New energy typical time sequence scene generation method, new energy typical time sequence scene extraction method, equipment and medium

Abstract

The invention discloses a new energy typical time sequence scene generation and scene extraction method, and the method comprises the steps: obtaining a new energy output fluctuation range based on historical similar day data, carrying out the sampling probability interval correction of error sampling according to the new energy output fluctuation range, and generating a new energy time sequence scene, comprising the steps of new energy fluctuation range determination, new energy output modeling and time sequence scene sampling based on sampling probability interval correction. Performing reduction on the time sequence scene by using a k-medios method to obtain a scene set including a typical scene and an extreme scene; the scene generation quality is evaluated according to the scene coverage rate, the scene width, the correlation approximation degree and the climbing similarity index; establishing a time sequence scene state matrix and a power deviation matrix, analyzing the deviation between the generated scene and the predicted power, extracting an information matrix according to the state matrix and the deviation matrix scene, and carrying out typical time sequence scene extraction; according to the method, safety and economy risks caused by new energy output volatility and uncertainty are reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of generating and extracting typical time-series scenes of new energy, and more specifically, to a method, device and medium for generating and extracting scenes of new energy. Background Art

[0002] Renewable energy such as wind energy and solar energy has the characteristics of randomness, volatility and intermittency, and the uncertainty of its output has brought challenges to the planning and dispatching of power systems. Through the new energy scenario generation technology, a series of representative future scenarios can be generated based on historical data and prediction models. These scenarios can reflect the possible range of changes in the output of new energy and its probability distribution, providing a rich information basis for planners and dispatchers of power systems, helping them to formulate more scientific and reasonable planning and dispatching plans to cope with the uncertainty of new energy output. . Through in-depth analysis of new energy scenarios, key indicators such as the supply and demand balance, spare capacity requirements, and system stability of the power system under different scenarios can also be evaluated, thereby identifying potential risk points and weak links. It is of great significance for the optimal design and safe and stable operation of the power system, and can provide strong support for decision makers to ensure that the power system can still maintain reliable operation when a high proportion of new energy is connected.

[0003] The time series scenario method is a commonly used technical means for uncertainty analysis of power systems and is widely used in business areas such as power balance analysis, new energy consumption assessment, and optimized scheduling. The time series scenario can provide grid operation boundary constraints for the above businesses, effectively improving the reliability and flexibility of the actual operation of the grid. Therefore, how to construct a limited number of scenarios to cover various grid operation conditions, while ensuring the effectiveness of relevant analysis and decision-making business results while reducing the amount of problem analysis and calculation, is a key problem that the time series scenario method needs to solve urgently.

[0004] There are at least the following technical problems in the above-disclosed technical solution: the previous generation and extraction of new energy scenes often adopts a random sampling method, which does not take into account the temporal correlation of new energy, resulting in no fluctuation or drastic fluctuation in sampling before and after.

[0005] In view of the above problems, the present invention proposes a solution. Summary of the invention

[0006] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present invention provide a method, device and medium for generating and extracting typical time series scenarios of new energy, and solve the problems of low accuracy and weak time series correlation of new energy prediction scenarios through a method for generating typical time series scenarios of new energy based on sampling probability interval correction.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] The method for generating and extracting typical time-series scenarios of new energy sources includes the following steps:

[0009] Based on historical similar daily data, the fluctuation range of new energy output is obtained, and the sampling probability interval of error sampling is corrected according to the fluctuation range of new energy output to generate a new energy time series scenario; the generation of the new energy time series scenario includes: determining the fluctuation range of new energy, modeling new energy output, and sampling time series scenarios based on the sampling probability interval correction;

[0010] Use the k-mediods method to simplify the time series scenarios and obtain a scenario set that includes typical scenarios and extreme scenarios;

[0011] The quality of scene generation is evaluated based on scene coverage, scene width, correlation approximation, and slope similarity indicators;

[0012] Establish a time series scenario state matrix and a power deviation matrix, analyze the deviation between the generated scenario and the predicted power, extract the information matrix based on the state matrix and the deviation matrix scenario, and carry out typical time series scenario extraction.

