example, multiple second subsequences that do not overlap with the first subsequences are identified from a plurality of first subsequences. Then, for any first subsequence, the Euclidean distance between the first subsequence and each of the second subsequences is calculated, and the minimum Euclidean distance is selected as the distance profile of the first subsequence.

[0085] For example, each first subsequence has a distance profile, so the first subsequence with the smallest distance profile can be selected as the primary pattern for the hill climbing event.

[0086] For example, the first subsequence with the smallest distance from the image can be used to determine the climbing duration and climbing amplitude of the climbing event.

[0087] According to the above implementation method, the distance profile of each first subsequence belonging to the climbing event can be accurately described by using the Euclidean distance between it and other subsequences. Therefore, by using the distance profile of each first subsequence, the first subsequence that can serve as the main pattern of the climbing event can be selected from multiple first subsequences. This first subsequence can then be used to adjust the evaluation criteria for the climbing event, further improving the detection accuracy of the climbing event.

[0088] The following is an example of calculating the distance profile and neighbor sampling time for each window subsequence. The window subsequence can be either the first subsequence mentioned above or the wind power subsequence mentioned above, as detailed below:

[0089] 1. For the i-th window subsequence {p i ,…,p i+Δt To calculate the distance of this window subsequence relative to all other window subsequences, we need to determine the distance between the current window subsequence and all other window subsequences.

[0090] like Figure 3 As shown, traversing j∈{1,2,…,T}, and j≠i, the Euclidean distance is used to measure the i-th window subsequence {p i ,…,p i+Δt} and the j-th window subsequence {p j ,…,p j+Δt The distances between} are as follows:

[0091]

[0092] 2. Set exclusion regions to ignore unimportant matches. For example, if the i-th window subsequence overlaps with the k-th window subsequence, then skip the k-th window subsequence, where k is a positive integer;

[0093] 3. Use the minimum value of d(i,j), j∈{1,2,…,T} as the distance profile of the i-th window subsequence; select j with the smallest d(i,j) and the smallest value of |ji| as the neighbor sampling time of the i-th window subsequence;

[0094] 4. If i = T, then end the calculation process of this example; otherwise, let i = i + 1 and return to step 1.

[0095] According to the above implementation method, climbing events can be accurately detected and predicted.

[0096] Figure 4 This is a structural block diagram of a hill-climbing event prediction device according to an embodiment of the present disclosure.

[0097] like Figure 4 As shown, the hill-climbing event prediction device may include:

[0098] The subsequence truncation module 410 is used to slide a time window for each power of the wind power sequence arranged in the sampling time order and truncate the sequence in the time window to obtain multiple wind power subsequences.

[0099] The ramp event detection module 420 is used to determine multiple first subsequences belonging to ramp events among the multiple wind power subsequences;

[0100] The subsequence filtering module 430 is used to determine the neighboring subsequences of each first subsequence based on the Euclidean distance between each first subsequence and other subsequences in the plurality of first subsequences;

[0101] The time interval determination module 440 is used to determine the time interval of the ramping event based on the sampling time of the wind power in the neighboring subsequences of each first subsequence;

[0102] The hill-climbing event prediction module 450 is used to determine the next occurrence time of the hill-climbing event based on the most recent occurrence time of the hill-climbing event and the occurrence time interval.

[0103] In one embodiment, the subsequence filtering module 430 includes:

[0104] A first filtering unit is configured to, for any first sub-sequence, determine, among the plurality of first sub-sequences, a plurality of second sub-sequences that do not overlap with the first sub-sequence;

[0105] The second filtering unit is used to select, based on the Euclidean distance between the first subsequence and each of the second subsequences, the second subsequence with the smallest Euclidean distance to the first subsequence, as the neighboring subsequence of the first subsequence.

[0106] The specific functions and examples of each module and submodule of the apparatus in this disclosure can be found in the relevant descriptions of the corresponding steps in the above method embodiments, and will not be repeated here.

[0107] The acquisition, storage, and application of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0108] According to embodiments of this disclosure, this disclosure also provides an electronic device and a readable storage medium.

