Wind power output scene generation method, system and device considering extreme weather influence and storage medium

Abstract

The invention discloses a wind power output scene generation method, system and device considering extreme weather influence, and a storage medium, and the method comprises the steps: obtaining the historical data of a year-round wind power scene, and carrying out the clustering to obtain a day type sequence of each day in the year-round; according to the day type sequence, establishing an outer-layer MCMC model to obtain a transition probability matrix among different day types, and establishing an inner-layer MCMC model to obtain an intra-day output state transition probability matrix; combining the two transition probability matrixes to generate an intra-day output state sequence of each day, and converting the intra-day output state sequence of each day into a time sequence value of intra-day wind power output based on a sampling method; and when extreme weather occurs, correcting the time sequence value of the wind power output in the corresponding time period according to a set rule so as to obtain a wind power output time sequence scene considering the influence of the extreme weather. Finally, a wind power scene considering the influence of extreme weather on wind power output is generated, and the statistical characteristics of historical scene data are well inherited.

Description

TECHNICAL FIELD

[0001] The application belongs to the field of wind power scene generation, and relates to a wind power output scene generation method, system, device and storage medium considering the influence of extreme weather. BACKGROUND

[0002] With the increasingly serious global environmental problems, actively developing new energy has become an important measure to cope with climate change, reduce environmental pollution and achieve sustainable development. As the main form of new energy utilization, wind power and photovoltaic power generation have been rapidly increasing in installed capacity in power systems year by year. At the same time, the randomness and volatility of new energy generation have brought new challenges to the planning, operation and safe supply of power systems.

[0003] In order to evaluate the balance between supply and demand, economy and reliability of power systems under high proportion of new energy access, a large number of wind power outputs with sufficient representativeness need to be generated as input data for analysis and research. It should be noted that the existing scene generation methods rarely consider the influence of extreme weather events on wind power output, partly because the influence mechanism of extreme weather such as typhoon and cold wave on wind power output is difficult to accurately model, and completely ignoring the influence of extreme weather will make the evaluation results of safe supply of high proportion of new energy power system too optimistic. SUMMARY

[0004] The purpose of the present application is to overcome the shortcomings of the prior art, and to provide a wind power output scene generation method, system, device and storage medium considering the influence of extreme weather, which finally generates wind power scenes considering the influence of extreme weather on wind power output, and better inherits the statistical characteristics of historical scene data.

[0005] To achieve the above purpose, the following technical solutions are adopted:

[0006] A wind power output scene generation method considering the influence of extreme weather, comprising the following processes:

[0007] S1, obtaining annual wind power scene historical data, and clustering to obtain a daily type sequence to which each day of the year belongs;

[0008] S2, establishing an outer MCMC model of different daily types based on the MCMC method according to the daily type sequence of each day, and then obtaining a transition probability matrix between different daily types, and establishing an inner MCMC model within a single day, and then obtaining an output state transition probability matrix within the day;

[0009] S3, combining the transition probability matrix between different daily types and the output state transition probability matrix within the day to generate an intra-day output state sequence of each day, and converting the intra-day output state sequence of each day into a time series value of intra-day wind power output based on a sampling method;

[0010] S4, when the extreme weather occurs, the time series value of the wind power output corresponding to the time period is corrected according to the set rule, and then a wind power output time series scenario considering the influence of the extreme weather is obtained.

[0011] Preferably, in S1, the K-means clustering method is used to obtain a daily type sequence of each day in a year.

[0012] Preferably, the specific process of S1 is that the wind power output of 365 days of historical data in a year is clustered into K categories, so that each day in the daily sequence of 365 days has its corresponding cluster daily type, thereby obtaining a daily type sequence with a length of 365 days.

[0013] Preferably, in S2, the specific process of calculating the transition probability matrix between different daily types is that, according to the daily type sequence of each day, the daily inter-day transition probability of different categories of days in the mth month (m = 1, 2, …, 12) is calculated.

[0014]

[0015] In the formula: is the probability of transition from daily type i to daily type j in the mth month, that is, the probability that the daily type of a certain day in the mth month is i and the daily type of the next day is j is and denote the daily types of adjacent two days in the mth month.

