Power system standby stochastic optimization method, system and equipment based on photovoltaic typical scene, and medium

Abstract

The invention belongs to the technical field of power system optimization scheduling, and discloses a power system standby stochastic optimization method, system and device based on a photovoltaic typical scene and a medium. The method comprises the following steps: acquiring predicted photovoltaic power probability data, forming a sequence by using data corresponding to different quantiles, and obtaining a photovoltaic power cumulative distribution function by using a linear interpolation method to calculate photovoltaic predicted power; constructing a multivariate distribution function satisfying photovoltaic power time sequence correlation by using a Gaussian Copula function, and obtaining a plurality of photovoltaic power prediction scenes through Monte Carlo sampling; reducing the photovoltaic power prediction scene based on a K-means + + algorithm to obtain a plurality of photovoltaic typical scenes; and constructing an objective function based on the operation cost, the standby cost and the start-stop cost, and obtaining a preset standby stochastic optimization condition, so as to construct a standby stochastic optimization model of the power system in the multi-photovoltaic typical scene. According to the method, the operation efficiency and economy of the power system are improved, and guarantee is provided for safe operation scheduling of the system.

Description

Technical Field

[0001] The present invention belongs to the technical field of power system optimization and dispatching, and specifically relates to a method, system, equipment and medium for random optimization of power system standby based on typical photovoltaic scenarios. Background Art

[0002] In order to continuously optimize the energy structure, vigorously developing new energy such as photovoltaics and wind power has become the core support for the construction of new power systems. However, affected by the chaotic properties of the atmospheric system, the output of new energy such as wind power shows a high degree of uncertainty and strong volatility, resulting in the power system facing significant power deviation challenges after a high proportion of new energy is connected to the grid. Therefore, it is particularly necessary to configure a backup power supply of appropriate capacity while new energy is connected to the grid. However, the traditional backup quantification model has shortcomings in considering the uncertainty of new energy and has low calculation efficiency, which directly affects the reasonable reservation of backup capacity of conventional units and energy storage equipment. Summary of the invention

[0003] Based on the above-mentioned shortcomings and deficiencies in the prior art, one of the objects of the present invention is to at least solve one or more of the above-mentioned problems in the prior art. In other words, one of the objects of the present invention is to provide a random optimization method, system, equipment and medium for power system backup based on typical photovoltaic scenarios that meet one or more of the aforementioned needs, so as to meet the needs of efficient and accurate consideration of the uncertainty of new energy and reasonable reservation of backup capacity of conventional units and energy storage equipment.

[0004] In order to achieve the above-mentioned object of the invention, the present invention adopts the following technical solutions: In a first aspect, the present invention provides a method for stochastic optimization of power system backup based on a typical photovoltaic scenario, comprising the steps of: S1. Obtain predicted photovoltaic power probability data and compose a sequence of data corresponding to different quantiles therein, and obtain a photovoltaic power cumulative distribution function based on the sequence using a linear interpolation method to calculate photovoltaic predicted power; S2. Based on the photovoltaic predicted power, a multivariate distribution function satisfying the time series correlation of photovoltaic power is constructed by using a Gaussian Copula function, and the multivariate distribution function is sampled by a Monte Carlo method to obtain a plurality of photovoltaic power prediction scenarios with time series correlation; S3. Based on the K-means++ algorithm, the plurality of photovoltaic power prediction scenarios with time series correlation are reduced to obtain a plurality of photovoltaic typical scenarios; S4. Construct an objective function based on the operating cost, backup cost and start-stop cost of typical photovoltaic scenarios, obtain the preset backup random optimization conditions, and build a random optimization model for power system backup under multiple typical photovoltaic scenarios, quantify the system backup under random photovoltaic output in typical photovoltaic scenarios, and optimize it.

[0005] As a preferred solution, step S1 is specifically as follows: Based on the quantile regression theory, the photovoltaic power is defined at a certain moment. The cumulative distribution function of ; Defining quantile levels Quantile for ,and , where is the probability operator, Indicates time of photovoltaic power; Using the probability prediction method of quantile regression, the predicted quantile of photovoltaic power is expressed as , where Indicates time Percentile level When is the sequence of predicted quantiles, is the number of quantiles, Indicates the actual quantile An estimated value of At the moment Based on the prediction quantile series , the complete photovoltaic power cumulative distribution function is obtained by linear interpolation ; Let the random variable sequence obey The uniform distribution of Represents the duration of the scheduling cycle, expressed as a random variable sequence As the cumulative probability of a random variable, according to the cumulative distribution function of photovoltaic power have , and the photovoltaic predicted power is obtained .

