Resource uncertainty wind-solar-storage multi-energy complementary installation configuration method and system

Abstract

The invention discloses a resource uncertainty wind-solar-storage multi-energy complementary installation configuration method and system, and relates to the technical field of optimal configuration and operation management of a power system, and the method comprises the steps: collecting meteorological data and an electrical load historical sequence in a planning region, determining a time period and a step length of simulation according to the features of the historical data, and carrying out the simulation; the method comprises the steps of constructing a historical data set, performing seasonal Gaussian mixture distribution simulation on illumination and wind speed, generating a periodic wind speed simulation scene, performing scene reduction through a back substitution elimination method, obtaining a scene set, constructing a wind and light combined scene, determining wind and light installation alternative schemes, and calculating wind and light output. And an optimal wind and light energy storage installation configuration scheme is determined through scene simulation. By optimizing the energy storage configuration scheme and combining scene simulation, the consumption proportion and economic benefits of the system are improved, the method has remarkable advantages in the aspects of optimizing resource configuration and improving system operation efficiency, and a new technical path is provided for development of the wind-solar-storage multi-energy complementary system.

Description

Technical Field

[0001] The present invention relates to the technical field of optimal configuration and operation management of power systems, and in particular to a method and system for configuring wind, solar, and storage multi-energy complementary installed capacity with resource uncertainty. Background Art

[0002] Renewable resources such as wind and solar power have significant randomness and volatility characteristics. The multi-energy complementary system of wind, solar and other power sources with storage has become one of the important means to promote the consumption of renewable energy and ensure the safe operation of power grids under high penetration rates. In terms of installed capacity planning of wind, solar and storage multi-energy complementary systems, the target technology mostly determines the installed capacity based on historical measured wind and solar data and load data, and insufficiently considers the uncertainty of wind and solar resources. It is impossible to fully consider the random scenarios of new energy, and it is difficult to achieve the expected results in long-term operation.

[0003] However, the existing installation configuration methods of wind, solar and storage multi-energy complementary systems have certain limitations. First, when processing meteorological data and historical series of electricity load, traditional methods often ignore the seasonal characteristics of data, resulting in deviations between the simulated scenarios and the actual situation. Second, the existing scenario simulation technology fails to effectively consider the uncertainty of resources, making it impossible for the generated scenario set to accurately reflect the various possibilities in actual operation. In addition, when determining the optimal installation configuration plan, the existing technology lacks the optimal configuration of the energy storage system, resulting in the system may not achieve the expected absorption ratio and economic benefits in actual operation. Summary of the invention

[0004] In view of the above-mentioned existing problems, the present invention provides a method and system for configuring wind, solar and storage multi-energy complementary installed capacity with resource uncertainty, so as to solve the problems in the prior art that the simulated scenarios deviate from the actual situation, the scenario collection cannot accurately reflect the various possibilities in actual operation, and cannot achieve the expected absorption ratio and economic benefits.

[0005] In order to solve the above technical problems, a wind-solar-storage multi-energy complementary installed capacity configuration method with resource uncertainty is proposed, including:

[0006] Collect meteorological data and historical series of electricity load in the planning area, and determine the simulation time period and step size based on the characteristics of historical data to construct a historical data set; simulate seasonal Gaussian mixture distribution of light and wind speed, generate periodic wind speed simulation scenarios, and reduce the scenarios through back-substitution elimination to obtain scenario sets; construct wind-solar combination scenarios, determine alternative wind and solar installation plans, calculate wind and solar output, and determine the optimal wind, solar and energy storage installation configuration plan through scenario simulation.

[0007] As a preferred solution of the resource uncertainty wind, solar and storage multi-energy complementary installed capacity configuration method described in the present invention, the meteorological data includes collecting wind speed data, light data and temperature data in the planning area.

[0008] The electricity load history sequence includes the load data, load characteristics and load change trends collected in the planning area; the load characteristics include the maximum value, minimum value, average value and the time when the load peak occurs; the load change trend includes the daily load curve, weekly load curve and seasonal change curve.