[0016] After calculating the daily inter-day transition probability of all different categories of days in each month, 12 daily inter-day transition probability matrices of daily types with a dimension of K × K are obtained, that is, each month has its corresponding daily type transition probability matrix.

[0017] Further, in S2, the specific process of calculating the output state transition probability matrix within a day is that: first, the wind power output data of the mth month with daily type k is input, if the number of days with daily type k is N k , then the dimension of the input wind power output data is N k × 24;

[0018] According to the input historical data, the maximum value and the minimum value of the wind power output of the mth month with daily type k are counted, and N states are divided respectively, and the wind power output falling within the interval is defined as state i (i = 1, 2, …, N).

[0019]

[0020]

[0021] The probability distribution of the state of the first time of the day type k wind power in the mth month is counted, and then the state transition probability matrix between adjacent time is calculated by counting the number of times the output falls in the corresponding interval of each state.

[0022] The probability distribution of the first time of the wind power of each month of all different types of days is counted, and the state transition probability matrix between each adjacent time after the first time is counted, and each element in the matrix is as follows:

[0023]

[0024] In the formula: The probability of the state of the wind power of the day type k in the mth month at t time is i, and at t+1 time is j. And The state of the wind power of the day type k in the mth month at t time and t+1 time is represented by and respectively.

[0025] Further, the specific process of S3 is: according to the probability distribution of the first time of the output state, the first time of the output state is sampled to generate the next each time of the output state by the state transition probability matrix of the output state in the day, to obtain the length of 24 of the output state sequence in the day, and then the interval corresponding to the state of each time is uniformly sampled to complete the conversion of the state sequence to the time sequence value, to obtain the length of 24 of the time sequence value of the wind power in the day.

[0026] Preferably, the specific process of S4 is:

[0027] For typhoon weather, it is set to occur at most once a year, and two typhoon levels of ten-year and fifty-year are set, with occurrence probabilities of 10% and 2% respectively, and the typhoon occurrence time period is set to June to September, with a duration of 48 hours. It is assumed that the probability of typhoon occurrence at each time in the typhoon occurrence time period is the same, i.e. the specific occurrence time of typhoon is obtained by random sampling in June to September; the wind power output rule under typhoon weather is set as follows: when a fifty-year typhoon occurs, the wind power output is corrected to 0; when a ten-year typhoon occurs, the time sequence value of the wind power output at each time is related to the real-time maximum wind speed of the area affected by the typhoon, and when the maximum wind speed exceeds the set wind turbine cut-out wind speed, the wind power output is reduced to 0, as shown in the following formula, and if it does not exceed the cut-out wind speed, it is not affected;

[0028]

[0029] For cold wave weather, it is assumed that a cold wave occurs once a year, with the occurrence period set from December to February and a duration of 48 hours. The specific occurrence time of the cold wave is obtained through random sampling between December and February. The wind power output pattern during cold wave weather is set as follows: considering that wind turbines will shut down when they freeze at low temperatures, the time series values ​​of their wind power output are... The value is 0, as shown in the following formula.

[0030]

[0031] A wind power output scenario generation system that takes into account the impact of extreme weather, comprising:

[0032] The daily type sequence acquisition module is used to acquire historical data of wind power scenarios throughout the year and cluster them to obtain the daily type sequence of each day throughout the year.

[0033] The MCMC model building module is used to build outer MCMC models for different day types based on the daily day type sequence and the MCMC method, thereby obtaining the transition probability matrix between different day types, and to build an inner MCMC model within a single day, thereby obtaining the output state transition probability matrix within the day.

[0034] The time series value conversion module is used to combine the transition probability matrix between different day types and the intraday power output state transition probability matrix to generate the intraday power output state sequence for each day. Based on the sampling method, the intraday power output state sequence for each day is converted into the time series value of intraday wind power output.

[0035] The extreme weather input module corrects the time series values ​​of wind power output for the corresponding time period according to the set rules when extreme weather occurs, thereby obtaining a wind power output time series scenario that takes into account the impact of extreme weather.

[0036] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the wind power output scenario generation method considering the impact of extreme weather.