[0013] Furthermore, the simplification of the time series scenario includes:

[0014] Added time-series scene grouping;

[0015] Use k-mediods method to reduce time series scenarios.

[0016] Furthermore, the typical time series scene extraction includes:

[0017] Use the time series scenario power deviation matrix to store the difference between the power of the new energy generation time series scenario and the power of the new energy prediction scenario;

[0018] Generate a new energy time series scenario state matrix according to the deviation of each element in the deviation matrix from the threshold;

[0019] According to the new energy time series scenario state matrix, the typical new energy time series scenario extraction information matrix is ​​obtained, and then the new energy typical time series scenario is extracted.

[0020] Furthermore, the obtaining of the fluctuation range of new energy output based on historical similar day data includes:

[0021] Based on the weather forecast information for the next day, the actual operation data of new energy on similar weather days in history are collected, and the fluctuation curve of new energy output data is analyzed to obtain the fluctuation range of new energy output in each adjacent period on similar weather days; the calculation formula for the fluctuation of new energy output before and after is as follows:

[0022] ΔP t =P t+T -Pt

[0023] Where: ΔP t is the output fluctuation value of the adjacent moments before and after the interval T; T is the time interval; P t is the output of the new energy at time t;

[0024] The new energy output fluctuation set A is:

[0025]

[0026] Where: k t→t+1.dn , k t→t+1.up are the lower and upper limits of the power fluctuation of new energy at adjacent sampling moments; t is the sampling moment; ΔP t.q is the power fluctuation from time t to time t+1 on the q similar day; S ander For similar day collection.

[0027] Furthermore, the new energy output modeling includes:

[0028] Based on historical forecast data and actual operation data of new energy, a new energy forecast error model is established:

[0029] P t =P t,predict +ξ t

[0030] Where: P t,predict is the predicted power of the new energy at time t; t It is the prediction error of new energy output.

[0031] Furthermore, the time series scene sampling based on sampling probability interval correction includes:

[0032] The Latin hypercube sampling (LHS) method is used to extract the initial prediction error values ​​of all time series scenarios "vertically", and the prediction values ​​are superimposed to calculate the power of all time series scenarios at the first moment;

[0033] For each time series scenario, the sampling interval is corrected by considering the fluctuation range of renewable energy output at adjacent moments “horizontally”.

[0034] Furthermore, the scene coverage, scene width, correlation approximation, and climbing similarity indicators are:

[0035] Scene coverage P cover Indicates the coverage of the generated scenario power value to the actual scenario power value:

[0036]

[0037] Where: B is a 0-1 variable. If the actual scene power value is between the maximum and minimum values ​​of the generated scene, then B = 1, otherwise B = 0;

[0038] 2) Scene width P width Reflects the maximum power range between different scenarios in the generated scenario set:

[0039]

[0040] Where: P s,t ,P t,t are the active output values ​​of the generated time sequence scenario s at time t; S is the generated scenario set;

[0041] 3) Correlation approximation P corr Reflects the approximation degree of the correlation between the generated scene and the actual data at any time:

[0042] P corr =|s real,t,t+d -s s,t,t+d |

[0043] Where: s real,t,t+d ,s s,t,t+d are the correlation coefficients between the actual scene and the generated scene at any interval d;

[0044] 4) Climbing similarity P clim Reflects the similarity between the generated scene climbing situation and the actual scene climbing situation:

[0045]

[0046] Where: Δ real,t,t+1 ,Δ s,t,t+1 They are the climbing power from time t to time t+1 in the actual scenario and the climbing power from time t to time t+1 in the sth generated scenario.