[0009] As a preferred scheme of the resource uncertainty wind, solar and storage multi-energy complementary installed capacity configuration method described in the present invention, wherein: the construction of the historical data set includes determining the time period and step length of the random simulation according to the characteristics of the historical data, and constructing the data set of the wind speed and light historical data according to the sequence length.

[0010] As a preferred scheme of the resource uncertainty wind, solar and storage multi-energy complementary installed capacity configuration method described in the present invention, the seasonal Gaussian mixed distribution simulation includes performing seasonal Gaussian mixed distribution simulation on light and wind speed to generate a set of random simulation scenarios respectively.

[0011] The scenario set for generating random simulation includes determining the autocorrelation order D, constructing a data set for seasonal Gaussian mixture simulation, constructing a Gaussian mixture joint distribution and conditional distribution model for the j-th subset in each cycle, determining the parameters of the Gaussian mixture model using a K-means clustering method, initializing and generating wind speed scenarios, and repeating the wind speed assignment process until the number of cycles reaches the required number of cycles.

[0012] The formula for constructing the Gaussian mixture joint distribution and conditional distribution model is expressed as:

[0013]

[0014] in, is the joint distribution function, x( 1 )for That is, the column vector of wind speed at the D moments before the current moment j, x (2) v i,j That is, the wind speed observation value of the i-th time series at the j-th moment, is the conditional distribution function, p(x (1) ,x (2) ) is the conditional probability density function, p(x (2) ∣x (1) ) is the joint probability density function of the Gaussian mixture model, K is the hyperparameter of the Gaussian mixture model, π k is the regression coefficient of the kth Gaussian component, and is the mean of the kth Gaussian model, and is the mean square error of the k-th Gaussian model, and k is the variable index.

[0015] The K-means clustering method includes determining a hyperparameter K, dividing the data set into K clusters, taking the center of each cluster as the initial mean of each component in the Gaussian mixture model, calculating the difference between the data points in each cluster and the cluster center, i.e., calculating the covariance moment, calculating the proportion of the number of samples in each cluster to the total number of samples, i.e., the weight, and adjusting the K value to achieve the best simulation effect.

[0016] Creating a wind speed simulation scenario includes initializing the wind speed of the first D moments of the first cycle using the average wind speed value of the cycle, and randomly generating the wind speed at each moment starting from the first moment of the first cycle. During the generation process, if the current moment is less than D, the multi-cycle average wind speed is used as the initial value; if the current moment is equal to or greater than D, the wind speed value of the previous moment is used; and a uniformly distributed random number is randomly generated and input into the conditional Gaussian mixture distribution model to determine the wind speed at each moment, and the random generation process is continued until the wind speeds of the N time periods of the first cycle are generated, the cycle counter is increased by 1, and the wind speed assignment and generation steps are repeated until the full number of cycles are simulated.

[0017] As a preferred scheme of the resource uncertainty wind, solar and storage multi-energy complementary installed capacity configuration method described in the present invention, wherein: the obtaining of the scene set includes simulating the seasonal Gaussian mixed distribution of light and wind speed, generating a periodic wind speed simulation scene, and reducing the scene by back-substitution elimination method to obtain the scene set.

[0018] The back-elimination method includes determining the number of typical scenes, comparing all scenes in the scene set pairwise, calculating the Euclidean probability distance, finding the two scenes with the smallest distance, deleting one scene, adding the probability of the deleted scene to the retained scene, and updating the scene set until the number of scenes remaining in the scene set reaches the number of typical scenes.

[0019] The formula for calculating the Euclidean probability distance is:

[0020]

[0021] Among them, d i,j is the Euclidean distance between the i-th and j-th scenes in the scene set, i, j and k are variable indices, and For the i-th and j-th scenes, p i and p j is the occurrence probability of the i-th and j-th scenes, and n is the sequence length of each scene.

[0022] As a preferred scheme of the resource uncertainty wind, solar and storage multi-energy complementary installed capacity configuration method described in the present invention, the calculation of wind and solar output includes establishing a regression prediction model of temperature to wind speed and light through historical data, constructing a wind and solar combination scenario, determining alternative wind and solar installation plans, and calculating wind and solar output.