[0037] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method for generating wind power output scenarios considering the impact of extreme weather.

[0038] Compared with the prior art, the present invention has the following beneficial effects:

[0039] The application is based on a double-layer MCMC method, the day-to-day characteristics and the intra-day characteristics of the historical scene data are described, and the good or bad of the generated scene is whether the related index characteristics are similar to the original data, so that the day-to-day characteristics and the intra-day characteristics of the historical scene data are better inherited, and the influence of extreme weather is considered, and finally the wind power scene considering the influence of extreme weather is generated. BRIEF DESCRIPTION OF DRAWINGS

[0040] Figure 1 The scene generation method flowchart proposed in the application.

[0041] Figure 2 The autocorrelation comparison of the generated wind power scene and the original wind power scene in the application.

[0042] Figure 3 The duration curve comparison of the generated wind power scene and the original wind power scene in the application.

[0043] Figure 4 The real-time maximum wind speed when a ten-year typhoon occurs generated by sampling in the application.

[0044] Figure 5 The wind power output curve when a ten-year typhoon occurs generated by sampling in the application. DETAILED DESCRIPTION

[0045] The embodiments of the application are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar notations represent the same or similar elements or elements with the same or similar functions throughout. The embodiments described below by referring to the accompanying drawings are exemplary, only for explaining the application, and cannot be understood as a limitation of the application.

[0046] In the description of the application, it should be understood that the orientation or positional relationship indicated by the terms “center”, “longitudinal”, “transverse”, “length”, “width”, “thickness”, “upper”, “lower”, “front”, “rear”, “left”, “right”, “vertical”, “horizontal”, “top”, “bottom”, “inner”, “outer”, “clockwise”, “counterclockwise” and the like are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the application and simplifying the description, and therefore cannot be understood as indicating or implying that the devices or elements indicated must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation of the application. In addition, the terms “first” and “second” are only for the purpose of description, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features limited by “first” and “second” can explicitly or implicitly include one or more of the features. In the description of the application, the meaning of “multiple” is two or more, unless otherwise specifically limited.

[0047] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. For example, the terms "mounted", "connected" and "coupled" are used broadly and encompass both direct and indirect mounting, connecting, and coupling, as well as any other means for mechanically, electrically and / or communicatively coupling two elements. Term "and / or" includes any and all combinations of one or more of the associated listed items. Other specific terms have their ordinary meanings as used in the art. The use of "including", "comprising" or "having" and variations thereof herein is meant to encompass the items listed thereafter and equivalents thereof as well as additional items. Unless otherwise indicated, the use of relational terms, if any, such as "top", "bottom", "front", "back", "leading", "trailing" and the like are used for clarity in only the view of the accompanying drawings. The use of the term "about" in relation to a measurement means that the measurement is likely to vary by ±10% or ±5% of the stated value.

[0048] In the present application, unless specifically stated and limited otherwise, the use of the terms "on", "above", "under", "below" and the like can be used in relation to one structural feature's position relative to another structural feature. At the very least, it is within the purview of the applicant to express this type of positional relationship in any manner that conveys one item's position relative to another item as described in the claims. In addition, unless otherwise specified, the use of the terms "on", "above", "under", "below" and the like can be used in relation to one structural feature's position relative to another structural feature. At the very least, it is within the purview of the applicant to express this type of positional relationship in any manner that conveys one item's position relative to another item as described in the claims. In addition, unless otherwise specified, the use of the terms "on", "above", "under", "below" and the like can be used in relation to one structural feature's position relative to another structural feature. At the very least, it is within the purview of the applicant to express this type of positional relationship in any manner that conveys one item's position relative to another item as described in the claims.