[0006] As a preferred solution, step S2 includes the steps of: S21. Using Multivariate Gaussian Copula Function Constructing a multivariate distribution function that satisfies the timing correlation of photovoltaic power ,make ,but ; S22. Generate a set of Uniformly distributed random numbers ; S23. Order Get the solution random variable Value , let the random variable The marginal cumulative distribution function value of is equal to , using the formula Get random variables Value , based on the formula Get random variables Value ; S24, repeat the calculation process of step S22 and step S23 times, we get the multivariate random variable The sampling results of the group are In the sampling, the multivariate random variable is ; S25, according to ,Depend on Solve the time-dependent scene Photovoltaic power , traverse ,get The photovoltaic power prediction scenario with time correlation based on probability prediction.

[0007] As a preferred solution, step S3 includes the steps of: S31, from The photovoltaic power prediction scenarios are randomly selected As the first cluster center; S32, for The photovoltaic power prediction scenarios are calculated and their respective cluster centers are calculated. The shortest distance between , and all the shortest distances Sum the squares of , the shortest distance The calculation formula is ; S33, calculating the probability of each photovoltaic power prediction scenario being selected as the next cluster center , the probability The calculation formula is ; S34. Pick a random number between the interval [0,1] ,use minus If the result is greater than 0, continue to subtract until the result is not greater than 0 and the probability The corresponding photovoltaic power prediction scenario is recorded as the second cluster center; S35, repeat steps S32 to S34 to obtain Initial cluster centers; S36. Based on Initial cluster centers are obtained using the K-means clustering algorithm. Typical photovoltaic scenarios And the corresponding probability , and the probability satisfy .

[0008] As a preferred solution, step S4 is specifically as follows: Based on the typical photovoltaic scenario, Typical photovoltaic scenarios Recorded as a set , from the collection Select any one as the base scene and record the rest as , in order to construct a random optimization model of power system reserve under typical multi-photovoltaic scenarios.

[0009] As a preferred solution, the objective function is: , In the formula, It is a collection of conventional units in the power system. represents the collection of energy storage devices in the power system, and Conventional units Startup cost factor and downtime cost factor, and Represents conventional units Provide positive and negative standby cost factors, and Energy storage devices Provide positive and negative standby cost factors, Indicates conventional unit Operating cost factor, and Represents energy storage devices Discharge cost coefficient and charge cost coefficient, and Represents conventional units At the moment Power on state and power off state, and they are binary variables, and they cannot be both ,when When the In the startup state, when When the is closed. and Represents conventional units At the moment Positive and negative reserve capacities provided, and Energy storage devices exist Positive and negative reserve capacity provided at all times, Representation scene Conventional unit exist Active power at the moment, and Representing scenes Energy storage equipment exist The discharge power and charging power at the moment.

[0010] As a preferred solution, the standby random optimization conditions include power balance constraints, power system flow constraints, minimum start and stop time constraints, unit output constraints, unit climbing constraints, unit standby capacity constraints, energy storage device constraints, energy storage device standby constraints and photovoltaic output constraints; The expression of the power balance constraint is: , In the formula, and represent the photovoltaic collection and load collection respectively, Representation scene Next Photovoltaic at the moment The actual output, It's a scene Next The load at time The load value; The expression of the power system flow constraint is: , In the formula, is a collection of nodes; , , and Respectively represent nodes The combination of conventional units, energy storage equipment, photovoltaics and loads, represents the set of power system lines, It is a line Transmit power cap, Is a node To line transfer factor; The expression of the minimum start-stop time constraint includes , , , , In the formula, It is a conventional unit exist The state at the moment is a binary variable. When the exist Always in power on state, when When the exist Always in shutdown state. and Represents conventional units Minimum startup and shutdown times; The expression of the unit output constraint is: , In the formula, and Represents conventional units The upper and lower limits of active output; The expression of the unit climbing constraint includes , , In the formula, and Represents conventional units Enable and disable ramp rate, and Conventional units The climbing rate and the descending rate; The expression of the unit reserve capacity constraint includes