[0023] The regression prediction model formula is expressed as:

[0024]

[0025] Among them, f T is the regression prediction model, is the temperature at time t, r t is the light intensity at time t, v t is the wind speed at time t.

[0026] The formula for calculating wind and solar power output is:

[0027]

[0028] in, is the wind power output at time t, is the photovoltaic output at time t, is the installed capacity of wind energy, is the installed capacity of photovoltaic power generation, ν t is the wind speed at the wind turbine during period t, ν in is the wind turbine cut-in wind speed, ν out is the wind turbine cut-out wind speed, ν rated is the rated wind speed of the wind turbine, R stc is the solar radiation intensity under standard test conditions, r t is the solar radiation intensity during period t, T stc is the temperature under standard test conditions, α p is the temperature-power conversion coefficient, T t is the solar panel temperature, T NOC is the rated operating temperature of the photovoltaic cell, is the temperature at time t; the standard test conditions are that the light intensity is 1000 watts per square meter, the temperature is 25 degrees Celsius, and the atmospheric pressure is one standard atmosphere.

[0029] As a preferred scheme of the resource uncertainty wind, photovoltaic and storage multi-energy complementary installed capacity configuration method described in the present invention, wherein: the determination of the optimal wind, photovoltaic and energy storage installed capacity configuration scheme includes setting up energy storage configuration alternatives, and determining the optimal wind, photovoltaic and energy storage installed capacity configuration scheme through the expected absorption ratio of scenario simulation.

[0030] The energy storage configuration alternatives include taking 10% of the total wind and solar power installed capacity as a medium energy storage power configuration plan, floating up and down by 25% and 50% respectively as medium-high, high, medium-low and low configuration plans, and the configuration capacity is 2 hours of rated power.

[0031] Determining the optimal energy storage installed capacity configuration plan includes simulating and analyzing the absorption ratio of typical combination scenarios for different energy storage and wind and solar installed capacity combinations, and calculating the expected absorption ratio under different installed capacity ratios based on the simulated absorption ratio and the probability of the combination scenario, and determining the installed capacity plan with the highest absorption ratio expectation.

[0032] Another object of the present invention is to provide a wind, solar, and storage multi-energy complementary installed capacity configuration system with resource uncertainty. The present invention improves the multi-energy complementary system's carrying capacity for the uncertainty of wind and solar resources, and provides strong support for energy planning decisions involving highly random resources such as wind and solar. The system of the present invention randomly simulates the uncertainty of wind and solar resources through a seasonal Gaussian mixture model, comprehensively considers the combination scenarios of wind and solar resources under different installation schemes, and determines the optimal installation scheme through multi-scenario simulation, thus overcoming the problem that the current wind, solar, and storage multi-energy complementary installed capacity planning method is difficult to achieve expected benefits under long-term multi-scenario operation.

[0033] As a preferred solution of the resource uncertainty wind, solar, and storage multi-energy complementary installed capacity configuration system described in the present invention, it is characterized by including a data collection and processing module, a seasonal Gaussian mixture distribution simulation module, a scene reduction and set construction module, a wind and solar output calculation module, and an optimal installed capacity configuration determination module.

[0034] The data collection and processing module is used to collect meteorological data and power load historical sequences in the planning area, and determine the simulation time period and step length according to data characteristics to construct a historical data set.

[0035] The seasonal Gaussian mixture distribution simulation module is used to perform seasonal Gaussian mixture distribution simulation on light and wind speed, generate periodic wind speed simulation scenes, and initialize and generate wind speed scenarios by determining the autocorrelation order, constructing Gaussian mixture distribution and conditional distribution models, and using the K-means clustering method to determine model parameters.

[0036] The scenario reduction and set building module is used to reduce the generated simulation scenarios by back-elimination, calculate the Euclidean probability distance, find and delete similar scenarios, and update the scenario set until the number of typical scenarios is reached to obtain a scenario set.

[0037] The wind and solar power output calculation module is used to construct a wind and solar power combination scenario by establishing a regression prediction model of air temperature to wind speed and light, determine alternative wind and solar power installation plans, and calculate wind and solar power output.