[0049] The following disclosure provides many different embodiments, or examples, for implementing different structures of the present application. For purposes of simplicity of the present disclosure, the following description of a particular embodiment or examples will not necessarily be specifically directed to its application to the problems that were solved by the described embodiment. However, it should be understood that a particular embodiment or example can be used in the solving of any of the problems previously described, and that no particular embodiment or example is necessarily limited to that use. In addition, the present application can be used in various environments and with various technologies, and, thus, the specific nature of certain

[0050] As Figure 1The shown is the method for generating the wind power output scene considering the extreme weather effect, and the flow is as follows: firstly, based on the annual wind power scene historical data, the day type sequence of each day in the year is obtained by clustering; then, according to the clustering result of the wind power historical time sequence, an outer MCMC model is established to obtain the day type transfer probability matrix in each month; then, an inner MCMC model is established to obtain the wind power output intra-day state transfer probability matrix corresponding to each day type in each month; subsequently, the sequence scene generation link is entered, the day type sequence in each month is generated by outer MCMC sampling, and the wind power output intra-day state of each day in each month is generated by inner MCMC sampling; then, the wind power output intra-day sequence is generated by sampling the output intra-day state of each day; after the day wind power sequence of 365 days in the year is generated, the annual 8760-hour sequence is obtained by splicing in sequence; finally, considering the decision maker's preference, the extreme weather related characteristics that are focused on are set, the extreme weather occurrence is generated, the wind power time sequence scene after correction is output, and the corrected wind power time sequence scene is output.

[0051] Specifically includes the following steps:

[0052] Step one, based on the annual wind power scene historical data, the day type sequence of each day in the year is obtained by clustering.

[0053] The day type clustering is performed based on the annual wind power scene historical data. The K-means clustering method is adopted to cluster the wind power output of 365 days (a total of 8760 hours) of the annual historical data into K classes, so that each day in the 365-day day sequence has its corresponding clustering day type, thereby obtaining a day type sequence with a length of 365 days.

[0054] Step two, based on the MCMC method, the outer MCMC model of different day types is established to obtain the transfer probability matrix between different day types, and the inner MCMC model of a single intra-day of wind power is established to obtain the output state transfer probability matrix of the intra-day.

[0055] According to the statistical result of the day type sequence obtained by clustering, the inter-day transfer probability of different categories of days in the mth month (m=1, 2, …, 12) is calculated:

[0056]

[0057] In the formula, is the probability of transferring from day type i to day type j in the mth month, that is, the probability of the day type being i and the next day type being j in the mth month is and indicate the day types of adjacent two days in the mth month.

[0058] After calculating the daily transition probability of each month of all different types of days, 12 KxK dimension daily type daily transition probability matrices can be obtained, that is, each month has its corresponding daily type transition probability matrix, and the modeling process of the outer MCMC model is completed.

[0059] When establishing the inner MCMC model of the wind power output sequence, first input the wind power output data of the day type k in the mth month. If the number of days of the day type k is N k , then the dimension of the input wind power output data is N k x 24.

[0060] According to the input historical data, the maximum value and the minimum value of the wind power output of the day type k in the mth month are counted, and N states are divided respectively, and the state of the wind power output falling in the interval is defined as i (i = 1, 2, …, N).

[0061]

[0062]

[0063] The probability distribution of the state of the wind power output at the first time of the day type k in the mth month is counted, and then the state transition probability matrix between adjacent time intervals is calculated by counting the number of times of the output falling in the interval corresponding to each state.

[0064] Through the above steps, the state probability distribution of the wind power output at the first time of each month of all different types of days, and the state transition probability matrix of the wind power output between each adjacent time interval after the first time can be obtained, and each element in the matrix is as follows:

[0065]

[0066] In the formula, P m(k, i, j) represents the probability of the wind power output state of the day type k in the mth month being i at t time and j at t+1 time; and represent the wind power output state at t time and t+1 time of the day type k in the mth month, respectively.

[0067] Step three, combine the transition probability matrix between different day types and the output state transition probability matrix within the day to generate the daily output state sequence within the day. Based on the sampling method, the generated daily output state sequence within the day is converted into the time sequence value of the daily wind power output.

[0068] Based on the sampling method, for the generation of wind power output sequence, the first time output state probability distribution obtained in step 2) is sampled to generate the first time output state, and then the output state transition probability matrix in the day can be used to continue sampling to generate the output state of each time in the following time, and the length of the day is 24. The state sequence is converted to time sequence value, and the length of the day is 24. The time sequence value of the wind power output is obtained

[0069] Step four, based on the influence of extreme weather on wind power output, and then the wind power time sequence scenario considering the influence of extreme weather is obtained.