[0109] Figure 5 A schematic block diagram of an example electronic device 600 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0110] like Figure 5 As shown, device 600 includes a computing unit 601, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 602 or a computer program loaded from storage unit 608 into random access memory (RAM) 603. RAM 603 may also store various programs and data required for the operation of device 600. The computing unit 601, ROM 602, and RAM 603 are interconnected via bus 604. Input / output (I / O) interface 605 is also connected to bus 604.

[0111] Multiple components in device 600 are connected to I / O interface 605, including: input unit 606, such as keyboard, mouse, etc.; output unit 607, such as various types of monitors, speakers, etc.; storage unit 608, such as disk, optical disk, etc.; and communication unit 609, such as network card, modem, wireless transceiver, etc. Communication unit 609 allows device 600 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0112] The computing unit 601 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 601 performs the various methods and processes described above, such as a hill-climbing event prediction method. For example, in some embodiments, a hill-climbing event prediction method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on device 600 via ROM 602 and / or communication unit 609. When the computer program is loaded into RAM 603 and executed by the computing unit 601, one or more steps of a hill-climbing event prediction method described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform a hill-climbing event prediction method by any other suitable means (e.g., by means of firmware).

[0113] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0114] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0115] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0116] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0117] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0118] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0119] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0120] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for predicting hill climbing events, characterized in that, The method is based on wind turbines in micro-meteorological scenarios in mountainous and coastal areas, and includes: The output power data of the wind turbine is obtained to form a wind power sequence arranged in chronological order. The time window of the wind power sequence is slid through one power and the sequence in the time window is extracted to obtain multiple wind power sub-sequences. Among the multiple wind power subsequences, multiple first subsequences belonging to the ramping event are determined; wherein, the ramping event satisfies the following conditions: the difference between the maximum and minimum wind power values ​​in the multiple first subsequences is greater than the power threshold of the rated installed capacity of the wind turbine; based on the Euclidean distance between each first subsequence and other subsequences in the multiple first subsequences, the neighboring subsequences of each first subsequence are determined, including: for each first subsequence, determining other subsequences in the multiple first subsequences that do not overlap with the time of the first subsequence, and selecting the subsequence with the smallest Euclidean distance as the neighboring subsequence; The time interval for the occurrence of the ramping event is determined based on the sampling time of wind power in the neighboring subsequences of each first subsequence; Based on the most recent occurrence time of the climbing event and the occurrence time interval, the next occurrence time of the climbing event is determined; Based on the Euclidean distance between each of the first subsequences and other subsequences in the plurality of first subsequences, a distance profile for each of the first subsequences is determined. Among the multiple first subsequences, the first subsequence with the smallest distance from the image is selected as the main pattern of the climbing event; Based on the main pattern of the climbing event, adjust the climbing duration and climbing amplitude of the climbing event; The step of determining the time interval for the occurrence of the ramping event based on the sampling time of wind power in the neighboring subsequences corresponding to each of the first subsequences includes: Based on the sampling time of wind power in the neighboring subsequences of each first subsequence, the neighbor sampling time of each first subsequence is determined respectively; The time interval for the occurrence of the climbing event is determined based on the neighbor sampling time of each of the first sub-sequences; Determining the time interval for the occurrence of the climbing event based on the neighbor sampling time of each of the first sub-sequences includes: Arrange the neighbor sampling times of each of the first subsequences in chronological order to obtain the neighbor sampling time sequence; Starting from an initial value of 1 for s, the s-th time interval between the (s+1)-th neighbor sampling time and the s-th neighbor sampling time in the neighbor sampling time sequence is obtained one by one to obtain the time interval sequence, where s is a positive integer; Using any time interval in the time interval sequence as the independent and dependent variables of a third-order polynomial, the third-order polynomial is fitted to obtain the coefficients of each term in the third-order polynomial. The time interval between the occurrences of the hill-climbing events is obtained by solving the third-order polynomial using the coefficients of each term.

2. The method according to claim 1, characterized in that, The step of determining the neighboring subsequences of each first subsequence based on the Euclidean distance between each first subsequence and other subsequences among the plurality of first subsequences includes: For any first subsequence, determine a plurality of second subsequences that do not overlap with the first subsequences from the plurality of first subsequences; Based on the Euclidean distance between the first subsequence and each of the second subsequences, the second subsequence with the smallest Euclidean distance to the first subsequence is selected from the plurality of second subsequences and used as the neighbor subsequence of the first subsequence.