[0038] The optimal installed capacity configuration determination module is used to set energy storage configuration alternatives and determine the optimal wind and solar energy storage installed capacity configuration scheme through the expected absorption ratio of scenario simulation.

[0039] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and is characterized in that when the processor executes the computer program, the steps of a method described in a wind, solar, and storage multi-energy complementary installed capacity configuration with resource uncertainty are implemented.

[0040] A computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of a method described in a wind, solar, and storage multi-energy complementary installed capacity configuration with resource uncertainty are implemented.

[0041] The beneficial effects of the present invention are as follows: the present invention constructs a seasonal Gaussian mixture distribution model of wind and light resources based on random simulation technology, generates massive random scenarios based on historical wind and light characteristics, and can fully consider the volatility of wind and light resources; then, through scenario reduction and combination, a typical combination scenario of wind, light and temperature is formed, and through simulation analysis of typical scenarios, the expectation of new energy consumption of multi-energy complementary system under different installed capacity ratios is obtained; compared with the prior art, the present method takes the uncertainty of wind and light into more sufficient consideration, and it is easier to achieve the expected consumption effect during the long-term operation of the multi-energy complementary system. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work, among which:

[0043] Figure 1 An overall flow chart of a method for configuring a wind, solar, and storage multi-energy complementary installed capacity with resource uncertainty provided by an embodiment of the present invention.

[0044] Figure 2 A schematic diagram of the installed capacity configuration strategy flow of a wind, solar, and storage multi-energy complementary installed capacity configuration method with resource uncertainty is provided as an embodiment of the present invention.

[0045] Figure 3 A system solution flow chart of a resource-uncertain wind, solar, and storage multi-energy complementary installed capacity configuration system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0046] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0047] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0048] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it an embodiment that is mutually exclusive with other embodiments, either individually or selectively.

[0049] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0050] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0051] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0052] Example 1, reference Figure 1 and Figure 2, which is the first embodiment of the present invention, and provides a method for configuring wind, solar and storage multi-energy complementary installations with resource uncertainty, comprising:

[0053] S1: Collect meteorological data and historical series of electricity load in the planning area, and determine the simulation time period and step size based on the characteristics of historical data to construct a historical data set.

[0054] The meteorological data includes collecting wind speed data, light data and temperature data within the planning area;

[0055] The electricity load history sequence includes the load data, load characteristics and load change trends collected in the planning area; the load characteristics include the maximum value, minimum value, average value and the time when the load peak occurs; the load change trend includes the daily load curve, weekly load curve and seasonal change curve.

[0056] It should be noted that the construction of the historical data set includes determining the time period and step length of the random simulation according to the characteristics of the historical data, and constructing the data set according to the sequence length of the wind speed and light historical data;

[0057] The historical wind speed dataset is represented as:

[0058]

[0059] Among them, V his is the historical wind speed dataset, ν i,j is the wind speed observation value of the i-th time series at the j-th moment, is the wind speed data sequence of the jth period, T is the total time, M is the number of periods, i and j are variable indexes;

[0060] The historical lighting dataset is represented as:

[0061]

[0062] Among them, R his is the historical illumination dataset, r i,j is the illumination observation value of the i-th time series at the j-th moment, is the illumination data sequence of the jth cycle, T is the total time, M is the number of cycles, and i and j are variable indexes.

[0063] S2: Simulate seasonal Gaussian mixture distribution of light and wind speed to generate periodic wind speed simulation scenarios, and reduce the scenarios by back-substitution elimination to obtain a set of scenarios.