[0070] The empirical estimation of the initial pressure difference in Batts model, the translation speed of typhoon and the probability distribution of typhoon moving direction is as follows, that is, the initial pressure difference between the center and the periphery of the typhoon should obey the logarithmic normal probability distribution, the translation speed of the typhoon should obey the logarithmic normal probability distribution, and the moving direction of the typhoon should obey the bivariate normal distribution.

[0071]

[0072]

[0073]

[0074]

[0075] In the formula, ΔH is the initial pressure difference between the center and the periphery of the typhoon; v T is the translation speed of the typhoon; θ is the translation direction angle of the typhoon; μ1 is 2.9001, σ1 is 0.6274; μ2 is 2.6680, σ2 is 0.5185; μ3 is-73.3392, μ4 is-7.2084, σ3 is 22.5891, σ4 is 0.3532, and α is 0.5035.

[0076] For typhoon weather, it is set to occur at most once a year, and two typhoon levels of ten-year and fifty-year return period are considered, and the occurrence probability in a year is set to 10% and 2% respectively. Considering that typhoon usually occurs in summer, the occurrence time period is set to June to September, and the duration is 48 hours. It is assumed that the probability of typhoon occurrence at each time in the occurrence time period is the same, that is, the specific occurrence time of typhoon is obtained by random sampling in June to September. The wind power output law under typhoon weather is set as follows: when the fifty-year return period typhoon occurs, the wind power output is corrected to 0. When the ten-year return period typhoon occurs, the wind power output level is related to the real-time maximum wind speed in the area affected by the typhoon When the maximum wind speed When the fan cut-out wind speed is set, the wind power output is reduced to 0, as shown in the following formula, and if the cut-out wind speed is not exceeded, it is not affected.

[0077]

[0078] The initial air pressure difference ΔH, the typhoon translation speed v and the typhoon moving direction θ are sampled from the probability distribution empirical estimation formula T The maximum wind speed at each time can be calculated by substituting the coast line angle of the typhoon affected area

[0079]

[0080] For the cold wave weather, it is set to occur once a year, and the occurrence time period of the cold wave is considered to be from December to February, and the duration is 48 hours. It is assumed that the probability of the occurrence of the cold wave at each time in the occurrence time period is the same, that is, the specific occurrence time of the cold wave in December to February is obtained by random sampling. The wind power output law of the cold wave weather is set as follows: considering that the wind turbine will be shut down when icing at low temperature, its output is 0, as shown in the following formula.

[0081]

[0082] Step five, verify the effectiveness of the wind power scenario generation method considering the influence of extreme weather based on the example analysis.

[0083] The wind power output historical data of a province in a year is used as the original scenario, the statistical characteristics of the scenario generated by the double-layer MCMC method proposed in the application and the original scenario are compared and analyzed, and the modified wind power output characteristics considering the influence of extreme weather are analyzed.

[0084] Mean / variance: see table 1 and table 2, the monthly mean / variance of the sequence scenario generated by the double-layer MCMC method and the original scenario are very close, which shows that the method proposed in this paper can better reflect the characteristics of the original scenario.

[0085] Table 1 monthly mean of generated wind power scenario and original wind power scenario

[0086]

[0087]

[0088] Table 2 monthly variance of generated wind power scenario and original wind power scenario

[0089]

[0090] Autocorrelation: see Figure 2 ​The autocorrelation function value of the wind power sequence generated by the double-layer MCMC method is close to that of the original sequence, which indicates that the method can retain the autocorrelation of the original sequence to a high degree.

[0091] Duration curve: refer to Figure 3 It can be seen that the scene generation method can restore the wind power duration characteristics with high accuracy.

[0092] Wind power under extreme weather: wind power under typhoon weather is shown in Figure 4 and Figure 5 It is assumed that the cut-out wind speed of the wind turbine is 30 m / s, and Figure 4 It can be seen that the maximum wind speed in the typhoon-affected area is greater than the cut-out wind speed of the wind turbine 24 hours before the time in the figure. According to the description in section 2.1, the wind power should be corrected to 0 in the previous 23 hours because the wind turbine is in a shutdown state. After 24 hours, because the maximum wind speed is less than the cut-out wind speed of the wind turbine, the wind power is consistent with the uncorrected wind power, as shown in Figure 5 .