[0047] Furthermore, the method for extracting typical time series scenes is:

[0048] Use the time series scenario power deviation matrix to store the difference between the power of the new energy generation time series scenario and the power of the new energy prediction scenario:

[0049] ΔP=P sce,out -P p ' re,out

[0050]

[0051] Where: ΔP is the power deviation matrix of the time series scene; P sce,out is the total sum matrix of new energy output for the generated time series scenario; Pp ' re,out Because P sce,out The expanded total matrix of new energy output forecast;

[0052] The time sequence scene state matrix includes:

[0053]

[0054] Where: Matrix element S is a 0-1 variable, representing the power deviation state quantity of time sequence scenario s at time c;

[0055] Set the threshold value ξ for the power of the new energy time series scene to deviate from the predicted scene power renew,pos ,ξ renew,neg , respectively represent the new energy positive deviation threshold and the new energy negative deviation threshold:

[0056]

[0057] Where: p is the scene type, ΔP st and S st They are the power deviation matrix elements and deviation state matrix elements of new energy timing scenarios respectively;

[0058] Perform product operation on the state matrix of new energy time series scenario and the transposed matrix of load time series scenario state matrix to obtain the typical source-load time series scenario extraction information matrix Y:

[0059]

[0060] The time period threshold ξ is set, and the new energy time series scenario m that satisfies Y>ξ is extracted as the new energy typical time series scenario.

[0061] A new energy typical time sequence scene generation and scene extraction device comprises the following steps:

[0062] A new energy time series scenario generation module is used to obtain the new energy output fluctuation range based on historical similar day data, perform error sampling sampling probability interval correction according to the new energy output fluctuation range, and generate a new energy time series scenario; the generation of the new energy time series scenario includes: new energy fluctuation range determination, new energy output modeling and time series scenario sampling based on sampling probability interval correction;

[0063] The scenario set acquisition module is used to simplify the time series scenarios using the k-mediods method to obtain a scenario set containing typical scenarios and extreme scenarios;

[0064] The scene generation quality evaluation module is used to evaluate the quality of scene generation based on scene coverage, scene width, correlation similarity, and climbing similarity indicators;

[0065] The typical time series scene extraction module is used to establish a time series scene state matrix and a power deviation matrix, analyze the deviation between the generated scene and the predicted power, extract the information matrix based on the state matrix and the deviation matrix scene, and carry out typical time series scene extraction.

[0066] A computing device comprising:

[0067] one or more processing units;

[0068] A storage unit for storing one or more programs,

[0069] Wherein, when the one or more programs are executed by the one or more processing units, the one or more processing units execute the new energy typical time series scene generation and scene extraction method as described above.

[0070] A computer-readable storage medium having a non-volatile program code executable by a processor, wherein when the computer program is executed by the processor, the steps of the above-mentioned new energy typical time sequence scene generation and scene extraction method are implemented.

[0071] The method and device for generating and extracting typical time-series scenes of new energy of the present invention have the following beneficial effects:

[0072] 1. The present invention comprehensively evaluates the impact of various factors on the generation of new energy scenarios by considering the impact of time series correlation, which can improve the accuracy of new energy scenario prediction and ensure the stability and reliability of the operation and dispatch of the power system under the background of high proportion of new energy access;

[0073] 2. Through multi-faceted analysis, the present invention can accurately identify typical scenarios and extreme scenarios, thereby achieving optimal prediction of new energy output scenarios, improving the economy and operating efficiency of the power system, and reducing operating costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Figure 1 A schematic diagram of a flow chart of the time series scene generation based on sampling probability interval correction of the present invention;

[0075] Figure 2 A schematic diagram of the time series scene sampling generation process of the present invention;

[0076] Figure 3 This is a functional module diagram of the new energy typical time sequence scenario generation and extraction device of the present invention. DETAILED DESCRIPTION

[0077] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0078] Generation of new energy time series scenarios: The new energy output time series scenario can be regarded as a random process X which can be represented by a set of N-dimensional random variables:

[0079]

[0080] Where x is the random variable of renewable energy output at each moment. By performing multiple time series sampling on renewable energy output, we can obtain a set of renewable energy output time series scenarios.