[0064] Further, such as Figure 2 , the seasonal Gaussian mixture distribution simulation includes performing seasonal Gaussian mixture distribution simulation on light and wind speed, and generating a set of random simulation scenarios respectively;

[0065] The generation of the set of random simulation scenarios includes determining the order of autocorrelation, constructing a dataset for seasonal Gaussian mixture simulation, for the j-th subset within each period, constructing Gaussian mixture joint distribution and conditional distribution models, and using the K-means clustering method to determine the parameters of the Gaussian mixture model, initializing and generating wind speed scenarios, and repeating the wind speed assignment process until the number of periods reaches the required number of periods;

[0066] The formula for determining the order of autocorrelation is:

[0067] When j ≥ D:

[0068]

[0069] When j < D:

[0070]

[0071] where D is the order of autocorrelation of the wind speed, is the column vector composed of the wind speed at the current time j and the previous D times, is the column vector composed of the wind speed at the previous D times before the current time j, T is the total number of time, M is the number of periods, and i and j are variable indices;

[0072] The formula for constructing the Gaussian mixture joint distribution and conditional distribution models is expressed as:

[0073]

[0074]

[0075] where, is the joint distribution function, x( 1 ) is that is, the column vector composed of the wind speed at the previous D times before the current time j, x( 2 ) is v i,j that is, the wind speed observation value of the i-th time series at the j-th time, is the conditional distribution function, p(x (1) ,x (2) ) is the conditional probability density function, p(x (2) ∣x (1) ) is the joint probability density function of the Gaussian mixture model, K is the hyperparameter of the mixture Gaussian model, π k is the regression coefficient of the k-th Gaussian component, and are the means of the k-th Gaussian model, and are the mean variances of the k-th Gaussian model, and k is a variable index;

[0076] The K-means clustering method includes determining a hyperparameter K, dividing the data set into K clusters, taking the center of each cluster as the initial mean of each component in the Gaussian mixture model, calculating the difference between the data points in each cluster and the cluster center, i.e., calculating the covariance moment, calculating the proportion of the number of samples in each cluster to the total number of samples, i.e., the weight, and adjusting the K value to achieve the best simulation effect;

[0077] Creating a wind speed simulation scenario includes initializing the wind speed of the first D moments of the first cycle using the average wind speed value of the cycle, and randomly generating the wind speed at each moment starting from the first moment of the first cycle. During the generation process, if the current moment is less than D, the multi-cycle average wind speed is used as the initial value; if the current moment is equal to or greater than D, the wind speed value of the previous moment is used; and a uniformly distributed random number is randomly generated and input into the conditional Gaussian mixture distribution model to determine the wind speed at each moment, and the random generation process is continued until the wind speeds of the N time periods of the first cycle are generated, the cycle counter is increased by 1, and the wind speed assignment and generation steps are repeated until the full number of cycles are simulated.

[0078] Furthermore, the obtaining of the scene set includes performing seasonal Gaussian mixture distribution simulation on light and wind speed to generate periodic wind speed simulation scenes, and performing scene reduction by back-substitution elimination method to obtain the scene set;

[0079] The back-generation elimination method includes determining the number of typical scenes, comparing all scenes in the scene set in pairs, calculating the Euclidean probability distance, finding two scenes with the smallest distance, deleting one scene, adding the probability of the deleted scene to the retained scene, and updating the scene set until the number of scenes remaining in the scene set reaches the number of typical scenes;

[0080] The formula for calculating the Euclidean probability distance is:

[0081]

[0082] Among them, d i,j is the Euclidean distance between the i-th and j-th scenes in the scene set, i, j and k are variable indices, and For the i-th and j-th scenes, p i and p j is the probability of occurrence of the i-th and j-th scenes, and n is the sequence length of each scene;

[0083] Replace the wind speed data in the above steps with light data and temperature data, repeat the above steps to simulate the seasonal Gaussian mixture distribution of light and temperature, and generate a set of typical light and temperature scenes.

[0084] S3: Construct a wind-solar combination scenario, determine alternative wind and solar installation plans, calculate wind and solar output, and determine the optimal wind, solar and energy storage installation configuration plan through scenario simulation.