[0093] As can be seen from the above figures, the wind power scene generation method generates a wind power scene considering the influence of extreme weather on wind power output, and better inherits the statistical characteristics of historical scene data.

[0094] The following is an apparatus embodiment of the present application, which can be used to execute the method embodiment of the present application. For details not mentioned in the apparatus embodiment, please refer to the method embodiment of the present application.

[0095] In another embodiment of the present application, a wind power output scene generation system considering the influence of extreme weather is provided, which can be used to implement the wind power output scene generation method considering the influence of extreme weather. Specifically, the wind power output scene generation system considering the influence of extreme weather includes a day type sequence acquisition module, an MCMC model establishment module, a time sequence value conversion module, and an extreme weather introduction module.

[0096] The day type sequence acquisition module is used to acquire historical data of wind power scenes throughout the year, and cluster to obtain the day type sequence to which each day throughout the year belongs.

[0097] The MCMC model establishment module is used to establish an outer-layer MCMC model of different day types based on the MCMC method according to the day type sequence of each day, and then obtain a transition probability matrix between different day types, and establish an inner-layer MCMC model within a single day, and then obtain an output state transition probability matrix within the day.

[0098] The time series value conversion module is configured to combine the transition probability matrix between different day types and the output state transition probability matrix within a day to generate the output state sequence within a day for each day, and convert the output state sequence within a day for each day into the time series value of the wind power output within a day based on a sampling method.

[0099] The extreme weather bringing module is configured to correct the time series value of the wind power output in a corresponding time period according to a set rule when extreme weather occurs, and thus obtain the wind power output time series scenario considering the influence of the extreme weather.

[0100] In another embodiment of the present application, a terminal device is provided, which comprises a processor and a memory. The memory is configured to store a computer program, and the computer program comprises program instructions. The processor is configured to execute the program instructions stored in the computer storage medium. The processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The processor is the computing core and control core of the terminal, and is suitable for implementing one or more instructions, and is specifically suitable for loading and executing one or more instructions to implement a corresponding method flow or a corresponding function. The processor in the embodiment of the present application can be used for the operation of the wind power output scenario generation method considering the influence of extreme weather, which comprises the following steps: S1, obtaining the historical data of the annual wind power scenario, and clustering to obtain the day type sequence to which each day in a year belongs; S2, establishing the outer MCMC model of different day types based on the MCMC method according to the day type sequence of each day, and thus obtaining the transition probability matrix between different day types, and establishing the inner MCMC model within a single day, and thus obtaining the output state transition probability matrix within a day; S3, combining the transition probability matrix between different day types and the output state transition probability matrix within a day to generate the output state sequence within a day for each day, and converting the output state sequence within a day for each day into the time series value of the wind power output within a day based on a sampling method; and S4, correcting the time series value of the wind power output in a corresponding time period according to a set rule when extreme weather occurs, and thus obtaining the wind power output time series scenario considering the influence of the extreme weather.

[0101] In another embodiment, the present application also provides a computer readable storage medium (Memory), which is a memory device in the terminal device, used for storing programs and data. It can be understood that the computer readable storage medium herein can include the built-in storage medium in the terminal device, and of course can also include the expansion storage medium supported by the terminal device. The computer readable storage medium provides a storage space, which stores the operating system of the terminal. Moreover, one or more instructions suitable for being loaded and executed by the processor are also stored in the storage space, and the instructions can be one or more computer programs (including program codes). It should be noted that the computer readable storage medium herein can be a high-speed RAM memory, or a non-volatile memory such as at least one disk memory.