[0081] The generation process of new energy uncertain time series scenarios based on sampling probability interval correction is as follows: Figure 1 As shown, it can be divided into three steps: determining the fluctuation range of new energy, output modeling, and generating time series scene sampling.

[0082] New energy fluctuation range is determined:

[0083] Based on the weather forecast information for the next day, the actual operation data of new energy on similar weather days in history are collected, and the fluctuation curve of new energy output data is analyzed to obtain the fluctuation range of new energy output in each adjacent period on similar weather days. The calculation formula for the fluctuation of new energy output before and after is as follows:

[0084] ΔP t =P t+T -P t

[0085] Where: ΔP t is the output fluctuation value of the adjacent moments before and after the interval T; T is the time interval; P t The output of new energy at time t.

[0086] The new energy output fluctuation set A is

[0087]

[0088] Where: k t→t+1.dn , k t→t+1.up are the lower and upper limits of the power fluctuation of new energy at adjacent sampling moments; t is the sampling moment; ΔP t.q is the power fluctuation from time t to time t+1 on the q similar day; S ander For similar day collection.

[0089] New energy output modeling: Based on historical forecast data and actual operation data of new energy, a new energy forecast error model is established

[0090] P t =P t,predict +ξ t

[0091] Where: P t,predict is the predicted power of the new energy at time t; t It is the prediction error of new energy output;

[0092] Time series scene sampling based on sampling probability interval correction:

[0093] 1) Use the Latin hypercube sampling (LHS) method to extract the initial prediction error values ​​of all time series scenarios "vertically", and superimpose the prediction values ​​to calculate the power of the first moment of all time series scenarios; for each time series scenario, consider the output fluctuation range of new energy at adjacent moments "horizontally" and correct the sampling interval.

[0094] Assume that N time series scenarios need to be generated. Based on the cumulative distribution of power prediction error corresponding to the first moment of new energy, use LHS to extract N prediction error values, and then superimpose the output prediction values ​​to obtain the power sampling value corresponding to the first moment of each scenario.

[0095] 2) Sample the prediction error for each time series scenario s moment by moment. Considering the historical volatility of new energy, the power at adjacent moments must meet the following requirements:

[0096] P s,t+1,sample -P s,t,sample ∈[k t→t+1,dn ,k t→t+1,up ]

[0097] Where: P s,t+1,sample , P s,t,sample are respectively the power sampling values ​​of the time series scenario s at time t+1.

[0098] Before sampling the prediction error, the sampling interval is corrected first. Under the premise that the power sampling value at time t is known, the new energy power prediction value determines the power prediction error sampling range at time t+1:

[0099]

[0100] Where: P s,t+1,error is the sample value of the prediction error of the new energy power of the time series scenario s at time t+1; P s,Δ,t→t+1 is the difference between the predicted values ​​of new energy power of time series scenario s at two moments.

[0101] Ps,t+1,error Substituting into the prediction error cumulative distribution function F, we get the corresponding probability interval [c1, c2], that is:

[0102]

[0103] In the formula: c1 is the lower limit of the probability interval; c2 is the upper limit of the probability interval. The sampling probability interval is adjusted from [0, 1] to [c1, c2], and random sampling is performed in the interval [c1, c2] to obtain the new energy power prediction error P at the sampling time t+1 s,t+1,error , superimposed predicted value P t+1,predict Then, the new energy power sampling value P of the time series scenario s at time t+1 considering the historical fluctuation characteristics of new energy can be obtained. s,t+1,predict ;

[0104] 3) Repeat step 2) until the power sampling at all times of all time series scenarios is completed.

[0105] Construction of scene coverage, scene width, correlation approximation, and climbing similarity indicators:

[0106] 1) Scene coverage P cover Indicates the coverage of the generated scenario power value to the actual scenario power value.