[0085] Furthermore, the calculation of wind and solar output includes establishing a regression prediction model of temperature to wind speed and light intensity through historical data, constructing a wind and solar combination scenario, determining alternative wind and solar installation plans, and calculating wind and solar output;

[0086] The regression prediction model formula is expressed as:

[0087]

[0088] Among them, f T is the regression prediction model, is the temperature at time t, r t is the light intensity at time t, v t is the wind speed at time t;

[0089] The determination of the alternative wind and solar power installation schemes includes setting three wind and solar power installation ratio schemes of 1:3, 2:2, and 3:1, and determining the wind and solar power installed capacities respectively, and the formula is expressed as follows:

[0090] Option 1:

[0091]

[0092] Option 2:

[0093]

[0094] Option 3:

[0095]

[0096] in, is the installed capacity of wind energy, is the photovoltaic installed capacity, is the total installed capacity of renewable energy;

[0097] The formula for calculating wind and solar power output is:

[0098]

[0099] in, is the wind power output at time t, is the photovoltaic output at time t, is the installed capacity of wind energy, is the installed capacity of photovoltaic power generation, ν t is the wind speed at the wind turbine during period t, ν in is the wind turbine cut-in wind speed, ν out is the wind turbine cut-out wind speed, νrated is the rated wind speed of the wind turbine, R stc is the solar radiation intensity under standard test conditions, r t is the solar radiation intensity during period t, T stc is the temperature under standard test conditions, α p is the temperature-power conversion coefficient, T t is the solar panel temperature, T NOC is the rated operating temperature of the photovoltaic cell, is the temperature at time t; the standard test conditions are that the light intensity is 1000 watts per square meter, the temperature is 25 degrees Celsius, and the atmospheric pressure is one standard atmosphere.

[0100] Furthermore, the determining of the optimal wind and solar energy storage installed capacity configuration scheme includes setting up energy storage configuration alternatives and determining the optimal wind and solar energy storage installed capacity configuration scheme through the expected absorption ratio of the scenario simulation;

[0101] The energy storage configuration alternatives include taking 10% of the total wind and solar power installed capacity as a medium energy storage power configuration plan, floating up and down by 25% and 50% respectively as medium-high, high, medium-low and low configuration plans, and configuring a capacity of 2 hours of rated power;

[0102] Determining the optimal energy storage installed capacity configuration plan includes simulating and analyzing the absorption ratio of typical combination scenarios for five different energy storage and three wind and solar installed capacity combinations, and calculating the expected absorption ratio under different installed capacity ratios based on the simulated absorption ratio and the probability of the combination scenario, and determining the installation plan with the highest absorption ratio expectation.

[0103] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

[0104] Example 2, reference Figure 3 , which is the second embodiment of the present invention, provides a resource uncertainty wind, solar, and storage multi-energy complementary installed capacity configuration system, including a data collection and processing module 100, a seasonal Gaussian mixture distribution simulation module 200, a scene reduction and set construction module 300, a wind and solar output calculation module 400, and an optimal installed capacity configuration determination module 500.

[0105] The data collection and processing module 100 is used to collect meteorological data and historical series of power load in the planning area, and determine the simulation time period and step size according to the data characteristics to construct a historical data set.

[0106] The seasonal Gaussian mixture distribution simulation module 200 is used to perform seasonal Gaussian mixture distribution simulation on light and wind speed, generate periodic wind speed simulation scenes, and initialize and generate wind speed scenarios by determining the autocorrelation order, constructing Gaussian mixture distribution and conditional distribution models, and using K-means clustering method to determine model parameters.

[0107] The scenario reduction and set building module 300 is used to reduce the generated simulation scenarios by back-elimination, calculate the Euclidean probability distance, find and delete similar scenarios, and update the scenario set until the number of typical scenarios is reached to obtain a scenario set.

[0108] The wind-solar output calculation module 400 is used to construct a wind-solar combination scenario, determine alternative wind and solar installation plans, and calculate the wind-solar output by establishing a regression prediction model of air temperature to wind speed and light.

[0109] The optimal installed capacity configuration determination module 500 is used to set energy storage configuration alternatives and determine the optimal wind and solar energy storage installed capacity configuration schemes through the expected absorption ratio of scenario simulation.

[0110] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

[0111] Embodiment 3, the third embodiment of the present invention, is different from the first two embodiments in that:

[0112] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program codes.