[0102] The one or more instructions stored in the computer readable storage medium can be loaded and executed by the processor to implement the corresponding steps of the method for generating a wind power output scene considering the influence of extreme weather in the above embodiments; the one or more instructions stored in the computer readable storage medium are loaded and executed by the processor to perform the following steps: S1, obtaining annual wind power scene historical data, and clustering to obtain a daily type sequence to which each day belongs; S2, based on the daily type sequence of each day, establishing an outer MCMC model of different daily types based on an MCMC method, and then obtaining a transition probability matrix between different daily types, and establishing an inner MCMC model within a single day, and then obtaining an output state transition probability matrix within the day; S3, combining the transition probability matrix between different daily types and the output state transition probability matrix within the day to generate a daily output state sequence within the day, and based on a sampling method, converting the daily output state sequence within the day into a time sequence value of the daily wind power output within the day; S4, when extreme weather occurs, correcting the time sequence value of the wind power output in the corresponding time period according to a set rule, and then obtaining a wind power output time sequence scene considering the influence of extreme weather.

[0103] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can adopt a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer usable program codes.

[0104] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flow or blocks. Figure 1 one or more flow or blocks.

[0105] These computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart block or blocks. Figure 1 one or more flow or blocks. Figure 1 one or more flow or blocks.

[0106] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flow or blocks. Figure 1 one or more flow or blocks.

[0107] It should be noted that, in the present document, the terms such as first and second, etc., are used only to distinguish one entity or operation from another, and do not necessarily require or imply these entities or operations to be in any such actual relationship or order. Moreover, the terms "comprising", "including" or any other variant thereof are intended to cover a non-exclusive inclusion, such that a process, method, article or apparatus that comprises a list of elements does not include only those elements but can also include other elements not expressly listed or inherent to such process, method, article or apparatus.

[0108] It is to be understood that the above description is intended to be illustrative, and not restrictive. Many embodiments and applications other than the examples provided would be apparent to those of skill in the art upon reading the above description. The scope of the technology should be determined, not with reference to the above description, but should instead be determined with reference to the appended claims, along with the full scope of equivalents to which such claims are entitled. The disclosures of all articles and references, including patent applications and publications, are incorporated by reference for all purposes. The omission in the foregoing description of any aspect of the subject matter disclosed herein is not a disclaimer of such subject matter, nor should it be regarded that the applicant has disclaimed any such subject matter, nor should any such omission be regarded as affecting the scope of the claimed teaching.

Claims

1. A method for generating wind power output scenarios considering the impact of extreme weather, characterized in that, The method comprises the following steps: S1, obtaining annual wind power scene historical data, and clustering to obtain a daily type sequence to which each day in a year belongs; S2, based on the daily type sequence of each day, establishing an outer MCMC model of different daily types based on an MCMC method, and then obtaining a transition probability matrix between different daily types, and establishing an inner MCMC model in a single day, and then obtaining an output state transition probability matrix in the day; S3, combining the transition probability matrix between different daily types and the output state transition probability matrix in the day to generate a daily output state sequence of each day, and converting the daily output state sequence of each day into a time sequence value of the daily wind power output based on a sampling method; S4, when an extreme weather occurs, correcting the time sequence value of the wind power output in the corresponding time period according to a set rule, and then obtaining a wind power output time sequence scene considering the influence of the extreme weather.

2. The method for generating wind power output scenarios considering the impact of extreme weather according to claim 1, characterized in that, In S1, a K-means clustering method is used to obtain the daily type sequence to which each day in a year belongs. 3.The method for generating wind power output scenarios considering extreme weather impacts according to claim 1, characterized in that, The specific process of S1 is that the wind power outputs of 365 days of the annual historical data are clustered into K categories, so that each day in the daily sequence of 365 days has its corresponding cluster daily type, thereby obtaining a daily type sequence with a length of 365 days. 4.The method of claim 1, wherein, In S2, the specific process of calculating the transition probability matrix between different daily types is as follows: according to the daily type sequence of each day, the daily inter-day transition probability of different categories of days in the mth month (m = 1, 2, …, 12) is calculated: wherein: is the probability of moving from day type i to day type j in the mth month, i.e. given that the day type in the mth month is i, the probability of the next day being of type j is and denotes the day types of the two consecutive days in the mth month; After calculating the daily inter-day transition probability of all different categories of days in each month, 12 daily type inter-day transition probability matrices with a dimension of K × K are obtained, that is, each month has a corresponding daily type transition probability matrix.