[0011]

[0012]

[0013]

[0014] In the formula, Indicates conventional units in the basic scenario At the moment The active power, and Conventional units Provide positive and negative reserve caps; The expressions of the energy storage device constraints include , , , , , , In the formula, and Represents energy storage devices The minimum and maximum values ​​of charge and discharge power, and Respectively for scenes Energy storage equipment At the moment The charge and discharge state is a binary variable, and both cannot be 1 at the same time. When, it indicates the scene Energy storage equipment At the moment In charging state, when When, it indicates the scene Energy storage equipment At the moment In discharge state, Representation scene Energy storage equipment At the moment The energy and Represents energy storage devices The charging and discharging efficiency, and Energy storage devices Minimum and maximum values ​​of energy; The expression of the backup constraint of the energy storage device includes , , , , In the formula, and Respectively represent the energy storage devices in the basic scenario At the moment Active power of The expression of the photovoltaic output constraint is: , In the formula, Representation scene Next Photovoltaic at the moment Output forecast value.

[0015] In a second aspect, the present invention provides a power system reserve random optimization system based on a typical photovoltaic scenario, which is used to implement the power system reserve random optimization method as described in the first aspect.

[0016] In a third aspect, the present invention provides an electronic device, wherein the computer device includes a memory, a processor, and a computer program, and when the computer program is executed by the processor, the random optimization method for power system backup as described in the first aspect is implemented.

[0017] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the method for random optimization of power system backup as described in the first aspect is implemented.

[0018] Compared with the prior art, the present invention has the following beneficial effects: The present invention first adopts the quantile regression method to perform the probability prediction of photovoltaic power, effectively avoiding the calculation errors that may be introduced by parameterized assumptions, thereby more realistically and accurately describing the cumulative distribution function of photovoltaic power. Then, using the multivariate Gaussian Copula function, a photovoltaic power prediction scenario set with time correlation is constructed, providing rich data support for the subsequent power system operation and scheduling. In order to further improve the computational efficiency of the model, the present invention introduces the photovoltaic power prediction scenario reduction of the K-means++ algorithm, which effectively reduces the number of scenarios, while ensuring that the typical scenario can fully represent the main features of the original scenario, thereby improving the computational efficiency of the model. On this basis, the present invention establishes a random optimization model of power system reserve under multiple scenarios, which can comprehensively quantify the impact of photovoltaic output uncertainty on system reserve, and provides a scientific basis for realizing the optimal configuration of reserve. Compared with the traditional power system reserve quantification method, the power system reserve random optimization method based on photovoltaic typical scenarios proposed in the present invention shows significant advantages in terms of computational efficiency, prediction accuracy and application value. This method not only improves the operating efficiency and economy of the power system, but also provides a strong guarantee for the safe operation and dispatching of the power system. It is of great significance to promote the optimization of energy structure and achieve the goals of carbon peak and carbon neutrality.

[0019] Further or more detailed beneficial effects will be described in detail in conjunction with specific examples in the specific implementation manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0021] Figure 1 It is a flow chart of the random optimization method for power system standby provided in an embodiment of the present invention.

[0022] Figure 2 is a structural diagram of the electronic device provided in an embodiment of the present invention.

[0023] Figure Number: 200. Electronic equipment; 201, processor; 202, communication bus; 203, user interface; 204, network interface; 205, memory. DETAILED DESCRIPTION

[0024] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0025] In the following description, multiple embodiments of the present invention are provided, and different embodiments may be replaced or combined, so the present invention may also be considered to include all possible combinations of the same and / or different embodiments described. Therefore, if one embodiment includes features A, B, and C, and another embodiment includes features B and D, then the present invention should also be considered to include embodiments containing one or more of A, B, C, and D, all other possible combinations, even though the embodiment may not be clearly described in the following text.