[0107]

[0108] Wherein: B is a 0-1 variable. If the actual scene power value is between the maximum and minimum values ​​of the generated scene, then B=1, otherwise B=0.

[0109] 2) Scene width P width Reflects the maximum power range between different scenarios in the generated scenario set.

[0110]

[0111] Where: P s,t ,P t,t are the generated time sequence scenario s and the active output value at time t respectively; S is the generated scenario set.

[0112] 3) Correlation approximation P corr Reflects the degree of correlation between the generated scenario and the actual data at any time.

[0113] P corr =|s real,t,t+d -s s,t,t+d |

[0114] Where: s real,t,t+d ,s s,t,t+d are the correlation coefficients between the actual scene and the generated scene at any interval d.

[0115] 4) Climbing similarity

[0116] Climbing similarity P clim Reflects the similarity between the climbing conditions of the generated scenario and the climbing conditions of the actual scenario.

[0117]

[0118] Where: Δ real,t,t+1 ,Δ s,t,t+1 are the climbing power from time t to time t+1 in the actual scenario and the climbing power from time t to time t+1 in the sth generated scenario respectively;

[0119] Time series scenario power deviation matrix: Use the time series scenario power deviation matrix to store the difference between the power of the new energy generation time series scenario and the power of the new energy prediction scenario.

[0120] ΔP=P sce,out -P p ' re,out

[0121]

[0122] Where: ΔP is the power deviation matrix of the time series scene; P sce,out is the total sum matrix of new energy output for the generated time series scenario; P p ' re,out Because P sce,out The expanded total matrix of new energy output forecast;

[0123] Timing scenario state matrix:

[0124]

[0125] Where: the matrix element S is a 0-1 variable, which represents the power deviation state quantity of the time sequence scenario s at time c.

[0126] Set the threshold value ξ for the power of the new energy time series scene to deviate from the predicted scene power renew,pos ,ξ renew,neg , respectively represent the new energy positive deviation threshold and the new energy negative deviation threshold.

[0127]

[0128] Where: p is the scene type, ΔP st and S st They are respectively the power deviation matrix elements and deviation state matrix elements of new energy timing scenarios.

[0129] Extraction of typical time series scenarios of new energy: Multiply the state matrix of new energy time series scenarios and the transposed matrix of load time series scenarios to obtain the typical source-load time series scenario extraction information matrix Y:

[0130]

[0131] The time period threshold ξ is set, and the new energy time series scenario m that satisfies Y>ξ is extracted as the new energy typical time series scenario.

[0132] The above is an introduction to the method embodiment. The following is a further explanation of the scheme described in this application through an apparatus embodiment.

[0133] Figure 3 FIG. 4 shows a block diagram of a new energy typical time sequence scene generation and extraction device according to an embodiment of the present application, as shown in FIG. Figure 3 As shown, the device comprises:

[0134] A new energy time series scenario generation module 310 is used to obtain a new energy output fluctuation range based on historical similar day data; perform error sampling sampling probability interval correction according to the new energy output fluctuation range to generate a new energy time series scenario;

[0135] The new energy scenario simplification module 320 is used to simplify the time series scenarios using the k-mediods method to obtain a scenario set including typical scenarios and extreme scenarios, and evaluate the quality of scenario generation based on indicators such as scenario coverage, scenario width, correlation approximation, and climbing similarity;

[0136] The new energy time series scenario extraction module 330 is used to establish a time series scenario state matrix and a power deviation matrix to analyze the deviation between the generated scenario and the predicted power, extract the information matrix based on the state matrix and the deviation matrix scenario, and carry out typical time series scenario extraction;

[0137] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0138] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0139] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0140] A computing device is also provided, comprising:

[0141] one or more processing units;

[0142] A storage unit for storing one or more programs,

[0143] Among them, when the one or more programs are executed by the one or more processing units, the one or more processing units execute the new energy typical time series scenario generation and scenario extraction method in this embodiment; it should be noted that the computing device may include but is not limited to a processing unit and a storage unit; those skilled in the art can understand that the computing device including a processing unit and a storage unit does not constitute a limitation on the computing device, and may include more components, or a combination of certain components, or different components. For example, the computing device may also include input and output devices, network access devices, buses, etc.