5. The method for generating wind power output scenarios considering the impact of extreme weather according to claim 4, characterized in that, In S2, the specific process of calculating the power state transition probability matrix of the day is as follows: first, input the wind power output data of the day type k in the mth month, if the number of days of the day type k is N k , then the dimension of the input wind power output data is N k ×24; According to the input historical data, the maximum value of the wind power output of the day type k in the mth month is counted and the minimum value N states are respectively divided, and the state of the wind power output falling in the interval is defined as i (i = 1, 2, …, N). The probability distribution of the state of the wind power output at the first time of the day of the type k in the mth month is counted, and then the output state transition probability matrix between adjacent time periods is calculated by counting the number of times that the output falls into the interval corresponding to each state at each time. The probability distribution of the state of the wind power output at the first time of each month of all different categories of days, and the output state transition probability matrix between each adjacent time period after the first time are counted, and each element in the matrix is as shown in the following formula: In the formula: Pm(k, i, j) represents the probability of the wind power output state being i at time t and j at time t+1 of the day type k in the mth month; and Pm(k, i) and Pm(k, j) represent the wind power output states at times t and t+1 of the day type k in the mth month, respectively.

6. The method for generating wind power output scenarios considering the impact of extreme weather according to claim 5, characterized in that, The specific process of S3 is as follows: according to the probability distribution of the state of the output at the first time, the state of the output at the first time is sampled to generate, and then the state of the output at each time is generated by sampling based on the output state transition probability matrix in the day, thereby obtaining a daily output state sequence with a length of 24. At this time, the state sequence is converted into a time sequence value by uniformly sampling in the interval corresponding to each time of the output state, thereby obtaining a daily wind power output time sequence value with a length of 24. 7.The method for generating wind power output scenarios considering extreme weather impacts according to claim 1, wherein, The specific process of S4 is as follows: For typhoon weather, set it to occur at most once a year, and set two typhoon levels of ten-year and fifty-year, with their occurrence probabilities in a year being 10% and 2% respectively, set the typhoon occurrence time period to be from June to September, and the duration to be 48 hours, assume that the probability of typhoon occurrence at each time in the occurrence time period is the same, that is, the specific occurrence time of typhoon is obtained by random sampling within the period from June to September; the wind power output law under typhoon weather is set as follows: when a fifty-year typhoon occurs, the wind power output is corrected to 0; when a ten-year typhoon occurs, the time series value of wind power output at each time is related to the real-time maximum wind speed of the area affected by the typhoon, and when the maximum wind speed exceeds the set wind turbine cut-out wind speed, the wind power output is reduced to 0, as shown in the following formula, and if it does not exceed the cut-out wind speed, it is not affected; For cold wave weather, it is assumed that a cold wave occurs once a year, with the occurrence period set from December to February and a duration of 48 hours. The specific occurrence time of the cold wave is obtained through random sampling between December and February. The wind power output pattern during cold wave weather is set as follows: considering that wind turbines will shut down when they freeze at low temperatures, the time series values ​​of their wind power output are... The value is 0, as shown in the following formula: 8.A system for generating wind power output scenarios considering the impact of extreme weather, characterized in that, It comprises: a daily type sequence acquisition module, configured to obtain annual wind power scene historical data, and cluster to obtain a daily type sequence to which each day in a year belongs; an MCMC model establishment module, configured to establish an outer MCMC model of different daily types based on an MCMC method according to the daily type sequence of each day, and then obtain a transition probability matrix between different daily types, and establish an inner MCMC model in a single day, and then obtain an output state transition probability matrix in the day; and a time series value transformation module, configured to combine the transition probability matrix between different day types and the intra-day output state transition probability matrix to generate an intra-day output state sequence of each day, and transform the intra-day output state sequence of each day into time series values of the intra-day wind power output based on a sampling method; an extreme weather bringing module, configured to correct the time series values of the wind power output in a corresponding time period according to a set rule when extreme weather occurs, and thus obtain a wind power output time series scenario considering the influence of the extreme weather.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor implements the steps of the method for generating a wind power output scenario considering the influence of extreme weather according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 9. The computer program implements the steps of the method for generating a wind power output scenario considering the influence of extreme weather according to any one of claims 1 to 7 when executed by the processor.

Images