[0026] The following description provides examples and does not limit the scope, applicability or examples set forth in the claims. Changes may be made to the functions and arrangements of the elements described without departing from the scope of the present invention. Various processes or components may be appropriately omitted, substituted or added to each example. For example, the described method may be performed in an order different from the described order, and various steps may be added, omitted or combined. In addition, the features described in some examples may be combined in other examples.

[0027] In order to facilitate a better understanding of the embodiments of the present invention, before explaining the specific implementation modes of the present invention in detail, its application scenarios are first described.

[0028] The power system standby random optimization method described in the embodiments of this specification is applied to scenarios of power supply and management. In these scenarios, the application of the power system standby random optimization method is intended to make the power supply more stable and reliable, thereby significantly improving the operating efficiency and safety of the entire power system.

[0029] The following is a brief explanation of typical photovoltaic scenarios, quantile regression method, linear interpolation method, Gaussian Copula function, K-means++ algorithm, and Monte Carlo method involved in multiple embodiments of this specification: Photovoltaic typical scenarios refer to several representative or common situations in which the power output characteristics are caused by various factors such as weather, season, and geographical location during the photovoltaic power generation process. Through the study and analysis of these typical scenarios, we can better understand and predict the behavior of photovoltaic power generation, and then optimize the backup power configuration of the power system.

[0030] Quantile regression is a statistical method used to estimate the conditional quantile of a response variable. In the stochastic optimization of power system reserve, quantile regression can be used to predict the fluctuation range of power demand and configure appropriate reserve power based on these prediction results. This method can capture the uncertainty of power demand and improve the accuracy and flexibility of reserve power configuration.

[0031] Linear interpolation is a simple mathematical method used to estimate the value of an unknown data point between two known data points. In the stochastic optimization of power system reserve, linear interpolation can be used to fill or smooth missing values ​​in historical data or to predict future trends in power demand. Although this method is simple, it can provide effective approximation results in some cases.

[0032] The Gaussian Copula function is a tool for modeling the dependencies between multidimensional random variables. In the random optimization of power system reserve, the Gaussian Copula function can be used to capture the correlation between different power demands or photovoltaic power generation scenarios, so as to more accurately evaluate the demand and risk of reserve power.

[0033] The K-means++ algorithm is an improved K-means clustering algorithm that is used to divide a data set into K clusters. In the random optimization of power system reserve, the K-means++ algorithm can be used to perform cluster analysis on historical power demand data and identify different demand patterns or scenarios in order to configure appropriate reserve power for each scenario.

[0034] The Monte Carlo method is a statistical method based on random sampling, which is used to estimate the behavior or performance of complex systems. In the random optimization of power system backup, the Monte Carlo method can be used to simulate the operation of the power system under different scenarios, evaluate the effect of backup power configuration, and find the optimal backup power configuration plan. This method can take into account the influence of various uncertainties and random factors in the power system and provide more accurate evaluation results.

[0035] Embodiment 1: like Figure 1 As shown, this embodiment provides a random optimization method for power system backup based on a typical photovoltaic scenario, including the steps of: S1. Obtain predicted photovoltaic power probability data and compose a sequence of data corresponding to different quantiles therein, and obtain a photovoltaic power cumulative distribution function based on the sequence using a linear interpolation method to calculate photovoltaic predicted power; S2. Based on the photovoltaic predicted power, a multivariate distribution function satisfying the time series correlation of photovoltaic power is constructed by using a Gaussian Copula function, and the multivariate distribution function is sampled by a Monte Carlo method to obtain a plurality of photovoltaic power prediction scenarios with time series correlation; S3. Based on the K-means++ algorithm, the plurality of photovoltaic power prediction scenarios with time series correlation are reduced to obtain a plurality of photovoltaic typical scenarios; S4. Construct an objective function based on the operating cost, backup cost and start-stop cost of typical photovoltaic scenarios, obtain the preset backup random optimization conditions, and build a random optimization model for power system backup under multiple typical photovoltaic scenarios, quantify the system backup under random photovoltaic output in typical photovoltaic scenarios, and optimize it.