[0113] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0114] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0115] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

Claims

1. A method for configuring wind, solar and storage multi-energy complementary installed capacity with resource uncertainty, characterized by: include, Collect meteorological data and historical series of electricity load in the planning area, and determine the simulation time period and step size based on the characteristics of historical data to construct a historical data set; The seasonal Gaussian mixture distribution of light and wind speed is simulated to generate periodic wind speed simulation scenes, and the scenes are reduced by back-substitution elimination method to obtain a scene set. Build a wind-solar combination scenario, determine alternative wind and solar installation plans, calculate wind and solar output, and determine the optimal wind, solar and energy storage installation configuration plan through scenario simulation.

2. A method for configuring wind, solar and storage multi-energy complementary installed capacity with resource uncertainty as claimed in claim 1, characterized in that: The meteorological data includes collecting wind speed data, light data and temperature data within the planning area; The power load history sequence includes collecting load data, load characteristics and load change trends in the planning area; the load characteristics include the maximum value, minimum value, average value and time of load peak; The load variation trend includes a daily load curve, a weekly load curve and a seasonal variation curve.

3. A method for configuring wind, solar and storage multi-energy complementary installed capacity with resource uncertainty as claimed in claim 2, characterized in that: The construction of the historical data set includes determining the time period and step length of the random simulation according to the characteristics of the historical data, and constructing a data set based on the sequence length of the wind speed and light historical data.

4. A method for configuring wind, solar and storage multi-energy complementary installed capacity with resource uncertainty as claimed in claim 3, characterized in that: The seasonal Gaussian mixture distribution simulation includes performing seasonal Gaussian mixture distribution simulation on light and wind speed to generate a set of random simulation scenarios respectively; The scenario set for generating random simulation includes determining the autocorrelation order D, constructing a data set for seasonal Gaussian mixture simulation, constructing a Gaussian mixture joint distribution and conditional distribution model for the j-th subset in each cycle, determining the parameters of the Gaussian mixture model using a K-means clustering method, initializing and generating wind speed scenarios, and repeating the wind speed assignment process until the number of cycles reaches the required number of cycles; The formula for constructing the Gaussian mixture joint distribution and conditional distribution model is expressed as: in, is the joint distribution function, x (1) for That is, the column vector of wind speeds at the D moments before the current moment j, x (2) v i,j That is, the wind speed observation value of the i-th time series at the j-th moment, is the conditional distribution function, p(x (1) ,x (2) ) is the conditional probability density function, p(x (2) ∣x (1) ) is the joint probability density function of the Gaussian mixture model, K is the hyperparameter of the Gaussian mixture model, π k is the regression coefficient of the kth Gaussian component, and is the mean of the kth Gaussian model, and is the mean square error of the k-th Gaussian model, k is the variable index; The K-means clustering method includes determining a hyperparameter K, dividing the data set into K clusters, taking the center of each cluster as the initial mean of each component in the Gaussian mixture model, calculating the difference between the data points in each cluster and the cluster center, i.e., calculating the covariance moment, calculating the proportion of the number of samples in each cluster to the total number of samples, i.e., the weight, and adjusting the K value to achieve the best simulation effect; Creating a wind speed simulation scenario includes initializing the wind speed of the first D moments of the first cycle using the average wind speed value of the cycle, and randomly generating the wind speed at each moment starting from the first moment of the first cycle. During the generation process, if the current moment is less than D, the multi-cycle average wind speed is used as the initial value; if the current moment is equal to or greater than D, the wind speed value of the previous moment is used; and a uniformly distributed random number is randomly generated and input into the conditional Gaussian mixture distribution model to determine the wind speed at each moment, and the random generation process is continued until the wind speeds of the N time periods of the first cycle are generated, the cycle counter is increased by 1, and the wind speed assignment and generation steps are repeated until the full number of cycles are simulated.

5. A method for configuring wind, solar and storage multi-energy complementary installed capacity with resource uncertainty as claimed in claim 4, characterized in that: The obtaining of the scene set includes performing seasonal Gaussian mixture distribution simulation on light and wind speed to generate periodic wind speed simulation scenes, and performing scene reduction by back-substitution elimination method to obtain the scene set; The back-generation elimination method includes determining the number of typical scenes, comparing all scenes in the scene set in pairs, calculating the Euclidean probability distance, finding two scenes with the smallest distance, deleting one scene, adding the probability of the deleted scene to the retained scene, and updating the scene set until the number of scenes remaining in the scene set reaches the number of typical scenes; The formula for calculating the Euclidean probability distance is: Among them, d i,j is the Euclidean distance between the i-th and j-th scenes in the scene set, i, j and k are variable indices, and For the i-th and j-th scenes, p i and p j is the occurrence probability of the i-th and j-th scenes, and n is the sequence length of each scene.