3. The method according to claim 1, characterized in that, The step of determining the neighbor sampling time of each first subsequence based on the sampling time of wind power in the neighbor subsequences corresponding to each first subsequence includes one of the following: For any of the first subsequences, if the first subsequence corresponds to a neighboring subsequence, the sampling time of the first wind power in the neighboring subsequence is taken as the neighbor sampling time of the first subsequence. For any first subsequence, in the case of multiple neighboring subsequences corresponding to the first subsequence, the sampling time of the first wind power in each neighboring subsequence is obtained to obtain multiple sampling times, and among the multiple sampling times, the sampling time with the smallest time interval between it and the sampling time of the first wind power in the first subsequence is selected as the neighbor sampling time of the first subsequence.

4. A hill-climbing event prediction device, characterized in that, The device is based on wind turbines used in microclimate scenarios in mountainous and coastal areas, and includes: The subsequence extraction module is used to acquire the output power data of the wind turbine, form a wind power sequence arranged in time order, slide the time window of the wind power sequence one by one and extract the sequence in the time window to obtain multiple wind power subsequences. A ramp event detection module is used to determine multiple first subsequences belonging to ramp events among the multiple wind power subsequences; wherein the ramp event satisfies the following conditions: the difference between the maximum and minimum wind power values ​​in the multiple first subsequences is greater than the power threshold of the rated installed capacity of the wind turbine. The subsequence filtering module is used to determine the neighboring subsequences of each first subsequence based on the Euclidean distance between each first subsequence and other subsequences in the plurality of first subsequences, including: for each first subsequence, determining other subsequences in the plurality of first subsequences that do not overlap with the time of the first subsequence, and selecting the subsequence with the smallest Euclidean distance as the neighboring subsequence; The time interval determination module is used to determine the time interval of the ramping event based on the sampling time of the wind power in the neighboring subsequences of each first subsequence; The hill-climbing event prediction module is used to determine the next occurrence time of the hill-climbing event based on the most recent occurrence time of the hill-climbing event and the occurrence time interval. A module for determining the distance profile of each first subsequence based on the Euclidean distance between each first subsequence and other subsequences in the plurality of first subsequences, selecting the first subsequence with the smallest distance profile among the plurality of first subsequences as the main pattern of the climbing event, and adjusting the climbing duration and climbing amplitude of the climbing event based on the main pattern of the climbing event. The time interval determination module is further configured to determine the neighbor sampling time of each first subsequence based on the sampling time of wind power in the neighbor subsequences of each first subsequence; and to determine the time interval of the occurrence of the ramp event based on the neighbor sampling time of each first subsequence. The time interval determination module is further configured to arrange the neighbor sampling times of each of the first sub-sequences in chronological order to obtain a neighbor sampling time sequence; starting from the initial value of s as 1, it sequentially obtains the s-th time interval between the (s+1)-th neighbor sampling time and the s-th neighbor sampling time in the neighbor sampling time sequence to obtain a time interval sequence, where s is a positive integer; using any time interval in the time interval sequence as the independent and dependent variables of a third-order polynomial, it fits the third-order polynomial to obtain the coefficients of each term in the third-order polynomial; and uses the coefficients of each term in the third-order polynomial to solve the third-order polynomial to obtain the time interval of the hill-climbing event.

5. The apparatus according to claim 4, characterized in that, The subsequence filtering module includes: A first filtering unit is configured to, for any first sub-sequence, determine, among the plurality of first sub-sequences, a plurality of second sub-sequences that do not overlap with the first sub-sequence; The second filtering unit is used to select, based on the Euclidean distance between the first subsequence and each of the second subsequences, the second subsequence with the smallest Euclidean distance to the first subsequence, as the neighboring subsequence of the first subsequence.

6. An electronic device, characterized in that, include: At least one processor; as well as The memory that is communicatively connected to the at least one processor; The memory stores instructions that can be executed by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the method according to any one of claims 1-3.

7. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, in, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-3.

Images