[0036] Specifically, this embodiment provides a preferred implementation, and step S1 is specifically as follows: Based on the quantile regression theory, the photovoltaic power is defined at a certain moment. The cumulative distribution function of ; Defining quantile levels Quantile for ,and , where is the probability operator, Indicates time of photovoltaic power; Using the probability prediction method of quantile regression, the predicted quantile of photovoltaic power is expressed as , where Indicates time Percentile level When is the sequence of predicted quantiles, is the number of quantiles, Indicates the actual quantile An estimated value of At the moment Based on the prediction quantile series , the complete photovoltaic power cumulative distribution function is obtained by linear interpolation ; Let the random variable sequence obey The uniform distribution of Represents the duration of the scheduling cycle, expressed as a random variable sequence As the cumulative probability of a random variable, according to the cumulative distribution function of photovoltaic power have , and the photovoltaic predicted power is obtained .

[0037] Specifically, this embodiment provides a preferred implementation, step S2 includes the steps of: S21. Using Multivariate Gaussian Copula Function Constructing a multivariate distribution function that satisfies the timing correlation of photovoltaic power ,make ,but ; S22. Generate a set of Uniformly distributed random numbers ; S23. Order Get the solution random variable Value , let the random variable The marginal cumulative distribution function value of is equal to , using the formula Get random variables Value , based on the formula Get random variables Value ; S24, repeat the calculation process of step S22 and step S23 times, we get the multivariate random variable The sampling results of the group are In the sampling, the multivariate random variable is ; S25, according to ,Depend on Solve the time-dependent scene Photovoltaic power , traverse ,get The photovoltaic power prediction scenario with time correlation based on probability prediction.

[0038] Specifically, this embodiment provides a preferred implementation, step S3 includes the steps of: S31, from The photovoltaic power prediction scenarios are randomly selected As the first cluster center; S32, for The photovoltaic power prediction scenarios are calculated and their respective cluster centers are calculated. The shortest distance between , and all the shortest distances Sum the squares of , the shortest distance The calculation formula is ; S33, calculating the probability of each photovoltaic power prediction scenario being selected as the next cluster center , the probability The calculation formula is ; S34. Pick a random number between the interval [0,1] ,use minus If the result is greater than 0, continue to subtract until the result is not greater than 0 and the probability The corresponding photovoltaic power prediction scenario is recorded as the second cluster center; S35, repeat steps S32 to S34 to obtain Initial cluster centers; S36. Based on Initial cluster centers are obtained using the K-means clustering algorithm. Typical photovoltaic scenarios And the corresponding probability , and the probability satisfy .

[0039] Specifically, this embodiment provides a preferred implementation, and step S4 is specifically as follows: Based on the typical photovoltaic scenario, Typical photovoltaic scenarios Recorded as a set , from the collection Select any one as the base scene and record the rest as , in order to construct a random optimization model of power system reserve under typical multi-photovoltaic scenarios.

[0040] Specifically, this embodiment provides a preferred implementation, and the objective function is: , In the formula, It is a collection of conventional units in the power system. represents the collection of energy storage devices in the power system, and Conventional units Startup cost factor and downtime cost factor, and Represents conventional units Provide positive and negative standby cost factors, and Energy storage devices Provide positive and negative standby cost factors, Indicates conventional unit Operating cost factor, and Represents energy storage devices Discharge cost coefficient and charge cost coefficient, and Represents conventional units At the moment Power on state and power off state, and they are binary variables, and they cannot be both ,when When the In the startup state, when When the is closed. and Represents conventional units At the moment Positive and negative reserve capacities provided, and Energy storage devices exist Positive and negative reserve capacity provided at all times, Representation scene Conventional unit exist Active power at the moment, and Representing scenes Energy storage equipment exist The discharge power and charging power at the moment.