[0144] A computer-readable storage medium having a non-volatile program code executable by a processor, wherein the computer program, when executed by the processor, implements the steps of the method for generating typical time-series scenes and extracting scenes of new energy in this embodiment; it should be noted that the readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof; the program contained on the readable medium may be transmitted by any appropriate medium, including, but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination thereof. For example, the program code for performing the operation of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and also conventional procedural programming languages ​​such as C language or similar programming languages. The program code may be executed entirely on a user computing device, partially on a user device, as an independent software package, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0145] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0146] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for generating and extracting typical time-series scenarios of new energy, characterized in that: The steps include: Based on historical similar daily data, the fluctuation range of new energy output is obtained, and the sampling probability interval of error sampling is corrected according to the fluctuation range of new energy output to generate a new energy time series scenario; The generation of new energy time series scenarios includes: determining the new energy fluctuation range, new energy output modeling, and sampling time series scenarios based on sampling probability interval correction; Use the k-mediods method to simplify the time series scenarios and obtain a scenario set that includes typical scenarios and extreme scenarios; The quality of scene generation is evaluated based on scene coverage, scene width, correlation approximation, and slope similarity indicators; Establish a time series scenario state matrix and a power deviation matrix, analyze the deviation between the generated scenario and the predicted power, extract the information matrix based on the state matrix and the deviation matrix scenario, and carry out typical time series scenario extraction.

2. The method for generating and extracting typical time-series scenarios of new energy according to claim 1, characterized in that: The simplification of the time series scenario includes Added time series scene grouping; Use k-mediods method to reduce time series scenarios.

3. The method for generating and extracting typical time-series scenarios of new energy according to claim 1, characterized in that: The typical time series scene extraction includes: Use the time series scenario power deviation matrix to store the difference between the power of the new energy generation time series scenario and the power of the new energy prediction scenario; Generate a new energy time series scenario state matrix according to the deviation of each element in the deviation matrix from the threshold; According to the new energy time series scenario state matrix, the typical new energy time series scenario extraction information matrix is ​​obtained, and then the new energy typical time series scenario is extracted.

4. The method for generating and extracting typical time-series scenes of new energy according to claim 1, characterized in that: The new energy output fluctuation range obtained based on historical similar day data includes: Based on the weather forecast information for the next day, the actual operation data of new energy on similar weather days in history are collected, and the fluctuation curve of new energy output data is analyzed to obtain the fluctuation range of new energy output in each adjacent period on similar weather days; the calculation formula for the fluctuation of new energy output before and after is as follows: ΔP t =P t+T -P t Where: ΔP t is the output fluctuation value of the adjacent moments before and after the interval T; T is the time interval; P t is the output of the new energy at time t; The new energy output fluctuation set A is: Where: k t→t+1.dn , k t→t+1.up are the lower and upper limits of the power fluctuation of new energy at adjacent sampling moments; t is the sampling moment; ΔP t.q is the power fluctuation from time t to time t+1 on the q similar day; S ander For similar day collection.

5. The method for generating and extracting typical time-series scenes of new energy according to claim 1, characterized in that: The new energy output modeling includes: Based on historical forecast data and actual operation data of new energy, a new energy forecast error model is established: P t =P t,predict +ξ t Where: P t,predict is the predicted power of the new energy at time t; t It is the prediction error of new energy output.