6. A method for configuring wind, solar and storage multi-energy complementary installed capacity with resource uncertainty as claimed in claim 5, characterized in that: The calculation of wind and solar output includes establishing a regression prediction model of temperature to wind speed and light intensity through historical data, constructing a wind and solar combination scenario, determining alternative wind and solar installation plans, and calculating wind and solar output; The regression prediction model formula is expressed as: Among them, f T is the regression prediction model, is the temperature at time t, r t is the light intensity at time t, v t is the wind speed at time t; The formula for calculating wind and solar power output is: in, is the wind power output at time t, is the photovoltaic output at time t, is the installed capacity of wind energy, is the installed capacity of photovoltaic power generation, ν t is the wind speed at the wind turbine during period t, ν in is the wind turbine cut-in wind speed, ν out is the wind turbine cut-out wind speed, ν rated is the rated wind speed of the wind turbine, R stc is the solar radiation intensity under standard test conditions, r t is the solar radiation intensity during period t, T stc is the temperature under standard test conditions, α p is the temperature-power conversion coefficient, T t is the solar panel temperature, T NOC is the rated operating temperature of the photovoltaic cell, is the temperature at time t; the standard test conditions are that the light intensity is 1000 watts per square meter, the temperature is 25 degrees Celsius, and the atmospheric pressure is one standard atmosphere.

7. A method for configuring wind, solar and storage multi-energy complementary installed capacity with resource uncertainty as claimed in claim 6, characterized in that: Determining the optimal wind and solar energy storage installed capacity configuration scheme includes setting an energy storage configuration alternative scheme and determining the optimal wind and solar energy storage installed capacity configuration scheme through the expected absorption ratio of the scenario simulation; Determining the optimal energy storage installed capacity configuration plan includes simulating and analyzing the absorption ratio of typical combination scenarios for different energy storage and wind and solar installed capacity combinations, and calculating the expected absorption ratio under different installed capacity ratios based on the simulated absorption ratio and the probability of the combination scenario, and determining the installed capacity plan with the highest absorption ratio expectation.

8. A system using a resource uncertainty wind, solar and storage multi-energy complementary installed capacity configuration method as described in any one of claims 1 to 7, characterized in that: It includes data collection and processing module, seasonal Gaussian mixture distribution simulation module, scenario reduction and set construction module, wind and solar power output calculation module and optimal installed configuration determination module; The data collection and processing module is used to collect meteorological data and historical series of power load in the planning area, and determine the simulation time period and step length according to the data characteristics to construct a historical data set; The seasonal Gaussian mixture distribution simulation module is used to perform seasonal Gaussian mixture distribution simulation on light and wind speed, generate periodic wind speed simulation scenarios, and initialize and generate wind speed scenarios by determining the autocorrelation order, constructing Gaussian mixture distribution and conditional distribution models, and determining model parameters using the K-means clustering method; The scenario reduction and set building module is used to reduce the generated simulation scenarios by back-elimination, calculate the Euclidean probability distance, find and delete similar scenarios, and update the scenario set until the number of typical scenarios is reached to obtain a scenario set; The wind and solar output calculation module is used to construct a wind and solar combination scenario by establishing a regression prediction model of air temperature to wind speed and light, determine alternative wind and solar installation plans, and calculate wind and solar output; The optimal installed capacity configuration determination module is used to set energy storage configuration alternatives and determine the optimal wind and solar energy storage installed capacity configuration scheme through the expected absorption ratio of scenario simulation.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of a method for configuring a wind, solar, and storage multi-energy complementary installation with resource uncertainty described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a method for configuring a wind, solar, and storage multi-energy complementary installed capacity with resource uncertainty described in any one of claims 1 to 7 are implemented.

Images