[0041] Specifically, this embodiment provides a preferred implementation method, wherein the standby random optimization conditions include power balance constraints, power system flow constraints, minimum start and stop time constraints, unit output constraints, unit climbing constraints, unit standby capacity constraints, energy storage device constraints, energy storage device standby constraints, and photovoltaic output constraints; The expression of the power balance constraint is: , In the formula, and represent the photovoltaic collection and load collection respectively, Representation scene Next Photovoltaic at the moment The actual output, It's a scene Next The load at time The load value; The expression of the power system flow constraint is: , In the formula, is a collection of nodes; , , and Respectively represent nodes The combination of conventional units, energy storage equipment, photovoltaics and loads, represents the set of power system lines, It is a line Transmit power cap, Is a node To line transfer factor; The expression of the minimum start-stop time constraint includes , , , , In the formula, It is a conventional unit exist The state at the moment is a binary variable. When the exist Always in power on state, when When the exist Always in shutdown state. and Represents conventional units Minimum startup and shutdown times; The expression of the unit output constraint is: , In the formula, and Represents conventional units The upper and lower limits of active output; The expression of the unit climbing constraint includes , , In the formula, and Represents conventional units Enable and disable ramp rate, and Conventional units The climbing rate and the descending rate; The expression of the unit reserve capacity constraint includes

[0042]

[0043]

[0044]

[0045] In the formula, Indicates conventional units in the basic scenario At the moment The active power, and Conventional units Provide positive and negative reserve caps; The expressions of the energy storage device constraints include , , , , , , In the formula, and Represents energy storage devices The minimum and maximum values ​​of charge and discharge power, and Respectively for scenes Energy storage equipment At the moment The charge and discharge state is a binary variable, and both cannot be 1 at the same time. When, it indicates the scene Energy storage equipment At the moment In charging state, when When, it indicates the scene Energy storage equipment At the moment In discharge state, Representation scene Energy storage equipment At the moment The energy and Represents energy storage devices The charging and discharging efficiency, and Energy storage devices Minimum and maximum values ​​of energy; The expression of the backup constraint of the energy storage device includes , , , , In the formula, and Respectively represent the energy storage devices in the basic scenario At the moment Active power of The expression of the photovoltaic output constraint is: , In the formula, Representation scene Next Photovoltaic at the moment Output forecast value.

[0046] Embodiment 2: This embodiment provides a power system reserve random optimization system based on a typical photovoltaic scenario, which is used to implement the power system reserve random optimization method described in the first embodiment.

[0047] Embodiment three: like Figure 2 As shown, this embodiment provides an electronic device, which may include: at least one processor, at least one network interface, a user interface, a memory, and at least one communication bus.

[0048] The communication bus can be used to realize the connection and communication among the above-mentioned components.

[0049] The user interface may include buttons, and the optional user interface may also include a standard wired interface or a wireless interface.

[0050] The network interface may include but is not limited to a Bluetooth module, an NFC module, a Wi-Fi module, etc.

[0051] Among them, the processor may include one or more processing cores. The processor uses various interfaces and lines to connect the various parts of the entire electronic device, and executes various functions of the electronic device and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory, and calling data stored in the memory. Optionally, the processor can be implemented in at least one hardware form of DSP, FPGA, and PLA. The processor can integrate one or a combination of CPU, GPU, modem, etc. Among them, the CPU mainly processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display; the modem is used to handle wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor, but may be implemented separately through a chip.

[0052] Among them, the memory may include RAM or ROM. Optionally, the memory includes a non-transitory computer-readable medium. The memory can be used to store instructions, programs, codes, code sets or instruction sets. The memory may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory may also be at least one storage device located away from the aforementioned processor. The memory as a computer storage medium may include an operating system, a network communication module, a user interface module and an optimization application. The processor may be used to call the optimization application stored in the memory and execute the steps of the power system standby random optimization method mentioned in the above-mentioned embodiment.

[0053] Embodiment 4: This embodiment provides a computer-readable storage medium, which stores instructions. When the computer-readable storage medium is executed on a computer or a processor, the computer or the processor executes the above-mentioned Figure 1One or more steps in the illustrated embodiment. If the components of the electronic device described above are implemented in the form of software functional units and sold or used as independent products, they can be stored in the computer-readable storage medium.

[0054] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of this specification is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions can be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (Digital Subscriber Line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a digital versatile disc (DVD)), or a semiconductor medium (eg, a solid state drive (SSD)).

[0055] A person skilled in the art can understand that all or part of the processes in the method of the first embodiment can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. The aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk and other media that can store program codes. In the absence of conflict, the technical features in this embodiment and the implementation scheme can be combined arbitrarily.