6. The method for generating and extracting typical time-series scenes of new energy according to claim 1, characterized in that: The time series scene sampling based on sampling probability interval correction includes: The Latin hypercube sampling (LHS) method is used to extract the initial prediction error values ​​of all time series scenarios "vertically", and the predicted values ​​are superimposed to calculate the power of all time series scenarios at the first moment; For each time series scenario, the sampling interval is corrected by considering the fluctuation range of renewable energy output at adjacent moments "horizontally" moment by moment.

7. The method for generating and extracting typical time-series scenarios of new energy according to claim 1, characterized in that: The scene coverage, scene width, correlation approximation, and climbing similarity indicators are: Scene coverage P cover Indicates the coverage of the generated scenario power value to the actual scenario power value: Where: B is a 0-1 variable. If the actual scene power value is between the maximum and minimum values ​​of the generated scene, then B = 1, otherwise B = 0; 2) Scene width P width Reflects the maximum power range between different scenarios in the generated scenario set: Where: P s,t ,P t,t are the active output values ​​of the generated time sequence scenario s at time t; S is the generated scenario set; 3) Correlation approximation P corr Reflects the approximation degree of correlation between the generated scene and the actual data at any time: P corr =|s real,t,t+d -s s,t,t+d | Where: s real,t,t+d ,s s,t,t+d are the correlation coefficients between the actual scene and the generated scene at any interval d; 4) Climbing similarity P clim Reflects the similarity between the generated scene climbing situation and the actual scene climbing situation: Where: Δ real,t,t+1 ,Δ s,t,t+1 They are the climbing power from time t to time t+1 in the actual scenario and the climbing power from time t to time t+1 in the sth generated scenario.

8. The method for generating and extracting typical time-series scenes of new energy according to claim 1, characterized in that: The method for extracting typical time series scenes is: Use the time series scenario power deviation matrix to store the difference between the power of the new energy generation time series scenario and the power of the new energy prediction scenario: ΔP=P sce,out -P p ′ re,out Where: ΔP is the power deviation matrix of the time series scene; P sce,out is the total sum matrix of new energy output for the generated time series scenario; P p ' re,out Because P sce,out The expanded total matrix of new energy output forecast; The time sequence scene state matrix includes: Where: the matrix element S is a 0-1 variable, which represents the power deviation state quantity of the time sequence scenario s at time c; Set the threshold value ξ for the power of the new energy time series scene to deviate from the predicted scene power renew,pos ,ξ renew,neg , respectively represent the new energy positive deviation threshold and the new energy negative deviation threshold: Where: p is the scene type, ΔP st and S st They are the power deviation matrix elements and deviation state matrix elements of new energy timing scenarios respectively; Perform product operation on the state matrix of new energy time series scenario and the transposed matrix of load time series scenario state matrix to obtain the typical source-load time series scenario extraction information matrix Y: The time period threshold ξ is set, and the new energy time series scenario m that satisfies Y>ξ is extracted as the new energy typical time series scenario.

9. A device for generating and extracting typical time-series scenes of new energy, characterized in that: The steps include: A new energy time series scenario generation module is used to obtain the new energy output fluctuation range based on historical similar day data, perform sampling probability interval correction for error sampling according to the new energy output fluctuation range, and generate a new energy time series scenario; The generation of new energy time series scenarios includes: determining the new energy fluctuation range, new energy output modeling, and sampling time series scenarios based on sampling probability interval correction; The scenario set acquisition module is used to simplify the time series scenarios using the k-mediods method to obtain a scenario set containing typical scenarios and extreme scenarios; The scene generation quality evaluation module is used to evaluate the quality of scene generation based on scene coverage, scene width, correlation similarity, and climbing similarity indicators; The typical time series scene extraction module is used to establish a time series scene state matrix and a power deviation matrix, analyze the deviation between the generated scene and the predicted power, extract the information matrix based on the state matrix and the deviation matrix scene, and carry out typical time series scene extraction.

10. A computer-readable storage medium having a non-volatile program code executable by a processor, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images