[0056] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0057] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0058] The above is only an exemplary embodiment of the present invention and cannot be used to limit the scope of the present invention. That is, any equivalent changes and modifications made according to the teachings of the present invention are still within the scope of the present invention. After considering the specification and practicing the disclosure here, it will be easy for those skilled in the art to think of the implementation scheme of the present invention. The present invention is intended to cover any modification, use or adaptation of the present invention, which follows the general principles of the present invention and includes common knowledge or customary technical means in the art that are not recorded in the present invention. The description and examples are only regarded as exemplary, and the scope and spirit of the present invention are defined by the claims.

Claims

1. A random optimization method for power system backup based on typical photovoltaic scenarios, characterized in that: Includes steps: S1. Obtain predicted photovoltaic power probability data and compose a sequence of data corresponding to different quantiles therein, and obtain a photovoltaic power cumulative distribution function based on the sequence using a linear interpolation method to calculate photovoltaic predicted power; S2. Based on the photovoltaic predicted power, a multivariate distribution function satisfying the time series correlation of photovoltaic power is constructed by using a Gaussian Copula function, and the multivariate distribution function is sampled by a Monte Carlo method to obtain a plurality of photovoltaic power prediction scenarios with time series correlation; S3. Based on the K-means++ algorithm, the plurality of photovoltaic power prediction scenarios with time series correlation are reduced to obtain a plurality of photovoltaic typical scenarios; S4. Construct an objective function based on the operating cost, backup cost and start-stop cost of typical photovoltaic scenarios, obtain the preset backup random optimization conditions, and build a random optimization model for power system backup under multiple typical photovoltaic scenarios, quantify the system backup under random photovoltaic output in typical photovoltaic scenarios, and optimize it.

2. According to claim 1, a random optimization method for power system backup based on typical photovoltaic scenarios is characterized in that: Step S1 is specifically as follows: Based on the quantile regression theory, the photovoltaic power is defined at a certain moment. The cumulative distribution function of ; Defining quantile levels Quantile for ,and , where is the probability operator, Indicates time of photovoltaic power; Using the probability prediction method of quantile regression, the predicted quantile of photovoltaic power is expressed as , where Indicates time Percentile level When is the sequence of predicted quantiles, is the number of quantiles, Indicates the actual quantile An estimated value of At the moment Based on the prediction quantile series , the complete photovoltaic power cumulative distribution function is obtained by linear interpolation ; Let the random variable sequence obey The uniform distribution of Represents the duration of the scheduling cycle, expressed as a random variable sequence As the cumulative probability of a random variable, according to the cumulative distribution function of photovoltaic power have , and the photovoltaic predicted power is obtained .

3. The method for random optimization of power system backup based on typical photovoltaic scenarios according to claim 2 is characterized in that: Step S2 comprises the steps of: S21. Using Multivariate Gaussian Copula Function Constructing a multivariate distribution function that satisfies the timing correlation of photovoltaic power ,make ,but ； S22. Generate a set of Uniformly distributed random numbers ; S23. Order Get the solution random variable Value , let the random variable The marginal cumulative distribution function value of is equal to , using the formula Get random variables Value , based on the formula Get random variables Value ; S24, repeat the calculation process of step S22 and step S23 times, we get the multivariate random variable The sampling results of the group are In the sampling, the multivariate random variable is ; S25, according to ,Depend on Solve the time-dependent scene Photovoltaic power , traverse ,get The photovoltaic power prediction scenario with time correlation based on probability prediction.

4. The method for random optimization of power system backup based on typical photovoltaic scenarios according to claim 3 is characterized in that: Step S3 includes the steps of: S31, from The photovoltaic power prediction scenarios are randomly selected As the first cluster center; S32, for The photovoltaic power prediction scenarios are calculated and their respective cluster centers are calculated. The shortest distance between , and all the shortest distances Sum the squares of , the shortest distance The calculation formula is ； S33, calculating the probability of each photovoltaic power prediction scenario being selected as the next cluster center , the probability The calculation formula is ； S34. Pick a random number between the interval [0,1] ,use minus If the result is greater than 0, continue to subtract until the result is not greater than 0 and the probability The corresponding photovoltaic power prediction scenario is recorded as the second cluster center; S35, repeat steps S32 to S34 to obtain Initial cluster centers; S36. Based on the Initial cluster centers are obtained using the K-means clustering algorithm. Typical photovoltaic scenarios And the corresponding probability , and the probability satisfy .

5. The method for random optimization of power system backup based on typical photovoltaic scenarios according to claim 4 is characterized in that: Step S4 is specifically as follows: Based on the typical photovoltaic scenario, Typical photovoltaic scenarios Recorded as a set , from the collection Select any one as the base scene and record the rest as , in order to construct a random optimization model of power system reserve under typical multi-photovoltaic scenarios.

6. The method for random optimization of power system backup based on typical photovoltaic scenarios according to claim 5 is characterized in that: The objective function is: ， In the formula, It is a collection of conventional units in the power system. represents the collection of energy storage devices in the power system, and Conventional units Startup cost factor and downtime cost factor, and Represents conventional units Provide positive and negative standby cost factors, and Energy storage devices Provide positive and negative standby cost factors, Indicates conventional unit Operating cost factor, and Respectively represent energy storage devices Discharge cost coefficient and charge cost coefficient, and Represents conventional units At the moment Power on state and power off state, and they are binary variables, and they cannot be both ,when When the In the startup state, when When the is closed. and Represents conventional units At the moment Positive and negative reserve capacities provided, and Energy storage devices exist Positive and negative reserve capacity provided at all times, Representation scene Conventional unit exist Active power at the moment, and Representing scenes Energy storage equipment exist The discharge power and charging power at the moment.

7. The method for random optimization of power system backup based on typical photovoltaic scenarios according to claim 6, characterized in that: The standby random optimization conditions include power balance constraints, power system flow constraints, minimum start and stop time constraints, unit output constraints, unit climbing constraints, unit standby capacity constraints, energy storage device constraints, energy storage device standby constraints and photovoltaic output constraints; The expression of the power balance constraint is: ， In the formula, and represent the photovoltaic collection and load collection respectively, Representation scene Next Photovoltaic at the moment The actual output, It's a scene Next The load at time The load value; The expression of the power system flow constraint is: ， In the formula, is a collection of nodes; , , and Respectively represent nodes The combination of conventional units, energy storage equipment, photovoltaics and loads, represents the set of power system lines, It is a line Transmit power cap, Is a node To line transfer factor; The expression of the minimum start-stop time constraint includes ， ， ， ， In the formula, It is a conventional unit exist The state at the moment is a binary variable. When the exist Always in power on state, when When the exist Always in shutdown state. and Represents conventional units Minimum startup and shutdown times; The expression of the unit output constraint is: ， In the formula, and Represents conventional units The upper and lower limits of active output; The expression of the unit climbing constraint includes ， ， In the formula, and Represents conventional units Enable and disable ramp rate, and Conventional units The climbing rate and the descending rate; The expression of the unit reserve capacity constraint includes In the formula, Indicates conventional units in the basic scenario At the moment The active power, and Conventional units Provide positive and negative reserve caps; The expressions of the energy storage device constraints include ， ， ， ， ， ， In the formula, and Respectively represent energy storage devices The minimum and maximum values ​​of charge and discharge power, and Respectively for scenes Energy storage equipment At the moment The charge and discharge state is a binary variable, and both cannot be 1 at the same time. When, it indicates the scene Energy storage equipment At the moment In charging state, when When, it indicates the scene Energy storage equipment At the moment In discharge state, Representation scene Energy storage equipment At the moment The energy and Respectively represent energy storage devices The charging and discharging efficiency, and Energy storage devices Minimum and maximum values ​​of energy; The expression of the backup constraint of the energy storage device includes ， ， ， ， In the formula, and Respectively represent the energy storage devices in the basic scenario At the moment Active power of The expression of the photovoltaic output constraint is: ， In the formula, Representation scene Next Photovoltaic at the moment Output forecast value.

8. A random optimization system for power system backup based on typical photovoltaic scenarios, characterized in that: Used to implement the power system reserve random optimization method as described in any one of claims 1 to 7.

9. A computer device, comprising a memory, a processor and a computer program, characterized in that: When the computer program is executed by a processor, the power system reserve random optimization method according to any one of claims 1 to 7 is 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 power system reserve random optimization method according to any one of claims 1 to 7 is implemented.

Images